JP2020149132A - Image processing apparatus and image processing program - Google Patents

Abstract

To accurately discriminate a difference region extracted from a captured image into a moving body region and a shadow region.SOLUTION: First difference processing means 44 compares a target image 36a which is one of captured images 36, with a background image 38, and extracts a background difference region 62 composed of background difference extraction pixels that differ between the two images. Second difference processing means 50 compares the target image 36a with a past image 36b taken in the past by a difference period before the target image 36a to extract an inter-frame difference region 68 composed of inter-frame difference extraction pixels that differ between the two images. Shadow region determining means 52 determines a pixel group also extracted as inter-frame difference pixels by inter-frame difference processing as a moving body region 70 corresponding to a person, among each of the background difference extraction pixels included in the background difference region 62, and determines a pixel group not extracted as the inter-frame difference pixels by the inter-frame difference processing as a shadow region 72 corresponding to a shadow of the person, among each of the background difference extraction pixels included in the background difference region 62.SELECTED DRAWING: Figure 2

Description

The present invention relates to an image processing apparatus and an image processing program for detecting a moving body region indicating an image region of a moving body from within a captured image.

Conventionally, a process of extracting a difference area between a captured image acquired by photographing a predetermined area (monitoring area) with a camera and a background image (an image in which a moving body does not exist in the monitoring area) is performed. For example, when a moving object such as a person invades the monitoring area, the difference area is extracted from the captured image.

The difference region may include the shadow of the moving body in addition to the moving body itself. Therefore, conventionally, a process of determining whether the difference region is a moving body region indicating a moving body or a shadow region indicating a shadow is performed based on the image features of the difference region extracted from the captured image. It was.

For example, in Patent Document 1, among the difference regions extracted from the captured image, the difference region having a texture similar to the texture of the difference region in the background image and having a lower brightness value than the background image is shaded. The process of determining the area is disclosed.

Japanese Unexamined Patent Publication No. 2012-43021

In the conventional method of determining the shadow area by focusing on the texture or the brightness value, the shadow area may not be determined accurately. For example, when there is no texture in the background image (for example, when there is no pattern or shape on the floor surface, or when there is a pattern on the floor surface, the brightness of the difference area is too high in the background image or the captured image and the texture cannot be identified. ), Although it is originally a shadow area, it may be erroneously determined that it is not a shadow area.

An object of the present invention is to accurately discriminate a difference region extracted from a captured image into a moving body region and a shadow region.

The present invention is an image processing device that detects a moving body region indicating an image region of a moving body from a target image among captured images in which a predetermined region is sequentially captured, and is a background image obtained by capturing the background of the predetermined region and the above. A difference processing means that performs background subtraction processing between the target image and frame-to-frame difference processing between the target image and a comparison image taken in the past or future by a difference period from the target image, and the background subtraction. Among the pixels extracted by the processing, the pixels extracted by the inter-frame subtraction processing are determined as the pixels of the moving body region, and the pixels not extracted by the inter-frame subtraction processing are the pixels of the shadow region corresponding to the shadow. The image processing apparatus is characterized by comprising a shadow region determining means for determining the image.

Desirably, the difference processing means is characterized in that the larger the amount of movement of the background subtraction region between the plurality of captured images, the shorter the difference period is set.

Desirably, the shadow region determination means redetermines pixels having a predetermined width from the outer periphery of the shadow region as pixels in the shadow region among the pixels determined to be the moving body region.

Desirably, the shadow region determination means is characterized in that the larger the movement amount, the larger the predetermined width is set.

Desirably, the shadow region determining means sets the predetermined width based on the moving direction of the background subtraction region between the plurality of captured images.

Further, the present invention is an image processing program for detecting a moving body region indicating an image region of a moving body from a target image among captured images in which a predetermined region is sequentially captured, and a computer is used as a background of the predetermined region. A difference that performs background subtraction processing between the background image taken and the target image, and frame-to-frame difference processing between the target image and a comparison image taken in the past or future by a difference period from the target image. Among the pixels extracted by the processing means and the background subtraction processing, the pixels extracted by the interframe subtraction processing are determined as the pixels of the moving body region, and the pixels not extracted by the interframe subtraction processing are shadowed. It is an image processing program characterized by functioning as a shadow area determining means for determining as a pixel of a shadow area corresponding to.

According to the present invention, the difference region extracted from the captured image can be accurately discriminated into the moving body region and the shadow region.

It is a block diagram of the security system which concerns on this embodiment. It is a block diagram of the image sensor which concerns on this embodiment. It is a figure which shows the target image (a), the background image (b), and the background subtraction image (c). It is a figure which shows the target image (a), the past image (b), and the inter-frame difference image (c). It is a figure which shows the background subtraction image (a), the interframe subtraction image (b), and the shadow area determination processing result (c). It is a figure which shows the difference period when the amount of movement of a person between frames is relatively large. It is a figure which shows the difference period when the amount of movement of a person between frames is relatively small. It is a figure which shows the state of the shadow area expansion processing.

Hereinafter, embodiments of the present invention will be described.

FIG. 1 is a schematic configuration diagram of a security system 10 according to the present embodiment. The security system 10 is a security center connected to each security device 14 via a security device 14 installed in each monitored property 12 such as a store, office, condominium, warehouse, or house, and a communication network 16 such as a public telephone line. The device 18 and the user device 20 are included. Further, the security system 10 includes an image sensor 22 as one or more image processing devices for detecting an abnormality in the monitored property 12 based on a monitored image obtained by capturing the monitored area of the monitored property 12, and an image sensor 22. It is configured to include a recording device 24 for recording a surveillance image taken by the user. The image sensor 22 and the recording device 24 are communicably connected to the security device 14.

When the security device 14 receives an alarm signal from the image sensor 22 connected to itself via the premises LAN or the like, the security device 14 detects the alarm signal, the identification signal of the security device 14 itself, the monitored property 12, or an abnormality. The identification signal of the image sensor 22 is transmitted to the security center device 18. Therefore, the security device 14 has a communication interface for communicating with the image sensor 22, a communication interface for communicating with the security center device 18 and the user device 20, and a control unit for controlling them.

The security center device 18 is composed of a so-called computer, and includes a communication interface for communicating with the security device 14 via the communication network 16, a display device such as a liquid crystal display, and a notification unit composed of a buzzer, an LED, or the like. .. When the security center device 18 receives an alarm signal from the security device 14 via the communication network 16, the security center device 18 notifies the monitored property 12 in which the security device 14 that has transmitted the alarm signal is installed, and the content of the detected abnormality. Notify the observer through the display device.

The user device 20 is also composed of a so-called computer, and remotely operates the security device 14 such as a communication interface for communicating with the security device 14 via the communication network 16, a display device such as a liquid crystal display, and a keyboard and a mouse. It has a user interface for inputting operation commands for. When the user device 20 observes the pre-registered monitored property 12 via the user interface, the user device 20 currently photographs the security device 14 installed in the registered monitored property 12. Various image request signals requesting that the surveillance image inside or the surveillance image recorded in the recording device 24 be transmitted to the user device 20 are transmitted. Then, when the surveillance image is received from the security device 14, the user device 20 displays the requested surveillance image on the display device.

The recording device 24 is a recording medium that can be attached to and detached from the recording device 24, such as a magnetic disk device such as an HDD, a magnetic tape such as a DAT, and an optical recording medium such as a DVD-RAM, and data by accessing the recording medium. It consists of a device that reads and writes. The recording device 24 receives the surveillance image taken by the image sensor 22 from the security device 14 and records it in association with the shooting time.

FIG. 2 is a schematic configuration diagram of the image sensor 22. The image sensor 22 captures a predetermined region (monitoring region) to acquire a captured image, and then detects a moving body region indicating a moving body from the captured image. In the present embodiment, the image sensor 22 detects a moving body region indicating a person (intruder) among moving bodies from the captured image. The details of the image sensor 22 will be described below.

The communication unit 30 is an input / output interface for transmitting and receiving various setting signals and control signals between the image sensor 22 and the security device 14 via a communication network such as a premises LAN, and various types such as Ethernet (registered trademark). It is composed of the communication interface circuit of the above and the driver software that drives them. Specifically, when a person is detected by the signal processing unit 42 described later, the communication unit 30 outputs an alarm signal indicating that the person has been detected to the security device 14.

The photographing unit 32 includes a two-dimensional detector composed of a photoelectric converter having sensitivity to visible light such as a CCD, and an imaging optical system that forms an image of a monitoring area on the two-dimensional detector. It is composed. As the photographing unit 32, for example, a unidirectional camera or an omnidirectional camera can be used. The photographing unit 32 sequentially acquires captured images by sequentially photographing the monitoring area. In the present embodiment, the photographing unit 32 shoots at regular time intervals (for example, 1/5 second), but the photographing method of the photographing unit 32 is not limited to this. The acquired captured image is stored in the storage unit 34.

The storage unit 34 is composed of a semiconductor memory, a magnetic disk (HDD), an optical disk drive such as a CD-ROM or a DVD-RAM, and a recording medium thereof. The storage unit 34 stores an image processing program for operating each part of the image sensor 22. Further, as shown in FIG. 2, the storage unit 34 stores a plurality of captured images 36, background images 38, and reference information 40 sequentially acquired by the photographing unit 32.

The background image 38 is an image obtained by photographing the background of the monitoring area, and is created by the signal processing unit 42 based on the captured image 36 when no person exists in the monitoring area. For example, the signal processing unit 42 obtains the inter-frame difference between the plurality of captured images 36 sequentially acquired by the photographing unit 32, and obtains the average value of the absolute values of the brightness differences between the corresponding pixels between the frames. Then, the signal processing unit 42 stores the captured image 36 whose average value is smaller than a predetermined reference in the storage unit 34 as the background image 38. Further, it is preferable that the background image 38 is updated at regular intervals (for example, every 10 minutes) in order to cope with fluctuations in the monitoring area such as fluctuations in the lighting state and daily fluctuations in the sun.

The reference information 40 is information representing the characteristics of the detection target (person in the present embodiment), and in the present embodiment, the reference height (for example, 180 cm) indicating the standard height of the person and the standard width of the person are indicated. It contains a reference width (eg, 60 cm) and information indicating a reference movement speed indicating the standard movement speed of the person.

The signal processing unit 42 has a built-in microprocessor unit, memories such as ROM and RAM, and peripheral circuits thereof, and executes various signal processing of the image sensor 22. As shown in FIG. 2, the signal processing unit 42 serves as a first difference processing means 44, a label shaping means 46, a tracking means 48, a second difference processing means 50, a shadow area determination means 52, and an intruder determination means 54. Demonstrate the function of. When the signal processing unit 42 exerts these means, the moving body region, which is an image region showing a person (intruder), is detected in the captured image 36. Hereinafter, each means included in the signal processing unit 42 will be described.

The first difference processing means 44 compares the captured image 36 with the background image 38 stored in advance in the storage unit 34, extracts pixels that differ between the two images, and sets the extracted pixels as the first value. Performs background subtraction processing to obtain a background subtraction image which is a binary image in which pixels not extracted are set to (for example, 0) and a second value (for example, 0). Here, the "pixels different between the two images" mean the pixels of the captured image 36 in which the difference in luminance value or color component between the captured image 36 and the background image 38 is equal to or greater than a predetermined value. The first difference processing means 44 performs background subtraction processing between each of the plurality of captured images 36 that are sequentially acquired and the background image 38.

FIG. 3 shows examples of the target image 36 (a), the background image 38 (b), and the background subtraction image 60 (c), which are the captured images 36 for detecting the moving body region. By the way, the target image 36a does not necessarily have to be the latest captured image 36 among the plurality of captured images 36 stored in the storage unit 34. When a person is included in the target image 36a as in the example of FIG. 3A, background subtraction processing corresponds to the person and the shadow of the person as shown in FIG. 3C. A background subtraction region 62 composed of a group of pixels is extracted. The pixels included in the background subtraction region 62 are called background subtraction extraction pixels. As shown in FIG. 3C, when the target image 36a includes the shadow of a person, the area showing the shadow is also included in the background subtraction region 62.

In addition, the first subtraction processing means 44 performs labeling processing for assigning an identifier (label) to each background subtraction extraction pixel. As the label, for example, a unique numerical value in the background subtraction image 60 can be used. In the labeling process, when attention is paid to a certain background subtraction pixel, a group of pixels composed of other background subtraction extraction pixels adjacent to the pixel is regarded as one background subtraction region 62. The pixels adjacent to the background subtraction extraction pixels may be pixels adjacent to the background subtraction extraction pixels in the vertical and horizontal directions, or may include pixels adjacent to the background subtraction extraction pixels in the oblique direction. Then, different labels are given to each background subtraction region 62, and processing is performed to store the background subtraction image 60 as a pixel value. Hereinafter, the background subtraction area 62 to which the label is attached may be referred to as a label area 64.

The label shaping means 46 executes a label shaping process for shaping each label area 64 extracted by the first difference processing means 44. For example, a label integration process for integrating a plurality of label areas 64 based on a predetermined condition such as whether or not a plurality of label areas 64 within a predetermined range become a human-like size or shape area when integrated. To execute. According to the label integration process, for example, when the upper body and the lower body of the same person are extracted as different label areas 64, the two label areas 64 are integrated to correspond to the image of one person. It can be the label area 64.

Further, for example, the label shaping means 46 may perform a label deletion process for deleting the label area 64. The label deletion process is a process of deleting a label area 64 that can be clearly determined not to be a person. For example, the label area 64, which is too large or too small for the size of the person, is deleted.

The tracking means 48 performs a process of temporally tracking the label area 64 extracted from each of the plurality of captured images 36 sequentially acquired by the photographing unit 32 and shaped by the label shaping means 46. Specifically, the tracking means 48 is extracted from each label area 64 extracted from the captured image 36 acquired this time and shaped by the label shaping means 46, and stored in the captured image 36 acquired in the past. A process of identifying the label area 64 (hereinafter referred to as “tracking label area”) stored as tracking information in the unit 34 (a process of determining that the label area 64 corresponds to the same person) is performed. Here, the tracking information is information related to the tracking ID, the position on the captured image 36, and the tracking feature amount with respect to the tracking label area. The tracking feature amount is the size and shape of the tracking label area in the real space, the brightness histogram, the texture information, and the like.

The tracking means 48 compares the tracking feature amount and position of the label area 64 of the captured image 36 acquired this time with the tracking feature amount and position of the tracking label area, and thereby, the captured image 36 acquired this time. The label area 64 and the tracking label area are identified. For example, identification is performed by those having similar tracking features and close positions. Then, the same tracking ID as the identified tracking label area is assigned to the label area 64 of the captured image 36 acquired this time, and the tracking of the label area 64 of the captured image 36 acquired this time is tracked in chronological order. After associating the ID with the position on the captured image 36 and the like, the ID is stored in the storage unit 34 as tracking information.

In the label area 64 of the captured image 36 acquired this time, those that could not be identified as the tracking label area are assumed to have appeared as a new person, and a new tracking feature amount is added to the tracking feature amount of the label area 64. Give an ID. In addition, if there is a tracking label area that has been tracked so far that cannot be identified as the label area 64 of the captured image 36 acquired this time, it is assumed that the person corresponding to the tracking label area has disappeared. , Delete the tracking information.

The tracking means 48 can obtain the moving direction and the amount of movement of the label area 64 (background subtraction area 62) between the two captured images 36 by performing the tracking process of the label area 64 described above. Specifically, the direction from the predetermined position (coordinates) of the label area 64 included in the captured image 36 at the previous time to the predetermined position of the label area 64 given the same tracking ID included in the captured image at the later time is. It is the movement direction, and the distance between the two is the movement amount of the label area 64.

The second difference processing means 50 compares the target image 36a with the other captured image 36, extracts pixels that differ between the two images, and sets the extracted pixels as the first value (for example, 1). Inter-frame difference processing is performed to obtain an inter-frame difference image which is a binary image in which pixels that are not extracted are set as a second value (for example, 0). Here, the other captured image 36 as a comparative image is an image captured in the past or future for a difference period, which will be described in detail later than the target image 36a. In the present embodiment, the comparative image is a past image 36b taken in the past by a difference period from the target image 36a.

FIG. 4 shows examples of the target image 36a (a), the past image 36b (b), and the inter-frame difference image 66 (c). In the example of FIG. 4, the position of the person included in the target image 36a and the position of the person included in the past image 36b are slightly different. As shown in FIG. 4C, an inter-frame difference region 68 in which the difference in luminance value or color component is equal to or greater than a predetermined value is extracted between the target image 36a and the past image 36b. The pixels included in the inter-frame difference region 68 are referred to as inter-frame difference extraction pixels.

Even if the position of the person's part is slightly displaced due to the degree of light hitting the person, wrinkles or patterns of clothes, etc., when focusing on one pixel, the target image 36a In many cases, the brightness value and color component of the pixel are considerably different from those of the past image 36b. Therefore, in the inter-frame difference image 66, pixels in which a person overlaps between the target image 36a and the past image 36b are also extracted as inter-frame difference extraction pixels.

On the other hand, in the shadow portion of the person, there are many cases where all the pixels have similar brightness values and color components between the target image 36a and the past image 36b. Specifically, there are many cases where the brightness value is low and the pixels are such that the texture of the floor surface can be seen faintly. Therefore, in the inter-frame difference image 66, the pixels in which the shadows overlap between the target image 36a and the past image 36b are not extracted as the inter-frame difference extraction pixels. Only the pixels that were shadows in the target image 36a but no longer in the past image 36b and the pixels that were not shadows in the target image 36a but were shadows in the past image 36b are inter-frame difference pixels. Is extracted as.

The shadow region determining means 52 uses the interframe subtraction image 66 to perform the background subtraction region 62 (label region 64) included in the background subtraction image 60 with a moving body region corresponding to a person and a shadow corresponding to the shadow of the person. Performs shadow region determination processing to discriminate from the region.

FIG. 5 shows an example of the background subtraction image 60 (a), the inter-frame subtraction image 66 (b), and the determination result (c) of the shadow region determination means 52. As described above, in the inter-frame difference image 66, most of the shadows of the person are not extracted as the inter-frame difference extraction pixels.

Therefore, the shadow region determining means 52 corresponds to a person a group of pixels extracted as inter-frame subtraction pixels by inter-frame subtraction processing among the background subtraction extraction pixels included in the background subtraction region 62 of the background subtraction image 60. The moving body region 70 is used. More specifically, among the background subtraction extraction pixels of the background subtraction image 60, the pixels having the same coordinates in the interframe subtraction image 66 move the pixels included in the interframe subtraction region 68 (that is, the interframe subtraction extraction pixels). The body region is 70.

Further, the shadow region determining means 52 uses a group of pixels that are not extracted as interframe difference pixels by interframe subtraction processing among the background subtraction extraction pixels included in the background subtraction region 62 of the background subtraction image 60 as shadows of a person. The corresponding shadow region 72. More specifically, among the background subtraction extraction pixels of the background subtraction image 60, the pixels having the same coordinates in the interframe difference image 66 are not included in the interframe difference region 68 (that is, they are not the interframe subtraction extraction pixels). Area 72.

In this way, the background subtraction region 62 (label region 64) detected from the background subtraction image 60 is discriminated into the moving body region 70 and the shadow region 72, as shown in FIG. 5C.

As described above, the second difference processing means 50 obtains the inter-frame difference image 66 between the target image 36a and the past image 36b taken in the past by the difference period from the target image 36a. As the difference period, a preset period may be used, and for example, the image before a predetermined frame from the target image 36a may be the past image 36b.

However, when the moving speed of the person is high, the pixels in which the shadow of the person overlaps may disappear between the target image 36a and the past image 36b. In this case, the background subtraction region 62 cannot be discriminated into the moving body region 70 and the shadow region 72 by the above-mentioned shadow region determination process by the shadow region determining means 52. Specifically, of the background subtraction region 62, the shadow portion is actually determined to be the moving body region 70.

On the contrary, when the moving speed of the person is considerably slow, there is no difference in the brightness value or the color component not only in the shadow of the person but also in the pixels corresponding to the person between the target image 36a and the past image 36b. It may end up. In this case, in the inter-frame difference image 66, not only the shadow but also the person portion is not extracted as the inter-frame difference region 68. Also in this case, the background subtraction region 62 cannot be discriminated into the moving body region 70 and the shadow region 72 by the above-mentioned shadow region determination process by the shadow region determining means 52. Specifically, of the background subtraction region 62, the person portion is actually determined to be the shadow region 72.

Therefore, a portion corresponding to the person is extracted as the inter-frame difference area 68 in the inter-frame difference image 66 so that there are pixels in which the shadow of the person overlaps between the target image 36a and the past image 36b. As described above, it is preferable that the second difference processing means 50 sets the difference period according to the moving speed of the person.

The moving speed of the person is represented by the amount of movement of the background subtraction region 62 (label region 64) obtained by the tracking process of the tracking means 48. Therefore, in the present embodiment, the second difference processing means 50 sets the difference period shorter as the amount of movement of the background subtraction region 62 increases. In other words, the second difference processing means 50 sets the difference period longer as the amount of movement of the background subtraction region 62 is smaller.

The moving speed of the person may be acquired by another method. For example, a linear measurement sensor or the like for measuring the moving speed of the measurement target may be separately provided, and the moving speed of the person may be acquired based on the information transmitted from the linear measurement sensor. If the moving speed of the person is high, the amount of movement of the background subtraction region 62 between the plurality of captured images 36 is inevitably large.

FIG. 6 shows the target image 36a and a plurality of captured images 36-1 to 36-4 captured in the past of the target image 36a. The example of FIG. 6 is an example in which the moving speed of a person is high and the amount of movement of the background subtraction region 62 between each captured image is large. In this case, the second difference processing means 50 shortens the difference period, and sets the captured image 36-1, which is the frame immediately before the target image 36a, as the past image 36b.

FIG. 7 also shows the target image 36a and a plurality of captured images 36-1 to 36-4 captured in the past of the target image 36a. The example of FIG. 7 is an example in which the moving speed of the person is slow and the amount of movement of the background subtraction region 62 between the captured images is small. In this case, the second difference processing means 50 lengthens the difference period, and sets the captured image 36-3, which is the frame three before the target image 36a, as the past image 36b.

Further, in the inter-frame difference image 66, pixels that were shadows in the target image 36a but are no longer shadows in the past image 36b are extracted as inter-frame difference pixels, so that shadow region determination processing by the shadow region determination means 52 As shown in FIG. 5C, a part of the shadow portion of the background subtraction region 62 is actually determined to be the moving body region 70.

Therefore, of the background subtraction region 62, the shadow region determining means 52 is determined to be the moving body region 70 after the shadow region determining process so that the shadow portion is actually appropriately included in the shadow region 72. Of the pixels, it is preferable to perform shadow region expansion processing in which pixels having a predetermined width from the outer periphery of the shadow region 72 are redetermined as pixels in the shadow region 72.

FIG. 8 shows the state of the shadow area expansion process. After the shadow area determination process, the shadow area determination means 52 identifies a pixel group (pixel group surrounded by a broken line 74 in FIG. 8A) located outside a predetermined width from the outer circumference of the shadow area 72. Next, the shadow area determination means 52 redetermines the pixel determined to be the moving body area 70 as the shadow area 72 from the pixel group surrounded by the specified broken line 74. The result of the re-judgment is shown in FIG. 8 (b). As shown in FIG. 8B, according to the shadow area expansion process, the shadow portion is actually appropriately determined to be the shadow area 72.

Here, the faster the moving speed of the person, the fewer pixels the shadow of the person overlaps between the target image 36a and the past image 36b. Therefore, in the inter-frame difference image 66, the target image 36a is a shadow. However, the number of pixels that are no longer shadows in the past image 36b increases. As a result, the number of pixels that are actually shadows but are determined to be the moving body region 70 by the shadow region determination processing increases.

Therefore, it is preferable that the shadow area determining means 52 sets the width of the pixel (the predetermined width) specified outside the outer periphery of the shadow area 72 according to the moving speed of the person in the shadow area expansion process. Is.

Here, too, the moving speed of the person is represented by the movement amount of the background subtraction region 62 (label region 64) obtained by the tracking process of the tracking means 48. Therefore, in the present embodiment, the shadow region determining means 52 is The larger the amount of movement of the background subtraction region 62, the larger the predetermined width is set. In other words, the shadow region determining means 52 sets the predetermined width to a smaller value as the amount of movement of the background subtraction region 62 is smaller.

Further, depending on the moving direction of the person, the way of changing the number of pixels in which the shadow of the person overlaps may change between the target image 36a and the past image 36b. For example, when a person is moving in the stretching direction of the shadow, the shadow region (the region at the tip of the shadow) in the stretching direction becomes a region that is not a shadow in the past image 36b but is a shadow in the target image 36a. It is easy to extract as a difference pixel between frames. Further, when the person is moving in the direction orthogonal to the extending direction of the shadow, the shadow region (the region of the side portion of the shadow) in the orthogonal direction is not the shadow in the past image 36b, but the target image 36a. It tends to be a shadowed area and is easily extracted as an inter-frame difference pixel.

Therefore, it is preferable that the shadow area determining means 52 sets the width of the pixel (the predetermined width) specified outside the outer circumference of the shadow area 72 based on the moving direction of the person in the shadow area expanding process. Is. For example, the predetermined width of the portion corresponding to the moving direction of the person is set to be a large value.

Since the moving direction of the person is represented by the moving direction of the background subtraction area 62 (label area 64) obtained by the tracking process of the tracking means 48, the shadow area determining means 52 uses the background subtraction area 62 in the present embodiment. The predetermined width is set based on the moving direction of 62.

Returning to FIG. 2, the intruder determination means 54 corresponds to a moving person (intruder) for each of the label areas 64 included in the target image 36a based on the processing results of the above-mentioned means. Determine if it exists.

In the present embodiment, the intruder determination means 54 compares the number of pixels in the moving body region 70 with the number of pixels in the shadow region 72 in a certain label area 64. Then, when the number of pixels in the moving body region 70 is large, the label area 64 is determined to be a moving body. On the other hand, when the number of pixels in the shadow area 72 is large, it is determined that the label area 64 is a shadow.

Next, the intruder determining means 54 determines whether or not the label area 64 determined to be a moving body is human. For example, the estimated size (estimated height or estimated width) of the label area 64 is obtained, and it is determined whether or not the label area 64 is human by comparing it with the standard size of the person included in the reference information 40.

Further, the intruder determining means 54 obtains the estimated speed of the label area 64 based on the movement amount of the label area 64 from the result of the tracking process of the tracking means 48, and the standard moving speed of the person included in the reference information 40. It may be determined whether or not the label area 64 is human-like in consideration of the comparison result with.

When the label area 64 is determined to be human by the above processing, the intruder determination means 54 determines that the target image 36a includes a person (intruder), and causes the communication unit 30 to output an alarm signal. .. Here, further, the intruder determination means 54 communicates when it is determined that the label area 64 to which the same tracking ID is assigned is continuously determined to be human-like by a predetermined number of frames (for example, 5 frames) or more. The alarm signal may be output from the unit 30.

Although the embodiments according to the present invention have been described above, the present invention is not limited to the above embodiments, and various modifications can be made without departing from the spirit of the present invention.

For example, in the present embodiment, the background subtraction region 62 extracted by the first subtraction processing means is subjected to labeling processing or tracking processing, but the shadow region determination processing is performed first to perform the moving body region 70 and the shadow. Labeling processing or tracking processing may be performed on the background subtraction region 62 that is discriminated from the region 72. According to this, since the moving body region 70 and the shadow region 72 are discriminated from each other, the moving body region 70 and the shadow region 72 can be set as different label regions 64. Further, by separating the moving body region 70 and the shadow region 72 by the label shaping process, the shadow region 72 can be treated as a label region 64 different from the moving body region 70. It is also possible to remove the label area 64 corresponding to the shadow area 72.

10 security system, 12 monitored property, 14 security device, 16 communication network, 18 security center device, 20 user device, 22 image sensor, 24 recording device, 30 communication unit, 32 imaging unit, 34 storage unit, 36 captured image , 36a Target image, 36b Past image, 38 Background image, 40 Reference information, 42 Signal processing unit, 44 First subtraction processing means, 46 Label shaping means, 48 Tracking means, 50 Second difference processing means, 52 Shadow area determination means , 54 Intruder determination means, 60 background subtraction image, 62 background subtraction area, 64 label area, 66 interframe subtraction image, 68 interframe subtraction area, 70 moving body area, 72 shadow area, 74 broken line.

Claims (6)

An image processing device that detects a moving body area indicating an image area of a moving body from a target image among captured images obtained by sequentially shooting a predetermined area.
Background subtraction processing between the background image obtained by capturing the background of the predetermined region and the target image, and between frames between the target image and the comparative image captured in the past or future by a difference period from the target image. A means of difference processing that performs difference processing and
Among the pixels extracted by the background subtraction processing, the pixels extracted by the inter-frame subtraction processing are determined as the pixels of the moving body region, and the pixels not extracted by the inter-frame subtraction processing are shadows corresponding to shadows. Shadow subtraction determination means for determining as area pixels,
An image processing apparatus comprising. The difference processing means sets the difference period shorter as the amount of movement of the background subtraction region between the plurality of captured images is larger.
The image processing apparatus according to claim 1. The shadow region determination means redetermines pixels having a predetermined width from the outer periphery of the shadow region as pixels in the shadow region among the pixels determined to be the moving body region.
The image processing apparatus according to claim 2. The shadow region determining means sets the predetermined width to a larger value as the movement amount is larger.
The image processing apparatus according to claim 3. The shadow region determining means sets the predetermined width based on the moving direction of the background subtraction region between the plurality of captured images.
The image processing apparatus according to claim 3 or 4. An image processing program for detecting a moving body area indicating an image area of a moving body from a target image among captured images obtained by sequentially shooting a predetermined area.
Computer,
Background subtraction processing between the background image obtained by capturing the background of the predetermined region and the target image, and between frames between the target image and the comparative image captured in the past or future by a difference period from the target image. A means of difference processing that performs difference processing and
Among the pixels extracted by the background subtraction processing, the pixels extracted by the inter-frame subtraction processing are determined as the pixels of the moving body region, and the pixels not extracted by the inter-frame subtraction processing are shadows corresponding to shadows. Shadow subtraction determination means for determining as area pixels,
An image processing program characterized by functioning as.

Images