JP2020167508A - Image processing apparatus and image processing program - Google Patents

Abstract

To suppress that an image region obtained by photographing a mobile body as a detection object such as a person is mistakenly determined as a stable region, and set a stable region 42 with high accuracy.SOLUTION: An image processing apparatus 22 detects a mobile body region indicating an image region of a mobile body from a prescribed object image among photographing images 46 obtained by sequentially photographing a prescribed space by a photographing device 32, and comprises stable region determination means 54 that compares a first difference region extracted by comparing the object image with a background image 44 obtained by photographing a background of the prescribed space with a second difference region extracted by comparing the object image with the photographing image 46 obtained by photographing before or after the object image, and sets the image region in which the second difference region is not extracted and the first difference region is extracted in a determination period as a stable region 42, which is not detected as a mobile body region. In the image processing apparatus 22, the determination period is set to a length different in accordance with a position on the photographing image 46.SELECTED DRAWING: Figure 2

Description

The present invention relates to an image processing device and an image processing program that set a determination period for detecting a moving object according to the installation status of a camera.

An image processing device that monitors a predetermined space performs a process of updating a stored background image at any time with the passage of time (Patent Document 1). However, if the background image update interval is long, the change area caused by factors other than the person to be detected, such as opening and closing the door and turning on and off the fluorescent lamp, remains extracted, and the change area is the same as that of the person. In the case of size, there is a risk that something other than a person will be mistaken for a person. Therefore, even if the change area is extracted by background subtraction, the image area that does not move in the judgment period shorter than the update interval of the background image (the image area that is not extracted in the interframe difference image) is not regarded as the moving body area and is stable. It is conceivable that the region is determined to be a region, and even if a change region is extracted in the stable region, that region is excluded from the moving object detection process.

Japanese Unexamined Patent Publication No. 2005-46811

However, there is a problem that the image area in which a moving object such as a person to be detected is captured is erroneously determined as a stable area depending on the installation condition of the camera for photographing the surveillance space. For example, if there is a moving object that moves on the radiation from a line extending vertically below the camera, it will appear to be stationary on the captured image, although it is actually moving, and it will appear as a stable area. May be misjudged.

An object of the present invention is to prevent an image region in which a moving object such as a person is captured from being mistakenly determined as a stable region, and to accurately determine a change region other than the moving object as a stable region. ..

One aspect of the present invention is an image processing device that detects a moving body region indicating an image region of a moving body from a predetermined target image among captured images in which a predetermined space is sequentially photographed by the photographing device, and the target image The first difference region extracted by comparing the background image of the predetermined space with the background image, and the target image and the captured image taken before or after the target image were compared and extracted. An image processing means for comparing the second difference region and setting the image region in which the second difference region is not extracted during the determination period and the extracted first difference region is not detected as the moving body region is provided. The image processing apparatus is characterized in that the determination period is set to a different length depending on the position on the captured image.

Another aspect of the present invention is an image processing program that detects a moving body region indicating an image region of a moving body from a predetermined target image among captured images in which a predetermined space is sequentially captured by a photographing device, wherein the computer is used. The first difference region extracted by comparing the target image with the background image obtained by capturing the background of the predetermined space, and the captured image captured before or after the target image are compared with each other. Image processing that compares the extracted second difference regions and sets the image region in which the second difference region is not extracted and the first difference region is extracted as a stable region that is not detected as the moving body region during the determination period. It is an image processing program that functions as a means and is characterized in that the determination period is set to a different length depending on the position on the captured image.

Here, it is preferable that the determination period is set longer as the position closer to the vanishing point in the captured image.

Further, it is preferable that the determination period is set shorter when the installation height of the photographing device is higher than the reference value corresponding to the height of the moving body and when the installation height is higher than the reference value. ..

Further, it is preferable that the determination period is set longer as the depression angle of the photographing apparatus is smaller.

Further, based on the installation height of the photographing device, assuming that the entire photographed image is a floor surface, the distance from the optical center of the photographing device to the position of the floor surface corresponding to each region or each pixel of the photographed image. It is preferable to calculate and set the determination period, which is longer for a region or a pixel having a larger distance.

According to the present invention, it is possible to prevent an image region in which a moving object such as a person is captured from being mistakenly determined as a stable region, and to accurately determine a change region other than the moving object as a stable region. ..

It is a structural schematic diagram of the security system in embodiment of this invention. It is a structural schematic diagram of the image processing apparatus in embodiment of this invention. It is a figure explaining the installation state of the photographing part in embodiment of this invention. It is a figure explaining the setting process of the determination period in embodiment of this invention. It is a figure explaining the extraction process of the 1st difference region in embodiment of this invention. It is a figure explaining the setting process of the stable region in embodiment of this invention. It is a flowchart which shows the flow of the determination period setting process in embodiment of this invention. It is a flowchart which shows the flow of the intruder determination process in embodiment of this invention.

Hereinafter, embodiments of the present invention will be described.

FIG. 1 is a schematic configuration diagram of the 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 processing device 22 as one or more image processing devices for detecting an abnormality in the monitored property 12 based on a monitored image obtained by photographing the monitored area of the monitored property 12, and image processing. It includes a recording device 24 for recording a surveillance image taken by the device 22. The image processing device 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 processing device 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 processing device 22 is transmitted to the security center device 18. Therefore, the security device 14 has a communication interface for communicating with the image processing device 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 processing device 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 processing device 22.

The communication unit 30 is an input / output interface for transmitting and receiving various setting signals and control signals between the image processing device 22 and the security device 14 via a communication network such as a premises LAN, and is an input / output interface such as Ethernet (registered trademark). It consists of various communication interface circuits and driver software that drives them. Specifically, when an intruder is detected by the control unit 38 described later, the communication unit 30 outputs an intrusion alarm signal indicating that the intruder 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. The photographing unit 32 acquires a photographed image by photographing the monitoring area. In the present embodiment, the photographing unit 32 photographs 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 46 is stored in the storage unit 34.

When an intruder exists in the monitoring area, the captured image 46 acquired by the photographing unit 32 includes a person area corresponding to the person (intruder).

The storage unit 34 is a storage unit 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 processing device 22. Further, as shown in FIG. 2, the storage unit 34 stores the installation status 40 of the photographing unit 32, the stable area 42, the background image 44, and the captured image 46. As a result, the storage unit 34 stores the installation status storage means for storing the installation status 40, the stable area storage means for storing the stable area 42, the background image storage means for storing the background image 44, and the captured image storage for storing the captured image 46. Functions as a means.

The installation status 40 is information indicating a status in which the photographing unit 32 is installed. For example, a worker who installs the image processing device 22 measures the installation height H and the depression angle θ in which the photographing unit 32 is installed as shown in FIG. 3, and inputs the installation height H and the depression angle θ to the image processing device 22. Then, it is stored in the storage unit 34 as the installation status 40. Further, the depression angle θ and the installation height H may be acquired by automatic measurement. For example, a sensor such as a distance sensor may be used to measure the depression angle θ and the installation height H. The installation height H indicates, for example, the height from the floor surface to the image processing device 22, and the depression angle θ is, for example, the inclination of the horizontal plane and the optical axis of the image processing device 22 (angle information in the vertical direction of the image processing device 22). ) Is shown.

The stable region 42 indicates an image region in which a person to be detected is determined not to exist by the stable region determining means 54 described later. The background image 44 is an image that serves as a reference for performing background subtraction with the captured image 46, and is created by the control unit 38 based on the captured image 46 when no person exists in the monitoring area. The background image 44 may be one, but a plurality of background images 44 may be created.

The control unit 38 has a built-in microprocessor unit, memories such as ROM and RAM, and peripheral circuits thereof, and executes various signal processing of the image processing device 22. As shown in FIG. 2, the control unit 38 exerts functions as a determination period setting means 50, an extraction means 52, a stable area determination means 54, a person determination means 56, and a background image update means 58. When the control unit 38 exerts these means, the human area, which is an image area corresponding to the person to be detected, is detected in the captured image 46. Hereinafter, each means included in the control unit 38 will be described.

The determination period setting means 50 performs a process of setting a determination period for determining the stable area 42 based on the installation status 40, and makes the determination period set different according to the position on the captured image. The control unit 38 reads out the installation status 40 stored in advance in the storage unit 34, assumes that the entire captured image captured by the photographing unit 32 is the floor surface, and starts from the installation height H and the depression angle θ of the photographing unit 32. The distance L between the optical center of 32 and the floor surface is calculated for each pixel. For example, the distance L is calculated from the installation height, depression angle, and angle of view using the reverse perspective transformation. The method for calculating the distance L between the photographing unit 32 and the floor surface is not particularly limited, and a known method can be applied. Then, a determination period for determining a stable region is set for each pixel of the captured image 46 from the installation height H of the installation status 40 and the calculated distance L between the optical center of the photographing unit 32 and the floor surface as the depression angle θ. At this time, the smaller the depression angle θ, the longer the determination period is set. Further, the determination period is set longer as the installation height H approaches the reference value according to the height of the detection object. If the object to be detected is a person, the reference value according to the height of the object to be detected may be a value of about the height of the person, and may be set to, for example, 200 cm. Further, the determination period is set longer as the distance L from the floor surface assumed to be the photographing unit 32 increases. In addition, the installation height is usually not installed at a height lower than the detection target, but if it is installed lower, it may be considered that it is installed at the reference value when setting the judgment period. .. The determination period may be set not for each pixel but for each image area.

For example, the determination period is set based on the mathematical formula (1). In the present embodiment, the determination period is set to a value obtained by adding an adjustment value according to the coefficient W set based on the depression angle θ, the installation height H, and the distance L to each pixel with reference to 10 frames.

Judgment period = 10 [frame] + 10 [frame] x coefficient W ... (1)

Here, the coefficient W is calculated based on the coefficient X according to the depression angle θ, the coefficient Y according to the installation height H, and the coefficient Z according to the distance L between the photographing unit 32 and the floor surface. For example, the coefficient X is a value obtained by converting a range in which the depression angle θ is 36 ° to 45 ° into a numerical value of 1 to 0. Specifically, for example, the coefficient X is set to 1 if the depression angle θ is less than 36 °, 0 if it is larger than 45 °, and a value that decreases from 1 to 0 in the range of 36 ° or more and 45 ° or less. Further, for example, the coefficient Y is a value obtained by converting a range in which the installation height H is 200 cm to 350 cm into a numerical value of 1 to 0. Specifically, for example, the coefficient Y is set to 1 if the installation height H is less than 200 cm, 0 if it is larger than 350 cm, and a value that decreases from 1 to 0 in the range of 200 cm or more and 350 cm or less. Further, for example, the coefficient Z is a value obtained by converting the range in which the distance L between the photographing unit 32 and the floor surface is 500 cm to 1000 cm into 0 to 1. Specifically, for example, the coefficient Z is set to 0 if the distance L is less than 500 cm, 1 if it is larger than 1000 cm, and a value that increases from 0 to 1 in the range of 500 cm or more and 1000 cm or less. The coefficient W (= X × Y × Z) is calculated by multiplying the coefficient X, the coefficient Y, and the coefficient Z calculated in this way.

By such processing, as shown in FIG. 4, the determination period can be set corresponding to each pixel of the captured image 46. In FIG. 4, the determination period is set to 10 frames in the image region of the captured image close to the photographing unit 32, and the determination period is set to 11 to 19 frames and 20 frames as the distance from the photographing unit 32 increases. That is, the closer the pixel is to the vanishing point on the captured image, the longer the determination period is set. In the captured image, the determination period of the region in front of the vanishing point may be set longer as it approaches the vanishing point, and the determination period of the region farther than the vanishing point may be the same length as the vanishing point. For example, as shown in FIG. 4, in the image region (lower region on the image) close to the photographing unit 32, the determination period gradually becomes longer as the distance from the photographing unit 32 increases, and the determination period after the vanishing point (upper side of the image) Area) is set to the same length. The vanishing point may exist on the captured image or may not exist on the captured image but may exist on the imaging surface. In either case, the closer the pixel is to the vanishing point, the longer the determination period may be set. Further, instead of calculating the determination period based on the above-mentioned mathematical formula (1), the length of the determination period may be set differently for each pixel from the position of the vanishing point in the captured image.

However, the method of setting the determination period is not limited to the above method, and the smaller the depression angle θ and the closer the installation height H is to the value corresponding to the height of the detection object, the more the photographing unit 32 and the floor surface are set. Any method may be used as long as the distance L increases and the determination period becomes longer. That is, when the depression angle θ is small, the area of the image area for which the determination period is set to be longer is larger than when the depression angle θ is large, and the larger the installation height H is higher than the reference value according to the height of the detection object, the longer the determination period is. The determination period is set longer as the area of the image area set to be shorter is larger and the image area farther than the image area where the distance L between the photographing unit 32 and the floor surface is short. When determining only by the installation height H, this process is effective when the height of the installation height H is changed while the same area is photographed as the monitoring area to be photographed. The determination period may be set using only the depression angle θ, only the installation height H, or only the distance L.

When the lens of the photographing unit 32 is distorted, it is preferable to set the reference range with respect to the depression angle θ in consideration of the distortion of the lens. For example, the reference range of 36 ° to 45 ° for obtaining the coefficient X may be changed according to the distortion of the lens. Further, the determination period may be set based not only on the depression angle θ and the installation height H, but also on the angle of view, zoom rate, and the like of the photographing unit 32. Further, the determination period may be set based on the inclination information of the floor surface acquired from the topographical data of the monitoring space (3D data of the monitoring space, etc.).

Further, in the present embodiment, the determination period is set by the number of frames, but it may be set as the time. For example, the determination period = 10 [seconds] + 10 [seconds] × coefficient W may be set.

The extraction means 52 extracts the first difference region based on the background difference between the captured image 46 and the background image 44. Using one of the sequentially captured images 46 as the target image, the target image and the background image 44 stored in advance in the storage unit 34 are compared, and a change region composed of pixels different between the two images is extracted. The binary image (change area image) is obtained. Here, the "pixels different between the two images" mean the pixels of the captured image 46 in which the difference in luminance value or color component between the captured image 46 and the background image 44 is equal to or greater than a predetermined value.

Then, it is determined whether or not the extracted change area is the image area of the stable area 42 stored in the storage unit 34. When the change region is determined to be the stable region 42, it is not extracted as the first difference region, and when it is determined that the change region is not the stable region 42, it is extracted as the first difference region.

For example, as shown in FIG. 5, the background image 44 includes a region A1 showing a closed door, and the captured image 46 includes a region B1 showing a door opened and leaking outside light. It is assumed that the area B2 showing a person who has invaded the surveillance space is included. When the captured image 46 is used as the target image, the image regions corresponding to the regions B1 and B2 are extracted as the change region C1 and the change region C2, respectively, by background subtraction processing with the background image 44. Here, when the change area C1 is already stored in the storage unit 34 as the stable area 42, the change area C1 is not extracted as the first difference area, and only the change area C2 corresponding to the area B2 in which a person is copied is the first. 1 Extracted as a difference region D2.

The stable region determination means 54 performs a process of determining whether or not the first difference region is the stable region 42 when the first difference region is extracted by the extraction means 52. A second difference region (inter-frame difference region) is extracted by comparing the captured image 46 captured immediately before or after the target image with the target image. When the second difference region is extracted, the first difference region and the second difference region are compared, and the pixels extracted as the first difference region over the determination period set by the determination period setting means 50. The pixels that have not been extracted as the second difference region during the determination period are set as the stable region 42. The set stable region 42 is stored in the storage unit 34 and excluded from the processing target by the person determining means 56. If the second difference region is not extracted, it is not set as the stable region 42, and the process shifts to the processing by the person determining means 56 as the moving body region by a moving person or the like. The captured image 46 to be compared with the target image for extracting the second difference region may be two frames or more before or two or more frames after, as long as the target image is not too far from the time when the target image was captured. In addition, the image captured after the target image is not in real time but in terms of time compared to the target image when the intruder determination process is performed using the target image which is a captured image several seconds before the real time. It is a photographed image taken later.

For example, when the change region C1 is not the stable region 42 in FIG. 5, the change regions C1 and C2 are extracted as the first difference regions D1 and D2 as shown in FIG. The image area corresponding to the change area C1 showing the door that does not move in the inter-frame difference image between the photographed image 46 which is the target image and the photographed image 46 photographed before and after is not extracted as the second difference area and is a moving person. The image region corresponding to the change region C2 in which the image is copied is extracted as the second difference region E2. Therefore, even if the determination period set by the determination period setting means 50 is used as the reference time and extracted as the first difference region D1, the region that is not extracted as the second difference region beyond the determination period is caused by an object that does not move. It is set as the stable region 42. On the other hand, the area extracted as the first difference area D2 and further extracted as the second difference area E2 beyond the determination period is processed by the person determination means 56 as a moving body area caused by a moving person or the like.

Here, by setting the determination period according to the installation status 40 of the photographing unit 32 in the determination period setting means 50, it seems that the image 46 is actually moving but not moving and is stationary. It is possible to prevent the visible image area from being mistakenly set as the stable area 42. That is, by setting the determination period set for each pixel of the captured image longer in the captured image, the image region in which the image region is captured farther than the image region captured near the photographing unit 32 is set. It is possible to prevent accidentally setting the stable region 42. For example, the smaller the depression angle θ from the photographing unit 32, the closer the installation height H is to the value corresponding to the height of the object to be detected, and the farther the distance L between the photographing unit 32 and the floor surface is, the more the moving object is stationary. By setting the determination period longer, it is difficult to set the image region in which the moving object is captured as the stable region 42 because it becomes easier to see the image. As a result, it is possible to prevent the image region in which a moving object such as a person is captured from being erroneously determined as the stable region 42, and to set the stable region 42 with higher accuracy.

The person determining means 56 determines whether or not the first difference region extracted by the extracting means 52 is a person. As a method for determining a person in the person determining means 56, various known methods can be applied. For example, feature information representing the characteristics of a person to be detected is stored in the storage unit 34 in advance, and the first difference area is a person depending on whether or not the first difference area satisfies the feature represented by the feature information. It can be determined whether or not it is. The feature information may be, for example, information such as whether or not the image region has a human-like size or shape. Further, for example, whether or not a labeling process for assigning an identifier (label) to the first difference region is performed and the movement of the first difference region with the same label over a plurality of frames satisfies the characteristics of human movement. It is also possible to determine whether or not the change area is a person.

When the first difference region is determined to be a person, the person determination means 56 notifies an abnormality via the communication unit 30 to end the intruder detection process, and when it is determined that the person is not a person, the person determination means 56 notifies the person. The intruder detection process is terminated without any notice.

The background image updating means 58 updates the background image 44 based on the captured image 46 when the condition for updating the background image 44 is satisfied. The condition for updating the background image 44 is, for example, that the background image 44 is not updated beyond the preset update reference period, and the captured image 46 captured before or after the target image is compared with the target image. When the extracted second difference region (interframe difference region) is equal to or less than the threshold value over the update reference period, the target image is updated as the background image 44.

Here, the length of the renewal reference period may be set according to the determination period set by the determination period setting means 50. For example, if there is an image area with a determination period of 10 frames, the update reference period may be 30 frames, and if there is an image area with a determination period of 20 frames, the update reference period may be 60 frames.

Hereinafter, the flow of the determination period setting process will be described with reference to the flowchart shown in FIG.

In step S10, the distance L between the photographing unit 32 and the floor surface is calculated based on the depression angle θ and the installation height H included in the installation status 40. Then, in step S12, a determination period for determining the stable region 42 for each pixel of the captured image 46 is set based on the depression angle θ, the installation height H, and the calculated distance L.

Hereinafter, the flow of the intruder determination process will be described according to the flowchart shown in FIG.

In step S20, a first difference region is extracted by performing background subtraction using the target image and the background image 44. In step S22, if the first difference region is extracted in step S20, the process shifts to step S24, and if it is not extracted, the intruder determination process ends. In step S24, the second difference region is extracted by the difference between frames. In step S26, the first difference region and the second difference region are compared, the first difference region is extracted over the determination period set in the determination period setting process, and the second difference region is not extracted. Is determined to be the stable region 42. In step S28, it is determined whether or not the first difference region that has not been determined to be the stable region 42 remains. If the first difference region remains, the process shifts to step S30, and if it does not remain, the intruder determination process ends. In step S30, it is determined whether or not the first difference region, which is not determined to be the stable region 42, is an image region in which a person is photographed, and if it is a person, an alarm is issued. If it is not a person, the intruder determination process is terminated.

The photographing unit 32 may be an omnidirectional camera capable of setting an omnidirectional (360 degrees) as a photographing area (surveillance area). The omnidirectional camera is installed, for example, on the ceiling of the property 12 to be monitored, the monitoring area is downward, and the optical center is substantially vertically downward. The captured image 46 captured by the photographing unit 32, which is an omnidirectional camera, is an omnidirectional image, and is a circular image as a whole, and the center of the circle is a position corresponding to the optical center. Then, in the captured image 46, the vertically upward direction of the monitoring region is the radial direction of the captured image 46 and is the direction from the optical center to the outside, and the horizontal direction of the monitoring region is the circumferential direction of the captured image 46. When installing in the monitoring area, when the depression angle is fixed (for example, 90 degrees) and installed on the ceiling, and an omnidirectional camera whose optical center is perpendicular to the floor surface is applied, the installation height H and distance excluding the depression angle θ The determination period may be set based on L. When the omnidirectional camera is installed so that the optical center is perpendicular to the floor surface, the determination period is set longer in the image area near the circumference than in the image area near the center of the captured image 46.

The image processing device 22 is not limited to the one that performs image processing on the image stored in the storage unit 34 in the own device. For example, an image read from another external device may be image-processed, or an image received from an external camera may be image-processed.

As described above, according to the present embodiment, it is possible to suppress the erroneous determination of the image region in which the moving object to be detected by a person or the like is captured as the stable region 42, and to set the stable region 42 with high accuracy. ..

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.

10 Security system, 12 Monitored property, 14 Security device, 16 Communication network, 18 Security center device, 20 User device, 22 Image processing device, 24 Recording device, 30 Communication unit, 32 Imaging unit, 34 Storage unit, 38 Control Unit, 40 Installation status, 42 Stable area, 44 Background image, 46 Captured image, 50 Judgment period setting means, 52 Extraction means, 54 Stable area determination means, 56 Person judgment means, 58 Background image update means.

Claims (6)

An image processing device that detects a moving body area indicating an image area of a moving body from a predetermined target image among the shot images in which a predetermined space is sequentially shot by the shooting device.
The first difference region extracted by comparing the target image with the background image obtained by capturing the background of the predetermined space, and the captured image captured before or after the target image are compared with each other. An image in which the second difference region is not extracted during the determination period and the image region from which the first difference region is extracted is set as a stable region that is not detected as the moving body region. Equipped with processing means
The image processing apparatus, characterized in that the determination period is set to a different length depending on the position on the captured image. The image processing apparatus according to claim 1.
The image processing apparatus, characterized in that the determination period is set longer as the position closer to the vanishing point in the captured image. The image processing apparatus according to claim 1 or 2.
The image processing is characterized in that when the installation height of the photographing device is higher than the reference value corresponding to the height of the moving body, the determination period is set shorter than the case where the installation height is the reference value. apparatus. The image processing apparatus according to any one of claims 1 to 3.
An image processing device characterized in that the determination period is set longer as the depression angle of the photographing device is smaller. The image processing apparatus according to any one of claims 1 to 4.
Based on the installation height of the photographing device, the distance from the optical center of the photographing device to the position of the floor surface corresponding to each region or each pixel of the photographed image is calculated assuming that the entire photographed image is the floor surface. An image processing apparatus, characterized in that a region having a large distance or a pixel has a longer determination period. An image processing program that detects a moving body area indicating an image area of a moving body from a predetermined target image among captured images in which a predetermined space is sequentially shot by a shooting device.
Computer,
The first difference region extracted by comparing the target image with the background image obtained by capturing the background of the predetermined space, and the captured image captured before or after the target image are compared with each other. An image in which the second difference region is not extracted during the determination period and the image region from which the first difference region is extracted is set as a stable region that is not detected as the moving body region. To function as a processing means,
An image processing program characterized in that the determination period is set to a different length depending on the position on the captured image.