JP4811421B2 - Image processing apparatus and method, recording medium, and program - Google Patents

Description

  The present invention relates to an image processing apparatus and method, a recording medium, and a program. The processing speed is improved and the processing is performed in a distributed manner by executing image processing processing distributed on a plurality of servers in a network. Thus, the present invention relates to an image processing apparatus and method, a recording medium, and a program that can reduce only the cost required for the service by enabling only a process required by the user to be executed.

  A technique for synthesizing an image desired by a user via a network is generally spreading.

  In such a composite image, a user designates an image stored in a storage server on the network, or a plurality of existing images such as an image captured by a digital still camera are overlapped and joined. It was generated by such a process or synthesized by texture mapping.

  However, since the synthesized image generated by the above-described method cannot adjust, for example, so-called motion blur, which occurs when an object with motion is imaged, for example, low-accuracy synthesis processing is executed as a result. However, there is a problem that only an unnatural composite image can be generated.

  The present invention has been made in view of such a situation. In the above-described image composition processing, a natural composite image is generated.

An image processing apparatus according to one aspect of the present invention designates image data composed of pixel values determined for each pixel and according to an amount of light constituting a temporally integrated image, or the image data. Information for designating an object included in the image consisting of the image data, and a foreground object component constituting the foreground object of the image data based on a model in which each pixel value of the image data is developed in the time direction. Request information including area information for identifying any one of a foreground area, a background area composed of background object components constituting a background object of the image data, or a mixed area where the foreground area and the background area are mixed. input means for inputting, in response to the request information inputted by the input means, the image data, or the image data Based on the model to expand each pixel value of the image data to be acquired on the basis of constant information in a time direction, in the image data, the mixing ratio of the foreground object component and the background object components in said mixed area Signal processing means for estimation.

  The signal processing means can be made to extract a desired component from the mixing region based on the mixing ratio in accordance with request information input by the input means.

  The signal processing means may be configured to separate the mixed area into the foreground object component and the background object component based on the mixing ratio in accordance with request information input from the input means.

An image processing method according to an aspect of the present invention designates image data composed of pixel values determined for each pixel and according to the amount of light constituting an image integrated over time, or the image data. Information for designating an object included in the image consisting of the image data, and a foreground object component constituting the foreground object of the image data based on a model in which each pixel value of the image data is developed in the time direction. Request information including area information for identifying any one of a foreground area, a background area composed of background object components constituting a background object of the image data, or a mixed area where the foreground area and the background area are mixed. an input step of inputting, in response to the request information input by the processing of the input step, the image data, or, before Based on the model to expand each pixel value of the image data to be acquired on the basis of information for designating the image data in the time direction, in the image data, and the foreground object components in said mixed area of the background object components Signal processing step for estimating the mixing ratio.

The recording medium program according to one aspect of the present invention designates image data consisting of pixel values determined for each pixel and according to the amount of light constituting the temporally integrated image, or the image data. Foreground object components constituting the foreground object of the image data based on information for specifying an object included in the image composed of the image data, and a model for expanding each pixel value of the image data in the time direction Request information including area information for identifying any of a foreground area consisting of: a background area consisting of background object components constituting a background object of the image data; or a mixed area where the foreground area and the background area are mixed an input step of inputting, in response to the request information input by the processing of the input step, the image data, or , The image data on the basis of a model that expand each pixel value of the image data acquired in the time direction on the basis of the information specifying said in image data, the said foreground object components in said mixed area background object And causing a computer to execute a process including a signal processing step of estimating a mixing ratio with the component.

The program according to one aspect of the present invention is a program for each pixel and image data composed of pixel values determined according to the amount of light constituting the temporally integrated image, or information specifying the image data, Foreground consisting of foreground object components constituting the foreground object of the image data based on information for designating an object included in the image consisting of the image data and a model for expanding each pixel value of the image data in the time direction Input request information including area information for identifying either an area, a background area composed of background object components constituting a background object of the image data, or a mixed area where the foreground area and the background area are mixed. an input step, in response to the request information input by the processing of the input step, the image data, or the Based on the model to expand each pixel value of the image data to be acquired on the basis of the information designating the image data in the time direction, in the image data, and the foreground object components in said mixed area of the background object components And causing the computer to execute a process including a signal processing step of estimating the mixture ratio.

In one aspect of the present invention, image data consisting of pixel values determined for each pixel and according to the amount of light constituting the temporally integrated image, or information specifying the image data, Foreground region comprising foreground object components constituting the foreground object of the image data based on information for designating an object included in the image composed of image data and a model for expanding each pixel value of the image data in the time direction Request information including area information for identifying either a background area composed of background object components constituting a background object of the image data or a mixed area in which the foreground area and the background area are mixed; depending on the request information is input, the image data, or image which is obtained based on the information specifying the image data Based on the model to expand each pixel value of the data in the time direction, the in the image data, the mixing ratio of the foreground object component and the background object components in the mixed area is estimated.

  According to the present invention, based on the mixture ratio, the foreground component and the background component are separated from the input image, and the foreground component image including only the foreground component and the background component image including only the background component are output. It becomes possible to synthesize images more naturally.

  FIG. 1 is a diagram showing an embodiment of an image processing system according to the present invention.

  The image processing system of the present invention includes, for example, a separation processing server 11, a motion detection server 12, an area identification server 13, a mixture ratio calculation server 14, a foreground / background separation processing server 15, and a motion blur adjustment server 16 on a network 1 such as the Internet. , Encoding server 17, storage servers 18-1, 18-2, synthesis server 19, correction server 20, purchase server 21, sale server 22, search server 23, billing server 24, financial server (for customer) 25, financial server (Provider) 26, client computer 27, and camera terminal devices 28-1 to 28-n are connected to each other and can exchange data with each other. Separation processing server 11, motion detection server 12, region specifying server 13, mixing ratio calculation server 14, foreground / background separation processing server 15, motion blur adjustment server 16, encoding server 17, composition server 19, correction server 20, purchase server 21 , Sale server 22, search server 23, billing server 24, financial server (for customer) 25, and financial server (for provider) 26 are a separation service, a motion detection service, a region identification service, a mixing ratio calculation service, respectively. Providing foreground / background separation services, motion blur adjustment services, encoding services, synthesis services, correction services, purchase services, sale services, search services, billing services, and financial services (for customers and providers) It is a server that is managed or operated by a person. In the following description, when there is no need to individually distinguish the storage servers 18-1, 18-2 and the camera terminal devices 28-1 to 28-n, the storage server 18 and the camera terminal device 28 are simply used. Called. The same applies to other servers and devices.

  FIG. 2 is a diagram showing a configuration of the separation processing server 11 according to the present invention. A CPU (Central Processing Unit) 41 executes various processes according to a program stored in a ROM (Read Only Memory) 42 or a storage unit 48. A RAM (Random Access Memory) 43 appropriately stores programs executed by the CPU 41, data, and the like. The CPU 41, the ROM 42, and the RAM 43 are connected to each other by a bus 44.

  An input / output interface 45 is also connected to the CPU 41 via the bus 44. The input / output interface 45 is connected to an input unit 46 including a keyboard, a mouse, and a microphone, and an output unit 47 including a display and a speaker. The CPU 41 executes various processes in response to commands input from the input unit 46. Then, the CPU 41 outputs an image, sound, or the like obtained as a result of the processing to the output unit 47.

  The storage unit 48 connected to the input / output interface 45 is composed of a hard disk, for example, and stores programs executed by the CPU 41 and various data. The communication unit 49 communicates with an external device via the Internet or other networks.

  A program may be acquired via the communication unit 49 and stored in the storage unit 48.

  The drive 50 connected to the input / output interface 45 drives the magnetic disk 61, the optical disk 62, the magneto-optical disk 63, or the semiconductor memory 64 when they are mounted, and programs and data recorded there. Get etc. The acquired program and data are transferred to and stored in the storage unit 48 as necessary.

  It should be noted that the motion detection server 12, the area specifying server 13, the mixing ratio calculation server 14, the foreground / background separation processing server 15, the motion blur adjustment server 16, the encoding server 17, the storage servers 18-1 and 18-2, the synthesis server 19, The basic configuration of the correction server 20, the purchase server 21, the sale server 22, the search server 23, the billing server 24, the financial server (for customer) 25, the financial server (for provider) 26, and the client computer 27 is separated. Since it is the same as that of the process server 11, the description is abbreviate | omitted.

  FIG. 3 is a diagram showing the configuration of the camera terminal device 28 according to the present invention. The configuration of the camera terminal device 28 is separated except that an input unit 76 is provided with a sensor 76a and a GPS (Global Positioning System) 76b, and an output unit 77 is provided with an LCD (Liquid Crystal Display) 77a. The configuration is the same as that of the processing server 11. That is, the CPU 71, ROM 72, RAM 73, bus 74, input / output interface 75, input unit 76, output unit 77, storage unit 78, communication unit 79, drive 80, magnetic disk 91, optical disk 92, magneto-optical disk of the camera terminal device 28 93 and the semiconductor memory 94 are the CPU 41, ROM 42, RAM 43, bus 44, input / output interface 45, input unit 46, output unit 47, storage unit 48, communication unit 49, drive 50, magnetic disk of the separation processing server 11, respectively. 61, the optical disk 62, the magneto-optical disk 63, and the semiconductor memory 64, respectively.

  The sensor 76 a is an image sensor and outputs a captured image to the input unit 76. The GPS 76 b detects position information (latitude and longitude) on the earth based on a signal transmitted from a geostationary satellite (not shown), and outputs the detected position information to the input unit 76. The LCD 77a displays an image output from the output unit.

  Next, the separation processing server 11 will be described with reference to FIGS.

  As illustrated in FIG. 4, the separation processing server 11 separates an image input from the client computer 27 or the like via the network 1 into a foreground component image and a background component image by a method described later, Each of the foreground component image and the background component image is generated with an ID (Identifier) and output to the client computer 27, stored by itself, output to the storage server 18 for storage, or on the network Output to other servers and store. Here, the foreground component image indicates an image having a motion component in the input image, and the background component image indicates an image of a still portion that does not include the motion component in the input image. At this time, the billing processing unit 11a performs billing processing related to the separation processing for the billing server 24 via the network 1. As shown in FIG. 5, when an image ID that designates an image is input instead of an image, the separation processing server 11 accesses a search server 23 and a storage server 18 described later on the network 1, It searches its own storage unit (for example, storage unit 78 in FIG. 3), reads the image data corresponding to the input image ID, separates it into a foreground component image and a background component image, and then assigns an ID corresponding to each of them. At the same time, it is stored by itself or output to another server on the network 1 to execute processing corresponding to that server.

  In the following description, an image ID is described as an example of information for designating an image, but any information that can designate an image may be used. For example, image position information described later may be used.

  Next, the motion detection server 12 will be described with reference to FIGS.

  As illustrated in FIG. 6, the object extraction unit 12a of the motion detection server 12 extracts, for example, an image object in an image input from the client computer 27 and outputs the image object to the motion detection unit 12b. The motion detection unit 12b detects the motion vector and position information of the input image object and outputs it to the client computer 27, stores it by itself, or outputs it to another server on the network 1 and corresponds to that server. To execute the process. At this time, the billing processing unit 12c performs billing processing related to the detection of the motion vector and position information for each image object with respect to the billing server 24 via the network 1. In this specification, an image corresponding to an object in the real world that is a target of imaging is referred to as an object.

  As shown in FIG. 7, when an image ID that designates an image is input instead of an image, the motion detection server 12 accesses a search server 23 and a storage server 18 described later on the network 1, It searches its own storage unit (for example, storage unit 78 in FIG. 3), reads image data corresponding to the input image ID, and executes the same processing as described above.

  Next, the area specifying server 13 will be described with reference to FIGS.

  As shown in FIG. 8, the area specifying server 13 uses an image input from the client computer 27 or the like via the network 1 and object specification information for specifying an object in the image. Information indicating whether each pixel belongs to either the foreground area, the background area, or the mixed area, and indicating whether each pixel belongs to the foreground area, the background area, or the mixed area (hereinafter referred to as area information) Is output to the client computer 27, stored by itself, or output to another server on the network 1 to execute processing corresponding to the server. At this time, the billing processing unit 13 a performs billing processing for the fee related to the area specifying processing with respect to the billing server 24 via the network 1. As shown in FIG. 9, when an image ID for designating an image is input instead of an image, the area specifying server 13 accesses a search server 23 and a storage server 18 described later on the network 1, It searches its own storage unit (for example, storage unit 78 in FIG. 3), calls an image corresponding to the input image ID, and outputs area information corresponding to the object designation information of the image.

  Next, the mixing ratio calculation server 14 will be described with reference to FIGS. 10 and 11.

  As shown in FIG. 10, the mixture ratio calculation server 14 is based on, for example, an image input from the client computer 27 or the like via the network 1, object designation information for designating an object in the image, and region information. Then, a mixture ratio (hereinafter referred to as a mixture ratio α) corresponding to the pixels included in the mixture area is calculated, and the calculated mixture ratio is output to the client computer 27, stored by itself, or other on the network Output to the server and execute processing corresponding to the server. At this time, the billing processing unit 14 a performs billing processing related to the charge ratio calculation processing for the billing server 24 via the network 1. As shown in FIG. 11, when an image ID that designates an image is input instead of an image, the mixture ratio calculation server 14 accesses a search server 23 and a storage server 18 described later on the network 1. Then, it searches its own storage unit (for example, storage unit 78 in FIG. 3), calls an image corresponding to the input image ID, and executes the same processing as described above.

  Next, the foreground / background separation processing server 15 will be described with reference to FIGS.

  The foreground / background separation processing server 15, as shown in FIG. 12, for example, an image input from the client computer 27 or the like via the network 1, object designation information for designating an object in the image, area information, and Based on the mixture ratio α, a foreground component image consisting only of an image component corresponding to a foreground object (hereinafter also referred to as a foreground component) and a background component consisting only of a background component (hereinafter also referred to as a background component) The input image is separated from the image, and an ID is assigned to each image and output to the client computer 27, stored by itself, or output to another server on the network, and processing corresponding to the server is performed. Let it run. At this time, the billing processing unit 15 a performs billing processing related to the foreground / background separation processing to the billing server 24 via the network 1. Further, as shown in FIG. 13, when an image ID designating an image is input instead of an image, the foreground / background separation processing server 15 accesses a search server 23 and a storage server 18 described later on the network 1. Alternatively, it searches its own storage unit (for example, the storage unit 78 in FIG. 3), calls an image corresponding to the input image ID, and executes the same processing as described above.

  Next, the motion blur adjustment server 16 will be described with reference to FIGS. 14 and 15.

  As shown in FIG. 14, the motion blur adjustment server 16 converts the foreground component image into the foreground component image based on the foreground component image, the motion vector, and the motion blur amount input from the client computer 27 or the like via the network 1. Foreground component image that adjusts the amount of motion blur by adjusting the amount of motion blur included in the foreground component image, such as removing motion blur, reducing the amount of motion blur, or increasing the amount of motion blur Are generated and attached to each image and output to the client computer 27, stored by itself, or output to another server on the network, and processing corresponding to the server is executed. At this time, the billing processing unit 16 a executes billing processing related to the motion blur adjustment processing with respect to the billing server 24 via the network 1. As shown in FIG. 15, the motion blur adjustment server 16 receives a foreground component image ID for designating a foreground component image instead of the foreground component image, and stores a search server 23 (described later) on the network 1 or storage. The server 18 is accessed, or its own storage unit (for example, the storage unit 78 in FIG. 3) is searched, the foreground component image corresponding to the input foreground component image ID is called, and the same processing as described above is executed. To do.

  Next, the encoding server 17 will be described with reference to FIGS. 16 and 17.

  As shown in FIG. 16, the encoding server 17 separates an image input from, for example, the client computer 27 via the network 1 into a foreground component image and a background component image, and attaches an ID to each of them. Foreground component images such as URL (Universal Resource Locator) and background component images that were stored by yourself or output to other servers on the network and stored, and stored (output) Foreground component image position information and background component image position information composed of codes indicating the position of the server on the network 1 are generated and output together with information such as motion vectors, position information, and mixing ratios of these images. Further, the information output from the encoded information may be any of encoded information, an image, and an image and encoded information, and the information to be output can be changed as necessary. At this time, the billing processing unit 17a executes billing processing related to the encoding processing for the billing server 24 via the network 1. As shown in FIG. 17, when an image ID designating an image is input instead of an image, the encoding server 17 accesses a search server 23 and a storage server 18 described later on the network 1, It searches its own storage unit (for example, storage unit 78 in FIG. 3), calls an image corresponding to the input image ID, and executes the same processing as described above.

  Next, the storage server 18 will be described with reference to FIGS.

  As shown in FIG. 18, the accumulation server 18 is connected to the network 1 and accumulates images transmitted from various servers, and outputs image position information corresponding to the accumulated images together with an image ID. With this image position information, for example, the client computer 27 can access via the network 1 and call a desired image. That is, as shown in FIG. 19, for example, the client computer 27 accesses the storage server 18 in the network 1 on the basis of the image position information and designates an image ID corresponding to a desired image. The image to be read can be read out. In this specification, the image position information and the image ID will be described separately. However, the image position information may be a part of the image ID. In this case, the image position information is based on the image ID. It may be possible to recognize which server on the network 1 is stored (accumulated or processed). In addition to the image data, the storage server 18 may store a motion vector, position information, a mixture ratio, and a motion blur amount.

  Next, the synthesis server 19 will be described with reference to FIGS.

  As shown in FIG. 20, the composition server 19 includes two images such as images A and B input from the client computer 27 and the like via the network 1, a motion vector, position information, a mixing ratio, Then, the images A and B are synthesized from the amount of motion blur, and a synthesized image (A + B) is generated and output to the client computer 27, stored by itself, or output to other servers on the network 1, Execute the process corresponding to the server. In this case, one of images A and B is treated as a foreground component image and the other is treated as a background component image, so that both are combined. At this time, the billing processing unit 19a performs billing processing related to the composition processing with respect to the billing server 24 via the network 1. Further, as shown in FIG. 21, when the image A-ID and B-ID for designating an image are input instead of the images A and B, the composition server 19 receives a search server 23 (described later) on the network 1 or The storage server 18 is accessed, or its own storage unit (for example, the storage unit 78 in FIG. 3) is searched to call an image corresponding to the input images A-ID and B-ID. Execute the process.

  Next, the correction server 20 will be described with reference to FIGS.

  As shown in FIG. 22, the correction server 20 converts an image input from the client computer 27 or the like via the network 1 based on the motion vector, the position information, the mixing ratio, and the motion blur amount. It corrects, generates a corrected image, outputs it to the client computer 27, stores it by itself, or outputs it to another server on the network, and executes processing corresponding to that server. At this time, the billing processing unit 20 a performs billing processing for the fee related to the correction processing to the billing server 24 via the network 1. Further, as shown in FIG. 23, when an image ID designating an image is input instead of an image, the correction server 20 accesses a search server 23 and a storage server 18 described later on the network 1 or self- The storage unit (for example, the storage unit 78 in FIG. 3) is searched, an image corresponding to the input image ID is called, and the same processing as described above is executed.

  Next, the purchase server 21 will be described with reference to FIG.

  As shown in FIG. 24, the purchase server 21 operates the client computer 27 or the like via a network 1 to operate a client computer 27 or the like to specify an image desired to purchase. Is input, the corresponding image is accessed to the separation processing server 11, the storage server 18, the composition server 19, or the correction server 20 on the network 1, and the corresponding image is called and output to the client computer 27. At this time, the billing processing unit 21 a performs billing processing for a charge related to the image to be purchased, with respect to the billing server 24 via the network 1.

  Next, the sale server 22 will be described with reference to FIG.

  As shown in FIG. 25, the sale server 22, for example, generates a separated image owned by a predetermined user and synthesized by the separation processing server 11, the synthesis server 19, or the correction server 20 via the network 1. When an image or an image for which a modified image is desired to be sold is input, the image desired to be sold is stored in the separation processing server 11, the accumulation server 18, the composition server 19, or the modification server 20 on the network 1. At the same time, the billing processing unit 22a performs billing processing for the fee related to the image to be sold to the billing server 24 via the network 1 (in this case, the provider of the sale processing service wants to sell the user. The payment processing corresponding to the price corresponding to the sold image is executed).

  Next, the search server 26 will be described with reference to FIG.

  The search server 26 uses, for example, information indicating image characteristics desired by the user by the client computer 1 and physical position information of the camera terminal devices 28-1 to 28-n on the camera terminal device 28 on the network 1. The image currently captured at -1 to 28-n or the image captured in advance is searched and output to the client computer 1 as a request image. At this time, the billing processing unit 23 a executes billing processing for a charge related to the search processing to the billing server 24 via the network 1.

  In the present specification, encoding refers to conversion to foreground component image, background component image, motion vector, position information, motion blur amount, and mixture ratio information obtained based on image data. The data is referred to as encoded data.

  FIG. 27 is a block diagram showing the separation processing server 11.

  It does not matter whether each function of the separation processing server 11 is realized by hardware or software. That is, each block diagram in this specification may be considered as a hardware block diagram or a software functional block diagram.

  The input image supplied to the separation processing server 11 is supplied to the object extraction unit 101, the region specifying unit 103, the mixture ratio calculation unit 104, and the foreground / background separation unit 105.

  The object extraction unit 101 roughly extracts an image object corresponding to a foreground object included in the input image, and supplies the extracted image object to the motion detection unit 102. For example, the object extraction unit 101 detects the outline of the image object corresponding to the foreground object included in the input image, thereby roughly extracting the image object corresponding to the foreground object.

  The object extraction unit 101 roughly extracts an image object corresponding to a background object included in the input image, and supplies the extracted image object to the motion detection unit 102. For example, the object extraction unit 101 roughly extracts an image object corresponding to the background object from the difference between the input image and the image object corresponding to the extracted foreground object.

  Further, for example, the object extraction unit 101 corresponds to the image object corresponding to the foreground object and the background object from the difference between the background image stored in the background memory provided therein and the input image. You may make it extract the image object to perform roughly.

  The motion detection unit 102 calculates the motion vector of the image object corresponding to the coarsely extracted foreground object by a method such as a block matching method, a gradient method, a phase correlation method, and a per-recursive method. The motion vector and the position information of the motion vector (information specifying the position of the pixel corresponding to the motion vector) are supplied to the region specifying unit 103 and the motion blur adjusting unit 106.

  The motion vector output from the motion detection unit 102 includes information corresponding to the motion amount v.

  Further, for example, the motion detection unit 102 may output a motion vector for each image object to the motion blur adjustment unit 106 together with pixel position information for specifying a pixel in the image object.

  The motion amount v is a value that represents a change in the position of the image corresponding to the moving object in units of pixel intervals. For example, when the image of the object corresponding to the foreground is moved so as to be displayed at a position separated by four pixels in the next frame with reference to a certain frame, the motion amount v of the image of the object corresponding to the foreground is 4.

  Note that the object extraction unit 101 and the motion detection unit 102 are necessary when adjusting the amount of motion blur corresponding to a moving object.

  The area specifying unit 103 specifies each pixel of the input image as one of the foreground area, the background area, or the mixed area, and whether each pixel belongs to one of the foreground area, the background area, or the mixed area Is supplied to the mixture ratio calculation unit 104, the foreground / background separation unit 105, and the motion blur adjustment unit 106.

  The mixture ratio calculation unit 104 calculates a mixture ratio corresponding to the pixels included in the mixed region based on the input image and the region information supplied from the region specifying unit 103, and uses the calculated mixture ratio as the foreground / background separation unit. It supplies to 105.

  The mixing ratio α is a value indicating a ratio of an image component (hereinafter also referred to as a background component) corresponding to a background object in a pixel value, as shown in an equation (3) described later.

  Based on the region information supplied from the region specifying unit 103 and the mixture ratio α supplied from the mixture ratio calculation unit 104, the foreground / background separation unit 105 performs image component corresponding to the foreground object (hereinafter referred to as foreground component). The input image is separated into a foreground component image consisting of only the background component and a background component image consisting only of the background component, and the foreground component image is supplied to the motion blur adjustment unit 106 and the selection unit 107. Note that the separated foreground component image may be the final output. Only the foreground and the background can be specified without considering the conventional mixed region, and an accurate foreground and background can be obtained as compared with the separated method.

  The motion blur adjustment unit 106 determines a processing unit indicating one or more pixels included in the foreground component image based on the motion amount v and the region information that can be known from the motion vector. The processing unit is data that designates a group of pixels to be subjected to a process for adjusting the amount of motion blur.

  The motion blur adjustment unit 106 is the motion blur adjustment amount input to the separation processing server 11, the foreground component image supplied from the foreground / background separation unit 105, the motion vector and its position information supplied from the motion detection unit 102, and the processing Based on the unit, adjust the amount of motion blur included in the foreground component image, such as removing motion blur included in the foreground component image, reducing the amount of motion blur, or increasing the amount of motion blur. The foreground component image in which the amount of blur is adjusted is output to the selection unit 107. The motion vector and its position information may not be used.

  Here, the motion blur refers to a distortion included in an image corresponding to a moving object, which is caused by the movement of an object in the real world to be imaged and the imaging characteristics of the sensor.

  For example, the selection unit 107 adjusts the amount of foreground component image supplied from the foreground / background separation unit 105 and the amount of motion blur supplied from the motion blur adjustment unit 106 based on a selection signal corresponding to the user's selection. One of the foreground component images is selected, and the selected foreground component image is output.

  Next, an input image supplied to the separation processing server 11 will be described with reference to FIGS. 28 to 43.

  FIG. 28 is a diagram for explaining imaging by the sensor 76a. The sensor 76a is constituted by, for example, a CCD video camera provided with a CCD (Charge-Coupled Device) area sensor which is a solid-state imaging device. The object corresponding to the foreground in the real world moves horizontally between the object corresponding to the background and the sensor in the real world, for example, from the left side to the right side in the drawing.

  The sensor 76a images the object corresponding to the foreground together with the object corresponding to the background. The sensor 76a outputs the captured image in units of one frame. For example, the sensor 76a outputs an image composed of 30 frames per second. The exposure time of the sensor 76a can be 1/30 second. The exposure time is a period from when the sensor 76a starts converting the input light to the electric charge until the conversion of the input light to the electric charge ends. Hereinafter, the exposure time is also referred to as shutter time.

  FIG. 29 is a diagram illustrating the arrangement of pixels. In FIG. 29, A to I indicate individual pixels. The pixels are arranged on a plane corresponding to the image. One detection element corresponding to one pixel is arranged on the sensor 76a. When the sensor 76a captures an image, one detection element outputs a pixel value corresponding to one pixel constituting the image. For example, the position of the detection element in the X direction corresponds to the horizontal position on the image, and the position of the detection element in the Y direction corresponds to the vertical position on the image.

  As shown in FIG. 30, for example, a detection element that is a CCD converts input light into electric charges for a period corresponding to the shutter time, and accumulates the converted electric charges. The amount of charge is approximately proportional to the intensity of input light and the time during which light is input. The detection element adds the electric charge converted from the input light to the already accumulated electric charge in a period corresponding to the shutter time. That is, the detection element integrates the input light for a period corresponding to the shutter time, and accumulates an amount of charge corresponding to the integrated light. It can be said that the detection element has an integration effect with respect to time.

  The electric charge accumulated in the detection element is converted into a voltage value by a circuit (not shown), and the voltage value is further converted into a pixel value such as digital data and output. Therefore, each pixel value output from the sensor 76a is a value projected onto a one-dimensional space, which is the result of integrating a part of the object corresponding to the foreground or the background having a spatial extension with respect to the shutter time. Have

  The separation processing server 11 extracts significant information buried in the output signal, for example, the mixing ratio α by the accumulation operation of the sensor 76a. The separation processing server 11 adjusts the amount of distortion caused by the mixture of the foreground image objects themselves, for example, the amount of motion blur. Further, the separation processing server 11 adjusts the amount of distortion caused by the mixture of the foreground image object and the background image object.

  FIG. 31 is a diagram illustrating an image obtained by imaging an object corresponding to a moving foreground and an object corresponding to a stationary background. FIG. 31A shows an image obtained by imaging an object corresponding to a foreground with movement and an object corresponding to a stationary background. In the example shown in FIG. 31A, the object corresponding to the foreground is moving horizontally from the left to the right with respect to the screen.

  FIG. 31B is a model diagram in which pixel values corresponding to one line of the image shown in FIG. 31A are expanded in the time direction. The horizontal direction in FIG. 31B corresponds to the spatial direction X in FIG.

  The pixel value of the background region pixel is composed of only the background component, that is, the image component corresponding to the background object. The pixel value of the foreground region pixel is composed of only the foreground component, that is, the image component corresponding to the foreground object.

  The pixel value of the pixel in the mixed area is composed of a background component and a foreground component. Since the pixel value is composed of the background component and the foreground component, the mixed region can be said to be a distortion region. The mixed area is further classified into a covered background area and an uncovered background area.

  The covered background area is a mixed area at a position corresponding to the front end of the foreground object in the advancing direction with respect to the foreground area, and is an area where the background component is covered with the foreground as time passes.

  On the other hand, the uncovered background area is a mixed area at a position corresponding to the rear end portion of the foreground object in the advancing direction with respect to the foreground area, and an area where a background component appears as time passes. Say.

  In this way, an image including a foreground area, a background area, or a covered background area or an uncovered background area is input as an input image to the area specifying unit 103, the mixture ratio calculation unit 104, and the foreground / background separation unit 105. .

  FIG. 32 is a diagram illustrating the background area, the foreground area, the mixed area, the covered background area, and the uncovered background area as described above. In the case of corresponding to the image shown in FIG. 31, the background area is a stationary part, the foreground area is a moving part, and the covered background area of the mixed area is a part that changes from the background to the foreground. The uncovered background area is a portion that changes from the foreground to the background.

  FIG. 33 is a model diagram in which pixel values of pixels arranged in a row adjacent to each other in an image obtained by capturing an object corresponding to a stationary foreground and an object corresponding to a stationary background are expanded in the time direction. It is. For example, pixels arranged on one line of the screen can be selected as the pixels arranged adjacent to each other in one column.

  The pixel values F01 to F04 shown in FIG. 33 are pixel values corresponding to the still foreground object. The pixel values B01 to B04 shown in FIG. 33 are pixel values corresponding to the stationary background object.

  The vertical direction in FIG. 33 corresponds to time, and time elapses from the top to the bottom in the figure. The position of the upper side of the rectangle in FIG. 33 corresponds to the time when the sensor 76a starts to convert the input light into electric charge, and the position of the lower side of the rectangle in FIG. 33 indicates the position of the light input by the sensor 76a. Corresponds to the time when the conversion to charge ends. That is, the distance from the upper side to the lower side of the rectangle in FIG. 33 corresponds to the shutter time.

  Hereinafter, a case where the shutter time and the frame interval are the same will be described as an example.

  The horizontal direction in FIG. 33 corresponds to the spatial direction X described in FIG. More specifically, in the example shown in FIG. 33, the distance from the left side of the rectangle described as “F01” in FIG. 33 to the right side of the rectangle described as “B04” is 8 times the pixel pitch, That is, it corresponds to the interval between eight consecutive pixels.

  When the foreground object and the background object are stationary, the light input to the sensor 76a does not change during the period corresponding to the shutter time.

  Here, the period corresponding to the shutter time is divided into two or more periods having the same length. For example, if the number of virtual divisions is 4, the model diagram shown in FIG. 33 can be represented as the model shown in FIG. The virtual division number is set corresponding to the amount of movement v of the object corresponding to the foreground within the shutter time. For example, the number of virtual divisions is 4 corresponding to the motion amount v being 4, and the period corresponding to the shutter time is divided into 4.

  The top row in the figure corresponds to the first divided period after the shutter opens. The second row from the top in the figure corresponds to the second divided period from when the shutter has opened. The third line from the top in the figure corresponds to the third divided period from when the shutter has opened. The fourth row from the top in the figure corresponds to the fourth divided period from when the shutter has opened.

  Hereinafter, the shutter time divided in accordance with the motion amount v is also referred to as shutter time / v.

  Since the light input to the sensor 76a does not change when the object corresponding to the foreground is stationary, the foreground component F01 / v is equal to the value obtained by dividing the pixel value F01 by the number of virtual divisions. Similarly, when the object corresponding to the foreground is stationary, the foreground component F02 / v is equal to the value obtained by dividing the pixel value F02 by the virtual division number, and the foreground component F03 / v is the virtual value of the pixel value F03. The foreground component F04 / v is equal to the value obtained by dividing the pixel value F04 by the virtual division number.

  Since the light input to the sensor 76a does not change when the object corresponding to the background is stationary, the background component B01 / v is equal to the value obtained by dividing the pixel value B01 by the virtual division number. Similarly, when the object corresponding to the background is stationary, the background component B02 / v is equal to the value obtained by dividing the pixel value B02 by the virtual division number, and B03 / v is obtained by dividing the pixel value B03 by the virtual division number. B04 / v is equal to a value obtained by dividing the pixel value B04 by the number of virtual divisions.

  That is, when the object corresponding to the foreground is stationary, the light corresponding to the foreground object input to the sensor 76a does not change during the period corresponding to the shutter time, so the first shutter time / Corresponds to the foreground component F01 / v corresponding to v, the second foreground component F01 / v corresponding to the shutter time / v, and the third shutter time / v corresponding to the shutter time / v. The foreground component F01 / v and the foreground component F01 / v corresponding to the fourth shutter time / v after the shutter is opened have the same value. F02 / v to F04 / v have the same relationship as F01 / v.

  When the object corresponding to the background is stationary, the light corresponding to the background object input to the sensor 76a does not change during the period corresponding to the shutter time, so that the first shutter time / v after the shutter opens. The corresponding background component B01 / v, the second background component B01 / v corresponding to the shutter time / v when the shutter is opened, and the third background component corresponding to the shutter time / v corresponding to the shutter time / v The component B01 / v and the background component B01 / v corresponding to the fourth shutter time / v after the shutter is opened have the same value. B02 / v to B04 / v have the same relationship.

  Next, a case where the object corresponding to the foreground moves and the object corresponding to the background is stationary will be described.

  FIG. 35 is a model diagram in which pixel values of pixels on one line including the covered background area are expanded in the time direction when the object corresponding to the foreground moves toward the right side in the drawing. In FIG. 35, the foreground motion amount v is 4. Since one frame is a short time, it can be assumed that the object corresponding to the foreground is a rigid body and is moving at a constant speed. In FIG. 35, the image of the object corresponding to the foreground moves so as to be displayed on the right side by four pixels in the next frame with reference to a certain frame.

  In FIG. 35, the leftmost pixel through the fourth pixel from the left belong to the foreground area. In FIG. 35, the fifth through seventh pixels from the left belong to the mixed area, which is a covered background area. In FIG. 35, the rightmost pixel belongs to the background area.

  Since the object corresponding to the foreground is moving so as to cover the object corresponding to the background with the passage of time, the component included in the pixel value of the pixel belonging to the covered background area has a period corresponding to the shutter time. At this point, the background component is replaced by the foreground component.

  For example, the pixel value M with a thick line frame in FIG. 35 is expressed by Expression (1).

M = B02 / v + B02 / v + F07 / v + F06 / v
(1)

  For example, since the fifth pixel from the left includes a background component corresponding to one shutter time / v and includes a foreground component corresponding to three shutter times / v, the mixture ratio of the fifth pixel from the left α is 1/4. The sixth pixel from the left includes a background component corresponding to two shutter times / v and includes a foreground component corresponding to two shutter times / v. Therefore, the mixture ratio α of the sixth pixel from the left is 1/2. The seventh pixel from the left includes a background component corresponding to three shutter times / v, and includes a foreground component corresponding to one shutter time / v. Therefore, the mixture ratio α of the seventh pixel from the left is 3/4.

  Since it can be assumed that the object corresponding to the foreground is a rigid body and moves at a constant speed so that the foreground image is displayed on the right side of four pixels in the next frame, for example, the fourth pixel from the left in FIG. The foreground component F07 / v of the first shutter time / v after the shutter is opened is the foreground component of the fifth pixel from the left in FIG. 35 corresponding to the second shutter time / v after the shutter is opened. be equivalent to. Similarly, the foreground component F07 / v is the sixth pixel from the left in FIG. 35, the foreground component corresponding to the third shutter time / v from when the shutter has opened, and the seventh pixel from the left in FIG. And the foreground component corresponding to the fourth shutter time / v after the shutter is opened.

  Since it can be assumed that the object corresponding to the foreground is a rigid body and moves at a constant speed so that the foreground image is displayed on the right side of four pixels in the next frame, for example, the third pixel from the left in FIG. The foreground component F06 / v of the first shutter time / v after the shutter is opened is the foreground component of the fourth pixel from the left in FIG. 35 corresponding to the second shutter time / v after the shutter is opened. equal. Similarly, the foreground component F06 / v is the fifth pixel from the left in FIG. 35, the foreground component corresponding to the third shutter time / v from when the shutter has opened, and the sixth pixel from the left in FIG. And the foreground component corresponding to the fourth shutter time / v after the shutter is opened.

  Since it can be assumed that the object corresponding to the foreground is a rigid body and moves at a constant speed so that the foreground image is displayed on the right side of four pixels in the next frame, for example, the second pixel from the left in FIG. The foreground component F05 / v of the first shutter time / v after the shutter is opened is the foreground component of the third pixel from the left in FIG. 35 corresponding to the second shutter time / v after the shutter is opened. equal. Similarly, the foreground component F05 / v corresponds to the foreground component of the fourth pixel from the left in FIG. 35 corresponding to the third shutter time / v from when the shutter has opened, and the fifth from the left in FIG. And the foreground component corresponding to the fourth shutter time / v after the shutter is opened.

  Since it can be assumed that the object corresponding to the foreground is a rigid body and moves at a constant speed so that the foreground image is displayed on the right side of four pixels in the next frame, for example, the shutter of the leftmost pixel in FIG. The foreground component F04 / v of the first shutter time / v after opening is equal to the foreground component of the second pixel from the left in FIG. 35 corresponding to the second shutter time / v after the shutter is opened. Similarly, the foreground component F04 / v corresponds to the foreground component of the third pixel from the left in FIG. 35 corresponding to the third shutter time / v from when the shutter has opened, and the fourth pixel from the left in FIG. And the foreground component corresponding to the fourth shutter time / v after the shutter is opened.

  Since the foreground area corresponding to the moving object includes motion blur as described above, it can be said to be a distortion area.

  FIG. 36 is a model diagram in which pixel values of pixels on one line including the uncovered background area are expanded in the time direction when the foreground moves toward the right side in the drawing. In FIG. 36, the amount of motion v of the foreground is 4. Since one frame is a short time, it can be assumed that the object corresponding to the foreground is a rigid body and is moving at a constant speed. In FIG. 36, the image of the object corresponding to the foreground moves to the right by four pixels in the next frame with reference to a certain frame.

  In FIG. 36, the leftmost pixel through the fourth pixel from the left belong to the background area. In FIG. 36, the fifth through seventh pixels from the left belong to the mixed area, which is an uncovered background. In FIG. 36, the rightmost pixel belongs to the foreground area.

  Since the object corresponding to the foreground that covered the object corresponding to the background is moved so as to be removed from the front of the object corresponding to the background over time, it is included in the pixel value of the pixel belonging to the uncovered background area The component to be changed from the foreground component to the background component at a certain point in time corresponding to the shutter time.

  For example, a pixel value M ′ with a thick line frame in FIG. 36 is expressed by Expression (2).

M '= F02 / v + F01 / v + B26 / v + B26 / v
(2)

  For example, the fifth pixel from the left includes a background component corresponding to three shutter times / v, and includes a foreground component corresponding to one shutter time / v, so the mixing ratio of the fifth pixel from the left α is 3/4. The sixth pixel from the left includes a background component corresponding to two shutter times / v and includes a foreground component corresponding to two shutter times / v. Therefore, the mixture ratio α of the sixth pixel from the left is 1/2. Since the seventh pixel from the left includes a background component corresponding to one shutter time / v and includes a foreground component corresponding to three shutter times / v, the mixture ratio α of the seventh pixel from the left is 1/4.

  When the expressions (1) and (2) are generalized, the pixel value M is expressed by the expression (3).

  Here, α is a mixing ratio. B is a background pixel value, and Fi / v is a foreground component.

  Since the object corresponding to the foreground is a rigid body and can be assumed to move at a constant speed and the amount of movement v is 4, for example, the first pixel from the left in FIG. The foreground component F01 / v of the shutter time / v is equal to the foreground component of the sixth pixel from the left in FIG. 36 corresponding to the second shutter time / v from when the shutter has opened. Similarly, F01 / v represents the foreground component of the seventh pixel from the left in FIG. 36 corresponding to the third shutter time / v from when the shutter has opened, and the eighth pixel from the left in FIG. , And the foreground component corresponding to the fourth shutter time / v after the shutter is opened.

  Since it can be assumed that the object corresponding to the foreground is a rigid body and moves at a constant speed, and the number of virtual divisions is 4, for example, the first pixel from the left in FIG. The foreground component F02 / v of the shutter time / v is equal to the foreground component of the seventh pixel from the left in FIG. 36 corresponding to the second shutter time / v from when the shutter has opened. Similarly, the foreground component F02 / v is equal to the foreground component of the eighth pixel from the left in FIG. 36 corresponding to the third shutter time / v from when the shutter has opened.

  Since the object corresponding to the foreground is a rigid body and can be assumed to move at a constant speed and the amount of movement v is 4, for example, the seventh pixel from the left in FIG. The foreground component F03 / v of the shutter time / v is equal to the foreground component of the eighth pixel from the left in FIG. 36 corresponding to the second shutter time / v from when the shutter has opened.

  In the description of FIG. 34 to FIG. 36, it has been described that the virtual division number is 4, but the virtual division number corresponds to the motion amount v. The amount of movement v generally corresponds to the moving speed of the object corresponding to the foreground. For example, when the object corresponding to the foreground is moving so as to be displayed to the right by four pixels in the next frame with reference to a certain frame, the amount of movement v is 4. Corresponding to the motion amount v, the number of virtual divisions is 4. Similarly, for example, when the object corresponding to the foreground is moving so that it is displayed on the left by 6 pixels in the next frame with reference to a certain frame, the motion amount v is set to 6, and the number of virtual divisions is , 6.

  37 and 38, the above-described mixed area composed of the foreground area, the background area, the covered background area or the uncovered background area, and the foreground components and the background components corresponding to the divided shutter times, The relationship is shown.

  FIG. 37 shows an example in which pixels in the foreground area, the background area, and the mixed area are extracted from an image including a foreground corresponding to an object moving in front of a stationary background. In the example shown in FIG. 37, the object corresponding to the foreground is moving horizontally with respect to the screen.

  Frame # n + 1 is the next frame after frame #n, and frame # n + 2 is the next frame after frame # n + 1.

  Extract the pixels in the foreground area, background area, and mixed area extracted from any of frame #n to frame # n + 2, set the amount of motion v to 4, and set the pixel values of the extracted pixels in the time direction The developed model is shown in FIG.

  Since the object corresponding to the foreground moves, the pixel value in the foreground area is composed of four different foreground components corresponding to the shutter time / v period. For example, the leftmost pixel among the pixels in the foreground area shown in FIG. 38 is composed of F01 / v, F02 / v, F03 / v, and F04 / v. That is, the pixels in the foreground area include motion blur.

  Since the object corresponding to the background is stationary, the light corresponding to the background input to the sensor 76a does not change during the period corresponding to the shutter time. In this case, the pixel value in the background area does not include motion blur.

  The pixel value of the pixel belonging to the mixed area composed of the covered background area or the uncovered background area is composed of a foreground component and a background component.

  Next, when the image corresponding to the object is moving, the pixel values of the pixels at the same position on the frame that are adjacent to each other in a plurality of frames are developed in the time direction. The model will be described. For example, when the image corresponding to the object moves horizontally with respect to the screen, the pixels arranged on one line of the screen can be selected as the pixels arranged in a row adjacent to each other.

  FIG. 39 shows pixels arranged in a row adjacent to three frames of an image obtained by capturing an object corresponding to a stationary background, and the pixel values of the pixels at the same position on the frame are represented by time. It is the model figure developed in the direction. Frame #n is the next frame after frame # n-1, and frame # n + 1 is the next frame after frame #n. Other frames are also referred to in the same manner.

  The pixel values B01 to B12 shown in FIG. 39 are the pixel values of the pixels corresponding to the stationary background object. Since the object corresponding to the background is stationary, the pixel value of the corresponding pixel does not change in frame # n−1 to frame n + 1. For example, the pixel in frame #n and the pixel in frame # n + 1 corresponding to the position of the pixel having a pixel value of B05 in frame # n−1 each have a pixel value of B05.

  FIG. 40 shows pixels arranged in a row adjacent to each other in three frames of an image obtained by imaging an object corresponding to a foreground moving to the right side in the drawing together with an object corresponding to a stationary background, FIG. 5 is a model diagram in which pixel values of pixels at the same position on a frame are developed in the time direction. The model shown in FIG. 40 includes a covered background area.

  In FIG. 40, it can be assumed that the object corresponding to the foreground is a rigid body and moves at a constant speed, and the foreground image is moved so that the foreground image is displayed on the right by four pixels in the next frame. 4 and the number of virtual divisions is 4.

  For example, the foreground component of the leftmost pixel of frame # n-1 in FIG. 40 for the first shutter time / v after the shutter opens is F12 / v, and the second pixel from the left in FIG. The foreground component of the second shutter time / v after the shutter is opened is also F12 / v. The foreground component of the third pixel from the left in FIG. 40 for the third shutter time / v after the shutter opens, and the fourth shutter time for the fourth pixel from the left in FIG. The foreground component of / v is F12 / v.

  The foreground component of the leftmost pixel of frame # n-1 in FIG. 40 corresponding to the second shutter time / v from when the shutter has opened is F11 / v, and the second pixel from the left in FIG. The foreground component of the third shutter time / v after the shutter is opened is also F11 / v. The foreground component of the third pixel from the left in FIG. 40 corresponding to the fourth portion of the shutter time / v from when the shutter has opened is F11 / v.

  The foreground component of the leftmost pixel of frame # n-1 in FIG. 40 corresponding to the third shutter time / v from when the shutter has opened is F10 / v, and the second pixel from the left in FIG. The foreground component of the fourth shutter time / v after the shutter is opened is also F10 / v. The foreground component of the leftmost pixel of frame # n−1 in FIG. 40 corresponding to the fourth shutter time / v from when the shutter has opened is F09 / v.

  Since the object corresponding to the background is stationary, the background component of the second pixel from the left of frame # n-1 in FIG. Become. The background component of the third pixel from the left of frame # n−1 in FIG. 40 corresponding to the first and second shutter time / v from when the shutter has opened is B02 / v. The background component of the fourth pixel from the left of frame # n−1 in FIG. 40 corresponding to the first through third shutter time / v from when the shutter has opened is B03 / v.

  In frame # n−1 in FIG. 40, the leftmost pixel belongs to the foreground area, and the second to fourth pixels from the left belong to the mixed area which is a covered background area.

  The fifth through twelfth pixels from the left of frame # n−1 in FIG. 40 belong to the background area, and the pixel values thereof are B04 through B11, respectively.

  The first through fifth pixels from the left in frame #n in FIG. 40 belong to the foreground area. The foreground component of the shutter time / v in the foreground area of frame #n is any one of F05 / v to F12 / v.

  It can be assumed that the object corresponding to the foreground is a rigid body and moves at a constant speed, and the foreground image moves so as to be displayed on the right side of four pixels in the next frame. Therefore, from the left of frame #n in FIG. The foreground component of the fifth pixel at the first shutter time / v after the shutter opens is F12 / v, and the sixth pixel from the left in FIG. 40 opens the shutter at the second shutter time / v. The foreground component is also F12 / v. The foreground component of the seventh pixel from the left in FIG. 40 for the third shutter time / v after the shutter opens, and the fourth shutter time for the eighth pixel from the left in FIG. The foreground component of / v is F12 / v.

  The foreground component of the fifth pixel from the left in frame #n in FIG. 40 corresponding to the second shutter time / v from when the shutter has opened is F11 / v, and the sixth pixel from the left in FIG. The foreground component of the third shutter time / v after the shutter is opened is also F11 / v. The foreground component of the seventh pixel from the left in FIG. 40 corresponding to the fourth portion of the shutter time / v from when the shutter has opened is F11 / v.

  The foreground component of the fifth pixel from the left in frame #n in FIG. 40 corresponding to the third shutter time / v from when the shutter has opened is F10 / v, and the sixth pixel from the left in FIG. The foreground component of the fourth shutter time / v after the shutter is opened is also F10 / v. The foreground component of the fifth pixel from the left of frame #n in FIG. 40 corresponding to the fourth portion of the shutter time / v from when the shutter has opened is F09 / v.

  Since the object corresponding to the background is stationary, the background component of the sixth pixel from the left in frame #n in FIG. 40 corresponding to the first shutter time / v after the shutter opens is B05 / v. The background component of the seventh pixel from the left of frame #n in FIG. 40 corresponding to the first and second shutter time / v from when the shutter has opened is B06 / v. The background component of the eighth pixel from the left of frame #n in FIG. 40 corresponding to the first through third shutter time / v from when the shutter has opened is B07 / v.

  In frame #n in FIG. 40, the sixth through eighth pixels from the left belong to the mixed area, which is a covered background area.

  The ninth through twelfth pixels from the left of frame #n in FIG. 40 belong to the background area, and the pixel values thereof are B08 through B11, respectively.

  The first through ninth pixels from the left in frame # n + 1 in FIG. 40 belong to the foreground area. The foreground component of the shutter time / v in the foreground area of frame # n + 1 is any one of F01 / v to F12 / v.

  It can be assumed that the object corresponding to the foreground is a rigid body and moves at a constant speed, and the foreground image moves so as to be displayed on the right side by four pixels in the next frame, so that the frame # n + 1 in FIG. The foreground component of the ninth pixel from the left when the shutter opens is the first shutter time / v is F12 / v, and the tenth pixel from the left in FIG. 40 is the second shutter time after the shutter is opened. The foreground component of / v is also F12 / v. The foreground component of the eleventh pixel from the left in FIG. 40 and the third shutter time / v from when the shutter has opened, and the fourth shutter time from the shutter of the twelfth pixel from the left in FIG. The foreground component of / v is F12 / v.

  The foreground component of the ninth pixel from the left of frame # n + 1 in FIG. 40 corresponding to the second shutter time / v from when the shutter has opened is F11 / v, which is the tenth from the left in FIG. The foreground component of the third shutter time / v after the shutter opens is also F11 / v. The foreground component of the eleventh pixel from the left in FIG. 40 corresponding to the fourth shutter time / v from when the shutter has opened is F11 / v.

  The foreground component of the ninth pixel from the left of frame # n + 1 in FIG. 40 corresponding to the third shutter time / v from when the shutter has opened is F10 / v, which is the tenth pixel from the left in FIG. The foreground component of the fourth shutter time / v after the shutter is opened is also F10 / v. The foreground component of the ninth pixel from the left of frame # n + 1 in FIG. 40 corresponding to the fourth portion of the shutter time / v from when the shutter has opened is F09 / v.

  Since the object corresponding to the background is stationary, the background component of the tenth pixel from the left of frame # n + 1 in FIG. 40 corresponding to the first shutter time / v after the shutter is opened is B09 / v Become. The background component of the eleventh pixel from the left of frame # n + 1 in FIG. 40 corresponding to the first and second shutter time / v from when the shutter has opened is B10 / v. The background component of the twelfth pixel from the left of frame # n + 1 in FIG. 40 corresponding to the first through third shutter time / v from when the shutter has opened is B11 / v.

  In frame # n + 1 in FIG. 40, the tenth through twelfth pixels from the left correspond to the mixed area, which is a covered background area.

  FIG. 41 is a model diagram of an image obtained by extracting foreground components from the pixel values shown in FIG.

  FIG. 42 shows pixels arranged in a row adjacent to each other in three frames of an image obtained by capturing a foreground corresponding to an object moving to the right side in the figure together with a stationary background. It is the model figure which expand | deployed the pixel value of the pixel of the position of the time direction. In FIG. 42, an uncovered background area is included.

  In FIG. 42, it can be assumed that the object corresponding to the foreground is a rigid body and is moving at a constant speed. Since the object corresponding to the foreground is moved so as to be displayed on the right side by four pixels in the next frame, the motion amount v is 4.

  For example, the foreground component of the leftmost pixel of frame # n-1 in FIG. 42 that is the first shutter time / v after the shutter is opened is F13 / v, and is the second pixel from the left in FIG. The foreground component of the second shutter time / v after the shutter is opened is also F13 / v. The foreground component of the third pixel from the left in FIG. 42 for the third shutter time / v after the shutter opens, and the fourth shutter time for the fourth pixel from the left in FIG. The foreground component of / v is F13 / v.

  The foreground component of the second pixel from the left of frame # n-1 in FIG. 42 corresponding to the first shutter time / v from when the shutter has opened is F14 / v, and the third pixel from the left in FIG. The foreground component of the second shutter time / v after the shutter is opened is also F14 / v. The foreground component of the third pixel from the left in FIG. 42 corresponding to the first shutter time / v from when the shutter has opened is F15 / v.

  Since the object corresponding to the background is stationary, the background component of the leftmost pixel of frame # n-1 in FIG. 42 corresponding to the second to fourth shutter time / v from when the shutter has opened is B25. / v. The background component of the second pixel from the left of frame # n−1 in FIG. 42 corresponding to the third and fourth shutter time / v from when the shutter has opened is B26 / v. The background component of the third pixel from the left of frame # n−1 in FIG. 42 corresponding to the fourth portion of the shutter time / v from when the shutter has opened is B27 / v.

  In frame # n−1 in FIG. 42, the leftmost pixel through the third pixel belong to the mixed area, which is an uncovered background area.

  The fourth through twelfth pixels from the left of frame # n−1 in FIG. 42 belong to the foreground area. The foreground component of the frame is any one of F13 / v to F24 / v.

  The leftmost pixel through the fourth pixel from the left in frame #n in FIG. 42 belong to the background area, and the pixel values thereof are B25 through B28, respectively.

  It can be assumed that the object corresponding to the foreground is a rigid body and moves at a constant speed, and the foreground image moves so as to be displayed on the right side by four pixels in the next frame, so from the left of frame #n in FIG. The foreground component of the fifth pixel at the first shutter time / v after the shutter opens is F13 / v, and the sixth pixel from the left in FIG. 42 opens the shutter at the second shutter time / v. The foreground component is also F13 / v. The foreground component of the seventh pixel from the left in FIG. 42 for the third shutter time / v after the shutter opens, and the fourth shutter time for the eighth pixel from the left in FIG. The foreground component of / v is F13 / v.

  The foreground component of the sixth pixel from the left of frame #n in FIG. 42 corresponding to the first shutter time / v from when the shutter has opened is F14 / v, and the seventh pixel from the left in FIG. The foreground component of the second shutter time / v after opening is also F14 / v. The foreground component of the eighth pixel from the left in FIG. 42 corresponding to the first portion of the shutter time / v from when the shutter has opened is F15 / v.

  Since the object corresponding to the background is stationary, the background components of the fifth pixel from the left of frame #n in FIG. 42 corresponding to the second to fourth shutter time / v from when the shutter has opened are B29 / v. The background component of the sixth pixel from the left of frame #n in FIG. 42 corresponding to the third and fourth shutter time / v from when the shutter has opened is B30 / v. The background component of the seventh pixel from the left of frame #n in FIG. 42 corresponding to the fourth portion of the shutter time / v from when the shutter has opened is B31 / v.

  In frame #n in FIG. 42, the fifth through seventh pixels from the left belong to the mixed area, which is an uncovered background area.

  The eighth through twelfth pixels from the left in frame #n in FIG. 42 belong to the foreground area. The value corresponding to the period of the shutter time / v in the foreground area of frame #n is any one of F13 / v to F20 / v.

  The leftmost pixel through the eighth pixel from the left in frame # n + 1 in FIG. 42 belong to the background area, and the pixel values thereof are B25 through B32, respectively.

  It can be assumed that the object corresponding to the foreground is a rigid body and moves at a constant speed, and the foreground image moves so as to be displayed on the right side by four pixels in the next frame, so that the frame # n + 1 in FIG. The foreground component of the ninth pixel from the left when the shutter opens is the first shutter time / v is F13 / v, and the tenth pixel from the left in FIG. The foreground component of / v is also F13 / v. The foreground component of the eleventh pixel from the left in FIG. 42 and the third shutter time / v from when the shutter has opened, and the fourth shutter time from the shutter of the twelfth pixel from the left in FIG. The foreground component of / v is F13 / v.

  The foreground component of the tenth pixel from the left of frame # n + 1 in FIG. 42 corresponding to the first shutter time / v from when the shutter has opened is F14 / v, and the eleventh pixel from the left in FIG. The foreground component of the second shutter time / v after the shutter is opened is also F14 / v. The foreground component of the twelfth pixel from the left in FIG. 42 corresponding to the first shutter time / v from when the shutter has opened is F15 / v.

  Since the object corresponding to the background is stationary, the background components of the ninth pixel from the left of frame # n + 1 in FIG. , B33 / v. The background component of the tenth pixel from the left of frame # n + 1 in FIG. 42 corresponding to the third and fourth shutter time / v from when the shutter has opened is B34 / v. The background component of the eleventh pixel from the left of frame # n + 1 in FIG. 42 corresponding to the fourth portion of the shutter time / v from when the shutter has opened is B35 / v.

  In frame # n + 1 in FIG. 42, the ninth through eleventh pixels from the left belong to the mixed area, which is an uncovered background area.

  The twelfth pixel from the left of frame # n + 1 in FIG. 42 belongs to the foreground area. The foreground component of the shutter time / v in the foreground area of frame # n + 1 is any one of F13 / v to F16 / v.

  FIG. 43 is a model diagram of an image obtained by extracting foreground components from the pixel values shown in FIG.

  Returning to FIG. 27, the region specifying unit 103 associates a flag indicating that the pixel belongs to the foreground region, the background region, the covered background region, or the uncovered background region for each pixel using the pixel values of a plurality of frames. Thus, the region information is supplied to the mixture ratio calculation unit 104 and the motion blur adjustment unit 106.

  The mixture ratio calculation unit 104 calculates the mixture ratio α for each pixel for the pixels included in the mixed region based on the pixel values of a plurality of frames and the region information, and supplies the calculated mixture ratio α to the foreground / background separation unit 105. Supply.

  The foreground / background separation unit 105 extracts a foreground component image including only foreground components based on the pixel values of a plurality of frames, region information, and the mixture ratio α, and supplies the foreground component image to the motion blur adjustment unit 106.

  The motion blur adjustment unit 106 converts the foreground component image based on the foreground component image supplied from the foreground / background separation unit 105, the motion vector supplied from the motion detection unit 102, and the region information supplied from the region specifying unit 103. The amount of motion blur included is adjusted, and a foreground component image in which the amount of motion blur is adjusted is output.

  With reference to the flowchart of FIG. 44, the process of adjusting the amount of motion blur by the separation processing server 11 will be described. In step S11, the area specifying unit 103 obtains area information indicating whether each pixel of the input image belongs to the foreground area, the background area, the covered background area, or the uncovered background area based on the input image. Execute processing for specifying the area to be generated. Details of the area specifying process will be described later. The area specifying unit 103 supplies the generated area information to the mixture ratio calculating unit 104.

  In step S11, the area specifying unit 103, based on the input image, foreground area, background area, or mixed area for each pixel of the input image (does not distinguish between a covered background area or an uncovered background area). It may be possible to generate region information indicating which one of the items belongs to. In this case, the foreground / background separation unit 105 and the motion blur adjustment unit 106 determine whether the mixed region is a covered background region or an uncovered background region based on the direction of the motion vector. For example, when the foreground region, the mixed region, and the background region are arranged in order corresponding to the direction of the motion vector, the mixed region is determined as the covered background region, and the background is determined corresponding to the direction of the motion vector. When the region, the mixed region, and the foreground region are arranged in this order, the mixed region is determined as an uncovered background region.

  In step S12, the mixture ratio calculation unit 104 calculates the mixture ratio α for each pixel included in the mixed area based on the input image and the area information. Details of the mixing ratio calculation process will be described later. The mixture ratio calculation unit 104 supplies the calculated mixture ratio α to the foreground / background separation unit 105.

  In step S13, the foreground / background separator 105 extracts a foreground component from the input image based on the region information and the mixture ratio α, and supplies the foreground component image to the motion blur adjustment unit 106 as a foreground component image.

  In step S14, the motion blur adjustment unit 106 is a continuous pixel lined up in the motion direction based on the motion vector and the region information, and belongs to any one of the uncovered background region, the foreground region, and the covered background region. A processing unit indicating the position of the object on the image is generated, and the amount of motion blur included in the foreground component corresponding to the processing unit is adjusted. Details of the process of adjusting the amount of motion blur will be described later.

  In step S15, the separation processing server 11 determines whether or not the processing has been completed for the entire screen. If it is determined that the processing has not been completed for the entire screen, the separation processing server 11 proceeds to step S14, and foreground corresponding to the processing unit. The process of adjusting the amount of motion blur for the component is repeated.

  If it is determined in step S15 that the process has been completed for the entire screen, the process ends.

  As described above, the separation processing server 11 can adjust the amount of motion blur included in the foreground by separating the foreground and the background. That is, the separation processing server 11 can adjust the amount of motion blur included in the sample data that is the pixel value of the foreground pixel.

  Hereinafter, the configurations of the area specifying unit 103, the mixture ratio calculating unit 104, the foreground / background separating unit 105, and the motion blur adjusting unit 106 will be described.

  FIG. 45 is a block diagram illustrating an example of the configuration of the area specifying unit 103. 45 does not use a motion vector. The frame memory 201 stores the input image in units of frames. When the processing target is the frame #n, the frame memory 201 is a frame # n-2 that is a frame immediately before the frame #n, a frame # n-1 that is a frame immediately before the frame #n, A frame #n, a frame # n + 1 that is a frame subsequent to the frame #n, and a frame # n + 2 that is a frame subsequent to the frame #n are stored.

  The static motion determination unit 202-1 determines the pixel value of the pixel of frame # n + 2 at the same position on the image of the pixel that is the target of region specification of frame #n, and the region specification of frame #n. The pixel value of the pixel of frame # n + 1 at the same position as the position of the target pixel on the image is read from the frame memory 201, and the absolute value of the difference between the read pixel values is calculated. The static motion determination unit 202-1 determines whether or not the absolute value of the difference between the pixel value of frame # n + 2 and the pixel value of frame # n + 1 is greater than a preset threshold Th, When it is determined that the absolute value of the difference is greater than the threshold value Th, a static motion determination indicating motion is supplied to the region determination unit 203-1. When it is determined that the absolute value of the difference between the pixel value of the pixel of frame # n + 2 and the pixel value of the pixel of frame # n + 1 is equal to or less than the threshold value Th, the static motion determination unit 202-1 The static motion determination shown is supplied to the region determination unit 203-1.

  The static motion determination unit 202-2 is the target of the pixel value of the frame # n + 1 at the same position on the image of the pixel that is the target of region identification of the frame #n, and the target of the frame #n. The pixel value of the pixel is read from the frame memory 201, and the absolute value of the difference between the pixel values is calculated. The static motion determination unit 202-2 determines whether or not the absolute value of the difference between the pixel value of the frame # n + 1 and the pixel value of the frame #n is greater than a preset threshold value Th. When it is determined that the absolute value of the difference between the two is greater than the threshold value Th, a static motion determination indicating motion is supplied to the region determination unit 203-1 and the region determination unit 203-2. When it is determined that the absolute value of the difference between the pixel value of the pixel of frame # n + 1 and the pixel value of the pixel of frame #n is equal to or less than the threshold value Th, the static motion determination unit 202-2 indicates stillness. The static motion determination is supplied to the region determination unit 203-1 and the region determination unit 203-2.

  The static motion determination unit 202-3 determines the frame #n at the same position as the pixel value of the pixel that is the region specification target of the frame #n and the position of the pixel that is the region specification target of the frame #n. The pixel value of −1 pixel is read from the frame memory 201, and the absolute value of the difference between the pixel values is calculated. The static motion determination unit 202-3 determines whether or not the absolute value of the difference between the pixel value of the frame #n and the pixel value of the frame # n-1 is larger than a preset threshold value Th. When it is determined that the absolute value of the difference between the two is greater than the threshold value Th, a static motion determination indicating motion is supplied to the region determination unit 203-2 and the region determination unit 203-3. When it is determined that the absolute value of the difference between the pixel value of the pixel of frame #n and the pixel value of the pixel of frame # n-1 is equal to or less than the threshold value Th, the static motion determination unit 202-3 indicates the still state The static motion determination is supplied to the region determination unit 203-2 and the region determination unit 203-3.

  The static motion determination unit 202-4 determines the pixel value of the pixel of frame # n-1 at the same position on the image of the pixel that is the target of region specification of frame #n, and the region specification of frame #n. The pixel value of the pixel of frame # n-2 located at the same position on the image of the target pixel is read from the frame memory 201, and the absolute value of the difference between the pixel values is calculated. The static motion determination unit 202-4 determines whether or not the absolute value of the difference between the pixel value of the frame # n-1 and the pixel value of the frame # n-2 is greater than a preset threshold Th, When it is determined that the absolute value of the difference between the pixel values is greater than the threshold value Th, a static motion determination indicating motion is supplied to the region determination unit 203-3. When it is determined that the absolute value of the difference between the pixel value of the pixel of frame # n-1 and the pixel value of the pixel of frame # n-2 is equal to or less than the threshold value Th, the static motion determination unit 202-4 Is supplied to the region determination unit 203-3.

  The region determination unit 203-1 is configured such that the static motion determination supplied from the static motion determination unit 202-1 indicates stillness and the static motion determination supplied from the static motion determination unit 202-2 indicates movement. The pixel that is the target of region identification in frame #n is determined to belong to the uncovered background region, and the uncovered background region determination flag corresponding to the pixel that is determined to belong to the region belongs to the uncovered background region. “1” indicating “” is set.

  The area determination unit 203-1 indicates that the static motion determination supplied from the static motion determination unit 202-1 indicates movement, or the static motion determination supplied from the static motion determination unit 202-2 indicates stillness. When determining that the pixel that is the target of region identification in frame #n does not belong to the uncovered background region, the uncovered background region determination flag corresponding to the pixel to be determined for the region is set to the uncovered background region. “0” is set to indicate that it does not belong.

  The area determination unit 203-1 supplies the uncovered background area determination flag in which “1” or “0” is set as described above to the determination flag storage frame memory 204.

  The region determination unit 203-2 is configured such that the static motion determination supplied from the static motion determination unit 202-2 indicates static and the static motion determination supplied from the static motion determination unit 202-3 indicates static. Then, it is determined that the pixel that is the target of region identification in frame #n belongs to the still region, and “1” indicating that it belongs to the still region is set in the still region determination flag corresponding to the pixel to be determined for the region.

  In the area determination unit 203-2, the static motion determination supplied from the static motion determination unit 202-2 indicates a motion, or the static motion determination supplied from the static motion determination unit 202-3 indicates a motion. At this time, it is determined that the pixel that is the region identification target in frame #n does not belong to the still region, and “0” indicating that it does not belong to the still region is set in the still region determination flag corresponding to the pixel to be determined for the region. Set.

  The region determination unit 203-2 supplies the still region determination flag in which “1” or “0” is set as described above to the determination flag storage frame memory 204.

  The region determination unit 203-2 is configured such that the static motion determination supplied from the static motion determination unit 202-2 indicates movement and the static motion determination supplied from the static motion determination unit 202-3 indicates movement. Then, it is determined that the pixel that is the target of region identification in frame #n belongs to the motion region, and “1” indicating that it belongs to the motion region is set in the motion region determination flag corresponding to the pixel determined for the region.

  The area determination unit 203-2 indicates that the static motion determination supplied from the static motion determination unit 202-2 indicates static or the static motion determination supplied from the static motion determination unit 202-3 indicates static. At this time, it is determined that the pixel that is the region identification target in frame #n does not belong to the motion region, and “0” indicating that it does not belong to the motion region is set in the motion region determination flag corresponding to the pixel that is determined to be the region Set.

  The region determination unit 203-2 supplies the motion region determination flag set to “1” or “0” to the determination flag storage frame memory 204 in this way.

  The region determination unit 203-3 is configured such that the static motion determination supplied from the static motion determination unit 202-3 indicates movement and the static motion determination supplied from the static motion determination unit 202-4 indicates stillness. , It is determined that the pixel that is the target of region identification in frame #n belongs to the covered background region, and the covered background region determination flag corresponding to the pixel to be determined of the region indicates that it belongs to the covered background region. 1 ”is set.

  In the area determination unit 203-3, the static motion determination supplied from the static motion determination unit 202-3 indicates stillness, or the static motion determination supplied from the static motion determination unit 202-4 indicates movement. When determining that the pixel that is the target of region identification in frame #n does not belong to the covered background region, the covered background region determination flag corresponding to the pixel to be determined for the region does not belong to the covered background region. “0” is set to indicate.

  The area determination unit 203-3 supplies the covered background area determination flag set to “1” or “0” to the determination flag storage frame memory 204 in this way.

  The determination flag storage frame memory 204 is supplied from the uncovered background region determination flag supplied from the region determination unit 203-1, the still region determination flag supplied from the region determination unit 203-2, and the region determination unit 203-2. The movement area determination flag and the covered background area determination flag supplied from the area determination unit 203-3 are stored.

  The determination flag storage frame memory 204 supplies the stored uncovered background area determination flag, still area determination flag, motion area determination flag, and covered background area determination flag to the synthesis unit 205. Based on the uncovered background area determination flag, the still area determination flag, the motion area determination flag, and the covered background area determination flag supplied from the determination flag storage frame memory 204, the combining unit 205 Area information indicating that it belongs to any one of the covered background area, the stationary area, the motion area, and the covered background area is generated and supplied to the determination flag storage frame memory 206.

  The determination flag storage frame memory 206 stores the area information supplied from the synthesis unit 205 and outputs the stored area information.

  Next, an example of processing of the area specifying unit 103 will be described with reference to FIGS.

  When the object corresponding to the foreground is moving, the position on the screen of the image corresponding to the object changes for each frame. As shown in FIG. 46, in the frame #n, the image corresponding to the object located at the position indicated by Yn (x, y) is Yn + 1 (x, y in the frame # n + 1 which is the next frame. Located in y).

  FIG. 22 shows a model diagram in which pixel values of pixels arranged in a row adjacent to the moving direction of the image corresponding to the foreground object are developed in the time direction. For example, when the moving direction of the image corresponding to the foreground object is horizontal with respect to the screen, the model diagram in FIG. 47 shows a model in which pixel values of adjacent pixels on one line are expanded in the time direction.

  In FIG. 47, the line in frame #n is the same as the line in frame # n + 1.

  Foreground components corresponding to the objects included in the second through thirteenth pixels from the left in frame #n are included in the sixth through seventeenth pixels from the left in frame # n + 1.

  In frame #n, the pixels belonging to the covered background area are the 11th to 13th pixels from the left, and the pixels belonging to the uncovered background area are the 2nd to 4th pixels from the left. In frame # n + 1, the pixels belonging to the covered background area are the 15th to 17th pixels from the left, and the pixels belonging to the uncovered background area are the 6th to 8th pixels from the left.

  In the example shown in FIG. 47, the foreground component included in frame #n has moved four pixels in frame # n + 1, so the amount of motion v is four. The virtual division number corresponds to the motion amount v and is 4.

  Next, changes in pixel values of pixels belonging to the mixed region before and after the frame of interest will be described.

  In frame #n shown in FIG. 48 where the background is stationary and the foreground motion amount v is 4, the pixels belonging to the covered background area are the 15th to 17th pixels from the left. Since the motion amount v is 4, in the previous frame # n−1, the fifteenth through seventeenth pixels from the left include only background components and belong to the background area. In frame # n-2, the fifteenth through seventeenth pixels from the left include only background components and belong to the background area.

  Here, since the object corresponding to the background is stationary, the pixel value of the fifteenth pixel from the left in frame # n-1 does not change from the pixel value of the fifteenth pixel from the left in frame # n-2. . Similarly, the pixel value of the 16th pixel from the left of frame # n-1 does not change from the pixel value of the 16th pixel from the left of frame # n-2, and the 17th pixel from the left of frame # n-1 The pixel value of this pixel does not change from the pixel value of the 17th pixel from the left in frame # n-2.

  That is, the pixels of frame # n-1 and frame # n-2 corresponding to the pixels belonging to the covered background area in frame #n are composed of only background components, and the pixel value does not change. The value is almost zero. Therefore, the static motion determination for the pixels in frame # n-1 and frame # n-2 corresponding to the pixels belonging to the mixed region in frame #n is determined as static by the static motion determination unit 202-4.

  Since the pixels belonging to the covered background area in frame #n include the foreground components, the pixel values are different from the case of only the background components in frame # n-1. Therefore, the static motion determination for the pixels belonging to the mixed region in frame #n and the corresponding pixels in frame # n-1 is determined as motion by the static motion determination unit 202-3.

  As described above, the region determination unit 203-3 is supplied with the result of the static motion determination indicating the motion from the static motion determination unit 202-3, and is supplied with the result of the static motion determination indicating the static motion from the static motion determination unit 202-4. When it is done, it is determined that the corresponding pixel belongs to the covered background area.

  In the frame #n shown in FIG. 49 where the background is stationary and the foreground motion amount v is 4, the pixels included in the uncovered background area are the second through fourth pixels from the left. Since the motion amount v is 4, in the next frame # n + 1, the second through fourth pixels from the left include only background components and belong to the background area. Further, in the next frame # n + 2, the second through fourth pixels from the left include only background components and belong to the background area.

  Here, since the object corresponding to the background is stationary, the pixel value of the second pixel from the left of frame # n + 2 does not change from the pixel value of the second pixel from the left of frame # n + 1. . Similarly, the pixel value of the third pixel from the left of frame # n + 2 does not change from the pixel value of the third pixel from the left of frame # n + 1, and is the fourth from the left of frame # n + 2. The pixel value of this pixel does not change from the pixel value of the fourth pixel from the left in frame # n + 1.

  That is, the pixels of frame # n + 1 and frame # n + 2, which correspond to the pixels belonging to the uncovered background area in frame #n, consist only of background components, and the pixel value does not change. The absolute value is almost zero. Therefore, the static motion determination for the pixels in frame # n + 1 and frame # n + 2 corresponding to the pixels belonging to the mixed region in frame #n is determined as static by the static motion determination unit 202-1.

  Since the pixels belonging to the uncovered background area in frame #n include the foreground components, the pixel values are different from the case of only the background components in frame # n + 1. Therefore, the static motion determination for the pixels belonging to the mixed region in frame #n and the corresponding pixels in frame # n + 1 is determined as motion by the static motion determination unit 202-2.

  As described above, the region determination unit 203-1 is supplied with the result of the static motion determination indicating the motion from the static motion determination unit 202-2, and is supplied with the result of the static motion determination indicating the static motion from the static motion determination unit 202-1. Is determined to belong to the uncovered background area.

  FIG. 50 is a diagram illustrating the determination conditions of the area specifying unit 103 in frame #n. The pixel in frame # n-2 at the same position on the image of the pixel to be judged in frame #n and the same position on the image of the pixel to be judged in frame #n A pixel in frame # n-1 is determined to be stationary, and a pixel in frame # n-1 and a pixel in frame #n at the same position on the image of the pixel to be determined in frame #n Are determined to be movements, the area specifying unit 103 determines that the pixel to be determined for frame #n belongs to the covered background area.

  The pixel in frame # n-1 and the pixel in frame #n at the same position on the image of the pixel to be determined in frame #n are determined to be stationary, and the pixel in frame #n When it is determined that the pixel of frame # n + 1 at the same position on the image of the pixel to be determined as #n is still, the area specifying unit 103 determines that the determination target of frame #n is Is determined to belong to the still region.

  The pixel in frame # n-1 and the pixel in frame #n at the same position on the image of the pixel to be determined in frame #n are determined to move, and the pixel in frame #n When it is determined that a pixel in frame # n + 1 located at the same position on the image of a pixel to be determined as #n is a motion, the region specifying unit 103 determines that the determination is performed in frame #n. Is determined to belong to the motion region.

  The pixel in frame #n and the pixel in frame # n + 1 at the same position on the image of the pixel to be determined in frame #n are determined as motion, and the determination target in frame #n The pixel of frame # n + 1 at the same position as the position of the pixel on the image and the pixel of frame # n + 2 at the same position as the position of the pixel to be determined at frame #n on the image Are determined to be stationary, the area specifying unit 103 determines that the pixel to be determined for frame #n belongs to the uncovered background area.

  FIG. 51 is a diagram illustrating an example of the result of specifying the area of the area specifying unit 103. In FIG. 51A, pixels determined to belong to the covered background area are displayed in white. In FIG. 51B, pixels that are determined to belong to the uncovered background area are displayed in white.

  In FIG. 51C, pixels determined to belong to the motion region are displayed in white. In FIG. 51D, pixels that are determined to belong to the still region are displayed in white.

  FIG. 52 is a diagram illustrating, as an image, region information indicating a mixed region among region information output from the determination flag storage frame memory 206. In FIG. 52, a pixel determined to belong to the covered background area or the uncovered background area, that is, a pixel determined to belong to the mixed area is displayed in white. The area information indicating the mixed area output from the determination flag storage frame memory 206 indicates a mixed area and a portion having a texture surrounded by a portion having no texture in the foreground area.

  Next, the area specifying process of the area specifying unit 103 will be described with reference to the flowchart of FIG. In step S201, the frame memory 201 acquires images of frames # n-2 to # n + 2 including the frame #n to be determined.

  In step S202, the static motion determination unit 202-3 determines whether or not the pixel in frame # n-1 and the pixel at the same position in frame #n are stationary. Then, the static motion determination unit 202-2 determines whether or not the frame #n and the pixel at the same position in the frame # n + 1 are still.

  In step S203, if it is determined that the pixel in frame #n and the pixel in the same position in frame # n + 1 are determined to be stationary, the process proceeds to step S204, and the region determination unit 203-2 determines that the region is determined. A corresponding still area determination flag is set to “1” indicating that it belongs to a still area. The region determination unit 203-2 supplies the still region determination flag to the determination flag storage frame memory 204, and the procedure proceeds to step S205.

  When it is determined in step S202 that the pixel in frame # n-1 and the pixel at the same position in frame #n are in motion, or in step S203, the pixel in frame #n and the same position in frame # n + 1 If the pixel is determined to be moving, the pixel in frame #n does not belong to the still region, so the process of step S204 is skipped, and the procedure proceeds to step S205.

  In step S205, the static motion determination unit 202-3 determines whether or not the pixel in frame # n-1 and the pixel at the same position in frame #n are in motion, and if it is determined as motion, the process proceeds to step S206. Then, the static motion determination unit 202-2 determines whether or not there is motion between the pixel of frame #n and the pixel at the same position of frame # n + 1.

  If it is determined in step S206 that the pixel in frame #n and the pixel in the same position in frame # n + 1 are in motion, the process proceeds to step S207, and the region determination unit 203-2 determines that the region is determined. “1” indicating that it belongs to a motion region is set in the corresponding motion region determination flag. The region determination unit 203-2 supplies the motion region determination flag to the determination flag storage frame memory 204, and the procedure proceeds to step S208.

  If it is determined in step S205 that the pixel in frame # n-1 and the pixel in the same position in frame #n are still, or in step S206, the pixel in frame #n and the same position in frame # n + 1 If the current pixel is determined to be still, the pixel of frame #n does not belong to the motion region, so the process of step S207 is skipped, and the procedure proceeds to step S208.

  In step S208, the static motion determination unit 202-4 determines whether or not the pixel in frame # n-2 and the pixel in the same position in frame # n-1 are stationary. In step S209, the static motion determination unit 202-3 determines whether or not there is motion between the pixel in frame # n-1 and the pixel at the same position in frame #n.

  If it is determined in step S209 that the motion of the pixel in frame # n-1 and the pixel at the same position in frame #n is determined as moving, the process proceeds to step S210, and the region determination unit 203-3 determines that the region is to be determined. The corresponding covered background area determination flag is set to “1” indicating that it belongs to the covered background area. The area determination unit 203-3 supplies the covered background area determination flag to the determination flag storage frame memory 204, and the procedure proceeds to step S211.

  If it is determined in step S208 that the pixel in frame # n-2 and the pixel in the same position in frame # n-1 are in motion, or in step S209, the pixel in frame # n-1 and the pixel in frame #n If it is determined that the pixel at the same position is still, the pixel of frame #n does not belong to the covered background area, so the process of step S210 is skipped, and the procedure proceeds to step S211.

  In step S211, the static motion determination unit 202-2 determines whether or not the pixel in the frame #n and the pixel in the same position in the frame # n + 1 are in motion, and if it is determined to be in motion, the process proceeds to step S212. Then, the static motion determination unit 202-1 determines whether or not the pixel of frame # n + 1 and the pixel at the same position of frame # n + 2 are still.

  If it is determined in step S212 that the pixel in frame # n + 1 and the pixel in the same position in frame # n + 2 are stationary, the process proceeds to step S213, and the region determination unit 203-1 determines the region. In the uncovered background area determination flag corresponding to the pixel, “1” indicating that the pixel belongs to the uncovered background area is set. The area determination unit 203-1 supplies the uncovered background area determination flag to the determination flag storage frame memory 204, and the procedure proceeds to step S214.

  If it is determined in step S211 that the pixel in frame #n and the pixel in the same position in frame # n + 1 are stationary, or in step S212, the pixel in frame # n + 1 and the frame # n + 2 If it is determined that the motion is the same pixel, the pixel of frame #n does not belong to the uncovered background area, so the process of step S213 is skipped, and the procedure proceeds to step S214.

  In step S214, the area specifying unit 103 determines whether or not an area has been specified for all the pixels of frame #n. If it is determined that no area has been specified for all the pixels of frame #n, Returns to step S202 and repeats the area specifying process for other pixels.

  If it is determined in step S214 that the area has been specified for all the pixels of frame #n, the process proceeds to step S215, where the synthesis unit 205 stores the uncovered background area determination flag stored in the determination flag storage frame memory 204. And a covered background area determination flag, area information indicating a mixed area is generated, and each pixel belongs to one of an uncovered background area, a stationary area, a motion area, and a covered background area. The region information indicating this is generated, the generated region information is set in the determination flag storage frame memory 206, and the process ends.

  As described above, the region specifying unit 103 may generate region information indicating that each pixel included in the frame belongs to the motion region, the still region, the uncovered background region, or the covered background region. it can.

  The area specifying unit 103 generates area information corresponding to the mixed area by applying a logical sum to the area information corresponding to the uncovered background area and the covered background area, and is included in the frame. For each pixel, region information including a flag indicating that the pixel belongs to a motion region, a still region, or a mixed region may be generated.

  When the object corresponding to the foreground has a texture, the area specifying unit 103 can specify the movement area more accurately.

  The area specifying unit 103 can output area information indicating a motion area as area information indicating a foreground area, and area information indicating a still area as area information indicating a background area.

  In addition, although the object corresponding to the background has been described as stationary, the above-described processing for specifying the region can be applied even if the image corresponding to the background region includes a motion. For example, when the image corresponding to the background area is moving uniformly, the area specifying unit 103 shifts the entire image corresponding to this movement, and performs the same processing as when the object corresponding to the background is stationary. To do. In addition, when the image corresponding to the background region includes a different motion for each local area, the region specifying unit 103 selects a pixel corresponding to the motion and executes the above-described processing.

  FIG. 54 is a block diagram illustrating another example of the configuration of the area specifying unit 103. 54 does not use a motion vector. The background image generation unit 301 generates a background image corresponding to the input image, and supplies the generated background image to the binary object image extraction unit 302. For example, the background image generation unit 301 extracts an image object corresponding to a background object included in the input image, and generates a background image.

  FIG. 55 shows an example of a model diagram in which pixel values of pixels arranged in a line adjacent to the moving direction of the image corresponding to the foreground object are developed in the time direction. For example, when the moving direction of the image corresponding to the foreground object is horizontal to the screen, the model diagram in FIG. 55 shows a model in which pixel values of adjacent pixels on one line are expanded in the time direction.

  In FIG. 55, the line in frame #n is the same as the line in frame # n−1 and frame # n + 1.

  In frame #n, the foreground components corresponding to the objects included in the sixth through seventeenth pixels from the left are included in the second through thirteenth pixels from the left in frame # n-1. In frame # n + 1, they are included in the 10th to 21st pixels from the left.

  In frame # n−1, the pixels belonging to the covered background area are the 11th to 13th pixels from the left, and the pixels belonging to the uncovered background area are the 2nd to 4th pixels from the left. In frame #n, the pixels belonging to the covered background area are the 15th to 17th pixels from the left, and the pixels belonging to the uncovered background area are the 6th to 8th pixels from the left. In frame # n + 1, the pixels belonging to the covered background area are the 19th to 21st pixels from the left, and the pixels belonging to the uncovered background area are the 10th to 12th pixels from the left.

  In frame # n−1, the pixels belonging to the background area are the first pixel from the left and the fourteenth through twenty-first pixels from the left. In frame #n, the pixels belonging to the background area are the first through fifth pixels from the left, and the eighteenth through twenty-first pixels from the left. In frame # n + 1, the pixels belonging to the background area are the first through ninth pixels from the left.

  FIG. 56 shows an example of a background image generated by the background image generation unit 301 and corresponding to the example of FIG. The background image is composed of pixels corresponding to the background object, and does not include image components corresponding to the foreground object.

  The binary object image extraction unit 302 generates a binary object image based on the correlation between the background image and the input image, and supplies the generated binary object image to the time change detection unit 303.

  FIG. 57 is a block diagram showing the configuration of the binary object image extraction unit 302. The correlation value calculation unit 321 calculates the correlation between the background image and the input image supplied from the background image generation unit 301, generates a correlation value, and supplies the generated correlation value to the threshold processing unit 322.

Correlation value calculating section 321, for example, as shown in FIG. 58 (A), a block in the 3 × 3 of the background image around the X _4, as shown in FIG. 58 (B), the background image A correlation value corresponding to Y ₄ is calculated by applying Equation (4) to a block in the 3 × 3 input image centered on Y ₄ corresponding to the middle block.

  The correlation value calculation unit 321 supplies the correlation value calculated for each pixel in this way to the threshold processing unit 322.

In addition, the correlation value calculation unit 321 includes, for example, a block in a 3 × 3 background image centered on X ₄ as illustrated in FIG. 59A and a background as illustrated in FIG. 59B. The absolute value of the difference corresponding to Y ₄ may be calculated by applying Equation (7) to the block in the 3 × 3 input image centered on Y ₄ corresponding to the block in the image. Good.

  The correlation value calculation unit 321 supplies the difference absolute value calculated in this way to the threshold processing unit 322 as a correlation value.

  The threshold value processing unit 322 compares the pixel value of the correlation image with the threshold value th0. When the correlation value is equal to or less than the threshold value th0, the threshold value processing unit 322 sets the pixel value of the binary object image to 1 and sets the correlation value. Is greater than the threshold th0, the pixel value of the binary object image is set to 0, and a binary object image with 0 or 1 set to the pixel value is output. The threshold processing unit 322 may store the threshold th0 in advance, or may use the threshold th0 input from the outside.

  60 is a diagram showing an example of a binary object image corresponding to the model of the input image shown in FIG. In the binary object image, the pixel value is set to 0 for a pixel having a high correlation with the background image.

  FIG. 61 is a block diagram illustrating a configuration of the time change detection unit 303. The frame memory 341 determines the area for the pixel of frame #n, and the binary object image of frame # n−1, frame #n, and frame # n + 1 supplied from the binary object image extraction unit 302 Remember.

  The area determination unit 342 determines an area for each pixel of the frame #n based on the binary object images of the frame # n−1, the frame #n, and the frame # n + 1 stored in the frame memory 341. Region information is generated, and the generated region information is output.

  FIG. 62 is a diagram for explaining the determination by the region determination unit 342. When the pixel of interest of the binary object image of frame #n is 0, the region determination unit 342 determines that the pixel of interest of frame #n belongs to the background region.

  The pixel of interest of the binary object image of frame #n is 1, the corresponding pixel of the binary object image of frame # n-1 is 1, and the correspondence of the binary object image of frame # n + 1 When the pixel to be processed is 1, the region determination unit 342 determines that the pixel of interest in frame #n belongs to the foreground region.

  When the pixel of interest of the binary object image of frame #n is 1 and the corresponding pixel of the binary object image of frame # n-1 is 0, the region determination unit 342 It is determined that the pixel in question belongs to the covered background area.

  When the pixel of interest of the binary object image of frame #n is 1 and the corresponding pixel of the binary object image of frame # n + 1 is 0, the region determination unit 342 It is determined that the current pixel belongs to the uncovered background area.

  FIG. 63 is a diagram illustrating an example in which the time change detection unit 303 determines the binary object image corresponding to the input image model illustrated in FIG. 55. Since the corresponding pixel of frame #n of the binary object image is 0, the time change detection unit 303 determines that the first to fifth pixels from the left of the frame #n belong to the background area.

  The temporal change detection unit 303 has the uncovered background region as the sixth to ninth pixels from the left because the pixel of frame #n of the binary object image is 1 and the corresponding pixel of frame # n + 1 is 0. It is determined that it belongs to.

  The temporal change detection unit 303 has a pixel of frame #n of 1 in the binary object image, a corresponding pixel of frame # n−1 is 1, and a corresponding pixel of frame # n + 1 is 1. The tenth through thirteenth pixels are determined to belong to the foreground area.

  Since the pixel of frame #n of the binary object image is 1 and the corresponding pixel of frame # n−1 is 0, the time change detection unit 303 sets the 14th to 17th pixels from the left as the covered background area. Judge as belonging.

  The time change detection unit 303 determines that the 18th to 21st pixels from the left belong to the background area because the corresponding pixel of frame #n of the binary object image is 0.

  Next, the area specifying process of the area determination unit 103 will be described with reference to the flowchart of FIG. In step S301, the background image generation unit 301 of the region determination unit 103 generates a background image by extracting, for example, an image object corresponding to a background object included in the input image based on the input image, and generates the generated background. The image is supplied to the binary object image extraction unit 302.

  In step S302, the binary object image extraction unit 302 calculates a correlation value between the input image and the background image supplied from the background image generation unit 301, for example, by the calculation described with reference to FIG. In step S303, the binary object image extraction unit 302 calculates a binary object image from the correlation value and the threshold value th0, for example, by comparing the correlation value with the threshold value th0.

  In step S304, the time change detection unit 303 executes region determination processing, and the processing ends.

  Details of the region determination processing corresponding to step S304 will be described with reference to the flowchart of FIG. In step S321, the region determination unit 342 of the time change detection unit 303 determines whether or not the pixel of interest is 0 in the frame #n stored in the frame memory 341, and pays attention in the frame #n. If it is determined that the pixel is 0, the process proceeds to step S322, the pixel of interest in frame #n is set as belonging to the background area, and the process ends.

  If it is determined in step S321 that the pixel of interest is 1 in frame #n, the process proceeds to step S323, where the area determination unit 342 of the time change detection unit 303 stores the frame #n stored in the frame memory 341. In frame # n-1, it is determined whether or not the corresponding pixel is 0, and in frame #n, the target pixel is 1 and frame #n If it is determined at n−1 that the corresponding pixel is 0, the process proceeds to step S324, the pixel of interest in frame #n is set as belonging to the covered background area, and the process ends.

  If it is determined in step S323 that the pixel of interest is 0 in frame #n or the corresponding pixel is 1 in frame # n-1, the process proceeds to step S325, and the time change detection unit 303 The area determination unit 342 determines whether the pixel of interest is 1 in frame #n stored in the frame memory 341 and whether the corresponding pixel is 0 in frame # n + 1. If it is determined that the pixel of interest is 1 in frame #n and the corresponding pixel is 0 in frame # n + 1, the process proceeds to step S326, and the pixel of interest of frame #n is undefined. The process ends with setting to belong to the covered background area.

  If it is determined in step S325 that the pixel of interest is 0 in frame #n or the corresponding pixel is 1 in frame # n + 1, the process proceeds to step S327, and the time change detection unit 303 The area determination unit 342 sets the pixel of interest in frame #n as the foreground area, and the process ends.

  As described above, the area specifying unit 103 determines whether the pixels of the input image are the foreground area, the background area, the covered background area, and the uncovered background area based on the correlation value between the input image and the corresponding background image. It is possible to specify which one belongs, and generate region information corresponding to the specified result.

  FIG. 66 is a block diagram showing another configuration of the area specifying unit 103. 66 uses the motion vector supplied from the motion detection unit 102 and its position information. Parts that are the same as those shown in FIG. 54 are given the same reference numerals, and descriptions thereof are omitted.

  The robust unit 361 generates a robust binary object image based on the binary object images of N frames supplied from the binary object image extraction unit 302, and sends it to the time change detection unit 303. Output.

  FIG. 67 is a block diagram illustrating the configuration of the robust unit 361. The motion compensation unit 381 compensates for the motion of the binary object image of N frames based on the motion vector supplied from the motion detection unit 102 and its position information, and obtains a binary object image with motion compensated. Output to the switch 382.

  The motion compensation of the motion compensation unit 381 will be described with reference to the examples of FIGS. For example, when the region of frame #n is determined, when binary object images of frame # n-1, frame #n, and frame # n + 1 shown in FIG. 68 are input, the motion compensation unit 381 Based on the motion vector supplied from the motion detector 102, motion compensation is performed on the binary object image of frame # n-1 and the binary object image of frame # n + 1, as shown in FIG. Then, the binary object image subjected to motion compensation is supplied to the switch 382.

  The switch 382 outputs the motion-compensated binary object image of the first frame to the frame memory 383-1, and outputs the motion-compensated binary object image of the second frame to the frame memory 383-2. Similarly, the switch 382 outputs each of the motion compensated binary object images of the third to N−1th frames to any of the frame memory 383-3 to the frame memory 383- (N−1), The motion-compensated binary object image of the Nth frame is output to the frame memory 383-N.

  The frame memory 383-1 stores the binary object image for which motion compensation has been performed for the first frame, and outputs the stored binary object image to the weighting unit 384-1. The frame memory 383-2 stores the binary object image with motion compensation of the second frame, and outputs the stored binary object image to the weighting unit 384-2.

  Similarly, each of the frame memories 383-3 to 383- (N-1) stores and stores any of the motion compensated binary object images of the third frame to the (N-1) th frame. The binary object image thus output is output to any one of the weighting unit 384-3 to the weighting unit 384- (N-1). The frame memory 383-N stores the binary object image with motion compensation of the Nth frame, and outputs the stored binary object image to the weighting unit 384-N.

  The weighting unit 384-1 multiplies the pixel value of the motion-compensated binary object image of the first frame supplied from the frame memory 383-1 by a predetermined weight w1 and supplies the result to the integrating unit 385. The weighting unit 384-2 multiplies the pixel value of the motion compensated binary object image of the second frame supplied from the frame memory 383-2 by a predetermined weight w2, and supplies the result to the integrating unit 385.

  Similarly, each of the weighting units 384-3 to 384- (N-1) is the third to N-1 supplied from any one of the frame memories 383-3 to 383- (N-1). The pixel value of the motion-compensated binary object image of any one of the frames is multiplied by one of the predetermined weights w3 to w (N−1) and supplied to the accumulating unit 385. The weighting unit 384-N multiplies the pixel value of the motion-compensated binary object image of the Nth frame supplied from the frame memory 383-N by a predetermined weight wN and supplies the result to the integrating unit 385.

  The accumulating unit 385 accumulates the corresponding pixel values of the binary object image that have been subjected to motion compensation of the 1st to Nth frames and multiplied by one of the weights w1 to wN, respectively, and the accumulated pixel values are obtained in advance. A binary object image is generated by comparing with a predetermined threshold value th0.

  In this way, the robust unit 361 generates a robust binary object image from the N binary object images and supplies the generated binary object image to the time change detection unit 303. Therefore, the region specifying unit whose configuration is shown in FIG. Even if the input image includes noise, the area 103 can specify the area more accurately than the case shown in FIG.

  Next, the area specifying process of the area specifying unit 103 having the configuration shown in FIG. 66 will be described with reference to the flowchart of FIG. The processing in steps S341 to S343 is the same as that in steps S301 to S303 described with reference to the flowchart of FIG.

  In step S344, the robust unit 361 executes a robust process.

  In step S345, the time change detection unit 303 executes region determination processing, and the processing ends. Details of the process in step S345 are the same as those described with reference to the flowchart of FIG.

  Next, details of the robust processing corresponding to the processing in step S344 in FIG. 70 will be described with reference to the flowchart in FIG. In step S361, the motion compensation unit 381 performs motion compensation processing on the input binary object image based on the motion vector supplied from the motion detection unit 102 and its position information. In step S362, any of the frame memories 383-1 to 383-N stores the motion compensated binary object image supplied via the switch 382.

  In step S363, the robust unit 361 determines whether or not N binary object images are stored. If it is determined that N binary object images are not stored, the process returns to step S361. The motion compensation processing of the binary object image and the storage processing of the binary object image are repeated.

  If it is determined in step S363 that N binary object images have been stored, the process proceeds to step S364, and each of the weighting units 384-1 to 384-N adds w1 to w in each of the N binary object images. Multiply by one of the weights of wN.

  In step S365, the integration unit 385 integrates the weighted N binary object images.

  In step S366, the integrating unit 385 generates a binary object image from the integrated image, for example, by comparison with a predetermined threshold value th1, and the process ends.

  As described above, the region specifying unit 103 having the configuration shown in FIG. 66 can generate region information based on the robust binary object image.

  As described above, the area specifying unit 103 generates area information indicating that each of the pixels included in the frame belongs to the motion area, the still area, the uncovered background area, or the covered background area. Can do.

  FIG. 72 is a block diagram illustrating an example of the configuration of the mixture ratio calculation unit 104. Based on the input image, the estimated mixture ratio processing unit 401 calculates an estimated mixture ratio for each pixel by an operation corresponding to the model of the covered background area, and supplies the calculated estimated mixture ratio to the mixture ratio determining unit 403. To do.

  Based on the input image, the estimated mixture ratio processing unit 402 calculates an estimated mixture ratio for each pixel by an operation corresponding to the model of the uncovered background region, and the calculated estimated mixture ratio is sent to the mixture ratio determining unit 403. Supply.

  Since it can be assumed that the object corresponding to the foreground is moving at a constant speed within the shutter time, the mixture ratio α of the pixels belonging to the mixed area has the following properties. That is, the mixture ratio α changes linearly in response to changes in the pixel position. If the change in the pixel position is one-dimensional, the change in the mixture ratio α can be expressed by a straight line. If the change in the pixel position is two-dimensional, the change in the mixture ratio α is expressed by a plane. be able to.

  Since the period of one frame is short, it is assumed that the object corresponding to the foreground is a rigid body and moves at a constant speed.

  In this case, the gradient of the mixture ratio α is the inverse ratio of the motion amount v within the foreground shutter time.

  An example of an ideal mixing ratio α is shown in FIG. The gradient l in the mixing region of the ideal mixing ratio α can be expressed as the reciprocal of the motion amount v.

  As shown in FIG. 73, the ideal mixture ratio α has a value of 1 in the background region, a value of 0 in the foreground region, and a value greater than 0 and less than 1 in the mixed region. .

  In the example of FIG. 74, the pixel value C06 of the seventh pixel from the left of frame #n can be expressed by Expression (8) using the pixel value P06 of the seventh pixel from the left of frame # n-1. it can.

  In Expression (8), the pixel value C06 is expressed as the pixel value M of the pixel in the mixed region, and the pixel value P06 is expressed as the pixel value B of the pixel in the background region. That is, the pixel value M of the pixel in the mixed region and the pixel value B of the pixel in the background region can be expressed as Equation (9) and Equation (10), respectively.

M = C06
(9)
B = P06
(10)

  2 / v in equation (8) corresponds to the mixing ratio α. Since the motion amount v is 4, the mixture ratio α of the seventh pixel from the left of the frame #n is 0.5.

  As described above, the pixel value C of the focused frame #n is regarded as the pixel value of the mixed region, and the pixel value P of the frame # n-1 before the frame #n is regarded as the pixel value of the background region. Equation (3) indicating the mixing ratio α can be rewritten as Equation (11).

C = α ・ P + f
(11)

  F in Expression (11) is the sum ΣiFi / v of the foreground components included in the pixel of interest. There are two variables included in equation (11): the mixture ratio α and the sum f of the foreground components.

  Similarly, FIG. 75 shows a model in which pixel values are expanded in the time direction, with the amount of motion v being 4 and the number of virtual divisions in the time direction being 4, in the uncovered background area.

  In the uncovered background area, similarly to the above-described representation in the covered background area, the pixel value C of the frame #n of interest is regarded as the pixel value of the mixed area, and the frame # n + 1 after the frame #n Eq. (3) indicating the mixture ratio α can be expressed as Eq. (12) by regarding the pixel value N of と as the pixel value of the background region.

C = α ・ N + f
(12)

  Although it has been described that the background object is stationary, even when the background object is moving, by using the pixel value of the pixel at the position corresponding to the background motion amount v, the expression (8 ) To (12) can be applied. For example, in FIG. 74, when the motion amount v of the object corresponding to the background is 2 and the number of virtual divisions is 2, when the object corresponding to the background is moving to the right side in the figure, The pixel value B of the pixel in the background area is set to a pixel value P04.

  Since Expression (11) and Expression (12) each include two variables, the mixture ratio α cannot be obtained as it is. Here, since an image generally has a strong spatial correlation, adjacent pixels have almost the same pixel value.

  Therefore, since the foreground components have a strong spatial correlation, the formula is modified so that the sum f of the foreground components can be derived from the previous or subsequent frame to obtain the mixture ratio α.

  The pixel value Mc of the seventh pixel from the left in frame #n in FIG. 76 can be expressed by Expression (13).

  2 / v in the first term on the right side of Equation (13) corresponds to the mixing ratio α. The second term on the right side of Expression (13) is expressed as Expression (14) using the pixel value of the subsequent frame # n + 1.

  Here, Equation (15) is established using the spatial correlation of the foreground components.

F = F05 = F06 = F07 = F08 = F09 = F10 = F11 = F12
(15)
Expression (14) can be replaced with Expression (16) using Expression (15).

結果として、βは、式（１７）で表すことができる。

As a result, β can be expressed by equation (17).

β = 2/4
(17)

  In general, assuming that the foreground components related to the mixed region are equal as shown in Equation (15), Equation (18) is established from the relationship of the internal ratio for all the pixels in the mixed region.

β = 1-α
(18)

  If Expression (18) is established, Expression (11) can be expanded as shown in Expression (19).

  Similarly, if equation (18) holds, equation (12) can be expanded as shown in equation (20).

  In Expression (19) and Expression (20), C, N, and P are known pixel values, and therefore the variable included in Expression (19) and Expression (20) is only the mixture ratio α. FIG. 77 shows the relationship between C, N, and P in the equations (19) and (20). C is the pixel value of the pixel of interest in frame #n for calculating the mixture ratio α. N is a pixel value of a pixel in frame # n + 1 corresponding to a pixel of interest corresponding to a position in the spatial direction. P is a pixel value of a pixel in frame # n−1 in which the pixel of interest corresponds to the position in the spatial direction.

  Accordingly, since one variable is included in each of the equations (19) and (20), the mixture ratio α can be calculated using the pixel values of the pixels of the three frames. The condition for calculating the correct mixture ratio α by solving the equations (19) and (20) is that the foreground components related to the mixed region are equal, that is, the imaging is performed when the foreground object is stationary. In the foreground image object thus obtained, the pixel values of the pixels located at the boundary of the image object corresponding to the direction of the motion of the foreground object, which are twice as many as the movement amount v, are continuous. It is constant.

  As described above, the mixing ratio α of the pixels belonging to the covered background area is calculated by Expression (21), and the mixing ratio α of the pixels belonging to the uncovered background area is calculated by Expression (22).

α = (CN) / (PN)
(21)
α = (CP) / (NP)
(22)

  FIG. 78 is a block diagram illustrating a configuration of the estimated mixture ratio processing unit 401. The frame memory 421 stores the input image in units of frames, and supplies the frame immediately after the frame input as the input image to the frame memory 422 and the mixture ratio calculation unit 423.

  The frame memory 422 stores the input image in units of frames, and supplies the frame immediately after the frame supplied from the frame memory 421 to the mixture ratio calculation unit 423.

  Therefore, when the frame # n + 1 is input to the mixing ratio calculation unit 423 as an input image, the frame memory 421 supplies the frame #n to the mixing ratio calculation unit 423, and the frame memory 422 stores the frame # n− 1 is supplied to the mixture ratio calculation unit 423.

  The mixture ratio calculation unit 423 calculates the pixel value C of the pixel of interest in frame #n and the pixel of frame # n + 1 corresponding to the spatial position of the pixel of interest by the calculation shown in Expression (21). And the estimated mixture ratio of the pixel of interest was calculated based on the pixel value N of the pixel and the pixel value P of the pixel of frame # n-1 whose spatial position corresponds to the pixel of interest. Output the estimated mixture ratio. For example, when the background is stationary, the mixture ratio calculation unit 423 determines that the pixel value C of the pixel of interest in frame #n is the same as the pixel of interest in the frame # n + 1. Calculate the estimated mixture ratio of the pixel of interest based on the pixel value N of the pixel and the pixel value P of the pixel of frame # n-1, which has the same position in the frame as the pixel of interest. The estimated mixture ratio is output.

  As described above, the estimated mixture ratio processing unit 401 can calculate the estimated mixture ratio based on the input image and supply the estimated mixture ratio to the mixture ratio determining unit 403.

  The estimated mixture ratio processing unit 402 calculates the estimated mixture ratio of the pixel of interest by the calculation shown in the equation (21) by the estimated mixture ratio processing unit 401, whereas the calculation shown in the equation (22). Thus, the estimated mixture ratio processing unit 401 is the same as the estimated mixture ratio processing unit 401 except that a part for calculating the estimated mixture ratio of the pixel of interest is different.

  FIG. 79 is a diagram illustrating an example of the estimated mixture ratio calculated by the estimated mixture ratio processing unit 401. The estimated mixture ratio shown in FIG. 79 indicates the result when the foreground motion amount v corresponding to an object moving at a constant speed is 11, for one line.

  It can be seen that the estimated mixture ratio changes almost linearly in the mixed region as shown in FIG.

  Returning to FIG. 72, the mixture ratio determining unit 403 determines whether the pixel for which the mixture ratio α supplied from the region specifying unit 103 is to be calculated is a foreground area, a background area, a covered background area, or an uncovered background area. The mixing ratio α is set on the basis of the area information indicating which of the two. The mixture ratio determining unit 403 sets 0 as the mixture ratio α when the target pixel belongs to the foreground area, and sets 1 as the mixture ratio α when the target pixel belongs to the background area. When the pixel belongs to the covered background area, the estimated mixture ratio supplied from the estimated mixture ratio processing unit 401 is set to the mixture ratio α, and when the target pixel belongs to the uncovered background area, the estimated mixture ratio processing unit The estimated mixing ratio supplied from 402 is set to the mixing ratio α. The mixture ratio determination unit 403 outputs a mixture ratio α set based on the region information.

  FIG. 80 is a block diagram showing another configuration of the mixture ratio calculation unit 104. Based on the region information supplied from the region specifying unit 103, the selection unit 441 supplies the pixels belonging to the covered background region and the corresponding pixels of the previous and subsequent frames to the estimated mixture ratio processing unit 442. Based on the region information supplied from the region specifying unit 103, the selection unit 441 supplies the pixels belonging to the uncovered background region and the corresponding pixels in the previous and subsequent frames to the estimated mixture ratio processing unit 443. .

  Based on the pixel value input from the selection unit 441, the estimated mixture ratio processing unit 442 calculates the estimated mixture ratio of the pixel of interest belonging to the covered background region by the calculation shown in Expression (21). The calculated estimated mixture ratio is supplied to the selection unit 444.

  Based on the pixel value input from the selection unit 441, the estimated mixture ratio processing unit 443 calculates an estimated mixture ratio of the pixel of interest belonging to the uncovered background region by the calculation shown in Expression (22). Then, the calculated estimated mixture ratio is supplied to the selection unit 444.

  When the target pixel belongs to the foreground area based on the area information supplied from the area specifying unit 103, the selection unit 444 selects an estimated mixture ratio that is 0, sets the mixture ratio α, If the pixel belongs to the background region, an estimated mixture ratio of 1 is selected and set to the mixture ratio α. When the target pixel belongs to the covered background area, the selection unit 444 selects the estimated mixture ratio supplied from the estimated mixture ratio processing unit 442 and sets it to the mixture ratio α, and the target pixel is uncovered back. When belonging to the ground region, the estimated mixture ratio supplied from the estimated mixture ratio processing unit 443 is selected and set to the mixture ratio α. The selection unit 444 outputs the mixture ratio α selected and set based on the region information.

  In this way, the mixture ratio calculation unit 104 having another configuration shown in FIG. 80 can calculate the mixture ratio α for each pixel included in the image and output the calculated mixture ratio α.

  With reference to the flowchart of FIG. 81, the process of calculating the mixture ratio α of the mixture ratio calculator 104 shown in FIG. 72 will be described. In step S <b> 401, the mixture ratio calculation unit 104 acquires the region information supplied from the region specifying unit 103. In step S <b> 402, the estimated mixture ratio processing unit 401 performs an estimated mixture ratio calculation process using a model corresponding to the covered background region, and supplies the calculated estimated mixture ratio to the mixture ratio determining unit 403. Details of the calculation processing of the mixture ratio estimation will be described later with reference to the flowchart of FIG.

  In step S <b> 403, the estimated mixture ratio processing unit 402 performs an estimated mixture ratio calculation process using a model corresponding to the uncovered background region, and supplies the calculated estimated mixture ratio to the mixture ratio determining unit 403.

  In step S404, the mixture ratio calculation unit 104 determines whether or not the mixture ratio α is estimated for the entire frame. If it is determined that the mixture ratio α is not estimated for the entire frame, the process returns to step S402. Then, the process of estimating the mixture ratio α for the next pixel is executed.

  If it is determined in step S404 that the mixture ratio α has been estimated for the entire frame, the process proceeds to step S405, where the mixture ratio determination unit 403 determines that the pixel is a foreground area, background area, covered background area, or uncovered back. The mixture ratio α is set based on the area information supplied from the area specifying unit 103 indicating which of the ground areas belongs. The mixture ratio determining unit 403 sets 0 as the mixture ratio α when the target pixel belongs to the foreground area, and sets 1 as the mixture ratio α when the target pixel belongs to the background area. When the pixel belongs to the covered background area, the estimated mixture ratio supplied from the estimated mixture ratio processing unit 401 is set to the mixture ratio α, and when the target pixel belongs to the uncovered background area, the estimated mixture ratio processing unit The estimated mixture ratio supplied from 402 is set to the mixture ratio α, and the process ends.

  As described above, the mixture ratio calculation unit 104 can calculate the mixture ratio α, which is a feature amount corresponding to each pixel, based on the region information supplied from the region specifying unit 103 and the input image.

  The process of calculating the mixture ratio α by the mixture ratio calculation unit 104 having the configuration shown in FIG. 80 is the same as the process described with reference to the flowchart of FIG.

  Next, the mixing ratio estimation process using the model corresponding to the covered background area corresponding to step S402 in FIG. 81 will be described with reference to the flowchart in FIG.

  In step S421, the mixture ratio calculation unit 423 acquires the pixel value C of the target pixel of frame #n from the frame memory 421.

  In step S422, the mixture ratio calculation unit 423 acquires the pixel value P of the pixel of frame # n−1 corresponding to the target pixel from the frame memory 422.

  In step S423, the mixture ratio calculation unit 423 acquires the pixel value N of the pixel of frame # n + 1 corresponding to the target pixel included in the input image.

  In step S424, the mixture ratio calculation unit 423, based on the pixel value C of the pixel of interest in frame #n, the pixel value P of the pixel of frame # n-1, and the pixel value N of the pixel of frame # n + 1, Calculate the estimated mixture ratio.

  In step S425, the mixture ratio calculation unit 423 determines whether or not the process of calculating the estimated mixture ratio has been completed for the entire frame, and determines that the process of calculating the estimated mixture ratio has not been completed for the entire frame. If so, the process returns to step S421, and the process of calculating the estimated mixture ratio for the next pixel is repeated.

  If it is determined in step S425 that the process of calculating the estimated mixture ratio has been completed for the entire frame, the process ends.

  Thus, the estimated mixture ratio processing unit 401 can calculate the estimated mixture ratio based on the input image.

  The mixture ratio estimation process by the model corresponding to the uncovered background area in step S403 in FIG. 81 is the same as the process shown in the flowchart of FIG. 82 using the expression corresponding to the model of the uncovered background area. Description is omitted.

  Note that the estimated mixture ratio processing unit 442 and the estimated mixture ratio processing unit 443 illustrated in FIG. 80 perform the same processing as the flowchart illustrated in FIG. 82 to calculate the estimated mixture ratio, and thus description thereof is omitted.

  In addition, although it has been described that the object corresponding to the background is stationary, the above-described processing for obtaining the mixture ratio α can be applied even if the image corresponding to the background region includes a motion. For example, when the image corresponding to the background region is moving uniformly, the estimated mixture ratio processing unit 401 shifts the entire image corresponding to the movement of the background, and the object corresponding to the background is stationary. Process in the same way. In addition, when the image corresponding to the background region includes a different background motion for each local area, the estimated mixture ratio processing unit 401 selects a pixel corresponding to the background motion as a pixel corresponding to the pixel belonging to the mixed region. Then, the above-described processing is executed.

  In addition, the mixture ratio calculation unit 104 executes only the mixture ratio estimation process using the model corresponding to the covered background region for all pixels, and outputs the calculated estimated mixture ratio as the mixture ratio α. Also good. In this case, the mixing ratio α indicates the ratio of the background components for the pixels belonging to the covered background area, and indicates the ratio of the foreground components for the pixels belonging to the uncovered background area. If the absolute value of the difference between the mixture ratio α and 1 calculated in this way is calculated for the pixels belonging to the uncovered background area, and the calculated absolute value is set to the mixture ratio α, the separation processing server 11 For the pixels belonging to the uncovered background area, the mixing ratio α indicating the ratio of the background components can be obtained.

  Similarly, the mixture ratio calculation unit 104 executes only the mixture ratio estimation process using the model corresponding to the uncovered background area for all pixels, and outputs the calculated estimated mixture ratio as the mixture ratio α. You may make it do.

  Next, the mixing ratio calculation unit 104 that calculates the mixing ratio α using the property that the mixing ratio α changes linearly will be described.

  As described above, since the equations (11) and (12) each include two variables, the mixture ratio α cannot be obtained as it is.

  Therefore, using the property that the mixing ratio α changes linearly in response to changes in the pixel position due to the object corresponding to the foreground moving at a constant speed within the shutter time, mixing is performed in the spatial direction. An expression that approximates the ratio α and the sum f of the foreground components is established. By using a plurality of sets of pixel values of pixels belonging to the mixed area and pixel values belonging to the background area, an equation that approximates the mixing ratio α and the sum f of the foreground components is solved.

  When the change in the mixing ratio α is approximated as a straight line, the mixing ratio α is expressed by Expression (23).

α = il + p
(23)

  In Expression (23), i is an index in the spatial direction where the position of the pixel of interest is 0. l is the slope of the straight line of the mixing ratio α. p is a straight line intercept of the mixing ratio α and is the mixing ratio α of the pixel of interest. In equation (23), the index i is known, but the slope l and the intercept p are unknown.

  FIG. 83 shows the relationship between the index i, the slope l, and the intercept p.

  By approximating the mixture ratio α as shown in Expression (23), a plurality of different mixture ratios α are expressed by two variables for a plurality of pixels. In the example shown in FIG. 83, five mixing ratios for five pixels are expressed by two variables, gradient l and intercept p.

  Approximating the mixture ratio α in the plane shown in FIG. 84, when considering the motion v corresponding to two directions of the horizontal direction and the vertical direction of the image, the formula (23) is expanded to a plane, and the mixture ratio α is It is represented by Formula (24).

α = jm + kq + p
(24)

  In Expression (24), j is a horizontal index with the position of the pixel of interest being 0, and k is a vertical index. m is the horizontal inclination of the surface of the mixing ratio α, and q is the vertical inclination of the surface of the mixing ratio α. p is an intercept of the surface of the mixing ratio α.

  For example, in frame #n shown in FIG. 74, equations (25) to (27) are established for C05 to C07, respectively.

C05 = α05 ・ B05 / v + f05
(25)
C06 = α06 ・ B06 / v + f06
(26)
C07 = α07 ・ B07 / v + f07
(27)

  When the foreground components match in the vicinity, that is, F01 to F03 are equal, and F01 to F03 are replaced with Fc, Expression (28) is established.

f (x) = (1-α (x)) ・ Fc
(28)

  In Expression (28), x represents a position in the spatial direction.

  When α (x) is replaced with Expression (24), Expression (28) can be expressed as Expression (29).

f (x) = (1- (jm + kq + p)) ・ Fc
= j ・ (-m ・ Fc) + k ・ (-q ・ Fc) + ((1-p) ・ Fc)
= js + kt + u
(29)

  In the equation (29), (−m · Fc), (−q · Fc), and (1-p) · Fc are replaced as shown in the equations (30) to (32).

s = -m ・ Fc
(30)
t = -q ・ Fc
(31)
u = (1-p) ・ Fc
(32)

  In Expression (29), j is a horizontal index with the position of the pixel of interest as 0, and k is a vertical index.

  In this way, since it is assumed that the object corresponding to the foreground moves at a constant speed within the shutter time and the component corresponding to the foreground is constant in the vicinity, the sum of the foreground components is expressed by Equation (29). Approximated.

  When the mixture ratio α is approximated by a straight line, the sum of the foreground components can be expressed by Expression (33).

f (x) = is + u
(33)

  When the sum of the mixture ratio α and the foreground component in Expression (13) is replaced using Expression (24) and Expression (29), the pixel value M is expressed by Expression (34).

M = (jm + kq + p) ・ B + js + kt + u
= jB ・ m + kB ・ q + B ・ p + j ・ s + k ・ t + u
(34)

  In equation (34), the unknown variables are the horizontal gradient m of the surface of the mixing ratio α, the vertical inclination q of the surface of the mixing ratio α, the intercepts p, s, t, and u of the surface of the mixing ratio α. These are six.

  A plurality of normal equations in which the pixel value M or the pixel value B is set in the normal equation shown in the equation (34) in correspondence with the pixel in the vicinity of the pixel of interest, and the pixel value M or the pixel value B is set. Is calculated by the method of least squares to calculate the mixture ratio α.

  For example, the horizontal index j of the pixel of interest is set to 0, the index k of the vertical direction is set to 0, and a 3 × 3 pixel in the vicinity of the pixel of interest is expressed by the normal equation shown in Expression (34). When the pixel value M or the pixel value B is set, Expressions (35) to (43) are obtained.

M _{-1, -1} = ( _-1 ) ・ B _{-1, -1}・ m + ( _-1 ) ・ B _{-1, -1}・ q + B _{-1, -1}・ p + ( _-1 ) ・ s + (- 1) ・ t + u
(35)
M _{0, -1} = (0) ・ B _{0, -1}・ m + ( _-1 ) ・ B _{0, -1}・ q + B _{0, -1}・ p + (0) ・ s + (-1) ・ t + u
(36)
M _{+ 1, -1} = (+ 1) ・ B _{+ 1, -1}・ m + ( _-1 ) ・ B _{+ 1, -1}・ q + B _{+ 1, -1}・ p + (+ 1) ・ s + (- 1) ・ t + u
(37)
M _-1,0 = ( _-1 ) ・ B _-1,0・ m + (0) ・ B _-1,0・ q + B _-1,0・ p + ( _-1 ) ・ s + (0) ・ t + u
(38)
M _0,0 = (0) ・ B _0,0・ m + (0) ・ B _0,0・ q + B _0,0・ p + (0) ・ s + (0) ・ t + u
(39)
M _+1,0 = (+ 1) ・ B _+1,0・ m + (0) ・ B _+1,0・ q + B _+1,0・ p + (+ 1) ・ s + (0) ・ t + u
(40)
M _{-1, + 1} = ( _-1 ) ・ B _{-1, + 1}・ m + (+ 1) ・ B _{-1, + 1}・ q + B _{-1, + 1}・ p + ( _-1 ) ・ s + (+ 1) ・ t + u
(41)
M _{0, + 1} = (0) ・ B _{0, + 1}・ m + (+ 1) ・ B _{0, + 1}・ q + B _{0, + 1}・ p + (0) ・ s + (+ 1) ・ t + u
(42)
M _{+ 1, + 1} = (+1) ・ B _{+ 1, + 1}・ m + (+ 1) ・ B _{+ 1, + 1}・ q + B _{+ 1, + 1}・ p + (+ 1) ・ s + (+ 1) ・ t + u
(43)

  Since the index j in the horizontal direction of the pixel of interest is 0 and the index k in the vertical direction is 0, the mixture ratio α of the pixel of interest is expressed by j = 0 and k = It is equal to the value at 0, that is, the intercept p.

  Accordingly, based on the nine equations (35) to (43), the values of the horizontal gradient m, the vertical gradient q, the intercepts p, s, t, and u are calculated by the method of least squares. The intercept p may be output as the mixing ratio α.

  Next, a more specific procedure for calculating the mixture ratio α by applying the least square method will be described.

  When the index i and the index k are expressed by one index x, the relationship between the index i, the index k, and the index x is expressed by Expression (44).

x = (j + 1) ・ 3+ (k + 1)
(44)

  Express horizontal slope m, vertical slope q, intercepts p, s, t, and u as variables w0, w1, w2, w3, w4, and W5, respectively, jB, kB, B, j, k, And 1 are expressed as a0, a1, a2, a3, a4, and a5, respectively. In consideration of the error ex, Expressions (35) to (43) can be rewritten into Expression (45).

  In the formula (45), x is an integer value from 0 to 8.

  From equation (45), equation (46) can be derived.

  Here, in order to apply the method of least squares, an error sum of squares E is defined as shown in equation (47).

  In order to minimize the error, it is only necessary that the partial differentiation of the variable Wv with respect to the square sum E of the error becomes zero. Here, v is one of integers from 0 to 5. Therefore, wy is obtained so as to satisfy the equation (48).

  Substituting equation (46) into equation (48) yields equation (49).

  For example, a sweep method (Gauss-Jordan elimination method) is applied to six formulas obtained by substituting any one of integers 0 to 5 for v in formula (49) to calculate wy. . As described above, w0 is the horizontal gradient m, w1 is the vertical gradient q, w2 is the intercept p, w3 is s, w4 is t, and w5 is u.

  As described above, horizontal slope m, vertical slope q, intercepts p, s, t, and u are obtained by applying the method of least squares to the equation in which pixel value M and pixel value B are set. be able to.

  In the description corresponding to the expressions (35) to (43), the pixel value of the pixel included in the mixed area has been described as M, and the pixel value of the pixel included in the background area has been described as B. Therefore, it is necessary to establish a normal equation for each of the cases where they are included in the covered background region or the uncovered background region.

  For example, when obtaining the mixture ratio α of pixels included in the covered background area of frame #n shown in FIG. 74, pixel values P04 to C08 of pixels of frame #n and pixel values P04 to P08 of frame # n−1 P08 is set as a normal equation.

  When obtaining the mixture ratio α of pixels included in the uncovered background area of frame #n shown in FIG. 75, pixel values N28 to N32 of pixels C28 to C32 of frame #n and pixels of frame # n + 1 Is set to a normal equation.

  For example, when calculating the mixture ratio α of the pixels included in the covered background region shown in FIG. 85, the following equations (50) to (58) are established. The pixel value of the pixel for calculating the mixture ratio α is Mc5.

Mc1 = (-1) ・ Bc1 ・ m + (-1) ・ Bc1 ・ q + Bc1 ・ p + (-1) ・ s + (-1) ・ t + u
(50)
Mc2 = (0) ・ Bc2 ・ m + (-1) ・ Bc2 ・ q + Bc2 ・ p + (0) ・ s + (-1) ・ t + u
(51)
Mc3 = (+ 1) ・ Bc3 ・ m + (-1) ・ Bc3 ・ q + Bc3 ・ p + (+ 1) ・ s + (-1) ・ t + u
(52)
Mc4 = (-1) ・ Bc4 ・ m + (0) ・ Bc4 ・ q + Bc4 ・ p + (-1) ・ s + (0) ・ t + u
(53)
Mc5 = (0) ・ Bc5 ・ m + (0) ・ Bc5 ・ q + Bc5 ・ p + (0) ・ s + (0) ・ t + u
(54)
Mc6 = (+ 1) ・ Bc6 ・ m + (0) ・ Bc6 ・ q + Bc6 ・ p + (+ 1) ・ s + (0) ・ t + u
(55)
Mc7 = (-1) ・ Bc7 ・ m + (+ 1) ・ Bc7 ・ q + Bc7 ・ p + (-1) ・ s + (+ 1) ・ t + u
(56)
Mc8 = (0) ・ Bc8 ・ m + (+ 1) ・ Bc8 ・ q + Bc8 ・ p + (0) ・ s + (+ 1) ・ t + u
(57)
Mc9 = (+ 1) ・ Bc9 ・ m + (+ 1) ・ Bc9 ・ q + Bc9 ・ p + (+ 1) ・ s + (+ 1) ・ t + u
(58)

  When calculating the mixture ratio α of the pixels included in the covered background area of frame #n, the background of the pixel of frame # n−1 corresponding to the pixel of frame #n in equations (50) to (58) Pixel values Bc1 to Bc9 of the pixels in the area are used.

  When calculating the mixture ratio α of the pixels included in the uncovered background area shown in FIG. 85, the following equations (59) to (67) are established. The pixel value of the pixel for calculating the mixture ratio α is Mu5.

Mu1 = (-1) ・ Bu1 ・ m + (-1) ・ Bu1 ・ q + Bu1 ・ p + (-1) ・ s + (-1) ・ t + u
(59)
Mu2 = (0) ・ Bu2 ・ m + (-1) ・ Bu2 ・ q + Bu2 ・ p + (0) ・ s + (-1) ・ t + u
(60)
Mu3 = (+ 1) ・ Bu3 ・ m + (-1) ・ Bu3 ・ q + Bu3 ・ p + (+ 1) ・ s + (-1) ・ t + u
(61)
Mu4 = (-1) ・ Bu4 ・ m + (0) ・ Bu4 ・ q + Bu4 ・ p + (-1) ・ s + (0) ・ t + u
(62)
Mu5 = (0) ・ Bu5 ・ m + (0) ・ Bu5 ・ q + Bu5 ・ p + (0) ・ s + (0) ・ t + u
(63)
Mu6 = (+ 1) ・ Bu6 ・ m + (0) ・ Bu6 ・ q + Bu6 ・ p + (+ 1) ・ s + (0) ・ t + u
(64)
Mu7 = (-1) ・ Bu7 ・ m + (+ 1) ・ Bu7 ・ q + Bu7 ・ p + (-1) ・ s + (+ 1) ・ t + u
(65)
Mu8 = (0) ・ Bu8 ・ m + (+ 1) ・ Bu8 ・ q + Bu8 ・ p + (0) ・ s + (+ 1) ・ t + u
(66)
Mu9 = (+ 1) ・ Bu9 ・ m + (+ 1) ・ Bu9 ・ q + Bu9 ・ p + (+ 1) ・ s + (+ 1) ・ t + u
(67)

  When calculating the mixture ratio α of the pixels included in the uncovered background area of frame #n, in the equations (59) to (67), the pixels of the frame # n + 1 corresponding to the pixels of the frame #n are calculated. The pixel values Bu1 to Bu9 of the pixels in the background area are used.

  FIG. 86 is a block diagram illustrating a configuration of the estimated mixture ratio processing unit 401. The image input to the estimated mixture ratio processing unit 401 is supplied to the delay unit 501 and the adding unit 502.

  The delay circuit 221 delays the input image by one frame and supplies it to the adding unit 502. When the frame #n is input as an input image to the adding unit 502, the delay circuit 221 supplies the frame # n-1 to the adding unit 502.

  The adding unit 502 sets the pixel value of the pixel near the pixel for calculating the mixture ratio α and the pixel value of the frame # n−1 in a normal equation. For example, the adding unit 502 sets the pixel values Mc1 to Mc9 and the pixel values Bc1 to Bc9 in the normal equation based on the equations (50) to (58). The adding unit 502 supplies the normal equation in which the pixel value is set to the calculation unit 503.

  The computing unit 503 solves the normal equation supplied from the adding unit 502 by a sweeping method or the like to obtain an estimated mixture ratio, and outputs the obtained estimated mixture ratio.

  As described above, the estimated mixture ratio processing unit 401 can calculate the estimated mixture ratio based on the input image and supply the estimated mixture ratio to the mixture ratio determining unit 403.

  Note that the estimated mixture ratio processing unit 402 has the same configuration as the estimated mixture ratio processing unit 401, and thus description thereof is omitted.

  FIG. 87 is a diagram illustrating an example of the estimated mixture ratio calculated by the estimated mixture ratio processing unit 401. The estimated mixture ratio shown in FIG. 87 indicates that the foreground motion v corresponding to an object moving at a constant speed is 11, and the result of calculating an equation with a block of 7 × 7 pixels as a unit is 1 line. Is shown.

  It can be seen that the estimated mixture ratio changes substantially linearly in the mixed region as shown in FIG.

  Next, the mixing ratio estimation processing by the model corresponding to the covered background area by the estimated mixing ratio processing unit 401 having the configuration shown in FIG. 86 will be described with reference to the flowchart of FIG.

  In step S521, the adding unit 502 sets the pixel value included in the input image and the pixel value included in the image supplied from the delay circuit 221 to a normal equation corresponding to the model of the covered background area. .

  In step S522, the estimated mixture ratio processing unit 401 determines whether or not the setting for the target pixel has been completed. If it is determined that the setting for the target pixel has not been completed, the process proceeds to step S521. Returning, the process of setting the pixel value to the normal equation is repeated.

  If it is determined in step S522 that the pixel value setting for the target pixel has been completed, the process proceeds to step S523, and the calculation unit 173 calculates the estimated mixture ratio based on the normal equation in which the pixel value is set. Then, the obtained estimated mixture ratio is output.

  As described above, the estimated mixture ratio processing unit 401 having the configuration shown in FIG. 86 can calculate the estimated mixture ratio based on the input image.

  The mixing ratio estimation process using the model corresponding to the uncovered background area is the same as the process shown in the flowchart of FIG. 88 using the normal equation corresponding to the model of the uncovered background area.

  Note that although the object corresponding to the background has been described as stationary, the above-described processing for obtaining the mixture ratio can be applied even if the image corresponding to the background area includes movement. For example, when the image corresponding to the background region is moving uniformly, the estimated mixture ratio processing unit 401 shifts the entire image corresponding to this movement, and is the same as when the object corresponding to the background is stationary. To process. Further, when the image corresponding to the background region includes a different motion for each local area, the estimated mixture ratio processing unit 401 selects a pixel corresponding to the motion as a pixel corresponding to the pixel belonging to the mixed region, and Execute the process.

  As described above, the mixture ratio calculation unit 102 can calculate the mixture ratio α, which is a feature amount corresponding to each pixel, based on the region information supplied from the region specifying unit 101 and the input image.

  By using the mixing ratio α, it becomes possible to separate the foreground component and the background component included in the pixel value while leaving the motion blur information included in the image corresponding to the moving object. .

  Also, by compositing images based on the mixture ratio α, it is possible to create an image including correct motion blur that matches the speed of a moving object as if the real world was actually recaptured.

  Next, the foreground / background separation unit 105 will be described. FIG. 89 is a block diagram illustrating an example of the configuration of the foreground / background separator 105. The input image supplied to the foreground / background separator 105 is supplied to the separator 601, the switch 602, and the switch 604. The information indicating the covered background area and the area information supplied from the area specifying unit 103 indicating the uncovered background area are supplied to the separation unit 601. Area information indicating the foreground area is supplied to the switch 602. Area information indicating the background area is supplied to the switch 604.

  The mixing ratio α supplied from the mixing ratio calculation unit 104 is supplied to the separation unit 601.

  The separation unit 601 separates the foreground components from the input image based on the region information indicating the covered background region, the region information indicating the uncovered background region, and the mixing ratio α, and synthesizes the separated foreground components. The background component is separated from the input image, and the separated background component is supplied to the synthesis unit 605.

  The switch 602 is closed when a pixel corresponding to the foreground is input based on the region information indicating the foreground region, and supplies only the pixel corresponding to the foreground included in the input image to the combining unit 603.

  The switch 604 is closed when a pixel corresponding to the background is input based on the region information indicating the background region, and supplies only the pixel corresponding to the background included in the input image to the combining unit 605.

  The combining unit 603 combines the foreground component image based on the component corresponding to the foreground supplied from the separation unit 601 and the pixel corresponding to the foreground supplied from the switch 602, and outputs the combined foreground component image. Since the foreground area and the mixed area do not overlap, the synthesis unit 603 synthesizes the foreground component image by applying a logical sum operation to the component corresponding to the foreground and the pixel corresponding to the foreground, for example.

  In the initialization process executed at the beginning of the foreground component image synthesis process, the synthesis unit 603 stores an image in which all pixel values are 0 in the built-in frame memory, and performs synthesis of the foreground component image. In the process, the foreground component image is stored (overwritten). Accordingly, 0 is stored as the pixel value in the pixel corresponding to the background area in the foreground component image output by the synthesis unit 603.

  The combining unit 605 combines the background component images based on the components corresponding to the background supplied from the separation unit 601 and the pixels corresponding to the background supplied from the switch 604, and outputs the combined background component image. Since the background area and the mixed area do not overlap, the synthesis unit 605 synthesizes the background component image by applying a logical sum operation to the component corresponding to the background and the pixel corresponding to the background, for example.

  In the initialization process executed at the beginning of the background component image synthesis process, the synthesis unit 605 stores an image in which all pixel values are 0 in the built-in frame memory, and performs synthesis of the background component image. In the processing, the background component image is stored (overwritten). Accordingly, 0 is stored as the pixel value in the pixel corresponding to the foreground area in the background component image output from the synthesis unit 605.

  FIG. 90 is a diagram illustrating an input image input to the foreground / background separator 105 and a foreground component image and a background component image output from the foreground / background separator 105.

  FIG. 90A is a schematic diagram of a displayed image, and FIG. 90B shows pixels belonging to the foreground area, pixels belonging to the background area, and pixels belonging to the mixed area corresponding to FIG. 90A. 1 is a model diagram in which one line of pixels including is expanded in the time direction.

  As shown in FIGS. 90A and 90B, the background component image output from the foreground / background separation unit 105 is composed of pixels belonging to the background area and background components included in the pixels of the mixed area. The

  As shown in FIGS. 90A and 90B, the foreground component image output from the foreground / background separation unit 105 includes pixels belonging to the foreground area and foreground components included in the pixels of the mixed area. The

  The pixel values of the pixels in the mixed region are separated into a background component and a foreground component by the foreground / background separation unit 105. The separated background components together with the pixels belonging to the background area constitute a background component image. The separated foreground components together with the pixels belonging to the foreground area constitute a foreground component image.

  Thus, in the foreground component image, the pixel value of the pixel corresponding to the background area is set to 0, and a meaningful pixel value is set to the pixel corresponding to the foreground area and the pixel corresponding to the mixed area. Similarly, in the background component image, the pixel value of the pixel corresponding to the foreground area is set to 0, and a meaningful pixel value is set to the pixel corresponding to the background area and the pixel corresponding to the mixed area.

  Next, a process performed by the separation unit 601 to separate the foreground components and the background components from the pixels belonging to the mixed area will be described.

  FIG. 91 is an image model showing foreground components and background components of two frames including a foreground corresponding to an object moving from left to right in the drawing. In the image model shown in FIG. 91, the foreground motion amount v is 4, and the number of virtual divisions is 4.

  In frame #n, the leftmost pixel and the fourteenth through eighteenth pixels from the left consist only of background components and belong to the background area. In frame #n, the second through fourth pixels from the left include a background component and a foreground component, and belong to the uncovered background area. In frame #n, the eleventh through thirteenth pixels from the left include a background component and a foreground component, and belong to the covered background area. In frame #n, the fifth through tenth pixels from the left consist of only the foreground components and belong to the foreground area.

  In frame # n + 1, the first through fifth pixels from the left and the eighteenth pixel from the left consist of only the background components, and belong to the background area. In frame # n + 1, the sixth through eighth pixels from the left include a background component and a foreground component, and belong to the uncovered background area. In frame # n + 1, the fifteenth through seventeenth pixels from the left include a background component and a foreground component, and belong to the covered background area. In frame # n + 1, the ninth through fourteenth pixels from the left consist of only the foreground components, and belong to the foreground area.

  FIG. 92 is a diagram illustrating processing for separating foreground components from pixels belonging to the covered background area. In FIG. 92, α1 to α18 are mixing ratios corresponding to the respective pixels in frame #n. In FIG. 92, the fifteenth through seventeenth pixels from the left belong to the covered background area.

  The pixel value C15 of the fifteenth pixel from the left in frame #n is expressed by equation (68).

C15 = B15 / v + F09 / v + F08 / v + F07 / v
= α15 ・ B15 + F09 / v + F08 / v + F07 / v
= α15 ・ P15 + F09 / v + F08 / v + F07 / v
(68)
Here, α15 is the mixture ratio of the fifteenth pixel from the left in frame #n. P15 is the pixel value of the fifteenth pixel from the left in frame # n-1.

  Based on Expression (68), the sum f15 of the foreground components of the fifteenth pixel from the left in frame #n is expressed by Expression (69).

f15 = F09 / v + F08 / v + F07 / v
= C15-α15 ・ P15
(69)

  Similarly, the foreground component sum f16 of the 16th pixel from the left in frame #n is expressed by Equation (70), and the foreground component sum f17 of the 17th pixel from the left in frame #n is expressed by Equation (70). (71)

f16 = C16-α16 ・ P16
(70)
f17 = C17-α17 ・ P17
(71)

  In this way, the foreground component fc included in the pixel value C of the pixel belonging to the covered background area is calculated by Expression (72).

fc = C-α ・ P
(72)

  P is the pixel value of the corresponding pixel in the previous frame.

  FIG. 93 is a diagram for explaining processing for separating foreground components from pixels belonging to the uncovered background area. In FIG. 93, α1 to α18 are mixing ratios corresponding to the respective pixels in frame #n. In FIG. 93, the second through fourth pixels from the left belong to the uncovered background area.

  The pixel value C02 of the second pixel from the left in frame #n is expressed by Expression (73).

C02 = B02 / v + B02 / v + B02 / v + F01 / v
= α2 ・ B02 + F01 / v
= α2 ・ N02 + F01 / v
(73)

  Here, α2 is the mixture ratio of the second pixel from the left in frame #n. N02 is the pixel value of the second pixel from the left in frame # n + 1.

  Based on Expression (73), the sum f02 of the foreground components of the second pixel from the left in frame #n is expressed by Expression (74).

f02 = F01 / v
= C02-α2 ・ N02
(74)

  Similarly, the sum f03 of the foreground components of the third pixel from the left in frame #n is expressed by Expression (75), and the sum f04 of the foreground components of the fourth pixel from the left of frame #n is expressed by Expression (75). (76)

f03 = C03-α3 ・ N03
(75)
f04 = C04-α4 ・ N04
(76)

  In this way, the foreground component fu included in the pixel value C of the pixel belonging to the uncovered background area is calculated by Expression (77).

fu = C-α ・ N
(77)

  N is the pixel value of the corresponding pixel in the next frame.

  As described above, the separation unit 601 determines from the pixels belonging to the mixed region based on the information indicating the covered background region, the information indicating the uncovered background region, and the mixing ratio α for each pixel included in the region information. Foreground and background components can be separated.

  FIG. 94 is a block diagram showing an example of the configuration of the separation unit 601 that executes the processing described above. The image input to the separation unit 601 is supplied to the frame memory 621, and the region information indicating the covered background region and the uncovered background region supplied from the mixture ratio calculation unit 104, and the mixture ratio α are the separation processing block. It is input to 622.

  The frame memory 621 stores the input image in units of frames. When the object of processing is frame #n, the frame memory 621 is a frame that is the frame immediately after frame # n-1, frame #n, and frame #n. Remember # n + 1.

  The frame memory 621 supplies the pixels corresponding to the frame # n−1, the frame #n, and the frame # n + 1 to the separation processing block 622.

  The separation processing block 622 includes the frame # n−1, the frame #n, and the frame #n supplied from the frame memory 621 based on the area information indicating the covered background area and the uncovered background area, and the mixing ratio α. The operation described with reference to FIGS. 92 and 93 is applied to the pixel value of the corresponding pixel of +1 to separate the foreground component and the background component from the pixels belonging to the mixed region of frame #n, and This is supplied to the memory 623.

  The separation processing block 622 includes an uncovered area processing unit 631, a covered area processing unit 632, a combining unit 633, and a combining unit 634.

  The multiplier 641 of the uncovered area processing unit 631 multiplies the mixing ratio α by the pixel value of the pixel of frame # n + 1 supplied from the frame memory 621 and outputs the result to the switch 642. The switch 642 is closed when the pixel of frame #n (corresponding to the pixel of frame # n + 1) supplied from the frame memory 621 is an uncovered background area, and the mixture ratio supplied from the multiplier 641 The pixel value multiplied by α is supplied to the calculator 643 and the synthesis unit 634. The value obtained by multiplying the pixel value of the pixel of frame # n + 1 output from the switch 642 by the mixing ratio α is equal to the background component of the pixel value of the corresponding pixel of frame #n.

  The computing unit 643 subtracts the background component supplied from the switch 642 from the pixel value of the pixel of frame #n supplied from the frame memory 621 to obtain the foreground component. The computing unit 643 supplies the foreground component of the pixel of frame #n belonging to the uncovered background area to the synthesis unit 633.

  The multiplier 651 of the covered area processing unit 632 multiplies the mixture ratio α by the pixel value of the pixel of frame # n−1 supplied from the frame memory 621 and outputs the result to the switch 652. The switch 652 is closed when the pixel of the frame #n supplied from the frame memory 621 (corresponding to the pixel of the frame # n−1) is the covered background region, and the mixture ratio α supplied from the multiplier 651 is The pixel value multiplied by is supplied to the calculator 653 and the combining unit 634. A value obtained by multiplying the pixel value of the pixel of frame # n−1 output from the switch 652 by the mixing ratio α is equal to the background component of the pixel value of the corresponding pixel of frame #n.

  The arithmetic unit 653 subtracts the background component supplied from the switch 652 from the pixel value of the pixel of frame #n supplied from the frame memory 621 to obtain the foreground component. The calculator 653 supplies the foreground components of the pixels of the frame #n belonging to the covered background area to the synthesis unit 633.

  The synthesizer 633 outputs the foreground components of the pixel belonging to the uncovered background area supplied from the calculator 643 and the foreground of the pixel belonging to the covered background area supplied from the calculator 653 of the frame #n. The components are combined and supplied to the frame memory 623.

  The combining unit 634 receives the background component of the pixel belonging to the uncovered background area supplied from the switch 642 and the background component of the pixel belonging to the covered background area supplied from the switch 652 of the frame #n. Combined and supplied to the frame memory 623.

  The frame memory 623 stores the foreground components and the background components of the pixels in the mixed area of the frame #n supplied from the separation processing block 622, respectively.

  The frame memory 623 outputs the stored foreground components of the pixels in the mixed area of frame #n and the stored background components of the pixels of the mixed area in frame #n.

  By using the mixture ratio α, which is a feature amount, it is possible to completely separate the foreground component and the background component included in the pixel value.

  The synthesizing unit 603 combines the foreground components of the pixels in the mixed area of frame #n output from the separating unit 601 with the pixels belonging to the foreground area to generate a foreground component image. The synthesizing unit 605 synthesizes the background component of the pixel in the mixed area of frame #n output from the separating unit 601 and the pixel belonging to the background area to generate a background component image.

  FIG. 95 is a diagram illustrating an example of the foreground component image and an example of the background component image corresponding to frame #n in FIG.

  FIG. 95A shows an example of a foreground component image corresponding to frame #n in FIG. Since the leftmost pixel and the fourteenth pixel from the left consist of only background components before the foreground and the background are separated, the pixel value is set to zero.

  The second through fourth pixels from the left belong to the uncovered background area before the foreground and the background are separated, the background component is 0, and the foreground component is left as it is. The eleventh to thirteenth pixels from the left belong to the covered background area before the foreground and the background are separated, the background component is 0, and the foreground component is left as it is. The fifth through tenth pixels from the left are composed of only the foreground components and are left as they are.

  FIG. 95B shows an example of the background component image corresponding to frame #n in FIG. The leftmost pixel and the fourteenth pixel from the left are left as they are because they consisted only of the background components before the foreground and the background were separated.

  The second through fourth pixels from the left belong to the uncovered background area before the foreground and the background are separated, the foreground components are set to 0, and the background components are left as they are. The eleventh to thirteenth pixels from the left belong to the covered background area before the foreground and the background are separated, and the foreground components are set to 0 and the background components are left as they are. Since the fifth through tenth pixels from the left consist of only the foreground components before the foreground and the background are separated, the pixel value is set to zero.

  Next, foreground / background separation processing by the foreground / background separation unit 105 will be described with reference to a flowchart shown in FIG. In step S601, the frame memory 621 of the separation unit 601 obtains an input image, and determines the frame #n to be separated from the foreground and the background as the previous frame # n-1 and the subsequent frame # n + 1. Remember with.

  In step S <b> 602, the separation processing block 622 of the separation unit 601 acquires the region information supplied from the mixture ratio calculation unit 104. In step S <b> 603, the separation processing block 622 of the separation unit 601 acquires the mixture ratio α supplied from the mixture ratio calculation unit 104.

  In step S604, the uncovered area processing unit 631 extracts a background component from the pixel values of the pixels belonging to the uncovered background area supplied from the frame memory 621 based on the area information and the mixture ratio α.

  In step S605, the uncovered area processing unit 631 extracts the foreground components from the pixel values of the pixels belonging to the uncovered background area supplied from the frame memory 621 based on the area information and the mixture ratio α.

  In step S606, the covered area processing unit 632 extracts a background component from the pixel values of the pixels belonging to the covered background area supplied from the frame memory 621 based on the area information and the mixture ratio α.

  In step S607, the covered area processing unit 632 extracts the foreground components from the pixel values of the pixels belonging to the covered background area supplied from the frame memory 621 based on the area information and the mixture ratio α.

  In step S608, the synthesizer 633 extracts the foreground components of the pixels belonging to the uncovered background area extracted in step S605 and the foreground components of the pixels belonging to the covered background area extracted in step S607. And synthesize. The synthesized foreground components are supplied to the synthesis unit 603. Further, the synthesizing unit 603 combines the pixels belonging to the foreground area supplied via the switch 602 with the foreground components supplied from the separating unit 601 to generate a foreground component image.

  In step S609, the synthesizer 634 extracts the background component of the pixel belonging to the uncovered background area extracted in step S604 and the background component of the pixel belonging to the covered background area extracted in step S606. And synthesize. The synthesized background component is supplied to the synthesis unit 605. Furthermore, the synthesis unit 605 synthesizes the pixels belonging to the background area supplied via the switch 604 and the background components supplied from the separation unit 601 to generate a background component image.

  In step S610, the synthesis unit 603 outputs the foreground component image. In step S611, the synthesis unit 605 outputs a background component image, and the process ends.

  As described above, the foreground / background separation unit 105 separates the foreground component and the background component from the input image based on the region information and the mixture ratio α, and the foreground component image including only the foreground component and the background A background component image consisting only of components can be output.

  Next, adjustment of the amount of motion blur in the foreground component image will be described.

  FIG. 97 is a block diagram illustrating an example of the configuration of the motion blur adjustment unit 106. The motion vector and its position information supplied from the motion detection unit 102 are supplied to the processing unit determination unit 801, the modeling unit 802, and the calculation unit 805. The area information supplied from the area specifying unit 103 is supplied to the processing unit determination unit 801. The foreground component image supplied from the foreground / background separation unit 105 is supplied to the adding unit 804.

  The processing unit determination unit 801 generates a processing unit based on the motion vector, its position information, and region information, and supplies the generated processing unit to the modeling unit 802 and the adding unit 804.

  As shown in FIG. 98, the processing unit generated by the processing unit determination unit 801 starts from a pixel corresponding to the covered background area of the foreground component image, and moves in the direction of movement to the pixel corresponding to the uncovered background area. A continuous pixel lined up in a moving direction starting from a pixel lined up or a pixel corresponding to an uncovered background area to a pixel corresponding to a covered background area is shown. The processing unit is composed of, for example, two pieces of data: an upper left point (a pixel specified by the processing unit and located at the leftmost or uppermost pixel on the image) and a lower right point.

  The modeling unit 802 executes modeling based on the motion vector and the input processing unit. More specifically, for example, the modeling unit 802 previously stores a plurality of models corresponding to the number of pixels included in the processing unit, the number of virtual divisions of the pixel values in the time direction, and the number of foreground components for each pixel. A model for designating the correspondence between the pixel value and the foreground component as shown in FIG. 99 is selected based on the processing unit and the number of virtual divisions of the pixel value in the time direction.

  For example, when the number of pixels corresponding to the processing unit is 12 and the amount of motion v within the shutter time is 5, the modeling unit 802 sets the virtual division number to 5 and sets the leftmost pixel to 1 The foreground component, the second pixel from the left contains the two foreground components, the third pixel from the left contains the three foreground components, and the fourth pixel from the left contains the four foreground components The fifth pixel from the left contains five foreground components, the sixth pixel from the left contains five foreground components, the seventh pixel from the left contains five foreground components, and eight from the left. The tenth pixel includes five foreground components, the ninth pixel from the left includes four foreground components, the tenth pixel from the left includes three foreground components, and the eleventh pixel from the left is 2 The foreground component, and the twelfth pixel from the left contains one foreground component. As a whole, a model consisting of eight foreground components is selected.

  Note that the modeling unit 802 generates a model based on the motion vector and the processing unit when the motion vector and the processing unit are supplied, instead of selecting from the models stored in advance. Also good.

  The modeling unit 802 supplies the selected model to the equation generation unit 803.

  The equation generation unit 803 generates an equation based on the model supplied from the modeling unit 802. Referring to the foreground component image model shown in FIG. 99, the number of foreground components is 8, the number of pixels corresponding to the processing unit is 12, the amount of motion v is 5, and the number of virtual divisions is 5 The equation generated by the equation generation unit 803 will be described.

  When the foreground components corresponding to the shutter time / v included in the foreground component image are F01 / v to F08 / v, the relationship between F01 / v to F08 / v and the pixel values C01 to C12 is expressed by Equations (78) to (78). It is represented by Formula (89).

C01 = F01 / v
(78)
C02 = F02 / v + F01 / v
(79)
C03 = F03 / v + F02 / v + F01 / v
(80)
C04 = F04 / v + F03 / v + F02 / v + F01 / v
(81)
C05 = F05 / v + F04 / v + F03 / v + F02 / v + F01 / v
(82)
C06 = F06 / v + F05 / v + F04 / v + F03 / v + F02 / v
(83)
C07 = F07 / v + F06 / v + F05 / v + F04 / v + F03 / v
(84)
C08 = F08 / v + F07 / v + F06 / v + F05 / v + F04 / v
(85)
C09 = F08 / v + F07 / v + F06 / v + F05 / v
(86)
C10 = F08 / v + F07 / v + F06 / v
(87)
C11 = F08 / v + F07 / v
(88)
C12 = F08 / v
(89)

  The equation generation unit 803 generates an equation by modifying the generated equation. Equations generated by the equation generation unit 803 are shown in equations (90) to (101).

C01 = 1 ・ F01 / v + 0 ・ F02 / v + 0 ・ F03 / v + 0 ・ F04 / v + 0 ・ F05 / v
+0 ・ F06 / v + 0 ・ F07 / v + 0 ・ F08 / v
(90)
C02 = 1 ・ F01 / v + 1 ・ F02 / v + 0 ・ F03 / v + 0 ・ F04 / v + 0 ・ F05 / v
+0 ・ F06 / v + 0 ・ F07 / v + 0 ・ F08 / v
(91)
C03 = 1 ・ F01 / v + 1 ・ F02 / v + 1 ・ F03 / v + 0 ・ F04 / v + 0 ・ F05 / v
+0 ・ F06 / v + 0 ・ F07 / v + 0 ・ F08 / v
(92)
C04 = 1 ・ F01 / v + 1 ・ F02 / v + 1 ・ F03 / v + 1 ・ F04 / v + 0 ・ F05 / v
+0 ・ F06 / v + 0 ・ F07 / v + 0 ・ F08 / v
(93)
C05 = 1 ・ F01 / v + 1 ・ F02 / v + 1 ・ F03 / v + 1 ・ F04 / v + 1 ・ F05 / v
+0 ・ F06 / v + 0 ・ F07 / v + 0 ・ F08 / v
(94)
C06 = 0 ・ F01 / v + 1 ・ F02 / v + 1 ・ F03 / v + 1 ・ F04 / v + 1 ・ F05 / v
+1 ・ F06 / v + 0 ・ F07 / v + 0 ・ F08 / v
(95)
C07 = 0 ・ F01 / v + 0 ・ F02 / v + 1 ・ F03 / v + 1 ・ F04 / v + 1 ・ F05 / v
+1 ・ F06 / v + 1 ・ F07 / v + 0 ・ F08 / v
(96)
C08 = 0 ・ F01 / v + 0 ・ F02 / v + 0 ・ F03 / v + 1 ・ F04 / v + 1 ・ F05 / v
+1 ・ F06 / v + 1 ・ F07 / v + 1 ・ F08 / v
(97)
C09 = 0 ・ F01 / v + 0 ・ F02 / v + 0 ・ F03 / v + 0 ・ F04 / v + 1 ・ F05 / v
+1 ・ F06 / v + 1 ・ F07 / v + 1 ・ F08 / v
(98)
C10 = 0 ・ F01 / v + 0 ・ F02 / v + 0 ・ F03 / v + 0 ・ F04 / v + 0 ・ F05 / v
+1 ・ F06 / v + 1 ・ F07 / v + 1 ・ F08 / v
(99)
C11 = 0 ・ F01 / v + 0 ・ F02 / v + 0 ・ F03 / v + 0 ・ F04 / v + 0 ・ F05 / v
+0 ・ F06 / v + 1 ・ F07 / v + 1 ・ F08 / v
(100)
C12 = 0 ・ F01 / v + 0 ・ F02 / v + 0 ・ F03 / v + 0 ・ F04 / v + 0 ・ F05 / v
+0 ・ F06 / v + 0 ・ F07 / v + 1 ・ F08 / v
(101)

  Expressions (90) to (101) can also be expressed as Expression (102).

  In Expression (102), j indicates the position of the pixel. In this example, j has any one value of 1 to 12. I indicates the position of the foreground value. In this example, i has any one value of 1 to 8. aij has a value of 0 or 1 corresponding to the values of i and j.

  When expressed in consideration of the error, Expression (102) can be expressed as Expression (103).

式（１０３）において、ejは、注目画素Cjに含まれる誤差である。

In Expression (103), ej is an error included in the target pixel Cj.

  Expression (103) can be rewritten as Expression (104).

  Here, in order to apply the method of least squares, an error sum of squares E is defined as shown in Expression (105).

  In order to minimize the error, the partial differential value of the variable Fk with respect to the square sum E of the error may be zero. Fk is obtained so as to satisfy Expression (106).

  In Expression (106), since the motion amount v is a fixed value, Expression (107) can be derived.

  When equation (107) is expanded and transferred, equation (108) is obtained.

  This is expanded into eight equations obtained by substituting any one of integers 1 to 8 for k in equation (108). The obtained eight expressions can be expressed by one expression by a matrix. This equation is called a normal equation.

  An example of a normal equation generated by the equation generation unit 803 based on such a method of least squares is shown in Equation (109).

  When Expression (109) is expressed as A · F = v · C, C, A, v are known, and F is unknown. A and v are known at the time of modeling, but C is known by inputting a pixel value in the adding operation.

  By calculating the foreground component using a normal equation based on the method of least squares, the error included in the pixel C can be dispersed.

  The equation generation unit 803 supplies the normal equation generated in this way to the addition unit 804.

  The addition unit 804 sets the pixel value C included in the foreground component image to the matrix expression supplied from the equation generation unit 803 based on the processing unit supplied from the processing unit determination unit 801. The adding unit 804 supplies a matrix in which the pixel value C is set to the calculation unit 805.

  The calculation unit 805 calculates a foreground component Fi / v from which motion blur has been removed by processing based on a solution method such as a sweep-out method (Gauss-Jordan elimination method), and uses the foreground pixel values from which motion blur has been removed. A foreground component from which motion blur is removed, which is made up of Fi, which is a pixel value from which motion blur has been removed, is calculated by calculating Fi corresponding to any one of the integers from 0 to 8, as shown in FIG. The image is output to the motion blur adding unit 806 and the selection unit 807.

  In addition, in the foreground component image from which the motion blur shown in FIG. 100 is removed, each of F03 to F08 is set to each of C03 to C10 because the position of the foreground component image with respect to the screen is not changed. It can correspond to an arbitrary position.

  The motion blur adding unit 806 is a motion blur adjustment amount v ′ having a value different from the motion amount v, for example, a motion blur adjustment amount v ′ having a value half that of the motion amount v, or a motion blur having a value unrelated to the motion amount v. By giving the adjustment amount v ′, the amount of motion blur can be adjusted. For example, as illustrated in FIG. 101, the motion blur adding unit 806 calculates the foreground component Fi / v ′ by dividing the foreground pixel value Fi from which motion blur is removed by the motion blur adjustment amount v ′. Then, the sum of the foreground components Fi / v ′ is calculated to generate a pixel value in which the amount of motion blur is adjusted. For example, when the motion blur adjustment amount v ′ is 3, the pixel value C02 is (F01) / v ′, the pixel value C03 is (F01 + F02) / v ′, and the pixel value C04 is (F01 + F02 + F03) / v ′, and the pixel value C05 is (F02 + F03 + F04) / v ′.

  The motion blur adding unit 806 supplies the foreground component image in which the amount of motion blur is adjusted to the selection unit 807.

  The selection unit 807, for example, based on a selection signal corresponding to the user's selection, the foreground component image from which the motion blur supplied from the calculation unit 805 has been removed, and the amount of motion blur supplied from the motion blur addition unit 806 Is selected, and the selected foreground component image is output.

  Thus, the motion blur adjusting unit 106 can adjust the amount of motion blur based on the selection signal and the motion blur adjustment amount v ′.

  For example, as illustrated in FIG. 102, when the number of pixels corresponding to the processing unit is 8 and the motion amount v is 4, the motion blur adjustment unit 106 uses the matrix equation represented by Equation (110). Generate.

  The motion blur adjustment unit 106 thus calculates the number of expressions corresponding to the length of the processing unit in this way, and calculates Fi that is a pixel value in which the amount of motion blur is adjusted. Similarly, for example, when the number of pixels included in the processing unit is 100, an expression corresponding to 100 pixels is generated and Fi is calculated.

  FIG. 103 is a diagram illustrating another configuration of the motion blur adjusting unit 106. The same parts as those shown in FIG. 97 are denoted by the same reference numerals, and the description thereof is omitted.

  The selection unit 821 supplies the input motion vector and its position signal as they are to the processing unit determination unit 801 and the modeling unit 802 based on the selection signal, or the magnitude of the motion vector is set as the motion blur adjustment amount v ′. The motion vector whose size is replaced with the motion blur adjustment amount v ′ and its position signal are supplied to the processing unit determination unit 801 and the modeling unit 802.

  In this way, the processing unit determination unit 801 to the calculation unit 805 of the motion blur adjustment unit 106 in FIG. 103 sets the motion blur amount corresponding to the values of the motion amount v and the motion blur adjustment amount v ′. Can be adjusted. For example, when the motion amount v is 5 and the motion blur adjustment amount v ′ is 3, the processing unit determination unit 801 to the calculation unit 805 of the motion blur adjustment unit 106 in FIG. For the foreground component image of 5, the calculation is executed according to the model as shown in FIG. 101 corresponding to the motion blur adjustment amount v ′ of 3, and (motion amount v) / (motion blur adjustment amount v ′) = An image including motion blur corresponding to a motion amount v of 5/3, that is, approximately 1.7 is calculated. In this case, since the calculated image does not include motion blur corresponding to the motion amount v of 3, the result of the motion blur addition unit 806 is the relationship between the motion amount v and the motion blur adjustment amount v ′. It should be noted that the meaning of is different.

  As described above, the motion blur adjustment unit 106 generates an equation corresponding to the motion amount v and the processing unit, sets the pixel value of the foreground component image in the generated equation, and adjusts the amount of motion blur. A foreground component image is calculated.

  Next, processing for adjusting the amount of motion blur included in the foreground component image by the motion blur adjustment unit 106 will be described with reference to the flowchart of FIG.

  In step S801, the processing unit determination unit 801 of the motion blur adjustment unit 106 generates a processing unit based on the motion vector and the region information, and supplies the generated processing unit to the modeling unit 802.

  In step S802, the modeling unit 802 of the motion blur adjustment unit 106 selects and generates a model corresponding to the motion amount v and the processing unit. In step S803, the equation generation unit 803 creates a normal equation based on the selected model.

  In step S804, the adding unit 804 sets the pixel value of the foreground component image in the created normal equation. In step S805, the adding unit 804 determines whether or not the pixel values of all the pixels corresponding to the processing unit have been set, and if the pixel values of all the pixels corresponding to the processing unit have not been set. If it is determined, the process returns to step S804, and the process of setting the pixel value in the normal equation is repeated.

  If it is determined in step S805 that the pixel values of all the pixels in the processing unit have been set, the process advances to step S806, and the calculation unit 805 calculates a normal equation in which the pixel values supplied from the addition unit 804 are set. Based on this, the foreground pixel value adjusted for the amount of motion blur is calculated, and the process ends.

  As described above, the motion blur adjusting unit 106 can adjust the amount of motion blur from the foreground image including motion blur based on the motion vector and the region information.

  That is, it is possible to adjust the amount of motion blur included in the pixel value that is the sample data.

  FIG. 105 is a block diagram illustrating another example of the configuration of the motion blur adjusting unit 106. The motion vector and its position information supplied from the motion detection unit 102 are supplied to the processing unit determination unit 901 and the correction unit 905, and the region information supplied from the region specifying unit 103 is supplied to the processing unit determination unit 901. . The foreground component image supplied from the foreground / background separation unit 105 is supplied to the calculation unit 904.

  The processing unit determination unit 901 generates a processing unit based on the motion vector, its position information, and region information, and supplies the generated processing unit to the modeling unit 902 together with the motion vector.

  The modeling unit 902 performs modeling based on the motion vector and the input processing unit. More specifically, for example, the modeling unit 902 previously stores a plurality of models corresponding to the number of pixels included in the processing unit, the number of virtual divisions of the pixel values in the time direction, and the number of foreground components for each pixel. A model for designating the correspondence between the pixel value and the foreground component as shown in FIG. 106 is selected based on the processing unit and the number of virtual divisions of the pixel value in the time direction.

  For example, when the number of pixels corresponding to the processing unit is 12 and the amount of motion v is 5, the modeling unit 902 sets the virtual division number to 5 and the leftmost pixel is one foreground component. The second pixel from the left contains two foreground components, the third pixel from the left contains three foreground components, the fourth pixel from the left contains four foreground components, and The fifth pixel contains five foreground components, the sixth pixel from the left contains five foreground components, the seventh pixel from the left contains five foreground components, and the eighth pixel from the left Contains 5 foreground components, the 9th pixel from the left contains 4 foreground components, the 10th pixel from the left contains 3 foreground components, and the 11th pixel from the left contains 2 foreground components And the twelfth pixel from the left contains one foreground component, Select a model consisting of two foreground components.

  Note that the modeling unit 902 generates a model based on the motion vector and the processing unit when the motion vector and the processing unit are supplied, instead of selecting from the models stored in advance. Also good.

  The equation generation unit 903 generates an equation based on the model supplied from the modeling unit 902.

  With reference to the foreground component image model shown in FIGS. 106 to 108, the number of foreground components is 8, the number of pixels corresponding to the processing unit is 12, and the amount of motion v is 5. An example of an equation generated by the equation generation unit 903 will be described.

  When the foreground components corresponding to the shutter time / v included in the foreground component image are F01 / v to F08 / v, the relationship between F01 / v to F08 / v and the pixel values C01 to C12 is as described above. It represents with Formula (78) thru | or Formula (89).

  Focusing on the pixel values C12 and C11, the pixel value C12 includes only the foreground component F08 / v as shown in the equation (111), and the pixel value C11 includes the foreground component F08 / v and the foreground component F07 / v. Consists of product sums of v. Therefore, the foreground component F07 / v can be obtained by Expression (112).

F08 / v = C12
(111)
F07 / v = C11-C12
(112)

  Similarly, in consideration of the foreground components included in the pixel values C10 to C01, the foreground components F06 / v to F01 / v can be obtained by Expressions (113) to (118).

F06 / v = C10-C11
(113)
F05 / v = C09-C10
(114)
F04 / v = C08-C09
(115)
F03 / v = C07-C08 + C12
(116)
F02 / v = C06-C07 + C11-C12
(117)
F01 / v = C05-C06 + C10-C11
(118)

  The equation generation unit 903 generates equations for calculating foreground components based on pixel value differences, examples of which are shown in equations (111) to (118). The equation generation unit 903 supplies the generated equation to the calculation unit 904.

  The calculation unit 904 sets the pixel value of the foreground component image in the equation supplied from the equation generation unit 903, and calculates the foreground component based on the equation in which the pixel value is set. For example, when the equations (111) to (118) are supplied from the equation generator 903, the arithmetic unit 904 sets the pixel values C05 to C12 in the equations (111) to (118).

  The calculation unit 904 calculates the foreground components based on the formula in which the pixel values are set. For example, the calculation unit 904 calculates foreground components F01 / v to F08 / v as shown in FIG. 107 by calculations based on the formulas (111) to (118) in which the pixel values C05 to C12 are set. . The calculation unit 904 supplies the foreground components F01 / v to F08 / v to the correction unit 905.

  The correction unit 905 multiplies the foreground component supplied from the calculation unit 904 by the motion amount v included in the motion vector supplied from the processing unit determination unit 901 to calculate a foreground pixel value from which motion blur has been removed. . For example, when the foreground components F01 / v to F08 / v supplied from the calculation unit 904 are supplied, the correction unit 905 has a motion amount v that is 5 for each of the foreground components F01 / v to F08 / v. , The foreground pixel values F01 to F08 from which motion blur is removed are calculated as shown in FIG.

  The correction unit 905 supplies the foreground component image, which is calculated as described above and includes the foreground pixel values from which the motion blur is removed, to the motion blur addition unit 906 and the selection unit 907.

  The motion blur adding unit 906 is a motion blur adjustment amount v ′ having a value different from the motion amount v, for example, a motion blur adjustment amount v ′ having a value half the motion amount v, and a motion blur adjustment having a value unrelated to the motion amount v. With the amount v ′, the amount of motion blur can be adjusted. For example, as shown in FIG. 101, the motion blur adding unit 906 calculates the foreground component Fi / v ′ by dividing the foreground pixel value Fi from which motion blur is removed by the motion blur adjustment amount v ′. Then, the sum of the foreground components Fi / v ′ is calculated to generate a pixel value in which the amount of motion blur is adjusted. For example, when the motion blur adjustment amount v ′ is 3, the pixel value C02 is (F01) / v ′, the pixel value C03 is (F01 + F02) / v ′, and the pixel value C04 is (F01 + F02 + F03) / v ′, and the pixel value C05 is (F02 + F03 + F04) / v ′.

  The motion blur adding unit 906 supplies the foreground component image in which the amount of motion blur is adjusted to the selection unit 907.

  For example, based on a selection signal corresponding to the user's selection, the selection unit 907 removes the motion blur supplied from the correction unit 905 and the amount of motion blur supplied from the motion blur addition unit 906. Is selected, and the selected foreground component image is output.

  Thus, the motion blur adjusting unit 106 can adjust the amount of motion blur based on the selection signal and the motion blur adjustment amount v ′.

  Next, processing for adjusting the amount of foreground motion blur by the motion blur adjustment unit 106 having the configuration shown in FIG. 105 will be described with reference to the flowchart of FIG.

  In step S901, the processing unit determination unit 901 of the motion blur adjustment unit 106 generates a processing unit based on the motion vector and the region information, and supplies the generated processing unit to the modeling unit 902 and the correction unit 905.

  In step S902, the modeling unit 902 of the motion blur adjusting unit 106 selects and generates a model corresponding to the motion amount v and the processing unit. In step S903, the equation generation unit 903 generates an equation for calculating a foreground component based on a difference in pixel values of the foreground component image based on the selected or generated model.

  In step S904, the calculation unit 904 sets the pixel value of the foreground component image in the created equation, and extracts the foreground component from the difference between the pixel values based on the equation in which the pixel value is set. In step S905, the calculation unit 904 determines whether all foreground components corresponding to the processing unit have been extracted, and if it is determined that all foreground components corresponding to the processing unit have not been extracted, Returning to step S904, the process of extracting the foreground components is repeated.

  If it is determined in step S905 that all foreground components corresponding to the processing unit have been extracted, the process advances to step S906, and the correction unit 905 supplies the foreground components supplied from the calculation unit 904 based on the motion amount v. Each of F01 / v through F08 / v is corrected to calculate foreground pixel values F01 through F08 from which motion blur has been removed.

  In step S907, the motion blur adding unit 906 calculates a foreground pixel value in which the amount of motion blur is adjusted, and the selection unit 907 selects the image from which motion blur is removed or the image in which the amount of motion blur is adjusted. Either one is selected, the selected image is output, and the process ends.

  As described above, the motion blur adjustment unit 106 having the configuration illustrated in FIG. 105 can adjust motion blur from a foreground image including motion blur more quickly by simpler calculation.

  Conventional methods such as the Wiener filter that partially eliminates motion blur are effective in the ideal state, but they are quantized and not effective enough for actual images containing noise. In the motion blur adjusting unit 106 having the configuration shown in FIG. 105, a sufficient effect is recognized even for an actual image that is quantized and includes noise, and motion blur can be accurately removed.

  As described above, the separation processing server 11 having the configuration shown in FIG. 27 can adjust the amount of motion blur included in the input image.

  FIG. 110 is a block diagram illustrating another configuration of the functions of the separation processing server 11.

  The same parts as those shown in FIG. 27 are denoted by the same reference numerals, and description thereof will be omitted as appropriate.

  The area specifying unit 103 supplies the area information to the mixture ratio calculation unit 104 and the synthesis unit 1001.

  The mixture ratio calculation unit 104 supplies the mixture ratio α to the foreground / background separation unit 105 and the synthesis unit 1001.

  The foreground / background separation unit 105 supplies the foreground component image to the synthesis unit 1001.

  The synthesizing unit 1001 determines an arbitrary background image and a foreground component image supplied from the foreground / background separating unit 105 based on the mixture ratio α supplied from the mixture ratio calculating unit 104 and the region information supplied from the region specifying unit 103. Are combined to output a composite image in which an arbitrary background image and a foreground component image are combined.

  FIG. 111 is a diagram illustrating a configuration of the synthesis unit 1001. The background component generation unit 1021 generates a background component image based on the mixing ratio α and an arbitrary background image, and supplies the background component image to the mixed region image synthesis unit 1022.

  The mixed region image combining unit 1022 generates a mixed region combined image by combining the background component image and the foreground component image supplied from the background component generating unit 1021, and the generated mixed region combined image is used as the image combining unit. 1023.

  The image composition unit 1023 synthesizes the foreground component image, the mixed region composite image supplied from the mixed region image composition unit 1022 and an arbitrary background image based on the region information, and generates and outputs a composite image.

  As described above, the synthesizing unit 1001 can synthesize the foreground component image with an arbitrary background image.

  An image obtained by combining the foreground component image with an arbitrary background image based on the mixing ratio α, which is a feature amount, is more natural than an image obtained by simply combining pixels.

  FIG. 112 is a block diagram illustrating still another configuration of the function of the separation processing server 11 that adjusts the amount of motion blur. The separation processing server 11 shown in FIG. 27 performs region specification and calculation of the mixing ratio α in order, whereas the separation processing server 11 shown in FIG. 112 performs region specification and calculation of the mixing ratio α in parallel.

  The same parts as those shown in the block diagram of FIG. 27 are denoted by the same reference numerals, and the description thereof is omitted.

  The input image is supplied to the mixture ratio calculation unit 1101, foreground / background separation unit 1102, region specifying unit 103, and object extraction unit 101.

  Based on the input image, the mixture ratio calculation unit 1101 calculates the estimated mixture ratio when it is assumed that the pixel belongs to the covered background area, and the estimated mixture ratio when the pixel belongs to the uncovered background area. Calculated for each pixel included in the input image, estimated mixture ratio when the calculated pixel is assumed to belong to the covered background area, and estimated mixture when the pixel is assumed to belong to the uncovered background area The ratio is supplied to the foreground / background separator 1102.

  FIG. 113 is a block diagram illustrating an example of the configuration of the mixture ratio calculation unit 1101.

  An estimated mixture ratio processing unit 401 illustrated in FIG. 113 is the same as the estimated mixture ratio processing unit 401 illustrated in FIG. 72. The estimated mixture ratio processing unit 402 shown in FIG. 113 is the same as the estimated mixture ratio processing unit 402 shown in FIG.

  Based on the input image, the estimated mixture ratio processing unit 401 calculates an estimated mixture ratio for each pixel by an operation corresponding to the model of the covered background region, and outputs the calculated estimated mixture ratio.

  The estimated mixture ratio processing unit 402 calculates an estimated mixture ratio for each pixel by an operation corresponding to the model of the uncovered background area based on the input image, and outputs the calculated estimated mixture ratio.

  The foreground / background separation unit 1102 is supplied from the mixture ratio calculation unit 1101 and is estimated when the pixel is assumed to belong to the covered background area, and is estimated when the pixel is assumed to belong to the uncovered background area. Based on the mixing ratio and the region information supplied from the region specifying unit 103, a foreground component image is generated from the input image, and the generated foreground component image is supplied to the motion blur adjusting unit 106 and the selecting unit 107.

  FIG. 114 is a block diagram illustrating an example of the configuration of the foreground / background separation unit 1102.

  The same parts as those of the foreground / background separation unit 105 shown in FIG. 89 are denoted by the same reference numerals, and the description thereof is omitted.

  Based on the region information supplied from the region specifying unit 103, the selection unit 1121 supplies the estimated mixture ratio supplied from the mixture ratio calculation unit 1101 and assuming that the pixel belongs to the covered background region, and the pixel is undefined. One of the estimated mixture ratios when it is assumed to belong to the covered background region is selected, and the selected estimated mixture ratio is supplied to the separation unit 601 as the mixture ratio α.

  The separation unit 601 extracts the foreground components and the background components from the pixel values of the pixels belonging to the mixed region based on the mixture ratio α and the region information supplied from the selection unit 1121, and combines the extracted foreground components. At the same time, the background component is supplied to the synthesis unit 605.

  The separation unit 601 can have the same configuration as that shown in FIG.

  The synthesizing unit 603 synthesizes and outputs the foreground component image. The synthesizing unit 605 synthesizes and outputs the background component image.

  The motion blur adjustment unit 106 shown in FIG. 112 can have the same configuration as that shown in FIG. 27, and is included in the foreground component image supplied from the foreground / background separation unit 1102 based on the region information and the motion vector. The amount of motion blur is adjusted, and a foreground component image in which the amount of motion blur is adjusted is output.

  112, for example, based on a selection signal corresponding to the user's selection, the foreground component image supplied from the foreground / background separation unit 1102 and the amount of motion blur supplied from the motion blur adjustment unit 106 Is selected, and the selected foreground component image is output.

  In this way, the separation processing server 11 having the configuration shown in FIG. 112 can adjust and output the amount of motion blur included in the image corresponding to the foreground object included in the input image. . The separation processing server 11 having the configuration shown in FIG. 112 can calculate the mixture ratio α, which is the buried information, and output the calculated mixture ratio α, as in the first embodiment.

  FIG. 115 is a block diagram illustrating another configuration of the function of the separation processing server 11 that combines a foreground component image with an arbitrary background image. The separation processing server 11 shown in FIG. 110 serially performs area specification and calculation of the mixing ratio α, whereas the separation processing server 11 shown in FIG. 115 performs area specification and calculation of the mixing ratio α in parallel.

  The same parts as those shown in the block diagram of FIG. 112 are denoted by the same reference numerals, and the description thereof is omitted.

  The mixing ratio calculation unit 1101 illustrated in FIG. 115 is based on the input image and is estimated when the pixel is assumed to belong to the covered background area, and is estimated when the pixel is assumed to belong to the uncovered background area. The mixture ratio is calculated for each pixel included in the input image, and the estimated mixture ratio when the calculated pixel is assumed to belong to the covered background area and the pixel is assumed to belong to the uncovered background area are assumed. The estimated mixture ratio in the case is supplied to the foreground / background separation unit 1102 and the synthesis unit 1201.

  The foreground / background separation unit 1102 illustrated in FIG. 115 is assumed to be supplied from the mixture ratio calculation unit 1101 when the pixel belongs to the covered background area, and the pixel belongs to the uncovered background area. The foreground component image is generated from the input image based on the estimated mixture ratio in this case and the region information supplied from the region specifying unit 103, and the generated foreground component image is supplied to the combining unit 1201.

  The combining unit 1201 supplies the estimated mixture ratio supplied from the mixture ratio calculation unit 1101 when it is assumed that the pixel belongs to the covered background area, and the estimated mixture ratio when the pixel belongs to the uncovered background area. The arbitrary background image and the foreground component image supplied from the foreground / background separation unit 1102 are combined based on the region information supplied from the region specifying unit 103, and the arbitrary background image and the foreground component image are combined. The synthesized image is output.

  FIG. 116 is a diagram illustrating a configuration of the combining unit 1201. The same parts as those shown in the block diagram of FIG. 111 are denoted by the same reference numerals, and the description thereof is omitted.

  Based on the region information supplied from the region specifying unit 103, the selection unit 1221 supplies the estimated mixture ratio supplied from the mixture ratio calculation unit 1101 when it is assumed that the pixel belongs to the covered background region, and the pixel is undefined. One of the estimated mixture ratios when it is assumed to belong to the covered background region is selected, and the selected estimated mixture ratio is supplied to the background component generation unit 1021 as the mixture ratio α.

  The background component generation unit 1021 illustrated in FIG. 116 generates a background component image based on the mixing ratio α and an arbitrary background image supplied from the selection unit 1221, and supplies the background component image to the mixed region image composition unit 1022.

  116 mixes the background component image supplied from the background component generation unit 1021 and the foreground component image to generate a mixed region composite image, and generates the generated mixed region composite image. Is supplied to the image composition unit 1023.

  The image composition unit 1023 synthesizes the foreground component image, the mixed region composite image supplied from the mixed region image composition unit 1022 and an arbitrary background image based on the region information, and generates and outputs a composite image.

  As described above, the synthesis unit 1201 can synthesize the foreground component image with an arbitrary background image.

  The mixing ratio α has been described as the ratio of the background component included in the pixel value, but may be the ratio of the foreground component included in the pixel value.

  In addition, the direction of the foreground object has been described as being from left to right, but is not limited to that direction.

  In the above, the case where the image of the real space having the three-dimensional space and the time axis information is projected onto the time space having the two-dimensional space and the time axis information by using a video camera is taken as an example. In addition to this example, when the first information of more first dimensions is projected onto the second information of fewer second dimensions, distortion generated by the projection is corrected or significant It is possible to adapt to extracting information or synthesizing an image more naturally.

  The sensor 76a is not limited to a CCD, but is a solid-state imaging device, for example, a BBD (Bucket Brigade Device), a CID (Charge Injection Device), a CPD (Charge Priming Device), or a CMOS (Complementary Mental Oxide Semiconductor) sensor. In addition, the sensor is not limited to a sensor in which the detection elements are arranged in a matrix, and may be a sensor in which the detection elements are arranged in a line.

  The functions of the separation processing server 11 described above can also be realized by performing distributed processing on various servers configured on the network 1 shown in FIG. That is, the object extraction unit 101 and the motion detection unit 102 are in the motion detection server 12, the region specification unit 103 is in the region specification server 13, the mixture ratio calculation unit 104 is in the mixture ratio calculation server 14, and the foreground / background separation processing unit 105. Corresponds to the foreground / background separation processing server 15 and the motion blur adjustment unit 106 corresponds to the motion blur adjustment server 16. Therefore, the block diagram of the separation processing server 11 shown in FIG. 27 may be realized by hardware, realized by software, or realized by the network 1. The same applies to the synthesizing server 19, and the configuration corresponds to the synthesizing unit 1201, which is realized by hardware, realized by software, or realized by the network 1. It may be.

  The object extraction unit 101, the motion detection unit 102, the region specification unit 103, the mixture ratio calculation unit 104, the foreground / background separation processing unit 105, and the motion blur adjustment unit 106 described above are respectively performed by the motion detection server 12, The processing is the same as that in which the area specifying server 13, the mixture ratio calculation server 14, the foreground / background separation processing server 15, and the motion blur adjustment server 16 are replaced.

  Further, when the separation processing server 11 is realized as hardware or software as described above, the various servers connected to the network 1 illustrated in FIG. 1, the client computer 27, and the camera terminal device 28. It is good also as a structure integrated in each as a separation process part. Therefore, in the following description, when the separation processing server 11 is described as a single device having a function of simply separating an input image into a foreground component image and a background component image, the separation processing server 11 is also referred to as a separation processing unit 11. And

  Next, with reference to the flowchart of FIG. 117, the processing of the separation service for images input from the client computer 27 via the network 1 of FIG. 1 by the separation processing server 11 will be described.

  In step S <b> 1001, the client computer 27 outputs information specifying an image to the separation processing server 11. That is, as information for designating an image that the user wants to separate, a specific image or an image ID for designating an image is output to the separation processing server 11.

  In step S1011, the separation processing server 11 acquires the designated image. That is, when an image is transmitted from the client computer 27, the image is read from the network 1 and acquired when the information for designating is transmitted.

  In step S <b> 1012, the accounting processing unit 11 a of the separation processing server 11 performs accounting processing together with the accounting server 24 via the network 1. At the same time, in step S1021, the billing server 24 performs billing processing together with the separation processing server 11.

  Here, the above-described charging process will be described with reference to the flowchart of FIG. The actual billing process is executed by the separation processing server 11 and the billing server 24, but information necessary for various processes is also output from the client computer 27. Also explained.

  In step S1101, as shown in FIG. 119, the client computer 27 uses the usage amount together with ID information and authentication information (password, etc.) for identifying the user (user who receives the provision of the image separation service) by specifying the service. Is transmitted to the separation processing server 11 via the network 1. In other words, in this case, when information specifying an image is transmitted in the process of step S1001 in FIG. 117, the process of step S1101 is executed. The usage amount is a fee related to the separation service.

  In step S <b> 1111, as illustrated in FIG. 119, the charging processing unit 11 a of the separation processing server 11 receives the ID information and the authentication information, and further transmits the usage amount and its own ID to the charging server 24.

  In step S1121, as shown in FIG. 119, the accounting server 24 manages the authentication information, the customer account ID, and the usage amount by the financial institution of the customer account based on the ID transmitted from the separation processing server 11. The financial server 25 is inquired.

  In step S1131, as shown in FIG. 119, the financial server (for customer) 25 executes an authentication process based on the customer account ID and the authentication information, and notifies the billing server 24 of the authentication result and availability information. To do.

  In step S <b> 1122, as illustrated in FIG. 119, the billing server 24 transmits the authentication result and availability information to the separation processing server 11. In the following description, the description proceeds under the condition that the authentication result can be used without any problem. In addition, when information indicating that there is a problem with the authentication result and the use is not permitted is received, the processing ends.

  In step S1112, as illustrated in FIG. 119, the separation processing server 11 provides a service to the client computer 27 in a condition that there is no problem in the authentication result and the financial institution can be used. In step S1102, the client computer 27 receives a service. In other words, in this case, in step S1112, the separation processing server 11 separates the designated image into the foreground component image and the background component image and outputs them to the client computer 27. In step S1102, the client computer 27 is separated. The foreground component image and the background component image are received.

  In step S <b> 1113, the separation processing server 11 transmits a service usage notification to the accounting server 24. In step S1123, the billing server 24 notifies the financial server (for customer) 25 of the customer account ID, the usage amount, and the provider account ID.

  In step S1132, the financial server (for customer) 25 transfers the usage amount from the account of the customer account ID to the provider financial server (for provider) 26.

  Returning to the flowchart of FIG.

  After the accounting processing is performed between the separation processing server 11 and the accounting server 24 in steps S1012 and S1021, the separation processing server 11 executes image separation processing in step S1013. That is, the area specifying unit 103 of the separation processing server 11 performs the area specifying process described with reference to the flowchart of FIG. 53, and the mixture ratio calculating unit 104 performs the process of calculating the mixture ratio described with reference to the flowchart of FIG. The foreground / background separation unit 105 performs the foreground / background separation processing described with reference to the flowchart of FIG. 96, and the motion blur adjustment unit 106 performs the motion blur amount adjustment processing described with reference to the flowchart of FIG. Run and separate the specified image. Note that the motion blur amount adjustment process, the area specifying process, the mixture ratio calculation process, and the foreground / background separation process are all the same as described above, and thus the description thereof is omitted.

  In step S1014, the separation processing server 11 attaches IDs to the separated foreground component image and background component image and transmits them to the client computer 27. In step S1002, the client computer 27 receives the separated foreground component image and background component image transmitted from the separation processing server 11 and their IDs, and stores them in its own storage unit 48 (FIG. 2). Print out if necessary. The client computer 27 stores the foreground component image and the background component image separated by the separation processing server 11 in the separation processing server 11 itself or via the network 1 in accordance with a user instruction. It can also be output to the storage server 18 and stored (accumulated).

  In the above description, the processing in the case where the charge related to the separation processing is transferred to the financial servers 25 and 26 by the billing server 24 has been described. For example, the user previously separates the fee, such as prepaid points. A point indicating that the usage fee has been paid to the service provider is stored in the storage unit 48 (FIG. 2), and each time the provision of the separation service is received, the point is subtracted to execute the charging process. It may be.

  Here, with reference to the flowchart of FIG. 120, the charging process when using prepaid points will be described.

  In step S1201, the client computer 27 designates a service and transmits ID information and authentication information. That is, the client computer 27 executes the same process as the process in step S1101 of FIG.

  In step S1211, the accounting processing unit 11a of the separation processing server 11 receives the ID information and the authentication information. In step S <b> 1212, the billing processing unit 11 a obtains points corresponding to the usage amount related to the separation process from the prepaid points corresponding to the amount paid in advance by the user of the client computer 27 stored in the storage unit 48. Subtract and memorize. In step S1213, the separation processing server 11 provides a service. That is, in this case, the separation processing server 11 executes the separation processing of the input image, and transmits the separated foreground component image and background component image to the client computer 27.

  In step S1202, the client computer 27 receives a service. That is, in this case, the client computer 27 receives the foreground component image and the background component image transmitted from the separation processing server 11.

  In the above description, the case where the separation processing server 11 stores the prepaid point in its own storage unit 48 (FIG. 2) has been described. For example, a card on which a prepaid point is recorded, a so-called prepaid card is stored. The same processing is performed for use. In this case, the prepaid point stored in the prepaid card is read and transmitted by the client computer 27 in step S1201, and the separation processing server 11 subtracts the point corresponding to the usage fee from the point received by the billing process. To be transmitted to the client computer 27 and overwritten on the prepaid card.

  Next, the processing of the motion detection service for obtaining the motion vector and position information of the image designated by the client computer 27 will be described with reference to the flowchart of FIG.

  In step S <b> 1301, the client computer 27 outputs information specifying an image to the motion detection server 12. That is, as information for designating an image that the user wants to perform motion detection processing, a specific image or an image ID for designating an image is output to the motion detection server 12.

  In step S1311, the motion detection server 12 acquires the designated image. That is, when an image is transmitted from the client computer 27, the image is read from the network 1 and acquired when the information for designating is transmitted.

  In steps S1312, S1321, the billing processing unit 12c and the billing server 24 of the motion detection server 12 execute a billing process. The billing process is the same as in the case of the separation service in FIGS. 118 and 120, and the description thereof is omitted.

  In step S <b> 1313, the object extraction unit 12 a of the motion detection server 12 extracts each object from the acquired designated image, and the motion detection unit 12 b detects the position information and the motion vector and transmits them to the client computer 27. To do.

  In step S1302, the client computer 27 receives and stores the object position information and the motion vector transmitted from the motion detection server 12.

  The client computer 27 stores the position information and the motion vector detected by the motion detection server 12 in the motion detection server 12 itself according to a user's command, or the storage server 18 via the network 1. Can also be output and stored (accumulated).

  Next, with reference to the flowchart of FIG. 122, the process of the area specifying service for specifying the area from the information specifying the image and the object input from the client computer 27 executed by the area specifying server 13 will be described.

  In step S <b> 1401, the client computer 27 outputs information specifying an image and an object to the area specifying server 13. That is, as the information for designating the image that the user wants to specify the area, a specific image or information for specifying the object is output to the area specifying server 13 together with the image ID for specifying the image.

  In step S1411, the area specifying server 13 acquires the designated image. That is, when an image is transmitted from the client computer 27, when an image ID for designating the image is transmitted, an image corresponding to the image ID is read from the network 1 and obtained.

  In steps S1412, S1421, the billing processing unit 13a and the billing server 24 of the area specifying server 13 execute billing processing. The billing process is the same as in the case of the separation service in FIGS. 118 and 120, and the description thereof is omitted.

  In step S <b> 1413, the area specifying server 13 executes an area specifying process based on information specifying an object. Note that the area specifying process is the same as the process described with reference to the flowchart of FIG.

  In step S1414, the area specifying server 13 transmits the area information obtained in the process of step S1413 to the client computer 27.

  In step S1402, the client computer 27 receives and stores the area information transmitted from the area specifying server 13.

  The client computer 27 stores the area information obtained by the area specifying server 13 in the area specifying server 13 itself or outputs it to the storage server 18 via the network 1 in accordance with a user instruction. It can also be stored (accumulated).

  Next, referring to the flowchart of FIG. 123, the mixture ratio that is executed by the mixture ratio calculation server 14 and that calculates the mixture ratio from the information specifying the image and the object input from the client computer 27 and the region information. Processing of the calculation service will be described.

  In step S <b> 1501, the client computer 27 outputs information specifying an image and an object, and region information to the mixture ratio calculation server 14. That is, the information for designating the image for which the user wants to calculate the mixture ratio is a specific image, or the image ID for designating the image, the information for designating the object, and the area information are the mixture ratio calculation server 14. Is output.

  In step S1511, the mixture ratio calculation server 14 acquires the designated image. That is, when an image is transmitted from the client computer 27, when an image ID for designating the image is transmitted, an image corresponding to the image ID is read from the network 1 and obtained.

  In steps S1512 and S1521, the charging processing unit 14a and the charging server 24 of the mixture ratio calculation server 14 execute a charging process. The billing process is the same as in the case of the separation service in FIGS. 118 and 120, and the description thereof is omitted.

  In step S1513, the mixture ratio calculation server 14 executes a process for calculating the mixture ratio based on the information for specifying the object and the region information. Note that the process for calculating the mixture ratio is the same as the process described with reference to the flowchart in FIG.

  In step S1514, the mixture ratio calculation server 14 transmits the mixture ratio obtained in step S1513 to the client computer 27.

  In step S1502, the client computer 27 receives and stores the mixture ratio transmitted from the mixture ratio calculation server 14.

  The client computer 27 stores the mixture ratio obtained by the mixture ratio calculation server 14 in the mixture ratio calculation server 14 itself or in the storage server 18 via the network 1 in accordance with a user instruction. It can also be output and stored (accumulated).

  Next, referring to the flowchart in FIG. 124, the foreground / background separation server 15 executes the foreground component image and the background based on the information input from the client computer 27 and the information specifying the object, the area information, and the mixture ratio. Processing of a service that separates into component images will be described.

  In step S <b> 1601, the client computer 27 outputs information for designating an image and an object, region information, and mixture ratio information to the foreground / background separation server 15. That is, the information for specifying the image that the user wants to separate the foreground / background is a specific image, or the image ID for specifying the image, the information for specifying the object, the area information, and the information on the mixing ratio are foreground. It is output to the background separation server 15.

  In step S1611, the foreground / background separation server 15 obtains the designated image. That is, when an image is transmitted from the client computer 27, when an image ID for designating the image is transmitted, an image corresponding to the image ID is read from the network 1 and obtained.

  In steps S1612 and S1621, the accounting processing unit 15a and the accounting server 24 of the foreground / background separation server 15 execute an accounting process. The billing process is the same as in the case of the separation service in FIGS. 118 and 120, and the description thereof is omitted.

  In step S1613, the foreground / background separation server 15 executes foreground / background separation processing based on the information for specifying the object, the region information, and the mixture ratio. The foreground / background separation process is the same as the process described with reference to the flowchart of FIG.

  In step S1614, the foreground / background separation server 15 attaches IDs to the foreground component image and the background component image obtained in the process of step S1613 and transmits them to the client computer 27.

  In step S1602, the client computer 27 receives and stores the foreground component image and the background component image transmitted from the foreground / background separation server 15.

  Note that the client computer 27 stores the foreground / background separation image and the background component image transmitted by the foreground / background separation server 15 in the foreground / background separation server 15 itself or the network 1 according to a user instruction. The data can be output to the storage server 18 and stored (accumulated).

  Next, referring to the flowchart of FIG. 125, the image specified from the information specifying the image input from the client computer 27, the motion vector, and the motion blur adjustment amount, which is executed by the motion blur adjustment server 16. The processing of the service for adjusting the motion blur of the will be described.

  In step S <b> 1701, the client computer 27 outputs information designating an image, a motion vector, and information on the motion blur adjustment amount to the motion blur adjustment server 16. That is, as information for designating an image that the user wants to adjust motion blur, it is a specific image, or an image ID for designating an image, information for designating an object, a motion vector, and motion blur adjustment amount information Is output to the motion blur adjustment server 16.

  In step S1711, the motion blur adjustment server 16 acquires the designated image. That is, when an image is transmitted from the client computer 27, when an image ID for designating the image is transmitted, an image corresponding to the image ID is read from the network 1 and acquired.

  In steps S1712, S1721, the charging processing unit 16a and the charging server 24 of the motion blur adjustment server 16 execute a charging process. The billing process is the same as in the case of the separation service in FIGS. 118 and 120, and the description thereof is omitted.

  In step S1713, the motion blur adjustment server 16 executes motion blur amount adjustment processing based on the motion vector and the information on the motion blur adjustment amount. Note that the process of adjusting the amount of motion blur is the same as the process described with reference to the flowchart in FIG.

  In step S <b> 1714, the motion blur adjustment server 16 attaches an ID to the motion blur adjustment image obtained in step S <b> 1713 and transmits it to the client computer 27.

  In step S <b> 1702, the client computer 27 receives and stores the motion blur adjustment image transmitted from the motion blur adjustment server 16.

  The client computer 27 stores the motion blur adjustment image transmitted from the motion blur adjustment server 16 in the motion blur adjustment server 16 itself or outputs the motion blur adjustment image to the accumulation server 18 in accordance with a user instruction. It can also be stored (accumulated).

  Next, the detailed configuration of the encoding server 17 will be described with reference to FIG. The separation processing unit 2002 of the encoding server 17 converts the input image (including an image ID for specifying the image and the corresponding image read from the storage server 18 via the network 1) into the foreground component. The image and the background component image are separated and output to the encoding unit 2001 together with the mixture ratio, motion vector, and position information. The separation processing unit 2002 is the same as the separation processing server (separation processing unit) 11 described with reference to FIG. 27, and the mixing ratio, motion vector, and position information acquisition processing are also the same. Description is omitted.

  The encoding unit 2001 outputs and stores the foreground component image and the background component image input from the separation processing unit 2002 to the storage server 18 via the network 1 and stores the stored location information of the storage server 18 on the network. That is, it is converted into information such as a URL and output as foreground component image position information and background component image position information. At this time, the encoding unit 2001 also outputs the mixture ratio, motion vector, and position information extracted when the foreground component image and the background component image are separated.

  When the encoding unit 2001 converts the foreground component image and the background component image into the foreground component image position information and the background component image position information, respectively, the accounting processing unit 17a (FIGS. 16 and 17) Via the billing server 24. This charging process may be borne by a user who receives a composition service for generating a composite image using a composition server 19 described later. On the contrary, the user who uses the encoding service pays in advance, so that when using the synthesis service, it is possible to avoid receiving a usage fee from the user.

  Next, with reference to the flowchart of FIG. 127, the encoding service process executed by the encoding server 17 for encoding an image input from the client computer 27 will be described. In this description, a case where the user of the encoding service bears a usage fee will be described.

  In step S <b> 1801, the client computer 27 outputs information specifying an image to the encoding server 17. That is, as information for designating an image that the user wants to encode, a specific image, or an image ID for designating an image and information for designating an object are output to the encoding server 17.

  In step S1811, the encoding server 17 acquires the designated image. That is, when an image is transmitted from the client computer 27, when an image ID for designating the image is transmitted, an image corresponding to the image ID is read from the network 1 and acquired.

  In steps S1812, S1821, the accounting processing unit 17a and the accounting server 24 of the encoding server 17 execute an accounting process. The billing process is the same as in the case of the separation service in FIGS. 118 and 120, and the description thereof is omitted.

  In step S1813, the separation processing unit 2002 of the encoding server 17 performs image separation processing. The image separation process is the same as the process of step S1013 in the flowchart of FIG.

  In step S1814, the encoding server 17 outputs the foreground component image and the background component image obtained in the process of step S1813 to the accumulation server 18, and stores (accumulates) them. In step S1831, the accumulation server 18 stores the transmitted foreground component image and background component image.

  In step S1815, the encoding server 17 adds the motion vector and the position information to the foreground component image position information and the background component position information generated by the encoding, and transmits them to the client computer 27.

  In step S1802, the client computer 27 receives and stores the foreground component image position information, the background component image position information, the motion vector, and the position information transmitted from the encoding server 17.

  When the encoding unit 2001 separates and encodes the input image and encodes an image similar to the already encoded image, only the data that is the difference is already encoded. An image code (image position information) may be attached and output. For example, when an image as shown in FIG. 128 is synthesized, the foreground component image 1, the foreground component image 2, and the encoding information of the first image including the encoding information of the mixture ratio 1, and the foreground component image 1, When synthesizing the foreground component image 3 and the encoding information of the second image composed of the encoding information of the mixture ratio 2, the foreground component image 1 is included in any image information. When synthesizing, the encoding information of the foreground component image 1 of one image may be omitted, and as a result, the compression rate is improved by the amount by which the information of the foreground component image 1 is deleted as compared with the case of simple synthesis. Can be made.

  As a result, when the first image and the second image as shown in FIG. 128 are accumulated, if the first image is accumulated first, the second image is the foreground that becomes a difference. Only the encoded information of the component image 3 and the mixing ratio 2 needs to be accumulated. For this reason, in a case where a plurality of pieces of encoded information of the same image are stored, the compression rate is improved as the number of stored images increases.

  Further, the mixture ratio, motion vector, and position information encoded by the encoding server 17 may be information designated by the user as shown in FIG. Further, as shown in FIG. 129, the image to be encoded may be encoded by reading the foreground component image and the background component image corresponding to the image ID designated by the user from the storage server 18. In this case, the encoding server 17 may not include the separation processing unit 2002.

  Further, although the image ID has been used as the information for designating the image in this specification, the image position information may be used instead.

  Next, referring to the flowchart of FIG. 130, information specifying the images A and B input from the client computer 27, motion vector, mixture ratio, position information, and motion blur adjustment executed by the composition server 19 The processing of the service that combines the specified images A and B based on the amount will be described.

  In step S 1901, the client computer 27 outputs information specifying the images A and B, a motion vector, a mixture ratio, position information, and information on the motion blur adjustment amount to the synthesis server 19. That is, the information specifying the images A and B that the user wants to synthesize is a specific image, or the images A-ID and B-ID specifying the images A and B (the encoded images described above). Position information), motion vector, mixing ratio, position information, and motion blur adjustment amount information are output to the synthesis server 19.

  In step S1911, the composition server 16 acquires the designated image. That is, when an image is transmitted from the client computer 27, when an image ID (which may be the encoded image position information described above) is transmitted, an image corresponding to the image ID is Read from the network 1 and obtain it.

  In steps S1912, S1921, the charging processing unit 19a and the charging server 24 of the synthesis server 19 execute a charging process. The billing process is the same as in the case of the separation service in FIGS. 118 and 120, and the description thereof is omitted. Further, this billing process may be omitted when the user who has received the encoding service using the above-described encoding server 16 has paid. Conversely, instead of the user who has received the encoding service, the user who has received the combining service may bear the burden.

  In step S <b> 1913, the composition server 19 performs a process of combining the images A and B based on the motion vector, the mixture ratio, the position information, and the motion blur adjustment amount information.

  In step S1914, the composition server 19 attaches an ID to the composite image (A + B) obtained in the process of step S1913 and transmits it to the client computer 27.

  In step S1902, the client computer 27 receives and stores the composite image (A + B) transmitted from the composite server 19.

  The client computer 27 stores the composite image (A + B) transmitted by the composite server 19 in the composite server 19 itself or in the storage server 18 via the network 1 in accordance with a user instruction. It can also be output and stored (accumulated).

  By the way, the composition server 20 can compose a plurality of images as described above. At this time, the motion blur adjustment amount is used as a key to add motion blur of the composite image. Thus, an encrypted image can be generated. FIG. 131 shows a configuration of an encryption motion blur adding unit 2021 provided for causing the synthesis server 20 to generate an encrypted image.

  The input information processing unit 2031 of the encryption motion blur adding unit 2021 receives the input encrypted signal to be encrypted in the imaging unit 2032, the encryption key information in the motion blur creation unit 2033, and Image selection information for selecting an image (background component image) to be combined with the encrypted signal as a foreground component image is output to the combining server 20.

  When the encrypted signal input from the input information processing unit 2031 is not an image signal, the imaging unit 2032 converts the signal into an image signal and outputs the image signal to the motion blur adding unit 2033. That is, since the signal to be encrypted is an image signal, a signal that is not an image signal is imaged in order to correspond to the processing.

  The motion blur creation unit 2033 generates a motion blur adjustment amount based on information such as speed and direction input from the input information processing unit 2031, performs motion blur addition processing on the image signal input from the imaging unit 2032, and Output to the composition server 20. The composition server 20 acquires the background component image based on the image selection information input from the input information processing unit 2031 and further acquires the background component image acquired using the image input from the motion blur adding unit 2033 as the foreground component image. To generate and display a composite image. At this time, the image selection information for designating the background component image may be the background component image itself, the background component image position information, or the background component image ID.

  Next, referring to FIG. 132, the encryption motion blur removal unit 2041 that decrypts the composite image encrypted by the encryption motion blur addition unit 2021 provided in the composition server 20 and converts it into the original signal. explain. The encryption motion blur adding unit 2021 and the encryption motion blur removing unit 2041 shown in FIGS. 131 and 132 may be considered as functional block diagrams of software built in the client computer 27, for example. It may be considered as a block diagram of the wear. Further, the cryptographic motion blur adding unit 2021 and the cryptographic motion blur removing unit 2041 may be configured as dedicated servers on the network 1.

  The separation server 11 separates the encrypted composite image into the foreground component image and the background component image, and outputs the foreground component image to which motion blur is added to the input information processing unit 2051.

  When the input information processing unit 2051 receives the encrypted foreground component image input from the separation processing server 11 and the speed and direction information as a key for decrypting the encrypted foreground component image. And output to the motion blur removal unit 2052. The key speed and direction are set for each of the two-dimensional images in the x and y directions.

  The motion blur removal unit 2052 generates a motion blur amount based on the speed and direction information input from the input information processing unit 2051, and the encrypted motion blur addition unit 2021 applies it to the encrypted foreground component image. A motion blur addition process opposite to the motion blur addition process is performed, and the encrypted foreground component image is decoded and output to the signal conversion unit 2053. When the encrypted signal is not an image, the signal conversion unit 2053 converts the image signal input from the motion blur removal unit 2052 into an original signal and outputs the original signal.

  In other words, the motion blur creation unit 2033 (FIG. 131) and the motion blur removal unit 2052 execute substantially the same processing as the motion blur addition unit 806 in FIG. Using the amount of blur adjustment, an addition process of motion blur opposite to each other is executed. However, the difference is that a gain-up process is executed with respect to the motion blur addition process executed earlier in the motion blur addition process in the x direction or the y direction described later.

  Here, the principle of encrypting an image signal by adding motion blur will be described. For example, as shown in FIG. 133, when the subject moves in the direction of the arrow, if this is imaged by a sensor 76a made of a CCD or the like, a mixed region (covered background region and uncovered background region) is obtained before and after the moving direction. Occurs as a motion blur of the captured image (refer to FIG. 31 for details). FIG. 134 shows an example of this phenomenon. When a subject such as that shown in FIG. 134 (A) is imaged by the sensor 76a, when the subject is moving in the left-right direction in the figure, the speed is adjusted. Correspondingly, the motion blur area is expanded, and the captured color is further diffused. That is, when the subject is moving in the left-right direction at a speed v, an image as shown in FIG. 134B is taken. At this time, if the areas imaged when the subject is stationary are the areas a0 to a0 ′, the areas where the subject is imaged in FIG. 134B are areas a1 to a1 ′, and the original position a0. The color of the region from a0 ′ to light is dimmed, and the color is spread over the region a1 to a0 and the region a0 ′ to a1 ′ that become motion blur. Similarly, when the subject moves at a speed of 2v (twice the speed v), as shown in FIG. 134C, the areas a2 to a0 and the areas a0 ′ to a It is shown that the color spreads to a2 ′. Further, when the subject moves at a speed of 3v, as shown in FIG. 134 (D), it spreads over the areas a3 to a0 and the areas a0 ′ to a3 ′ that become motion blur, and moves at a speed of 4v. As shown in (E), the region spreads over the regions a4 to a0 and the regions a0 ′ to a4 ′ that become motion blur, and the color becomes light as a whole. That is, the individual pixel values output from the sensor 76a are the result of integrating a spatially widened part of the object to be imaged with respect to the shutter time, so that the pixel values integrated as a whole do not change. Each time the speed of the subject increases, the image is thinned by spreading spatially. Accordingly, it becomes difficult to interpret the subject as the color becomes lighter, the area widens, and the area of motion blur increases. Here, the color indicates the possibility of interpretation. The darker the color, the greater the possibility of interpretation. The lighter the color, the smaller the possibility of interpretation.

  Encryption by motion blur adjustment uses this property, and encryption is performed by causing motion blur in a two-dimensional direction that cannot occur in the real world in an image. That is, as shown in FIG. 135, an image obtained by capturing a black circle-shaped subject in a state where there is no movement is shown at the top of the leftmost column of the matrix. From this state, for example, when motion blur in a state where there is motion in the vertical direction is added, the black circle subject becomes an image in which motion blur occurs in the vertical direction as shown in the uppermost row of the middle row. Further, when motion blur is generated in the horizontal direction, an image with motion blur generated in the vertical and horizontal directions of the subject is obtained as shown in the middle row of the middle row.

  In this state, if the motion (speed) in the left-right direction is further increased and motion blur is added, an image in which the motion blur area further expands in the left-right direction as shown in the lowermost row of the middle row. If motion blur is further generated in this image in the vertical direction, as shown in the lowermost row in the rightmost column, the motion blur area of the black circle subject expands, and the color becomes light as a whole. As a result, the possibility of interpretation of the subject decreases, so that the image itself can be encrypted.

  Next, an encryption process using the motion blur adjustment amount of the encryption motion blur adding unit 2021 will be described with reference to the flowchart of FIG. In the following description, as shown in FIG. 137, an example of encrypting an image in which a subject having 5 × 5 pixels is captured will be described. Here, in FIG. 137, the pixel values a to y of each pixel of 5 × 5 pixels are indicated, the vertical direction is indicated by y, the horizontal direction is indicated by x, and the time axis is described as time t.

  In step S2001, the input information processing unit 2031 determines whether an encrypted signal has been input, and repeats the process until it is input. If it is determined that the signal has been input, the process proceeds to step S2002. .

  In step S2002, the input information processing unit 2031 outputs the input encrypted signal to the imaging unit 2032. In step S2003, the imaging unit 2032 determines whether or not the input encrypted signal is an image signal. For example, if it is determined that the encrypted signal is not an image signal, the imaging unit 2032 converts the encrypted signal into an image signal and outputs it to the motion blur adding unit 2033 in step S2004. If it is determined in step S2003 that the encrypted information is an image signal, the imaging unit 2032 outputs the input encrypted signal as it is to the motion blur adding unit 2033.

  In step S2005, the input signal processing unit 2031 determines whether or not key speed and direction information has been input. The input signal processing unit 2031 repeats the process until the key and speed and direction keys are input. Processing proceeds to step S2006.

  In step S2006, the motion blur adding unit 2033 encrypts the input image signal in the x direction (adds motion blur).

  Here, a specific method for generating a pixel value when the subject is encrypted by motion blur adjustment will be described with reference to FIGS. 137 to 149.

  Here, as shown in FIG. 137, a description will be given of a method of encrypting the pixels a to e in the lowermost stage by causing motion blur in the x direction. At this time, if the motion amount v indicating the key speed is 5 (the number of virtual divisions is 5), the lowermost pixel shown in FIG. 138 is shown as in FIG. That is, since the pixel value in each time direction is divided into five, a / 5 = a0 = a1 = a2 = a3 = a4, b / 5 = b0 = b1 = b2 = b3 = b4, c / 5 = c0 = c1 = C2 = c3 = c4, d / 5 = d0 = d1 = d2 = d3 = d4, and e / 5 = e0 = e1 = e2 = e3 = e4. Here, the pixel at the upper stage in FIG. 139 is the pixel value at the previous time.

  When a motion in the x direction is given to the subject (in this case, the right direction in the figure), the arrangement of the pixel values is slid at a predetermined time interval, and as a result, as shown in FIG. It becomes arrangement. In other words, the pixel values a0 to e0 are the original positions at the start timing of movement, and at the next timing, the pixel values a1 to e1 slide rightward by one pixel, and at the next timing, the pixel values a2 to e0. e2 slides further by one pixel in the right direction, and at the next timing, the pixel values a3 to e3 slide further by one pixel in the right direction, and at the next timing, the pixel values a4 to e4 further move in the right direction. In this arrangement, the pixel value is moved in accordance with the movement of the subject, such as sliding by one pixel.

  Each pixel value on the xy plane is obtained by adding the pixel values shown in FIG. 140 in the time direction. However, for example, in the leftmost column or the rightmost column, there are only pixel values a0 and e4, and the pixel value may be very small. In performing the same processing, gain increase processing is performed so as not to have a very small value. An example in which this gain-up processing is performed is shown in FIG.

  Here, a0 * = 5 × a0, b0 * = (5/2) × b0, a0 * = (5/2) × a1, c0 * = (5/3) × c0, b1 * = (5/3) ) × b1, a2 * = (5/3) × a2, d0 * = (5/4) × d0, c1 * = (5/4) × c1, b2 * = (5/4) × b2, a3 * = (5/4) × a3, e1 * = (5/4) × e1, d2 * = (5/4) × d2, c3 * = (5/4) × c3, b4 * = (5/4) × b4, e2 * = (5/3) × e2, d3 * = (5/3) × d3, c4 * = (5/3) × c4, e3 * = (5/2) × e3, d4 * = (5/2) × d4 and e4 * = 5 × e4. That is, the gain is adjusted so that the added value of each pixel becomes a pixel value for one pixel. As a result, when the pixels a to e shown in FIG. 138 are encrypted under the condition that the motion amount v is 5 in the x direction (when motion blur is added), the pixels ax to dx as shown in FIG. The number of pixels in the horizontal direction of the subject increases from 5 to 9 after being converted to '(encrypted). Here, the pixel values are ax = ax *, bx = (b0 *) + (a1 *), cx = (c0 *) + (b1 *) + (a2 *), dx = (d0 *) + (c1 *) + (B2 *) + (a3 *), ex = (e0) + (d1) + (c2) + (b3) + (a4), ax ′ = (e1 *) + (d2 *) + (c3 *) + (B4 *), bx ′ = (e2 *) + (d3 *) + (c4 *), cx ′ = (e3 *) + (d4 *), and ex = ex *.

  If the above processing is encrypted in the x direction for all y of 5 × 5 pixels shown in FIG. 137, pixel values as shown in FIG. 143 are obtained. That is, pixels ax to yx, pixels ax ′ to dx ′, fx ′ to ix ′, kx ′ to nx ′, px ′ to sx ′, and ux ′ to xx ′ are obtained in the x direction. When motion blur occurs, a spread occurs in the x direction, and nine pixels are obtained.

  Now, the description returns to the flowchart of FIG. 136.

  In step S2007, the motion blur adding unit 2033 encrypts the image signal encoded in the x direction in the y direction.

  Here, as shown in FIG. 144, a method of encrypting the pixels ax, fx, kx, px, ux in the rightmost column shown in FIG. 143 by causing motion blur in the y direction will be described. At this time, assuming that the motion amount v indicating the key speed is 5 (the number of virtual divisions is 5), the rightmost pixel shown in FIG. 143 is shown as in FIG. That is, since the pixel value in each time direction is divided into five, ax / 5 = ax0 = ax1 = ax2 = ax3 = ax4, fx / 5 = fx0 = fx1 = fx2 = fx3 = fx4, kx / 5 = kx0 = kx1 = Kx2 = kx3 = kx4, px / 5 = px0 = px1 = px2 = px3 = px4, ux / 5 = ux0 = ux1 = ux2 = ux3 = ux4. Here, the pixel at the upper stage in FIG. 145 is the pixel value at the previous time.

  When a movement is given to the subject in the y direction, the arrangement of the pixel values is slid at a predetermined time interval, and as a result, the arrangement is as shown in FIG. That is, the pixel values ax0, fx0, kx0, px0, ux0 are the original positions at the timing of starting the movement, and the pixel values ax1, fx1, kx1, px1, ux1 slide rightward by one pixel at the next timing. Then, at the next timing, the pixel values ax2, fx2, kx2, px2, ux2 slide to the right by one pixel, and at the next timing, the pixel values ax3, fx3, kx3, px3, ux3 The pixel value moves in accordance with the movement of the subject such that the pixel value ax4, fx4, kx4, px4, ux4 slides further one pixel in the right direction at the next timing. Will be arranged.

  Now, the description returns to the flowchart of FIG. 136.

  In step S2008, the composition server 19 combines the background component image to be combined with the encrypted image (foreground component image). For example, when a background component image (image consisting of one stage of pixels in the x direction) composed of pixel values B0 to B9 arranged in the y direction as shown in FIG. 147 is synthesized, as shown in FIG. A value obtained by adding the pixel values is the pixel value. That is, the pixel value of the image encrypted in the xy direction (with motion blur added) is synthesized as the pixel value of the foreground component image, and the pixel value of the synthesized image is synthesized as the pixel value of the background component image. As a result, pixel values A, F, K, P, U, Ay ′, Fy ′, Ky ′, and Py ′ as shown in FIG. 149 are obtained, and each pixel value has a pixel value A = ax0 + B0 × 4/5, pixel value F = fx0 + ax0 + B1 × 3/5, pixel value K = kx0 + fx1 + ax2 + B2 × 2/5, pixel value P = px0 + kx1 + fx2 + ax3 + B3 × 1/5, pixel value U = ux0 + px1 + k + 2 + x3 + a + 4 + x3 + a + 4 + x3 + a + 4 The pixel value Fy ′ = B6 × 2/5 + ux2 + px3 + kx4, the pixel value Ky ′ = B7 × 3/5 + ux3 + px4, and the pixel value Py ′ = B8 × 4/5 + ux4.

  By executing these processes for all y directions, a composite image having the encrypted foreground component image as a background component image as shown in FIG. 150 is generated. In other words, the input 5 × 5 pixel image includes 9 × 9 pixels (pixels A to Y, pixels Ax to Dx, pixels Fx to Ix, pixels Kx to Nx, pixels Px to Sx, pixels Ux to Xx, pixel Ay. 'To Ty', pixels Ax 'to Dx', pixels Fx 'to Ix', pixels Kx 'to Nx', and pixels Px 'to Sx').

  As for the decryption process, since the motion blur removal unit 2041 executes a motion blur addition process that is completely opposite to the process of the motion blur addition unit 2021, the description thereof will be omitted.

  Further, in the process of step S2006 described above, when encryption is performed in the x direction, after performing gain-up processing, encryption in the y direction is performed. Therefore, after decoding in the y direction, it is necessary to lower the gain and then decode in the x direction. In addition, the order of encryption processing in the y direction and the x direction may be interchanged. However, since gain-up processing is performed in the direction of encryption first, decryption needs to correspond to the order of encryption. There is.

  Next, an encryption service by the composition server 19 provided with the encryption motion blur adding unit 2021 shown in FIG. 131 will be described with reference to the flowchart of FIG. This processing is performed when the client computer 27-1 connected to the network 1 transmits an encrypted signal to the synthesis server 19 and encrypts the signal to be transmitted to the client computer 27-2. It is processing. Further, it is assumed that the client computer 27 is provided with hardware having an image separation processing function of the separation processing server 11 having the cryptographic motion blur removal unit 2041 or software is installed.

  In step S2101, the client computer 27-1 combines the information to be encrypted (encrypted signal), the speed and direction information to be the encryption key, and the image selection information (information for selecting the background component image). Transmit to server 19.

  In step S2111, the encryption motion blur adding unit 2021 of the composition server 19 encrypts and selects information to be encrypted (encrypted signal) based on the encryption key input from the client computer 27-1. An encryption process for synthesizing the background component images thus performed is executed. The encryption process has been described with reference to the flowchart of FIG.

  In step S2112, the composition server 19 transmits an image that has been encrypted and synthesized by adding motion blur to the client computer 27-1.

  In step S2102, the client computer 27-1 displays the composite image received from the composite server 19, determines whether the image is desired by the user, and determines that the image is a desired image. In step S2103, the composition server 19 is notified that the desired image has been obtained. In step S2113, the composition server 19 determines whether or not the image is a desired image. For example, in this case, since the notification that the image is a desired image is received in step S2103, the process is performed in step S2114. Proceed to

  In step S <b> 2114, the billing processing unit 19 a of the composition server 19 executes billing processing together with the billing server 24. The billing process is the same as in the case of the separation service in FIGS. 118 and 120, and the description thereof is omitted.

  In step S2115, the composition server 19 transmits the encrypted composite image to the client computer 27-1. In step S2104, the client computer 27-1 receives the encrypted composite image and transmits it as it is to the client computer 27-2.

  In step S <b> 2141, the client computer 27-2 receives the encrypted composite image. In step S2142, the client computer 27-2 determines whether or not a key has been input, and repeats the process until an encryption key is input. When speed and direction information is input as an encryption key in step S2142, the motion blur removal processing unit 2041 executes motion blur processing based on the input speed and direction in step S2143. In step S2144, an image from which motion blur has been removed is displayed.

  If it is determined in step S2102 that the image is not a desired image, in step S2015, the composition server 19 is notified that the image is not a desired image, and the processing returns to step S2101. Also, with this processing, it is determined in step S2114 that the image is not a desired image, so the processing of the composition server 19 returns to the processing of step S2111.

  That is, by this processing, when the user of the client computer 27-2 correctly inputs the speed and direction keys designated by the user of the client computer 27-1, the encrypted image is correctly decrypted. Is displayed. In addition, the decryption service can be provided by the same system as the encryption service described above.

  Next, the correction server 20 will be described with reference to FIG.

  The separation processing unit 11 of the correction server 20 converts the input image (which may be an image ID, or in the case of an image specified by the image ID, an image obtained by reading a corresponding image from the network 1) into a foreground component image and a background component image. The foreground component image is output to the motion blur adjustment unit 2101 and the background component image is output to the synthesis unit. The motion blur adjustment unit 2101 performs motion blur adjustment with the specified amount of motion blur (adjusts the degree of correction) of the input foreground component image, and outputs the image to the synthesis unit 2101. The synthesizing unit 2101 synthesizes the foreground component image subjected to motion blur adjustment and the input background component image, and outputs the resultant as a corrected image.

  For example, it is assumed that an image as shown in FIG. 153 (A) is input to the correction server 20. That is, as shown in the right part of FIG. 153 (A), when the foreground moves on the background in the direction of the arrow, motion blur occurs in the foreground traveling direction and in the opposite direction. This motion blur part is a mixed area, and as shown in the left part of FIG. 153 (A), the mixed area generated in the front part in the moving direction is CB (Covered Background), and the mixing generated in the rear part in the moving direction. The area is UB (Uncovered Background). In the left part of FIG. 153 (A), the time axis t is set in the vertical direction, so that the relationship between the accumulation state of the pixel value on the pixel and the passage of time is shown along with the movement. The separation processing unit 11 separates this input image into a foreground and a background as shown in FIG. 153 (B). At this time, the mixed area of the input image is also extracted.

  The motion blur adjustment unit 2101 adjusts the motion blur of the foreground component image as shown in FIG. 153 (B) to generate a foreground component image as shown in FIG. 153 (C), for example. That is, in this case, the motion blur is reduced (the CB and UB portions are reduced). The motion blur adjustment amount for adjusting the motion blur may be input while the user repeats the operation several times, or the motion blur adjustment unit 2101 may adjust the motion blur adjustment amount to a predetermined value. .

  The synthesizing unit 2102 synthesizes the foreground component image adjusted as shown in FIG. 153 and the input background component image to obtain the foreground component image after motion blur adjustment as shown in FIG. 153 (D). The image is synthesized with the background component image and output.

  When it is desired to change the background component image to another background component image different from that of the input image, the separated background component image is not output to the synthesizing unit 2102 and the background component image to be changed is not combined. To enter. The correction server 20 is configured by replacing the separation processing unit 11, the motion blur adjustment unit 2101, and the synthesis unit 2102 with the separation processing server 11, the motion blur adjustment server 16, and the synthesis server 19 on the network 1. You may do it.

  Next, with reference to the flowchart of FIG. 154, the processing of the correction service that is executed by the correction server 20 and corrects the image input from the client computer 27 will be described.

  In step S <b> 2201, the client computer 27 outputs information specifying an image to the correction server 20. That is, the information specifying the image that the user wants to correct is a specific image or an image ID specifying the image is output to the correction server 20.

  In step S2211, the correction server 20 acquires the designated image to be corrected and the background component image, and the separation processing unit 11 separates the image to be corrected into the foreground component image and the background component image. That is, when an image is transmitted from the client computer 27, when an image ID for designating the image is transmitted, an image corresponding to the image ID is read from the network 1 and obtained. Further, the separation processing unit 11 separates the acquired image into a foreground component image and a background component image.

  In steps S2212 and S2221, the charging processing unit 20a and the charging server 24 of the correction server 20 execute a charging process. The billing process is the same as in the case of the separation service in FIGS. 118 and 120, and the description thereof is omitted.

  In step S2213, the motion blur adjustment unit 2101 of the correction server 20 executes a motion blur adjustment process for the foreground component image. Note that the motion blur adjustment processing is the same as the processing described with reference to the flowchart of FIG.

  In step S2214, the combining unit 2102 combines the foreground component image adjusted for motion blur and the designated background component image. In step S <b> 2215, the correction server 20 transmits the composite image obtained in step S <b> 2214, that is, the correction image, to the client computer 27.

  In step S2202, the client computer 27 receives and stores the corrected image transmitted from the correction server 20.

  The client computer 27 stores the image corrected by the correction server 20 in the correction server 20 itself or outputs the image to the storage server 18 via a network and stores (accumulates) in accordance with a user instruction. It can also be made to do.

  Next, with reference to a flowchart of FIG. 155, processing of an image purchase service for purchasing an image designated by the client computer 27 executed by the purchase server 21 will be described.

  In step S <b> 2301, the client computer 27 outputs information designating an image desired to be purchased to the purchase server 21. That is, an image ID that designates an image is output to the purchase server 21 as information that designates an image that the user wants to purchase.

  In step S2311, the purchase server 21 acquires an image desired to be purchased. That is, an image corresponding to the image ID transmitted from the client computer 27 is read from the network 1 and acquired.

  In steps S2312, S2321, the charging processing unit 21a and the charging server 24 of the purchase server 21 execute charging processing. The billing process is the same as in the case of the separation service in FIGS. 118 and 120, and the description thereof is omitted.

  In step S2313, the purchase server 21 transmits the image acquired in step S2311 to the client computer 27.

  In step S2302, the client computer 27 receives and stores the image transmitted from the purchase server 21.

  Note that the client computer 27 stores the image purchased by the purchase server 21 in the purchase server 21 itself or outputs it to the storage server 18 for storage (accumulation) in accordance with a user instruction. You can also. Further, by enabling transmission to another client computer 27, for example, an image can be presented as a gift. Further, as described above, the other user can separate the foreground component image, the background component image, the synthesized composite image, or the corrected image that has been separated by the separation processing service, the synthesis service, or the correction service, respectively. Etc. can also be purchased.

  Next, with reference to a flowchart of FIG. 156, processing of an image sale service for selling an image designated by the client computer 27, which is executed by the sale server 22, will be described.

  In step S2401, the client computer 27 outputs information specifying an image desired to be sold to the purchase server 21. That is, an image that the user wants to sell is output to the sale server 22.

  In step S2411, the sale server 22 acquires an image desired to be sold. That is, the image transmitted from the client computer 27 is acquired.

  In step S2422, the sale server 22 sets an appropriate price for the image desired to be sold. For example, the price may be set in advance by the user, may be set in the auction format on the network 1, or is an image in which a person is captured. For example, a method of setting depending on whether or not the person being imaged is a predetermined celebrity may be used.

  In steps S2413 and S2431, the billing processing unit 22a and the billing server 24 of the sale server 22 execute sale billing processing.

  Here, the sales billing process will be described with reference to the flowchart of FIG. Note that the actual sales billing process is executed by the sale server 22 and the billing server 24, but information necessary for various processes is also output from the client computer 27. Also explained.

  In step S2501, ID information for identifying a user (a user who requests the sale of an image) is transmitted to the sale server 22 via the network 1.

  In step S <b> 2511, the sale server 22 transmits the sale price and the ID for identifying the sale server 22 to the accounting server 24 based on the ID information transmitted from the client computer 27.

  In step S2521, the accounting server 24 sends the purchase amount to the financial server 25 of the customer account corresponding to the ID information with respect to the financial server 26 having the provider account based on the transmitted ID for identifying the sale server 22. Request a transfer to.

  In step S2531, the provider's financial server 26 transfers the amount corresponding to the sale amount from the provider's account to the customer's financial server 25 where the customer's account is opened.

  Now, the description returns to the flowchart of FIG.

  In step S2424, the sale server 22 notifies the client computer 27 that the sale has been completed. In step S2402, the client computer 27 receives a sale completion notification.

  The sale server 22 may store the image sold by the user in the sale server 21 itself, or may output the image to the storage server 18 for storage (accumulation). Further, when the price is set in the auction format as described above, it may be transmitted to the client computer 27 of the winning bidder.

  Next, the search server 23 will be described with reference to FIG.

  The search server 23 searches for an image captured on the camera terminal device 1 connected to the network 1 based on a search condition (image request signal) input from the client computer 27 or the like, and outputs a request image. To do. Search conditions include time, season, weather, region, place, or subject.

  The control unit 2161 of the search server 23 controls the overall operation of the search server 23. The database 2162 is provided with position data (camera terminal device 28) of each camera terminal device 28 corresponding to the camera ID of each camera terminal device 28 connected to the network 1 and recognized by the search server 23 itself. Data 2162b such as meteorological data and data of the subject being imaged are stored as a database. The contents of the database 2162 are acquired and updated from the camera terminal devices 28 via the network 1 by the control unit 2161 controlling the communication unit 2165 at predetermined time intervals.

  The storage unit 2163 stores an image acquired from the communication terminal 2165 from the camera terminal device 28 on the network 1 or stores information necessary for processing various images.

  The request information generation unit 2164 arranges search conditions input from the client computer 27 on the network 1 and generates conditions that can be actually searched on the database 2162. That is, for example, when a season is input as a search condition, the season can be specified by the position data of each camera terminal device 28 and the time information calculated by the time calculation unit 2166. Therefore, for example, when a search condition such as “spring” is input, the request information generation unit 2164 generates position data of latitude and longitude on the earth whose season is “spring” from the current time. The control unit 2161 controls the communication unit 2165 to read out the captured image of the camera terminal device 28 having the camera ID corresponding to the position data from the network 1, thereby acquiring an image corresponding to “spring”.

  The separation processing unit 2167 acquires an image for search included in the read image by separation processing. The separation processing unit 2167 has the same function as the separation processing unit 11.

  Next, a search service process for searching for an image based on a search condition input from the client computer 27, executed by the search server 23, will be described with reference to the flowchart of FIG.

  In step S2601, the client computer 27 outputs the search condition to the search server 23. In step S2611, the search server 23 receives the search condition through the communication unit 2165.

  In steps S2612 and S2631, the charging processing unit 23a and the charging server 24 of the search server 23 execute a charging process. The billing process is the same as in the case of the separation service in FIGS. 118 and 120, and the description thereof is omitted. The billing process in the processes of steps S2612 and S2631 is a billing process related to a charge for executing a search.

  In step S2613, the search server 23 searches for an image corresponding to the search condition and calls an image corresponding to the corresponding image in step S2614. In step S2641, the camera terminal device 28 transmits the currently captured image to the search server 23.

  That is, for example, as shown in FIG. 160, it is assumed that client computers 27-1 to 27-5, search server 23, and camera terminal devices 28-1 to 28-5 are connected to the network 1. At this time, when the client computer 27-2 is operated by the user and transmits "human", "car", and "building" as search conditions in the process of step S2611, the search server 23 In step S2613, the database 2162 searches for “human”, “car”, and “building” subjects as search conditions. That is, in the case of FIG. 160, the search server 23 is configured such that the car 2172 has the camera terminal device 28-1 with camera ID = 1, the human 2183 has the camera terminal device 28-2 with camera ID = 2, and the building 2211 has the camera ID = 5 is searched for, and an image is acquired from each camera terminal device 28 in step S2614.

  In step S2515, the search server 23 determines whether the called image is separated, that is, whether an image (object) other than the desired condition is included.

  In the case of FIG. 160, the image transmitted from the camera terminal device 28-1 includes a cloud 2172 other than the search condition, and the image transmitted from the camera terminal device 28-2 includes other than the search condition. Since the house 2181 is included, the images corresponding to the search condition are not separated from these images, and the process proceeds to step S2616.

  In step S2616, the separation processing unit 2167 executes separation processing. The separation process is the same as the process of step S1013 in the flowchart of FIG. 117, and a description thereof will be omitted.

  In step S2617, the called images are combined and transmitted to the client computer 27. In step S2602, the client computer 27 acquires the image transmitted from the search server 23. In step S2603, the client computer 27 determines whether or not the received image is a desired image. As shown in FIG. 160, in the case of an image displayed on the display 27a-1, “human”, “car”, and “building” as search conditions are images as human 2182, car 2172, and building 2211. Therefore, in step S2604, the search server is notified that the image is the desired image.

  In step S2618, the search server 23 determines whether or not the notification transmitted from the client computer 27 is a desired image. In the case of FIG. 160, since the image is a desired image, the process proceeds to step S2619.

  In steps S2619 and S2632, the charging processing unit 23a and the charging server 24 of the search server 23 execute a charging process. The billing process is the same as in the case of the separation service in FIGS. 118 and 120, and the description thereof is omitted. The billing process in the processes of steps S2619 and S2632 is a billing process related to a fee for transmitting the searched image. In step S2515, if all the search condition images are included, the process in step S2616 is skipped.

  In step S2603, for example, although “house”, “cloud”, and “face” are specified as search conditions from the client computer 27-4, the image is displayed on the display 27a-4. In addition, when only the house 2181 and the cloud 2071 are displayed and the face 2201 is not displayed, the image is not a desired image. Therefore, the process proceeds to step S2605, and it is searched that the image is not a desired image. The data is transmitted to the server 23, and the process ends.

  At this time, the search server 23 is notified in step S2618 that the image is not a desired image, and thus the processing ends.

  In this case, the fee related to the search process is paid, but is not paid for the transmission of the searched image.

  According to the above, it is possible to improve the processing speed by executing the image processing processing by distributing the processing among a plurality of servers in the network, and by the user by performing the processing in a distributed manner. It is possible to reduce the cost associated with the service by enabling only the processing to be executed.

  As shown in FIGS. 2 and 3, a recording medium on which a program for performing signal processing according to the present invention is recorded is distributed to provide a program to a user separately from a computer. 61, 91 (including a flexible disk), optical disks 62, 92 (including a CD-ROM (Compact Disc-Read Only Memory), DVD (Digital Versatile Disc)), magneto-optical disks 63, 93 (MD (Mini-Disc)) (Including (trademark)), or ROMs 42 and 72 on which a program is provided, which is provided to the user in a state of being preinstalled in a computer. Or a hard disk included in the storage units 48 and 78.

  In the present specification, the step of describing the program recorded on the recording medium is not limited to the processing performed in chronological order according to the described order, but is not necessarily performed in chronological order. It also includes processes that are executed individually.

  Further, in this specification, the system represents the entire apparatus constituted by a plurality of apparatuses.

It is a figure which shows the structure of one Embodiment of the image processing system to which this invention is applied. It is a figure which shows the structure of the isolation | separation processing server of FIG. It is a figure which shows the structure of the camera terminal device of FIG. It is a figure which shows the function of the separation processing server of FIG. It is a figure which shows the function of the separation processing server of FIG. It is a figure which shows the function of the motion detection server of FIG. It is a figure which shows the function of the motion detection server of FIG. It is a figure which shows the function of the area | region specific server of FIG. It is a figure which shows the function of the area | region specific server of FIG. It is a figure which shows the function of the mixture ratio calculation server of FIG. It is a figure which shows the function of the mixture ratio calculation server of FIG. It is a figure which shows the function of the foreground / background separation processing server of FIG. It is a figure which shows the function of the foreground / background separation processing server of FIG. It is a figure which shows the function of the motion blur adjustment server of FIG. It is a figure which shows the function of the motion blur adjustment server of FIG. It is a figure which shows the function of the encoding server of FIG. It is a figure which shows the function of the encoding server of FIG. It is a figure which shows the function of the storage server of FIG. It is a figure which shows the function of the storage server of FIG. It is a figure which shows the function of the synthetic | combination server of FIG. It is a figure which shows the function of the synthetic | combination server of FIG. It is a figure which shows the function of the correction server of FIG. It is a figure which shows the function of the correction server of FIG. It is a figure which shows the function of the purchase server of FIG. It is a figure which shows the function of the sale server of FIG. It is a figure which shows the function of the search server of FIG. It is a block diagram which shows a separation processing server. It is a figure explaining the imaging by a sensor. It is a figure explaining arrangement | positioning of a pixel. It is a figure explaining operation | movement of a detection element. It is a figure explaining the image obtained by imaging the object corresponding to the moving foreground and the object corresponding to the stationary background. It is a figure explaining a background area | region, a foreground area | region, a mixing area | region, a covered background area | region, and an uncovered background area | region. FIG. 6 is a model diagram in which pixel values of pixels arranged in a row adjacent to each other in an image obtained by capturing an object corresponding to a stationary foreground and an object corresponding to a stationary background are developed in the time direction. FIG. 4 is a model diagram in which pixel values are developed in a time direction and a period corresponding to a shutter time is divided. FIG. 4 is a model diagram in which pixel values are developed in a time direction and a period corresponding to a shutter time is divided. FIG. 4 is a model diagram in which pixel values are developed in a time direction and a period corresponding to a shutter time is divided. It is a figure which shows the example which extracted the pixel of the foreground area | region, the background area | region, and the mixing area | region. It is a figure which shows a response | compatibility with the model which developed the pixel and the pixel value in the time direction. FIG. 4 is a model diagram in which pixel values are developed in a time direction and a period corresponding to a shutter time is divided. FIG. 4 is a model diagram in which pixel values are developed in a time direction and a period corresponding to a shutter time is divided. FIG. 4 is a model diagram in which pixel values are developed in a time direction and a period corresponding to a shutter time is divided. FIG. 4 is a model diagram in which pixel values are developed in a time direction and a period corresponding to a shutter time is divided. FIG. 4 is a model diagram in which pixel values are developed in a time direction and a period corresponding to a shutter time is divided. It is a flowchart explaining the process of adjustment of the amount of motion blur. 3 is a block diagram illustrating an example of a configuration of an area specifying unit 103. FIG. It is a figure explaining the image when the object corresponding to a foreground is moving. FIG. 4 is a model diagram in which pixel values are developed in a time direction and a period corresponding to a shutter time is divided. FIG. 4 is a model diagram in which pixel values are developed in a time direction and a period corresponding to a shutter time is divided. FIG. 4 is a model diagram in which pixel values are developed in a time direction and a period corresponding to a shutter time is divided. It is a figure explaining the conditions of area determination. FIG. 10 is a diagram illustrating an example of a region identification result of a region identifying unit 103. FIG. 10 is a diagram illustrating an example of a region identification result of a region identifying unit 103. It is a flowchart explaining an area | region identification process. 6 is a block diagram illustrating another example of the configuration of the area specifying unit 103. FIG. FIG. 4 is a model diagram in which pixel values are developed in a time direction and a period corresponding to a shutter time is divided. It is a figure which shows the example of a background image. 3 is a block diagram illustrating a configuration of a binary object image extraction unit 302. FIG. It is a figure explaining calculation of a correlation value. It is a figure explaining calculation of a correlation value. It is a figure which shows the example of a binary object image. 3 is a block diagram showing a configuration of a time change detection unit 303. FIG. It is a figure explaining the determination of the area | region determination part 342. FIG. It is a figure which shows the example of determination of the time change detection part 303. FIG. 5 is a flowchart for explaining area specifying processing of an area determination unit 103; It is a flowchart explaining the detail of a process of area | region determination. 12 is a block diagram showing still another configuration of the area specifying unit 103. FIG. 3 is a block diagram illustrating a configuration of a robust unit 361. FIG. It is a figure explaining the motion compensation of the motion compensation part. It is a figure explaining the motion compensation of the motion compensation part. It is a flowchart explaining an area | region identification process. It is a flowchart explaining the detail of the process of robustness. 3 is a block diagram illustrating an example of a configuration of a mixture ratio calculation unit 104. FIG. It is a figure which shows the example of ideal mixing ratio (alpha). FIG. 4 is a model diagram in which pixel values are developed in a time direction and a period corresponding to a shutter time is divided. FIG. 4 is a model diagram in which pixel values are developed in a time direction and a period corresponding to a shutter time is divided. It is a figure explaining the approximation using the correlation of the component of a foreground. It is a figure explaining the relationship of C, N, and P. 3 is a block diagram showing a configuration of an estimated mixture ratio processing unit 401. FIG. It is a figure which shows the example of an estimated mixture ratio. 6 is a block diagram showing another configuration of the mixture ratio calculation unit 104. FIG. It is a flowchart explaining the process of calculation of a mixture ratio. It is a flowchart explaining the process of calculation of an estimated mixture ratio. It is a figure explaining the straight line which approximates the mixture ratio (alpha). It is a figure explaining the plane which approximates the mixture ratio (alpha). It is a figure explaining a response | compatibility of the pixel of the some flame | frame when calculating the mixture ratio (alpha). 10 is a block diagram showing another configuration of the mixture ratio estimation processing unit 401. FIG. It is a figure which shows the example of an estimated mixture ratio. It is a flowchart explaining the process of the mixture ratio estimation by the model corresponding to a covered background area | region. 3 is a block diagram illustrating an example of a configuration of a foreground / background separation unit 105. FIG. It is a figure which shows an input image, a foreground component image, and a background component image. FIG. 4 is a model diagram in which pixel values are developed in a time direction and a period corresponding to a shutter time is divided. FIG. 4 is a model diagram in which pixel values are developed in a time direction and a period corresponding to a shutter time is divided. FIG. 4 is a model diagram in which pixel values are developed in a time direction and a period corresponding to a shutter time is divided. 6 is a block diagram illustrating an example of a configuration of a separation unit 601. FIG. It is a figure which shows the example of the foreground component image and background component image which were isolate | separated. It is a flowchart explaining the process of isolation | separation of a foreground and a background. 3 is a block diagram illustrating an example of a configuration of a motion blur adjustment unit 106. FIG. It is a figure explaining a processing unit. FIG. 5 is a model diagram in which pixel values of a foreground component image are developed in a time direction and a period corresponding to a shutter time is divided. FIG. 5 is a model diagram in which pixel values of a foreground component image are developed in a time direction and a period corresponding to a shutter time is divided. FIG. 5 is a model diagram in which pixel values of a foreground component image are developed in a time direction and a period corresponding to a shutter time is divided. FIG. 5 is a model diagram in which pixel values of a foreground component image are developed in a time direction and a period corresponding to a shutter time is divided. 6 is a diagram illustrating another configuration of the motion blur adjustment unit 106. FIG. 10 is a flowchart for describing processing for adjusting the amount of motion blur included in the foreground component image by the motion blur adjustment unit 106; 6 is a block diagram illustrating another example of the configuration of the motion blur adjustment unit 106. FIG. It is a figure which shows the example of the model which designates correspondence with a pixel value and a foreground component. It is a figure explaining calculation of a foreground component. It is a figure explaining calculation of a foreground component. 10 is a flowchart for explaining foreground motion blur removal processing; It is a block diagram which shows the other structure of the function of a separation processing server. 2 is a diagram illustrating a configuration of a combining unit 1001. FIG. It is a block diagram which shows the further another structure of the function of a separation processing server. 3 is a block diagram illustrating a configuration of a mixture ratio calculation unit 1101. FIG. FIG. 10 is a block diagram illustrating a configuration of a foreground / background separation unit 1102. It is a block diagram which shows the further another structure of the function of a separation processing server. 2 is a diagram illustrating a configuration of a combining unit 1201. It is a flowchart explaining a separation service. It is a flowchart explaining an accounting process. It is a figure explaining an accounting process. It is a flowchart explaining the other example of an accounting process. It is a flowchart explaining a motion detection service. It is a flowchart explaining area | region identification service. It is a flowchart explaining a mixing ratio calculation service. It is a flowchart explaining a foreground / background separation service. It is a flowchart explaining a motion blur adjustment service. It is a figure explaining an encoding server. It is a flowchart explaining an encoding service. It is a figure explaining the compression capability at the time of the compression by an encoding process. It is a figure explaining the other example of an encoding server. It is a flowchart explaining a composition service. It is a figure explaining the motion blur addition part for encryption. It is a figure explaining the motion blur removal part for encryption. It is a figure explaining the process which adds the motion blur for encryption. It is a figure explaining the process which adds the motion blur for encryption. It is a figure explaining the process which adds the motion blur for encryption. It is a flowchart explaining an encryption process. It is a figure explaining the process which adds the motion blur for encryption. It is a figure explaining the process which adds the motion blur for encryption. It is a figure explaining the process which adds the motion blur for encryption. It is a figure explaining the process which adds the motion blur for encryption. It is a figure explaining the process which adds the motion blur for encryption. It is a figure explaining the process which adds the motion blur for encryption. It is a figure explaining the process which adds the motion blur for encryption. It is a figure explaining the process which adds the motion blur for encryption. It is a figure explaining the process which adds the motion blur for encryption. It is a figure explaining the process which adds the motion blur for encryption. It is a figure explaining the process which adds the motion blur for encryption. It is a figure explaining the process which adds the motion blur for encryption. It is a figure explaining the process which adds the motion blur for encryption. It is a figure explaining the process which adds the motion blur for encryption. It is a flowchart explaining the service for encryption. It is a figure explaining a correction server. It is a figure explaining a correction process. It is a flowchart explaining a correction service. It is a flowchart explaining a purchase service. It is a flowchart explaining a sale service. It is a flowchart explaining sale charge processing. It is a figure explaining a search server. It is a flowchart explaining a search service. It is a figure explaining a search service.

Explanation of symbols

  11 separation processing server, 12 motion detection server, 13 area specifying server, 14 mixing ratio calculation server, 15 foreground / background separation server, 16 motion blur adjustment server, 17 encoding server, 18 storage server, 19 composition server, 20 correction server, 21 purchase server, 22 sale server, 23 search server, 24 billing server, 25, 26 financial server, 27 client computer, 28 camera terminal device, 41 CPU, 42 ROM, 43 RAM, 46 input unit, 47 output unit, 48 storage Unit, 49 communication unit, 71 CPU, 72 ROM, 73 RAM, 76 input unit, 76a sensor, 76b GPS, 77 output unit, 78 storage unit, 79 communication unit, 91 magnetic disk, 92 optical disk, 93 magneto-optical disk, 94 Semiconductor memo , 101 Object extraction unit, 102 Motion detection unit, 103 Region specifying unit, 104 Mixing ratio calculation unit, 105 Foreground / background separation unit, 106 Motion blur adjustment unit, 107 Selection unit, 201 Frame memory, 202-1 to 202-4 Static Motion determination unit, 203-1 to 203-3 area determination unit, 204 determination flag storage frame memory, 205 synthesis unit, 206 determination flag storage frame memory, 301 background image generation unit, 302 binary object image extraction unit, 303 time change Detection unit, 321 correlation value calculation unit, 322 threshold processing unit, 341 frame memory, 342 region determination unit, 361 robust unit, 381 motion compensation unit, 382 switch, 383-1 to 383-N frame memory, 384- 1 to 384-N Weighting unit, 385 integrating unit, 401 estimated mixture ratio processing unit, 402 estimated mixture ratio processing unit, 403 mixture ratio determining unit, 421 frame memory, 422 frame memory, 423 mixture ratio calculating unit, 441 selecting unit, 442 estimated mixture ratio processing Unit, 443 estimation mixing ratio processing unit, 444 selection unit, 501 delay circuit, 502 addition unit, 503 operation unit, 601 separation unit, 602 switch, 603 synthesis unit, 604 switch, 605 synthesis unit, 621 frame memory, 622 separation Processing block, 623 frame memory, 631 uncovered area processing section, 632 covered area processing section, 633 combining section, 634 combining section, 801 processing unit determining section, 802 modeling section, 803 equation generating section, 804 adding section, 805 calculation unit, 806 motion blur addition unit, 807 selection unit, 821 selection unit, 901 processing unit determination unit, 902 modeling unit, 903 equation generation unit, 904 calculation unit, 905 correction unit, 906 motion blur addition unit, 907 selection , 1001 synthesis unit, 1021 background component generation unit, 1022 mixed region image synthesis unit, 1023 image synthesis unit, 1101 mixing ratio calculation unit, 1102 foreground / background separation unit, 1121 selection unit, 1201 synthesis unit, 1221 selection unit, 2001 code Conversion unit, 2002 separation processing unit, 2021 encryption motion blur addition unit, 2031 input information processing unit, 2032 imaging unit, 2033 motion blur addition unit, 2041 encryption motion blur removal unit, 2051 input information processing unit, 2052 motion blur Removal section, 2053 Signal conversion unit, 2101 motion blur adjustment unit, 2102 synthesis unit, 2161 control unit, 2162 database, 2163 storage unit, 2164 request information generation unit, 2165 communication unit, 2166 time calculation unit, 2167 separation processing unit

Claims (6)

Included in image data consisting of pixel values determined according to the amount of light constituting an image integrated for each pixel and temporally, or information specifying the image data, and images consisting of the image data Based on information specifying the object, and a model in which each pixel value of the image data is expanded in the time direction, a foreground area composed of foreground object components constituting the foreground object of the image data, and a background object of the image data Input means for inputting request information including area information for identifying either a background area composed of background object components to be configured or a mixed area in which the foreground area and the background area are mixed;
According to the request information input by the input means, based on a model that expands each pixel value of the image data or the image data acquired based on the information specifying the image data in the time direction, An image processing apparatus comprising: signal processing means for estimating a mixture ratio of the foreground object component and the background object component in the mixed region in image data. The image processing apparatus according to claim 1, wherein the signal processing unit extracts a desired component from the mixed region based on the mixing ratio in accordance with request information input by the input unit. The image processing apparatus according to claim 2, wherein the signal processing unit separates the mixed region into the foreground object component and the background object component based on the mixing ratio in accordance with request information input by the input unit. . Included in image data consisting of pixel values determined according to the amount of light constituting an image integrated for each pixel and temporally, or information specifying the image data, and images consisting of the image data Based on information specifying the object, and a model in which each pixel value of the image data is expanded in the time direction, a foreground area composed of foreground object components constituting the foreground object of the image data, and a background object of the image data An input step of inputting request information including area information for identifying either a background area composed of background object components to be configured or a mixed area in which the foreground area and the background area are mixed;
Based on the request information input by the processing of the input step, based on a model that develops each pixel value of the image data or image data acquired based on information specifying the image data in the time direction An image processing method comprising: a signal processing step of estimating a mixture ratio of the foreground object component and the background object component in the mixed region in the image data. Included in image data consisting of pixel values determined according to the amount of light constituting an image integrated for each pixel and temporally, or information specifying the image data, and images consisting of the image data Based on information specifying the object, and a model in which each pixel value of the image data is expanded in the time direction, a foreground area composed of foreground object components constituting the foreground object of the image data, and a background object of the image data An input step of inputting request information including area information for identifying either a background area composed of background object components to be configured or a mixed area in which the foreground area and the background area are mixed;
Based on the request information input by the processing of the input step, based on a model that develops each pixel value of the image data or image data acquired based on information specifying the image data in the time direction A computer-readable recording medium recording a program for causing a computer to execute a process including a signal processing step of estimating a mixture ratio of the foreground object component and the background object component in the mixed region in the image data. Included in image data consisting of pixel values determined according to the amount of light constituting an image integrated for each pixel and temporally, or information specifying the image data, and images consisting of the image data Based on information specifying the object, and a model in which each pixel value of the image data is expanded in the time direction, a foreground area composed of foreground object components constituting the foreground object of the image data, and a background object of the image data An input step of inputting request information including area information for identifying either a background area composed of background object components to be configured or a mixed area in which the foreground area and the background area are mixed;
Based on the request information input by the processing of the input step, based on a model that develops each pixel value of the image data or image data acquired based on information specifying the image data in the time direction A program for causing a computer to execute processing including: a signal processing step of estimating a mixing ratio of the foreground object component and the background object component in the mixed region in the image data.

Images