Person tracking support apparatus

Abstract

To provide a person tracking support apparatus that enables improvement in efficiency of tracking work when a user tracks a person appearing in images captured by cameras.SOLUTION: A person tracking support apparatus identifies one or more persons appearing in at least one of a plurality of images. The person tracking support apparatus displays, on a display device, a person tracking screen including a first display part that synchronously reproduces and displays, over an image time period, monitoring images selected from among the plurality of images, and a second display part that displays an appearance section in which the person appears in at least one of the monitoring images within the image time period for each of the one or more persons. Further, when a user performs an operation to designate one time point of an appearance section related to a target person among the one or more persons, the person tracking support apparatus displays snapshots of one or more monitoring images at the designated one time point, and displays, on the person tracking screen, person tracking information that allows the user to recognize a portion in which the target person appears in the snapshots.SELECTED DRAWING: Figure 6

Description

[Technical Field]

[0001] The present disclosure relates to a technology for assisting in tracking a person appearing in a video captured by a camera. [Background technology]

[0002] Patent Document 1 discloses a security system that identifies suspicious behavior of a person included in camera images. The security system monitors the behavior of a person included in multiple camera images captured continuously in chronological order by a surveillance camera. The security system detects the person areas of each person included in the multiple camera images, and performs a tracking process to identify the person included in the multiple camera images in chronological order based on the person image data included in the person areas. If the identification by the tracking process fails midway, the security system determines that a person behaving suspiciously is included in the camera images.

[0003] Other documents that demonstrate the technical level in this field include Patent Documents 2 and 3 below. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Publication No. 2023-086471 [Patent Document 2] Japanese Patent Publication No. 2023-156963 [Patent Document 3] Japanese Patent Application Publication No. 2024-032346 Summary of the Invention [Problem to be solved by the invention]

[0005] Consider a case where a user tries to track a specific person appearing in a video while viewing the video. In this case, tracking of the person is usually performed across multiple videos captured by multiple cameras. Therefore, the user tracking the person is required to identify the person to be tracked within the video time for each of the multiple videos. Conventionally, this tracking task has required considerable manpower and time costs.

[0006] The present disclosure has been made in consideration of the above-mentioned problems, and an object of the present disclosure is to provide a technology that enables a user to track a person appearing in a video with improved efficiency. [Means for solving the problem]

[0007] One aspect of the present disclosure relates to a person tracking assistance device. The person tracking assistance device includes a storage device that stores data on multiple videos captured by multiple cameras and a processing circuit. The processing circuit identifies one or more people appearing in at least one of the multiple videos. The processing circuit also displays a person tracking screen on the display device, including a first display unit that displays one or more surveillance videos selected from the multiple videos by synchronously playing them over the video time, and a second display unit that displays, for each of the one or more people, an appearance period in at least one of the one or more surveillance videos within the video time. Furthermore, when a user performs an operation on the person tracking screen to specify a time point in an appearance period for a target person among the one or more people, the processing circuit displays, on the first display unit, snapshots of one or more surveillance videos at the specified time point, and displays, on the person tracking screen, person tracking information that allows the user to recognize the portion of the snapshot in which the target person appears. [Effects of the Invention]

[0008] According to the present disclosure, a person tracking screen is displayed, including a first display unit that displays one or more selected surveillance videos by synchronously playing them over the video time, and a second display unit that displays, for each identified person, an appearance interval in at least one of the one or more surveillance videos within the video time. This allows the user to easily determine the interval in which each person appears in the video. When the user performs an operation to specify a point in the appearance interval for the target person, snapshots of one or more surveillance videos at that point in time and person tracking information are displayed. This allows the user to easily recognize the portion in which the target person appears at each point in time during the appearance interval. In this way, the present disclosure can improve the efficiency of the user's tracking work. [Brief explanation of the drawings]

[0009] [Figure 1] FIG. 1 is a conceptual diagram for explaining an overview of a person tracking support device according to an embodiment. [Figure 2] 1 is a block diagram showing a basic configuration of a person tracking support device according to an embodiment. [Figure 3] FIG. 2 is a block diagram showing a functional configuration related to processing executed by the person tracking support device according to the embodiment. [Figure 4] 4 is a diagram showing an example of person identification information generated by the person identification unit shown in FIG. 3. FIG. [Figure 5] FIG. 10 is a diagram illustrating an example of a screen configuration of a person tracking screen. [Figure 6] 10A and 10B are diagrams for explaining operations performed by a user when tracking a target person on a person tracking screen. [Figure 7] FIG. 10 is a diagram showing a processing sequence when a user tracks a target person on a person tracking screen. [Figure 8] FIG. 10 is a conceptual diagram for explaining display of a virtual space image. DETAILED DESCRIPTION OF THE INVENTION

[0010] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. In each drawing, the same or corresponding components are designated by the same reference numerals, and the description thereof will be simplified or omitted.

[0011] 1. Person tracking support device FIG. 1 is a conceptual diagram for explaining an overview of a person tracking support device 100. The person tracking support device 100 acquires multiple images 30 captured by multiple cameras 20. Each camera 20 is positioned to monitor a person 10 moving within a predetermined area. Examples of the predetermined area include a city, a building, and the like. The person 10 can also be called a "pedestrian 10." The multiple cameras 20 may include two or more cameras capturing images of the same point from different viewpoints.

[0012] The person tracking assistance device 100 uses data of the acquired multiple videos 30 to display on the display device 210 a "person tracking screen 300" to assist the user 2 in tracking the person 10 appearing in the video 30. The user 2 tracks the person 10 appearing in the video 30 on the person tracking screen 300. Details of the person tracking screen 300 will be described later. Tracking the person 10 appearing in the video 30 is useful in fields such as traffic management and behavior analysis.

[0013] Here, consider a case where user 2 attempts to track a specific person 10-T (hereinafter referred to as "target person 10-T"). In this case, user 2 needs to identify target person 10-T within the video time of each of multiple videos 30. In the example shown in FIG. 1, frames at video time points t1, t2, and t3 are shown for each of three videos 30 (30-A, 30-B, and 30-C). In the example shown in FIG. 1, user 2 confirms that target person 10-T is shown in video 30-A from time point t1 to time point t2, and tracks target person 10-T. Similarly, user 2 confirms that target person 10-T is shown in video 30-B from time point t2 to time point t3, and that target person 10-T is shown in video 30-C at time point t3, and tracks target person 10-T. In this way, in the tracking task of tracking the target person 10-T appearing in the video 30, the user 2 needs to confirm which section of the video 30 of which camera 20 the target person 10-T appears in. In particular, when tracking the target person 10-T across multiple videos 30, it is necessary to determine whether the target person 10-T is the same person as the target person 10-T among the people 10 appearing in different videos 30. Conventionally, such tracking tasks by the user 2 have required considerable human or time costs. This embodiment proposes a person tracking assistance device 100 that displays a person tracking screen 300 that enables the user 2 to perform tracking tasks efficiently.

[0014] FIG. 2 is a block diagram showing the basic configuration of a person tracking support device according to this embodiment. The person tracking support device 100 is a computer including a processing circuit 110 and one or more storage devices 120 (hereinafter simply referred to as "storage devices 120"). The person tracking support device 100 is connected to multiple cameras 20 via a communication network 3. The communication network 3 may be, for example, a wired communication system, a wireless communication system, or the Internet. The person tracking support device 100 is also connected to a user interface 200 including a display device 210 and an input device 220. The display device 210 displays various types of information in response to the output from the person tracking support device 100. In particular, the display device 210 displays a person tracking screen 300. The display device 210 may be, for example, a display, a projector, a head-mounted display (HMD), or the like. The input device 220 accepts various inputs from a user 2 to the person tracking support device 100. The input device 220 may be, for example, a keyboard, a pointing device, a touchpad, a switch, a microphone, or the like. The person tracking assistance device 100 may be a server accessible via the communication network 3. In this case, the user interface 200 may be a user terminal (for example, a personal computer, a smartphone, a tablet, etc.) connected to the person tracking assistance device 100 via the communication network 3.

[0015] The processing circuitry 110 performs various processes. The processing circuitry 110 may be, for example, a general-purpose processor, a special-purpose processor, a central processing unit (CPU), a graphics processing unit (GPU), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), an integrated circuit, a conventional circuit, or a combination of one or more of these. A processor including transistors and other circuits is an example of the processing circuitry 110. The processing circuitry 110 may also be referred to as circuitry or processing circuitry. Circuitry is hardware that is programmed to realize or executes the functions described in this disclosure.

[0016] The storage device 120 stores various information necessary for the processing circuit 110 to execute processing. The storage device 120 is configured with a recording medium such as a RAM (Random Access Memory), a ROM (Read Only Memory), an SSD (Solid State Drive), or an HDD (Hard Disk Drive). The storage device 120 stores a computer program 121 that can be executed by the processing circuit 110. The computer program 121 is configured with a plurality of instructions that describe the processing to be executed by the processing circuit 110. The computer program 121 may be recorded on a computer-readable recording medium. The functions of the person tracking assistance device 100 are realized by cooperation between the processing circuit 110 that executes the computer program 121 and the storage device 120.

[0017] The storage device 120 further stores video data D10. The video data D10 is data for managing multiple videos 30 captured by multiple cameras 20. The person tracking support device 100 acquires the videos 30 captured by each camera 20, and records and manages the acquired videos 30 as video data D10. The person tracking support device 100 may acquire the videos 30 from each camera 20 sequentially online. The person tracking support device 100 may also acquire the videos 30 from the user 2 via the input device 220. Each video 30 managed by the video data D10 includes information on the time of capture and information on the camera 20 that captured the video 30.

[0018] 3 is a block diagram showing a functional configuration related to the processing executed by the person tracking support device 100. The person tracking support device 100 includes, as functional blocks, a person identification unit F10 and a person tracking screen display unit F20. These functional blocks are realized by the cooperation of a processing circuit 110 that executes a computer program 121 and a storage device 120.

[0019] The person identification unit F10 executes an identification process to identify one or more people 10 appearing in at least one of the multiple videos 30 managed by the video data D10, and generates person identification information IDF. By executing the identification process, each identified person 10 is assigned unique identification information (ID). By executing the identification process, the portion of each video 30 in which each identified person 10 appears is identified. The portion of the video 30 in which the person 10 appears is represented, for example, by a bounding box surrounding the person 10. That is, in this case, by executing the identification process, the position of the bounding box is identified. The portion of the video 30 in which the person 10 appears can also be represented in other forms, such as a polygon surrounding the person 10 or the skeletal position of the person 10. In the following explanation, a case in which the position of the bounding box is identified by executing the identification process is considered.

[0020] The identification process typically comprises a tracking process for detecting a person 10 appearing in a video 30 and tracking the detected person 10 within the video, and a human re-identification process for identifying the same person 10 across different videos 30. The tracking process and the human re-identification process are both well-known technologies, and the methods for performing them are not particularly limited. For example, the identification process can be realized by an AI pipeline including a trained machine learning model configured to perform the tracking process and the human re-identification process using multiple videos 30 as input.

[0021] The person identification information IDF is information that associates, for each frame of each of a plurality of videos 30, the ID of the person 10 shown in the video 30 with the portion of the video 30 in which the person 10 with that ID appears. FIG. 4 is a diagram showing an example of the person identification information IDF for one of the plurality of videos 30. In the example shown in FIG. 4, for each of the 0th to 3rd frames, the ID of the person 10 shown in the video 30 is associated with the position of a bounding box surrounding the person 10 with that ID in the video 30. The position of the bounding box is specified by the positions of the left and top edges, as well as the values ​​of width and height. According to the example shown in FIG. 4, it can be seen that the person 10 with the ID "8aff82a2" appears in the video 30 in the section from the 0th to the 3rd frame. It can also be seen that person 10 with ID "50ca6660" appears in the video 30 in the section from the first to third frames. In particular, the positions of the bounding boxes surrounding this person 10 in each frame can be seen.

[0022] By referencing the person identification information IDF generated by the person identification unit F10 in this way, it is possible to obtain, for each of the multiple videos 30, the section in which each identified person 10 appears in the video 30 and the portion in which each person 10 appears in the video 30. The person identification unit F10 may store the generated person identification information IDF in the storage device 120.

[0023] Referring again to Figure 3, the person tracking screen display unit F20 generates a person tracking screen 300 based on multiple videos 30 managed in the video data D10 and person identification information IDF acquired from the person identification unit F10, and displays it on the display device 210. The person tracking screen display unit F20 also accepts operation input from the user 2 on the person tracking screen 300 displayed on the display device 210 via the input device 220. The person tracking screen display unit F20 changes the display of the person tracking screen 300 in response to the operation input from the user 2.

[0024] The person tracking screen 300 displayed on the display device 210 by the person tracking screen display unit F20 will be described in detail below.

[0025] 2 Person tracking screen 2.1 Screen layout 5 is a conceptual diagram for explaining the screen configuration of the person tracking screen 300. The person tracking screen 300 includes a first display section 310 and a second display section 320.

[0026] The first display unit 310 displays one or more videos 30 by synchronously playing them back over a video time period. The one or more videos 30 displayed on the first display unit 310 are selected by the user 2 from among the multiple videos 30 managed by the video data D10. The person tracking screen display unit F20 accepts a selection input of the video 30 from the user 2. The selection input may be made by selecting a camera 20. For example, the user 2 selects the camera 20 from which the user wants to view the video 30 from a list of the multiple cameras 20. In this case, the video 30 captured by the selected camera 20 is displayed on the first display unit 310. The person tracking screen display unit F20 may also accept a designation input of a video time period from the user 2. For example, the user 2 designates a period based on the date and time of capture. Hereinafter, each of the one or more videos 30 displayed on the first display unit 310 will also be referred to as a "surveillance video 30." In the example shown in FIG. 5, two videos 30-X and 30-Y are shown as the surveillance video 30.

[0027] The first display unit 310 displays a button 311 for starting playback of the surveillance video 30 and a bar 312 indicating the playback position within the video time of the surveillance video 30. When user 2 operates button 311, "synchronized playback" of the surveillance video 30 begins. That is, on the first display unit, each surveillance video 30 is played back while its capture time is synchronized with that of the other surveillance videos. When user 2 operates button 311 while a surveillance video 30 is being played back, the playback of the surveillance video 30 may be paused. The bar 312 moves in accordance with the playback position of the surveillance video 30. By checking the position of the bar 312, user 2 can ascertain the playback position of the surveillance video 30 within the video time.

[0028] A bounding box BB surrounding the identified person 10 is superimposed on each surveillance video 30. In FIG. 5, the reference numerals for the person 10 and the bounding box BB are omitted except for one for each of the videos 30-X and 30-Y. The person tracking screen display unit F20 superimposes and displays the bounding box BB on each frame of each surveillance video 30 by referencing the person identification information IDF. As a variation of this embodiment, a polygon surrounding the person 10 or the skeletal position of the person 10 may be superimposed and displayed on each surveillance video 30 instead of the bounding box BB, depending on the person identification information IDF.

[0029] The first display unit 310 displays camera information CF of the camera 20 capturing the surveillance video 30 in association with the surveillance video 30. The camera information CF is information that can identify the camera 20. In the example shown in FIG. 5, the camera information CF is an identification number unique to each camera 20. The person tracking screen display unit F20 displays the camera information CF by referencing the camera information CF included in each surveillance video 30. By referencing the management data for the camera 20 based on the camera information CF, the user 2 can confirm the location and specifications of the camera 20 capturing each surveillance video 30. The camera information CF is also information unique to each surveillance video 30. Therefore, each surveillance video 30 can be identified and distinguished from the camera information CF. In the example shown in FIG. 5, camera information CF-X of the camera 20 capturing video 30-X and camera information CF-Y of the camera 20 capturing video 30-Y are displayed in association with the video 30-X and video 30-Y, respectively. As a variation of this embodiment, instead of the camera information CF, other information that can identify and distinguish each surveillance video 30 may be displayed. For example, a number indicating the display order of the surveillance video 30 or an identification number unique to each surveillance video 30 may be displayed.

[0030] The second display unit 320 displays a section 322 (hereinafter referred to as an "appearance section 322") in which each identified person 10 appears in at least one of the one or more surveillance videos 30 during the video time for each identified person 10. The person tracking screen display unit F20 acquires the appearance section 322 of each identified person 10 in the surveillance video 30 by referring to the person identification information IDF.

[0031] In the example shown in Fig. 5, the second display unit 320 displays a list of IDs 321 of each identified person 10. The second display unit 320 also displays an appearance period 322 of each person 10 in association with the ID 321 of each person 10. Note that in Fig. 5, the reference numerals for the IDs 321 and appearance periods 322 are omitted, with some exceptions. By checking the appearance period 322 associated with the ID 321, the user 2 can easily ascertain the time during the video when the person 10 with that ID 321 appears in the surveillance video 30.

[0032] 2.2 Tracking a target person on the person tracking screen On the person tracking screen 300 having the screen configuration described above, the user 2 can track the target person 10-T as follows. Fig. 6 is a conceptual diagram for explaining the tracking of the target person 10-T on the person tracking screen 300.

[0033] First, the user 2 performs an operation to designate a time point in the appearance section 322 for the target person 10-T. For example, the user 2 operates the pointing device to hover the pointer 4 over a time point in the appearance section 322. The example shown in FIG. 6 shows a case where the person 10 with the ID 321 of "8aff82a2" is the target person 10-T.

[0034] When user 2 performs an operation to specify a point in time within the appearance section 322, a snapshot of each surveillance video 30 at the specified point in time is displayed on the first display unit. In other words, each surveillance video 30 stops at the playback point corresponding to the specified point in time. The bar 312 may move to the playback point corresponding to the specified point in time. A snapshot can also be called a "still image."

[0035] Furthermore, when the user 2 performs an operation to specify a point in time in the appearance section 322, "person tracking information 323" is displayed on the person tracking screen 300. The person tracking information 323 is information that allows the user 2 to recognize the portion of the snapshot in which the target person 10-T appears. In particular, in this embodiment, the person tracking information 323 is information that associates an image IM obtained by cutting out the area of ​​a bounding box BB that surrounds the target person 10-T from the snapshot with camera information CF of the camera 20 that captured the surveillance video 30 showing the target person 10-T.

[0036] From the person tracking information 323 according to this embodiment, user 2 can recognize the portion of the snapshot of the surveillance video 30 in which the target person 10-T appears as follows. By comparing the camera information CF in the person tracking information 323 with the camera information CF associated with each surveillance video 30, user 2 can identify the surveillance video 30 in which the target person 10-T appears (target surveillance video). In this sense, the camera information CF in the person tracking information 323 can be said to be information for identifying the target surveillance video. Then, user 2 can recognize the portion in which the target person 10-T appears by comparing the image IM in the person tracking information 323 with the image surrounded by each bounding box BB in the target surveillance video. In this way, user 2 can easily recognize the portion in which the target person 10-T appears in the snapshot of the surveillance video 30 from the person tracking information 323. To make it easier to recognize the portion in which the target person 10-T is shown, the person tracking screen display unit F20 may match the color of the bounding box BB surrounding each person 10 with the color of the display of the appearance section 322 for each person 10.

[0037] By appropriately changing the time point designated within the appearance section 322 for the target person 10-T, the user 2 can easily recognize the portion in which the target person 10-T appears at each time point during the appearance section 322. As described above, according to this embodiment, the user 2 can efficiently track the target person 10-T on the person tracking screen 300.

[0038] FIG. 7 is a diagram showing a processing sequence when the user 2 tracks the target person 10-T on the person tracking screen 300.

[0039] First, in step S10, the user 2 operates the input device 220 to specify a point in time of the appearance section 322 of the target person 10-T. The operation input by the user 2 is transmitted to the person tracking support device 100.

[0040] In response to the specification of a point in time in the appearance section 322, the person tracking screen display unit F20 then displays a snapshot of the surveillance video 30 at the specified point in time on the first display unit 310 in step S20.

[0041] Next, in step S30, the person tracking screen display unit F20 generates person tracking information 323 for the target person 10-T based on the person identification information IDF. More specifically, the person tracking screen display unit F20 cuts out the area of ​​a bounding box BB that surrounds the target person 10-T from a snapshot of the surveillance video 30. Then, the person tracking screen display unit F20 generates the person tracking information 323 by associating an image IM of the area surrounding the cut-out target person 10-T with camera information CF that captured the target surveillance video in which the target person 10-T appears.

[0042] Next, in step S40, the person tracking screen display unit F20 displays the generated person tracking information 323 on the person tracking screen 300.

[0043] 2.3 Displaying virtual space images To enable the user 2 to track the target person 10-T more efficiently, the person tracking screen display unit F20 may further display a "virtual space image" on the person tracking screen 300. The virtual space image is an image that represents the movements of the person 10 appearing in the surveillance video 30 during the video time using objects in a virtual space.

[0044] FIG. 8 is a conceptual diagram illustrating the display of a virtual space image 40. The person tracking screen display unit F20 represents the movement of the person 10 appearing in the surveillance video 30 as an object OB in the virtual space VS. This can be achieved, for example, by applying a known image analysis technique to the surveillance video 30 to estimate the 3D posture of the person 10 and reflecting the estimated 3D posture in the object OB. The virtual space VS may be generated in advance. The object OB may be an avatar. The person tracking screen display unit F20 generates a virtual space image 40 that displays the virtual space from a predetermined viewpoint. The person tracking screen display unit F20 then displays the generated virtual space image 40 on the person tracking screen 300 so that it is played back synchronously with the surveillance video 30. The example shown in FIG. 8 illustrates a case in which the virtual space image 40 is displayed on the first display unit 310. When the user 2 operates the button 311, synchronous playback of the virtual space image 40 and the surveillance video 30 begins. The viewpoint of the virtual space image 40 may be freely changeable by the user 2.

[0045] By displaying the virtual space image 40 in this manner, the user 2 can check the movements of the target person 10-T from various viewpoints through the virtual space image 40. As a result, the user 2 can track the target person 10-T more efficiently.

[0046] 3. Effects As described above, according to this embodiment, a person tracking screen is displayed, including a first display unit 310 that synchronously plays back and displays one or more surveillance videos 30 over a video time period, and a second display unit 320 that displays, for each identified person 10, an appearance section 322 in which the person 10 appears in at least one of the surveillance videos 30 within the video time period. This allows the user to easily determine in which section each person 10 appears in the video 30. When user 2 performs an operation to specify a time point in the appearance section 322 for target person 10-T, snapshots of one or more surveillance videos 30 at that time and person tracking information 323 are displayed. This allows the user to easily recognize the portion in which target person 10-T appears at each time point during the appearance section 322. As such, this embodiment can improve the efficiency of tracking by user 2. [Explanation of symbols]

[0047] 2 users 20 Camera 30 Videos 40 Virtual Space Video 100 Person tracking support device 110 Processing circuit 120 Storage device 121 Computer Programs 200 User Interface 210 Display device 220 Input Device 300 Person Tracking Screen 310 1st display section 320 2nd display section 322 Appearance Section 323 Person Tracking Information BB Bounding Box CF Camera Information D10 video data

Claims

1. a storage device for storing data of a plurality of images captured by a plurality of cameras; a processing circuit; Equipped with The processing circuitry identifying one or more people appearing in at least one of the plurality of images; A person tracking screen including a first display unit that synchronously plays back and displays one or more monitoring videos selected from the plurality of videos over a video time period, and a second display unit that displays an appearance section in which, for each of the one or more people, the person is shown in at least one of the one or more monitoring videos over the video time period, is displayed on a display device. It is configured as follows: When a user performs an operation on the person tracking screen to specify a time point in the appearance interval for a target person among the one or more people, the processing circuit displaying a snapshot of the one or more surveillance images at the time on the first display unit; Displaying person tracking information on the person tracking screen, which allows the user to recognize the part of the snapshot in which the target person appears. A person tracking support device characterized by:

2. The person tracking support device according to claim 1, The processing circuitry further comprises: A bounding box enclosing the one or more persons is superimposed on the one or more surveillance images displayed on the first display unit. It is configured as follows: The person tracking information is information in which an image of the bounding box area surrounding the target person is cut out from the snapshot and information for identifying a target surveillance video showing the target person among the one or more surveillance videos is associated with the image. A person tracking support device characterized by:

3. The person tracking support device according to claim 2, The information for identifying the target surveillance video is information about the camera that captured the target surveillance video among the plurality of cameras. A person tracking support device characterized by:

4. The person tracking support device according to claim 1, The processing circuitry further comprises: generating a virtual space image that expresses the actions of the one or more people during the image time using objects in a virtual space; The virtual space image is displayed on the person tracking screen so as to be played back in synchronization with the one or more surveillance images. It is configured as follows: A person tracking support device characterized by:

5. a storage device for storing data of a plurality of images captured by a plurality of cameras; a processing circuit; Equipped with The processing circuitry identifying a person in each of the plurality of videos; A region surrounding the person is cut out from a snapshot of a video in which the person appears, and person tracking information is generated by associating the image of the region surrounding the person cut out from the snapshot with information about a camera among the plurality of cameras that captured the video in which the person appears. A person tracking support device characterized by:

Images