JPH10285586A - Image processor, monitoring image display system, image processing method and monitoring image display method - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an image processor and an image processing method for processing images obtained by picking up the images and automatically detecting the presence/absence of a neglected object and to provide a monitoring image display system and a monitoring image display method capable of easily and surely confirming the presence/absence of the neglected object. SOLUTION: The images photographed in an image input part 1 are time sequentially stored in an image recording part 2. A neglected object detection part 3 prepares comparison images for which a moving object is eliminated from the images by fetching the plural time sequentially continuous recording images and integrating them. Then, by extracting the different area of reference images stored in a reference image management part 3 and the comparison images, the neglected object or a lost object is detected.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an image processing apparatus and an image processing method for detecting an abandoned object or a lost object from a captured image, and to an image processing apparatus in a public place such as a station or an airport. Also, the present invention relates to a surveillance image display system and a surveillance image display method for monitoring a neglected object or a lost object by applying an image processing method.

[0002]

2. Description of the Related Art Conventionally, in public places such as train stations and airports where a large number of people enter and leave, monitoring has been carried out to check for missing luggage or leaving dangerous goods. Common monitoring methods include:
A surveillance camera is installed at the surveillance location, and a display device for displaying images captured by the surveillance camera is provided in the surveillance room. Is monitoring.

[0003]

By the way, in consideration of a case where a dangerous substance is left, it is necessary to respond quickly to the left.

[0004] However, conventionally, since only the image taken by the surveillance camera is displayed on the display device, the guard cannot easily determine the presence or absence of the neglected object from the displayed image. For this reason, it takes a long time for security guards to check for abandoned objects on the screen,
In some cases, it was not possible to respond quickly to an abandoned object.

An object of the present invention is to provide an image processing apparatus and an image processing apparatus for processing an image obtained by imaging in time series and a reference image to detect an abandoned object or a lost object in the imaged image area. It is to provide a method.

Further, the present invention is a monitoring image display system which can easily and surely confirm the presence or absence of an abandoned object by applying the image processing apparatus and the image processing method, and can quickly respond to an abandoned object. And a monitoring image display method.

[0007]

An image processing apparatus according to a first aspect of the present invention is configured such that an image obtained by imaging a predetermined area in time series is an image area different from a reference image of the predetermined area, and It is characterized by comprising extraction means for extracting an image area whose position does not change with time.

[0008] In this configuration, an image area of an object which is not present on the reference image and which is not moving in the captured image is extracted. That is, it is possible to extract a region where the abandoned object is imaged.

According to a second aspect of the present invention, the extraction means processes a plurality of images obtained by imaging a predetermined region in time series, and cancels a moving object from the image obtained by imaging the predetermined region. The comparison image and the reference image are means for extracting different image regions.

In this configuration, for example, a comparison image in which a moving object in a captured image is canceled is generated by integrating a plurality of images obtained by capturing a predetermined area in time series. Therefore, by extracting different image regions between the comparative image and the reference image, it is possible to extract the region where the neglected object has occurred.

According to a third aspect of the present invention, there is provided a storage device for storing, in association with the image area extracted by the extracting means, status information at the time of extracting the image area.

In this configuration, when an area where an abandoned object or a lost object has been extracted is extracted, the situation information at that time is stored in association with the area. Therefore, the situation when the abandoned object occurs is known from the situation information. be able to.

[0013] The invention described in claim 4 is characterized in that the status information is a time when the image area is extracted.

In this configuration, the time is stored as the situation information, so that the time when the abandoned object has occurred can be easily known.

According to a fifth aspect of the present invention, there is provided a recording means for recording an image of a predetermined area, and an output for extracting and outputting a corresponding image from the image recorded in the recording means using the status information as a key. Means.

In this configuration, a corresponding image is taken out from the image of the predetermined area recorded by the recording means, using the situation information as a key, and output. For example, if the time when this image area was extracted is stored as status information,
It is possible to output an image when an abandoned object occurs.

According to a sixth aspect of the present invention, in the image area extracted by the extracting means, an object in the reference image does not exist on the captured image or exists on the reference image. A determination unit is provided for determining whether an object is present on a captured image or not.

With this configuration, it is possible to determine whether a neglected object or a lost object has occurred by the determining means.

According to a seventh aspect of the present invention, when the determination by the determination means is that the object in the reference image does not exist on the captured image, the image in the reference image is determined. Reference image updating means for updating an area to an image area corresponding to a current image is provided.

In this configuration, when a lost object occurs, the image area of the lost object on the reference image is updated to the image area corresponding to the current image. Therefore,
When there are no more objects present on the reference image, the reference image can be automatically updated. Note that the current image referred to here is not the latest image captured at this time, but an image obtained by canceling a moving object obtained by processing the latest image.

According to an eighth aspect of the present invention, there is provided a surveillance image display system comprising the image processing apparatus according to any one of the first to sixth or seventh aspects, and further comprising an image area extracted by the extraction means and other parts. And a display device for displaying the image area separately from the image area.

In this configuration, since the image area in which the abandoned or lost object has occurred is displayed separately from the other image areas, the occurrence of the abandoned or lost object can be easily confirmed from this display. Therefore, it is possible to quickly respond to an abandoned object or a lost object.

According to a ninth aspect of the present invention, there is provided a surveillance image display system comprising the image processing apparatus according to any one of the first to sixth or seventh aspects, further comprising: Correspondingly, a display device is provided for displaying the time at which the image region was extracted or the elapsed time since the image region was extracted.

In this configuration, the time of occurrence or the elapsed time since the occurrence is displayed in association with the image area in which the abandoned or lost object has occurred, so that this can be easily known.

[0025]

FIG. 1 is a diagram showing a configuration of a monitoring image display system to which an image processing apparatus according to an embodiment of the present invention is applied. In the figure, reference numeral 1 denotes an image input unit including a surveillance camera for imaging a predetermined area. Reference numeral 2 denotes an image recording unit that records a captured image. Reference numeral 3 denotes a reference image management unit that stores a reference image of a predetermined area captured by the image input unit 1. The reference image is an image obtained by capturing the same area as the area captured by the image input unit 1, and is an image when there is no object (person or object) not placed in this area. . That is, the reference image is a background image of an image captured by the image input unit 1. Reference numeral 4 denotes a neglected object that compares a reference image created by processing a plurality of images (temporally continuous images) captured by the image input unit 1 with a reference image, and extracts an image region where the neglected object has occurred. It is a detection unit. Reference numeral 5 denotes an abandoned object information management unit that manages status information when the abandoned object detection unit 4 detects an abandoned object. Reference numeral 6 denotes a display control unit that controls the screen of the display unit 7. Reference numeral 8 denotes a designated image extracting unit that extracts an image at a designated time from the time-series image information stored in the image recording unit 2.

Next, the processing of the monitoring image display system according to this embodiment will be described. FIG. 2 is a diagram illustrating a process of the image recording unit according to the embodiment. The image recording unit 2 captures an image of a predetermined area captured by the image input unit 1 at predetermined time intervals, and accumulates and records the captured image in time series (n1, n2). For example, the image recording unit 2 captures an image captured every 5 seconds and accumulates and records the image in chronological order. In this way, the image recording unit 2 stores the images captured by the image input unit 1 at predetermined time intervals in chronological order.

FIG. 3 is a flowchart showing the processing of the abandoned object detection unit according to this embodiment. The neglected object detection unit 4 captures a predetermined number of images that are temporally continuous from the latest image recorded in the image recording unit 2 (n11).
The predetermined number of images are integrated to generate a comparison image in which the moving object is canceled from these images (n12). That is, the comparison image created in n12 is an image obtained by removing a moving person or object from the image captured by the image input unit 1. Therefore, if the comparison image matches the above-described reference image, no neglected object exists in the image area captured by the image input unit 1.

Therefore, the comparison image created in n12 is compared with the reference image stored in the reference image management unit 3 for each pixel, and the coincident pixels are outlined (n13, n1).
4). In n13, the difference between the reference image and the comparison image is calculated for each of the RGB ratio, hue, brightness, and vividness. If the difference is equal to or smaller than a preset reference value, the values match. If it exceeds the value, it is determined that they do not match. Then, the image created in n14 is divided into rectangles of a preset size (n15), the density of white pixels is calculated for each rectangle, and the density of the rectangle exceeding this set value is calculated. Are all white (n1
6). No processing is performed on pixels within a rectangle whose density is equal to or less than the set value. Next, the presence or absence of a neglected object is determined based on the degree of collection of rectangles that are not outlined (n17). In n17, an area in which a predetermined number of rectangles not blanked out in a predetermined range is determined as an area where a neglected object exists. Here, if there is no area where it is determined that an abandoned object is present, the process ends. On the other hand, if there is an area where the abandoned object exists, the outline of the abandoned object is determined from the collection of rectangles that are not outlined (n18). Then, the area where the abandoned object exists, the current time, the comparison image, and the like are output as the abandoned object information (n19). If there are a plurality of areas where abandoned objects are present, the processing of n18 and n19 described above is performed for each area.

As described above, the abandoned object detection unit 4 generates a comparison image in which a moving object is canceled from a predetermined number of temporally consecutive images captured by the image input unit 1, and generates a reference image and a comparison image. , A different image area is extracted, and it is determined that an abandoned object exists in this image area. For this reason,
A moving person or the like is not detected as an abandoned object.

The outline of the neglected object may be obtained from the image created in n14. However, since the outline of the neglected object is obtained from the collection of points (pixels), the outline of the neglected object is obtained. Lines cannot be determined with high accuracy. Therefore, in the present embodiment, n15 and n
Sixteen processes are provided, and the outline of the neglected object is determined from the degree of collection of rectangles of an appropriate size.

FIG. 4 is a flowchart showing the processing of the neglected object information management unit according to this embodiment. When the abandoned object information is input from the abandoned object detection unit 4 (n21), the abandoned object information management unit 5 determines whether or not the abandoned object is a newly detected abandoned object (n22). The abandoned object information management unit 5 includes a status information storage area that stores an area that exists for each abandoned object included in the abandoned object information, a detection time, and the like in association with each other. FIG. 5 is a diagram showing a configuration of the status information storage area. In the situation information storage area, the existence area of the neglected object is stored based on the coordinate data of the outline of the neglected object. In n22, it is determined whether or not the existence area of the neglected object to be determined is already stored in the situation information storage area to determine whether it is a newly detected neglected object. Here, if there is an abandoned object in a substantially matching area in the situation information storage area, it is a previously detected abandoned object. On the other hand, if there is no abandoned object in a substantially matching area in the situation information storage area, it is a newly detected abandoned object. If there is a newly detected abandoned object, the area, the current time (detection time), and the like are stored as status information in the status information storage area based on the input abandoned object information (n23). The neglected object information management unit 5 outputs the status information of the neglected object included in the neglected object information input in n21 (n24). In n24, not only the newly detected neglected object but also the status information of the previously detected neglected object is output. The status information output in n24 is input to the display control unit 6.

FIG. 6 is a flowchart showing the processing of the display control unit according to this embodiment. The display control unit 6
It is determined whether or not there is information on abandoned objects for which a predetermined time has not elapsed since the detection (n31). This is determined from the detection time of each abandoned object. Here, if there is no abandoned object for which a predetermined time has not elapsed since the detection, the latest image recorded in the image recording unit 2 is taken and input to the display unit 7 as display data (n36, n37). ). On the other hand, if there is an abandoned object for which a predetermined time has not elapsed since the detection, an image of an area where the abandoned object exists is extracted from the comparison image (n32). Then, the latest image recorded in the image recording unit 2 is fetched (n33), and the image extracted in n32 is superimposed on the latest image fetched here (n34). Further, data (situation information display data) for displaying the time when the corresponding abandoned object is detected is added near the portion where the extracted images are superimposed (n35). Image information obtained by performing the above-described processing of n34 and n35 on the latest image captured in n33 is input to the display unit 7 as display data (n3
6). The display unit 8 performs display based on the display data input from the display control unit 7.

FIG. 7 is a diagram showing an example of a display screen on the display unit 8. FIG. 7A is a display image when no abandoned object is detected. In this figure, it is assumed that the object A shown at the lower right is left at this time. After a certain time,
The object A shown in the lower right of FIG. 7A is detected as a neglected object. At this time, as shown in FIG. 7B, an image obtained by superimposing the image of the abandoned object (object A) on the latest image captured by the image input unit 1 is displayed on the display unit 7 as shown in FIG. I do. In addition, the detection time is also displayed near the displayed neglected object. As described above, since the detected neglected object is superimposed and displayed on the latest image, there is no problem that the neglected object cannot be seen on the screen due to crowding or the like. Further, since the detection time is displayed in correspondence with the image area of the abandoned object, the time at which the object A was abandoned can be immediately confirmed. In addition, since the abandoned object that has passed a predetermined time after detection is not displayed,
A large number of neglected objects are displayed on the screen, and there is no problem that the screen is difficult to understand. In addition, a blinking display is performed around the abandoned object, so that a security guard who sees this display can easily confirm the occurrence of the abandoned object. In this way, by making the display form of the detected area of the neglected object different from that of the other areas, it is possible to alert the security guard to the detected neglected object. Therefore, the security guard can take a quick response to the abandoned object.

It is to be noted that a function may be provided to prevent a displayed object from being displayed on the screen when a specific operation is performed, even for an abandoned object for which a predetermined time has not elapsed since the detection. Further, although the time at which the abandoned object is detected is displayed, the elapsed time from the detection may be displayed.

FIG. 8 is a diagram showing the processing of the designated image extracting unit 8 according to this embodiment. A cursor is displayed on the display screen, and the guard can move the cursor to specify an arbitrary position. When an arbitrary position on the display screen is designated, the designated image extracting unit 8 determines whether an abandoned object exists at that position (whether an abandoned object is designated) (n41). When it is determined that the abandoned object is specified, the status information of the specified abandoned object is fetched from the abandoned object information management unit 5 (n42). The time at which the abandoned object is detected is read from the status information (n43). The designated image extracting unit 8 extracts the image (image at the time of detection) obtained at n43 from the images recorded in time series in the image recording unit 2 (n44), and inputs the image at the time of detection to the display control unit 6. (N45). Display control unit 6
When the image at the time of detection is input, the processing shown in FIG. 5 is interrupted, and the image at the time of detection is displayed on the display unit 7.

As described above, the designated image extracting section 8 takes out the image when the abandoned object is detected when the abandoned object displayed on the screen is designated, and displays the image on the display section 7. Therefore, it is possible to easily confirm the situation when the abandoned object is abandoned and the abandoned person. Therefore,
If the abandoned object is a lost or lost item, the owner of the abandoned object can be easily confirmed. In addition, we can confirm whether abandoned object is dangerous substance from situation that was left alone,
Respond quickly to dangerous goods.

It should be noted that the abandoned object detection unit 4 may output an alarm when a new abandoned object is detected. The alarm may be output by sounding or sounding a buzzer to notify the guard that the neglected object has been detected, or by driving a patrol lamp or the like to notify the guard by light. You may make it notify that it was detected. In this way, the guard can respond more quickly to the abandoned object. In addition, the image other than the detected abandoned object may be displayed in monochrome, and the image of the abandoned object may be displayed in color to emphasize the display of the abandoned object on the screen of the display unit 7. Further, a function of enlarging and displaying the image of the neglected object on the screen of the display unit 7 may be provided. In this way, even if a small object is left, the left object can be easily confirmed on the screen of the display unit 7.

Next, another embodiment of the monitoring image display system according to the present invention will be described. FIG. 9 is a diagram showing the configuration of the monitoring image display system according to this embodiment. In this figure, components that perform the same processing as the components described in FIG. 1 are denoted by the same reference numerals. The surveillance image display system according to this embodiment has the same configuration as the surveillance image display system shown in FIG. 1 except that a lost object detection unit 11 for detecting a lost object and a reference image managed by the reference image management unit 3 are added. This is a configuration in which a reference image updating unit 12 for updating is added. The surveillance image display system of this embodiment detects an abandoned object by the same processing as in the above-described embodiment. Further, an object (lost object) that has been moved from within the imaging area of the image input unit 1 can also be detected.
In the monitoring image display system according to this embodiment,
The process of detecting an abandoned object is the same as in the above embodiment. Here, the description of the process of detecting an abandoned object will be omitted, and the process of detecting a lost object will be described.

The lost object detector 11 has a mounted object information storage area shown in FIG. The mounted object information storage area stores a movable object (for example,
An area on the reference image is stored for each mounted object such as a flowering plant or a chair. In addition, it has a storage area for storing the lost time (lost time) in association with each object.

FIG. 11 is a flowchart showing the processing of the lost object detection unit according to this embodiment. When the status information of the newly detected abandoned object is stored in the abandoned object information management unit 5, the lost object detection unit 11 takes in the area where the abandoned object exists (n51). Then, n5 is included in the mounted object stored in the mounted object information storage area.
It is determined whether or not there is an area that substantially matches the area captured in step 1 (n52). If there is a thing in the same area at n52, this means that some object has not been abandoned,
The mounted object that originally existed at that location was moved. That is, the originally placed object has been lost. If the lost object detection unit 11 determines that there is an object in the same area in n52, the lost object detection unit 11 takes in the situation information on this object stored in the neglected object information management unit 5 and deletes it (n53). Then, the lost time and the like are stored for the object in the mounted object information storage area (n54). The lost time and the like are stored in n5
This is performed based on the status information captured in step 3.

As described above, the provision of the lost object detection unit 11 can detect not only that the object has been abandoned, but also that the originally existing object has been lost. If there is no object in the same area in n52, the detected object is a neglected object. The same processing as in the above-described embodiment is performed on an abandoned object.

FIG. 12 is a flowchart showing the processing of the reference image updating unit according to this embodiment. When the lost object detection unit 11 detects a lost object (n61), the reference image update unit 12 captures the reference image from the reference image management unit 3 and captures the comparison image used for detecting the lost object (n62). , N63). Then, on the reference image, the image of the area where the detected lost object was present is replaced with the image of the area corresponding to this comparison image (n64). For example, when the reference image is the one shown in FIG. 13A, and the object B shown in the figure is detected as a lost object, the reference image is converted into the one shown in FIG.
The image is updated to the image shown in (B).

As described above, when the originally placed object is lost, the reference image updating unit 12 updates the reference image. Therefore, after the mounted object is lost,
Even when a new object is left at that location, it can be detected as a left object. Note that the display control unit 6 causes the display device 7 to display the lost object in a highlighted manner for a certain period of time. At this time, the image of the lost object is extracted from the corresponding area of the reference image.

In the above two embodiments,
The configuration of the reference image management unit 3 may be changed to the configuration shown in FIG. The reference image management unit 3 according to this embodiment includes a reference image storage area 21 and a reference image selection unit 22. Here, the image captured by the image input unit 1 is in the morning,
In daytime, evening, night, and the like, the brightness and the like of an image captured by disturbance light change. Therefore, if the reference image is always the same, there is a high possibility that an abandoned object or a lost object is erroneously detected due to a change in the brightness of the disturbance light. Therefore, in this embodiment, a plurality of reference images based on the difference in time are stored in the reference image storage area 21. Further, the reference image selecting unit 22 selects one appropriate reference image from the plurality of reference images stored in the reference image storage area 21 according to the time at that time. This makes it possible to accurately detect an abandoned object or a lost object without increasing the possibility of erroneously detecting an abandoned object or a lost object due to a change in brightness due to disturbance light. It is also possible to store a reference image having a different weather, an open / closed state of the door, an open / closed state of the shutter, and the like, and appropriately select the reference image selecting unit 22 according to the state at that time.

Further, the image input unit 1 may be provided with a function of switching the imaging range, and the reference image for each imaging range may be stored in the reference image storage area 21. This makes it possible to detect an abandoned object by switching the imaging range of the image input unit 1, so that a wide range of monitoring can be performed.

Next, an application example of the device according to the present embodiment will be described. (1) If the image input unit 1 is installed on a road and an image of a parked car is taken, illegal parking can be detected, and the time and effort required to control illegal parking can be reduced. (2) If the image capturing area of the image input unit 1 is within a railroad crossing, a car or a person stuck in the railroad crossing can be detected, and an accident at the railroad crossing can be prevented.

(3) If the imaging area of the image input unit 1 is set in a cage of a zoo, an animal that cannot move due to illness or injury can be detected, and treatment for such an animal can be performed quickly. become able to.

[0048]

As described above, according to the first and tenth aspects of the present invention, an image obtained by imaging a predetermined area in time series and an image of the predetermined area are different from each other in time. By extracting the image area that has not changed to the above, the area where the neglected object has occurred can be accurately detected.

According to the second and eleventh aspects of the present invention, a moving object such as a person is erroneously detected as an abandoned object by creating a comparison image in which a moving object in a captured image is canceled. There is no.

According to the third and twelfth aspects of the present invention, when an area in which an abandoned object or a lost object has been extracted is extracted, the situation information at that time is stored in association with the extracted area. You can easily know the situation when you did.

According to the fourth and thirteenth aspects of the present invention, the time is stored as the situation information, so that the time at which an abandoned object or a lost object has occurred can be easily known.

According to the fifth and fourteenth aspects of the present invention, it is possible to easily confirm an image when an abandoned object or a lost object is generated from the image recording unit based on the situation information.

According to the sixth and fifteenth aspects of the present invention, it is possible to determine whether an abandoned object or a lost object has occurred by the determining means.

According to the inventions described in claims 7 and 16, when the object existing on the reference image is lost (when a lost object is generated), the reference image can be automatically updated.

According to the inventions described in claims 8 and 17, since the image area in which the neglected object or the lost object has occurred and the other image area are displayed separately, the occurrence of the neglected object or the lost object can be easily determined from this display. You can check. Therefore, it is possible to quickly respond to an abandoned object or a lost object.

According to the ninth and eighteenth aspects of the present invention, the time of occurrence or the elapsed time since the occurrence is displayed in association with the image area in which an abandoned object or a lost object has occurred. You can know.

[Brief description of the drawings]

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

FIG. 2 is a flowchart illustrating a process of an image recording unit according to the embodiment;

FIG. 3 is a flowchart illustrating processing of a neglected object detection unit according to the embodiment;

FIG. 4 is a flowchart illustrating processing of a reference image management unit according to the embodiment.

FIG. 5 is a diagram showing a configuration of a situation commercial law storage area.

FIG. 6 is a flowchart illustrating a process of a display control unit according to the embodiment;

FIG. 7 is a diagram illustrating a display example on a display device.

FIG. 8 is a flowchart illustrating processing of a designated image extracting unit according to the embodiment.

FIG. 9 is a diagram showing a configuration of a monitoring image display system according to another embodiment of the present invention.

FIG. 10 is a diagram showing a configuration of a lost object information storage area.

FIG. 11 is a flowchart illustrating processing of a lost object detection unit according to the embodiment;

FIG. 12 is a diagram showing processing of a reference image updating unit according to the embodiment.

FIG. 13 is a diagram showing reference images before and after updating.

FIG. 14 is a diagram showing a configuration of a reference image management unit according to another embodiment of the present invention.

[Explanation of symbols]

 1-Image input unit 2-Image recording unit 3-Reference image management unit 4-Abandoned object detection unit 5-Abandoned object information management unit 6-Display control unit 7-Display unit 8-Designated image extraction unit 11-Lost object detection unit 12-Reference image update unit

Claims (18)

[Claims] An extracting unit configured to extract an image area different from a reference image of the predetermined area and whose position does not change with time from an image obtained by imaging the predetermined area in time series. An image processing apparatus characterized by the above-mentioned. 2. The image processing apparatus according to claim 1, wherein the extracting unit processes a plurality of images obtained by imaging the predetermined area in time series, creates a comparison image in which a moving object is canceled from the image obtained by imaging the predetermined area, and 2. The image processing apparatus according to claim 1, wherein the image processing unit extracts a different image area from the reference image. 3. The image processing apparatus according to claim 1, further comprising a storage unit configured to store, in association with the image region extracted by the extraction unit, status information at the time of extracting the image region. Image processing device. 4. The image processing apparatus according to claim 3, wherein the status information is a time when the image area is extracted. 5. A recording device for recording an image obtained by capturing an image of a predetermined area, and an output device for extracting and outputting a corresponding image from an image recorded on the recording device using the status information as a key. The image processing apparatus according to claim 3, wherein: 6. An image in which, for the image area extracted by the extracting means, whether an object in the reference image does not exist in the image in which the object is imaged or an image in which an object not existing in the reference image is imaged. The image processing apparatus according to claim 1, further comprising: a determination unit configured to determine whether the image is present on the image processing apparatus. 7. When the determination by the determination means is that an object in the reference image does not exist in the captured image, the image area in the reference image corresponds to the current image. 7. The image processing apparatus according to claim 6, further comprising a reference image updating unit that updates an image area to be updated. 8. A display device, comprising: the image processing device according to claim 1; and a display device that distinguishes and displays an image region extracted by the extraction unit from another image region. A surveillance image display system, which is provided. 9. An image processing apparatus according to any one of claims 1 to 6, or 7, further comprising:
A surveillance image display system comprising a display device for displaying a time at which the image area is extracted or an elapsed time since the image area is extracted. 10. An image processing method for extracting, from an image obtained by imaging a predetermined area in time series, an image area different from the reference image of the predetermined area and whose position does not change with time. 11. A method for processing a plurality of images obtained by imaging a predetermined area in time series, creating a comparison image in which a moving object is canceled from the image obtained by imaging the predetermined area, and comparing the comparison image with the reference image. The image processing method according to claim 10, wherein different image regions are extracted. 12. The image processing method according to claim 10, wherein the extracted image area is stored in association with status information at the time of extracting the image area. 13. The image processing method according to claim 12, wherein a time at which the image area is extracted is stored as the status information. 14. An image obtained by capturing an image of a predetermined area, and extracting and outputting a corresponding image from the recorded image using the status information as a key.
3. The image processing method according to 3. 15. In the extracted image area, whether an object in the reference image does not exist in the captured image or an object not existing in the reference image exists in the captured image. The image processing method according to any one of claims 10 to 13 or 14, wherein it is determined which of the following is true. 16. When the determination is that the object in the reference image does not exist in the captured image, the image area in the reference image is set to a corresponding image area of a current image. The image processing method according to claim 15, wherein the updating is performed. 17. A surveillance image display method characterized by displaying an image area extracted by the image processing method according to claim 10 and another image area separately. 18. The time when the image area is extracted or the time when the image area is extracted, corresponding to the image area extracted by the image processing method according to claim 10. A surveillance image display method, characterized by displaying an elapsed time from the monitoring image.