System, control unit, and program

Abstract

To provide a system that can track a specific subject with a plurality of imaging apparatuses different in photographing position and photographing direction.SOLUTION: A system includes: first and second control units that control the second imaging apparatus to track a predetermined subject on the basis of a first image picked up by the first imaging apparatus or a second image picked up by the second imaging apparatus, the imaging apparatuses being different in photographing direction. The first control unit has first determination means that determines the predetermined subject from subjects included in the first image, image processing means that cuts out a first area of the predetermined subject included in the first image on the basis of a photographic range of the second image, and first generation means that generates first feature information of the first area of the predetermined subject. The second control unit has second generation means that generates second feature information of subjects included in the second image, second determination means that determines the predetermined subject on the basis of the first feature information acquired from the first control unit and the second feature information, and second control means that controls the second imaging apparatus to track the predetermined subject.SELECTED DRAWING: Figure 3

Description

[Technical field]

[0001] The present invention relates to a system for tracking a specific subject using a plurality of image capturing devices with different shooting positions and shooting directions. [Background technology]

[0002] There is a technology that tracks a specific subject using an imaging device that can automatically control the pan / tilt / zoom (PTZ) from a remote location. In this type of automatic tracking control, the PTZ is automatically controlled so that the subject to be tracked is positioned at a desired position within the shooting angle of view.

[0003] Patent document 1 describes a technology in which, when detecting a specific subject through image recognition processing, parameters used in the image recognition processing are changed according to the zoom magnification so that the specific subject is not prevented from being detected due to a change in the zoom magnification.

[0004] Furthermore, Patent Document 2 describes a technology in which, when a subject to be tracked moves near the boundary of the imaging range of a first imaging device, template data of the subject to be tracked generated by the first imaging device is transmitted to a second imaging device, and the second imaging device takes over the tracking target. Patent Document 3 describes a technique for expanding the shooting range to search for a specific subject when the specific subject cannot be detected from a captured image. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] JP 2015-142181 A [Patent Document 2] JP 2002-290962 A [Patent Document 3] JP 2015-61239 A Summary of the Invention [Problem to be solved by the invention]

[0006] However, in Patent Documents 1 and 2, the object to be tracked is identified by template matching, so when tracking a specific object using multiple imaging devices, the multiple imaging devices need to be arranged so that their shooting positions and shooting directions are close to each other. Therefore, when the shooting positions and shooting directions of the multiple imaging devices are arranged far apart, it becomes difficult to track a specific object using the multiple imaging devices.

[0007] In addition, when the shooting areas of the subject to be tracked are different in the multiple imaging devices, the similarity of the subject to be tracked between the multiple imaging devices may decrease. For example, when the shooting angle of view of the first imaging device is the whole subject and the shooting angle of view of the second imaging device is the part of the subject, or when the part of the subject is outside the shooting angle of view, it becomes difficult for the multiple imaging devices to recognize the same subject.

[0008] Furthermore, in Patent Documents 2 and 3, if the size of the image of the subject to be tracked differs in the multiple imaging devices, the similarity of the subject to be tracked between the multiple imaging devices may decrease, making it difficult for the multiple imaging devices to recognize the same subject. The present invention has been made in view of the above-mentioned problems, and has as its object to realize a system that makes it possible to track a specific subject using a plurality of imaging devices with different shooting positions and shooting directions. [Means for solving the problem]

[0009] In order to solve the above problems and achieve the object, the present invention provides a system including a first imaging device and a second imaging device having different shooting directions, and a first control device and a second control device that control the second imaging device to track a predetermined subject based on a first image captured by the first imaging device or a second image captured by the second imaging device, wherein the first control device has a first determination means that determines the predetermined subject from a subject included in the first image, an image processing means that cuts out a first region of the predetermined subject included in the first image based on a shooting range of the second image acquired from the second imaging device, a first generation means that generates first feature information of the first region of the predetermined subject, and a first control means that controls the second imaging device to track the predetermined subject, and the second control device has a second generation means that generates second feature information of the subject included in the second image, a second determination means that determines the predetermined subject based on the first feature information and the second feature information acquired from the first control device, and a second control means that controls the second imaging device to track the predetermined subject. Effect of the Invention

[0010] According to the present invention, it is possible to track a specific subject using a plurality of imaging devices with different shooting positions and shooting directions. [Brief description of the drawings]

[0011] [Figure 1] FIG. 1 is a diagram illustrating an example of a system configuration according to a first embodiment. [Diagram 2] FIG. 2 is a diagram illustrating an example of the hardware configuration of devices constituting the system of the first embodiment. [Diagram 3] FIG. 2 is a diagram illustrating an example of the functional configuration of an apparatus constituting the system of the first embodiment. [Figure 4] 4 is a flowchart illustrating a basic operation of the apparatus constituting the system of the first embodiment. [Diagram 5] 4A to 4C are diagrams for explaining a coordinate conversion method for a captured image according to the first embodiment. [Figure 6]5A to 5C are views for explaining a subject detection method and a coordinate conversion method according to the first embodiment. [Figure 7] 5A to 5C are diagrams for explaining pan control according to the first embodiment. [Figure 8] 5A to 5C are diagrams for explaining tilt control according to the first embodiment. [Figure 9] 4 is a flowchart illustrating a control process according to the first embodiment. [Figure 10] 4A to 4C are diagrams for explaining a method for determining a subject to be tracked in the first embodiment. [Figure 11] 4A and 4B are diagrams illustrating the relationship between a subject to be tracked and a photographing angle of view. [Figure 12] 4 is a flowchart illustrating a trimming process according to the first embodiment. [Figure 13] 5A to 5C are views for explaining the trimming process according to the first embodiment. [Figure 14] 11 is a flowchart illustrating a control process according to the third embodiment. [Figure 15] 11 is a flowchart illustrating a zoom control according to the third embodiment. [Figure 16] FIG. 13 is a diagram illustrating an example of the functional configuration of an apparatus constituting a system according to a fourth embodiment. [Figure 17] 13 is a flowchart illustrating a control process according to the fourth embodiment. [Figure 18] 13 is a flowchart illustrating a control process according to the fourth embodiment. [Figure 19] 13 is a flowchart illustrating a control process according to the fifth embodiment. [Figure 20] 20 is a flowchart illustrating a control process according to the sixth embodiment. [Figure 21] FIG. 23 is a diagram illustrating an example of a system configuration according to a seventh embodiment. [Figure 22] 13 is a diagram showing an example of roles and contents that can be set in the imaging device of the seventh embodiment. [Figure 23] 20 is a flowchart illustrating a control process according to the eighth embodiment. [Figure 24] 20 is a flowchart illustrating a letter adding process according to the eighth embodiment. [Diagram 25] FIG. 10 is a diagram for explaining letter assignment in the eighth embodiment. [Figure 26] 13A to 13C are diagrams illustrating a skeleton estimation process according to the ninth embodiment. [Figure 27] 13A to 13C are diagrams illustrating processing using the skeleton estimation processing of the ninth embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0012] Hereinafter, the embodiments will be described in detail with reference to the attached drawings. Note that the following embodiments do not limit the invention according to the claims. Although the embodiments describe a number of features, not all of these features are essential to the invention, and the features may be combined in any manner. Furthermore, in the attached drawings, the same reference numbers are used for the same or similar configurations, and duplicated descriptions are omitted.

[0013] [Embodiment 1] <System configuration> First, the system configuration of the first embodiment will be described with reference to FIG.

[0014] The system of this embodiment includes a first control device 100, a second control device 200, a first imaging device 300, and a second imaging device 400. In the system of this embodiment, the second imaging device 400 is controlled by either the first control device 100 or the second control device 200 to track a specific subject. In this embodiment, the specific subject is, for example, a person, but may also be an animal or an object.

[0015] The first control device 100 detects a subject to be tracked from an overhead image captured by the first imaging device 300, and controls the second imaging device 400 based on the detection result. The first control device 100 is also called a workstation. The subject to be tracked is set, for example, by a user operation or automatically.

[0016] The second control device 200 controls the second imaging device 400 based on the result of recognizing the subject of the tracking target from the overhead image captured by the first imaging device 300 and the result of recognizing the subject of the tracking target from the sub-image captured by the second imaging device 300. The second control device 200 is also called an edge box.

[0017] The first imaging device 300 has a fixed shooting angle of view at a wide angle, and can capture an overhead image including all of subjects A, B, and C. The first imaging device 300 is also called an overhead camera. The second imaging device 400 has a variable shooting angle of view, and can capture at least one of subjects A, B, and C. The second imaging device 400 is called a sub-camera. The first imaging device 300 and the second imaging device 400 are placed at positions separated from each other so that their shooting positions and / or shooting directions are different.

[0018] The first control device 100, the second control device 200, the first imaging device 300, and the second imaging device 400 are communicatively connected by a network 600 such as a LAN (Local Area Network). In this embodiment, an example in which the first control device 100, the second control device 200, the first imaging device 300, and the second imaging device 400 are connected by the network 600 will be described, but they may be connected by a connection cable (not shown). In this embodiment, an example in which there is one second imaging device 400 will be described, but there may be two or more. When there are multiple second imaging devices 400, a second control device 200 is provided for each second imaging device 400.

[0019] Next, the basic functions of the system of this embodiment will be described.

[0020] The first imaging device 300 captures an overhead image and transmits the overhead image to the first control device 100 via the network 600 .

[0021] The second imaging device 400 captures a sub-image including a subject to be tracked (tracked subject) and transmits the sub-image to the second control device 200 via the network 600. The second imaging device 400 has a PTZ function. The PTZ function is a function that can control pan, tilt, and zoom of the imaging device. PTZ is an abbreviation of the initial letters of pan, tilt, and zoom. Pan is the horizontal movement of the optical axis of the imaging device. Tilt is the vertical movement of the optical axis of the imaging device. Zoom is zoom up (telephoto) and zoom out (wide angle). Pan and tilt are functions that change the shooting direction of the imaging device. Zoom is a function that changes the shooting range (shooting angle of view) of the imaging device.

[0022] The first control device 100 determines a tracking subject from subjects detected from the overhead image received from the first imaging device 300, and calculates first feature information of the tracking subject from the overhead image. The first control device controls the second imaging device 400 to change the shooting direction and shooting range of the second imaging device 400 to the shooting direction and shooting range of the tracking subject based on the first feature information of the tracking subject.

[0023] After changing the shooting direction and shooting range of the second imaging device 400 to the shooting direction and shooting range of the tracked subject, the first control device 100 transmits first feature information of the tracked subject calculated from the overhead image to the second control device 200.

[0024] The second control device 200 detects a subject from the sub-image received from the second imaging device 400, and calculates second feature information of the detected subject. The second control device 200 compares the second feature information of the subject detected from the sub-image with the first feature information of the tracking subject received from the first control device 100.

[0025] When the similarity between the first feature information of the tracked subject and the second feature information of the subject detected from the sub-image is low, the first control device 100 controls the second imaging device 400 to change the shooting direction and shooting range of the second imaging device 400 to the shooting direction and shooting range of the tracked subject based on the first feature information of the tracked subject.

[0026] In addition, when there is a high degree of similarity between the first feature information of the tracked subject and the second feature information of the subject detected from the sub-image, the second control device 200 controls the second imaging device 400 to change the shooting direction and shooting range of the second imaging device 400 to the shooting direction and shooting range of the tracked subject based on the second feature information of the subject detected from the sub-image that has a high degree of similarity to the first feature information of the tracked subject.

[0027] The feature information is information that can identify that the same subject is captured by multiple imaging devices with different shooting positions and / or shooting directions. The feature information is an inference result that is output by performing image recognition by inference processing using a trained model on multiple images captured by multiple imaging devices with different shooting positions and / or shooting directions as input. When an inference result that the subjects are the same is obtained, it is possible to identify that the subjects included in the multiple images captured by the multiple imaging devices with different shooting positions and / or shooting directions are the same subject.

[0028] In the following description, the first control device 100 is referred to as a workstation (WS), the second control device 200 as an edge box (EB), the first imaging device 300 as an overhead camera, and the second imaging device 400 as a sub-camera.

[0029] <Device configuration> Next, the hardware configuration of the WS 100, the EB 200, the overhead camera 300, and the sub-camera 400 will be described in detail with reference to FIG.

[0030] First, the configuration of the WS 100 will be described.

[0031] The WS 100 includes a control unit 101, a volatile memory 102, a non-volatile memory 103, an inference unit 104, a communication unit 105, and an operation unit 106, and each unit is connected via an internal bus 110 so as to be able to send and receive data.

[0032] The control unit 101 has a processor (CPU) that performs arithmetic processing and control processing of the WS 100 , and controls each of the components of the WS 100 by executing a control program stored in the non-volatile memory 103 .

[0033] The volatile memory 102 is a main storage device such as a RAM. Constants and variables for the operation of the control unit 101, and control programs and inference programs read from the non-volatile memory 103 are loaded into the volatile memory 102. The volatile memory 102 also stores information such as image data and inference programs received from an external device by the communication unit 105. The volatile memory 102 also stores overhead image data received from the overhead camera 300. The volatile memory 102 has a sufficient storage capacity to hold this information.

[0034] The non-volatile memory 103 is an auxiliary storage device such as an EEPROM, a flash memory, a hard disk drive (HDD), a solid state drive (SSD), a memory card, etc. The non-volatile memory 103 stores an OS (operating system) which is basic software executed by the control unit 101, a control program including an application which cooperates with the OS to realize applied functions, an inference program used by the inference unit 104 for inference processing, etc.

[0035] The inference unit 104 executes an inference process using a learned inference model and inference parameters according to an inference program. The inference unit 104 executes an inference process to estimate the presence or absence and position of a specific object and feature information of the object from an overhead image received from the overhead camera 300. The inference process in the inference unit 104 can be executed by a calculation processing device specialized for image processing and inference process, such as a GPU (Graphics Processing Unit). The GPU is a processor capable of performing a large amount of product-sum calculations, and has a calculation processing capacity for performing matrix calculations of a neural network in a short time. The inference process in the inference unit 104 may be realized by a reconfigurable logic circuit such as an FPGA (Field-Programmable Gate Array). The inference process may be performed by the CPU and GPU of the control unit 101 working together, or by either the CPU or the GPU of the control unit 101.

[0036] The communication unit 105 is an interface (I / F) that complies with a wired communication standard such as Ethernet (registered trademark) or an interface that complies with a wireless communication standard such as Wi-Fi (registered trademark). The communication unit 105 is connected to external devices such as the EB 200, the overhead camera 300, and the sub-camera 400 via a network 600 such as a wired LAN or a wireless LAN, and can transmit and receive data to and from the external devices. The control unit 101 realizes communication with the external devices by controlling the communication unit 105. Note that the communication method is not limited to Ethernet (registered trademark) or Wi-Fi (registered trademark), and a communication standard such as IEEE1394 may also be used.

[0037] The operation unit 106 is an operation member such as various switches, buttons, a touch panel, etc. that receives various operations by the user and outputs operation information to the control unit 101. The operation unit 106 also provides a user interface for the user to operate the WS100.

[0038] The display unit 111 displays an overhead image, a subject recognition result, a GUI (Graphical User Interface) for interactive operations, etc. The display unit 111 is a display device such as a liquid crystal display or an organic EL display. The display unit 111 may be an integral part of the WS 100, or may be an external device connected to the WS 100.

[0039] Next, the configuration of the EB 200 will be described.

[0040] The EB 200 includes a control unit 201, a volatile memory 202, a non-volatile memory 203, an inference unit 204, and a communication unit 205, and each unit is connected via an internal bus 210 so as to be able to transmit and receive data.

[0041] The control unit 201 has a processor (CPU) that performs arithmetic processing and control processing of the EB 200, and controls each component of the EB 200 by executing a control program stored in the non-volatile memory 203.

[0042] The volatile memory 202 is a main storage device such as a RAM. Constants and variables for the operation of the control unit 201, and control programs and inference programs read from the non-volatile memory 203 are loaded into the volatile memory 202. The volatile memory 202 also stores information such as image data and inference programs received from an external device by the communication unit 205. The volatile memory 202 also stores sub-image data received from the sub-camera 400. The volatile memory 202 has a sufficient storage capacity to hold this information.

[0043] The non-volatile memory 203 is an auxiliary storage device such as an EEPROM, a flash memory, a hard disk drive (HDD), a solid state drive (SSD), a memory card, etc. The non-volatile memory 203 stores an OS (operating system) which is basic software executed by the control unit 201, a control program including an application which cooperates with the OS to realize applied functions, an inference program used by the inference unit 204 for inference processing, etc.

[0044] The inference unit 204 executes an inference process using a learned inference model and inference parameters according to an inference program. The inference unit 204 executes an inference process to estimate the presence or absence and position of a specific object, and feature information of the object, from a sub-image received from the sub-camera 400. The inference process in the inference unit 204 can be executed by a calculation processing device specialized for image processing and inference process, such as a GPU (Graphics Processing Unit). The GPU is a processor capable of performing a large amount of product-sum calculations, and has a calculation processing capability for performing matrix calculations of a neural network in a short time. The inference process in the inference unit 204 may be realized by a reconfigurable logic circuit, such as an FPGA (Field-Programmable Gate Array). The inference process may be performed by a CPU and a GPU of the control unit 201 working together, or by either the CPU or the GPU of the control unit 201.

[0045] The communication unit 205 is an interface (I / F) that complies with a wired communication standard such as Ethernet (registered trademark) or an interface that complies with a wireless communication standard such as Wi-Fi (registered trademark). The communication unit 205 is connected to external devices such as the WS 100 and the sub-camera 400 via a network 600 such as a wired LAN or a wireless LAN, and can transmit and receive data to and from the external devices. The control unit 201 realizes communication with the external devices by controlling the communication unit 205. Note that the communication method is not limited to Ethernet (registered trademark) or Wi-Fi (registered trademark), and a communication standard such as IEEE1394 may also be used.

[0046] Next, the configuration of the overhead camera 300 will be described.

[0047] The overhead camera 300 includes a control unit 301, a volatile memory 302, a non-volatile memory 303, a communication unit 305, an imaging unit 306, and an image processing unit 307, and each unit is connected via an internal bus 310 so as to be able to send and receive data.

[0048] The control unit 301 performs overall control of the overhead camera 300 under the control of the WS 100. The control unit 301 has a processor (CPU) that performs calculation processing and control processing of the overhead camera 300, and controls each component of the overhead camera 300 by executing a control program stored in the non-volatile memory 303.

[0049] Volatile memory 302 is a main storage device such as a RAM. Constants and variables for the operation of control unit 301, and control programs and inference programs read from non-volatile memory 303 are loaded into volatile memory 302. Volatile memory 302 also stores overhead image data captured by imaging unit 306 and processed by image processing unit 307. Volatile memory 302 has a sufficient storage capacity to hold this information.

[0050] The non-volatile memory 303 is an auxiliary storage device such as an EEPROM, a flash memory, a hard disk drive (HDD), a solid state drive (SSD), a memory card, etc. The non-volatile memory 303 stores an OS (operating system) which is basic software executed by the control unit 301, and a control program including an application which cooperates with the OS to realize practical functions.

[0051] The imaging unit 306 has an image sensor composed of a CCD (charge-coupled device), a CMOS (complementary metal-oxide semiconductor) element, etc., and converts an optical image of a subject into an electrical signal. In this embodiment, the overhead camera 300 has a fixed shooting angle of view so that an overhead image including a plurality of subjects including a tracking subject can be captured.

[0052] The image processing unit 307 performs various image processing on image data output from the imaging unit 306 or image data read from the volatile memory 302. The various image processing includes, for example, image processing such as noise removal, edge emphasis, and enlargement / reduction, image correction processing such as contrast correction, brightness correction, and color correction, and trimming or cropping processing for cutting out a part of the image data. The image processing unit 307 converts the image data that has been subjected to the image processing into an image file in a predetermined format (for example, JPEG) and records it in the non-volatile memory 303. In addition, the image processing unit 307 performs predetermined calculation processing using the image data, and the control unit 301 performs AF (autofocus) processing and AE (autoexposure) processing based on the calculation results.

[0053] The communication unit 305 is an interface (I / F) that complies with a wired communication standard such as Ethernet (registered trademark) or an interface that complies with a wireless communication standard such as Wi-Fi (registered trademark). The communication unit 305 can connect to an external device such as WS100 via a network 600 such as a wired LAN or wireless LAN, and transmit and receive data to and from the external device. The control unit 301 realizes communication with the external device by controlling the communication unit 305. Note that the communication method is not limited to Ethernet (registered trademark) or Wi-Fi (registered trademark), and a communication standard such as IEEE1394 may also be used.

[0054] Next, the configuration of the sub-camera 400 will be described.

[0055] The sub-camera 400 comprises a control unit 401, a volatile memory 402, a non-volatile memory 403, a communication unit 405, an imaging unit 406, an image processing unit 407, an optical unit 408 and a PTZ drive unit 409, and each unit is connected via an internal bus 410 so as to be able to send and receive data.

[0056] The control unit 401 performs overall control of the sub-camera 400 under the control of the WS 100 or the EB 200. The control unit 401 has a processor (CPU) that performs arithmetic processing and control processing of the sub-camera 400, and controls each component of the sub-camera 400 by executing a control program stored in the non-volatile memory 403.

[0057] The volatile memory 402 is a main storage device such as a RAM. Constants and variables for the operation of the control unit 401, and control programs and inference programs read from the non-volatile memory 403 are loaded into the volatile memory 402. The volatile memory 402 also stores overhead image data captured by the imaging unit 406 and processed by the image processing unit 407. The volatile memory 402 has a sufficient storage capacity to hold this information.

[0058] The non-volatile memory 403 is an auxiliary storage device such as an EEPROM, a flash memory, a hard disk drive (HDD), a solid state drive (SSD), a memory card, etc. The non-volatile memory 403 stores an OS (operating system) which is basic software executed by the control unit 401, and a control program including an application which cooperates with the OS to realize practical functions.

[0059] The imaging unit 406 has an image sensor configured with a CCD (charge-coupled device), a CMOS (complementary metal-oxide semiconductor) element, or the like, and converts an optical image of a subject into an electrical signal.

[0060] The image processing unit 407 executes various image processing on image data output from the imaging unit 406 or image data read from the volatile memory 402. The various image processing includes, for example, image processing such as noise removal, edge emphasis, and enlargement / reduction, image correction processing such as contrast correction, brightness correction, and color correction, and trimming or cropping processing for cutting out a part of the image data. The image processing unit 407 converts the image data that has been subjected to image processing into an image file in a predetermined format (for example, JPEG) and records it in the non-volatile memory 403. In addition, the image processing unit 407 executes predetermined calculation processing using the image data, and the control unit 401 executes AF (autofocus) processing and AE (autoexposure) processing based on the calculation result.

[0061] The communication unit 405 is an interface (I / F) that complies with a wired communication standard such as Ethernet (registered trademark) or an interface that complies with a wireless communication standard such as Wi-Fi (registered trademark). The communication unit 405 can connect to an external device such as the EB 200 via a network 600 such as a wired LAN or wireless LAN, and can transmit and receive data to and from the external device. The control unit 401 realizes communication with the external device by controlling the communication unit 405. Note that the communication method is not limited to Ethernet (registered trademark) or Wi-Fi (registered trademark), and a communication standard such as IEEE1394 may also be used.

[0062] The optical unit 408 includes a lens group including a zoom lens and a focus lens, a shutter with an aperture function, and a mechanism for driving these optical members. The optical unit 408 drives the optical members to at least one of rotate the shooting direction of the sub-camera 400 around the pan (P) axis (horizontal direction) or the tilt (T) axis (vertical direction), and change the shooting range (shooting angle of view) of the sub-camera 400 along the zoom (Z) axis (enlargement / reduction direction).

[0063] The PTZ driving unit 409 includes actuators such as mechanical elements and motors for driving the optical unit 408 in the PTZ direction, and drives the optical unit 408 in the PTZ direction under the control of the control unit 401 .

[0064] Note that the zoom function of this embodiment is not limited to optical zoom, which changes the focal length by moving a zoom lens, but may be digital zoom, which cuts out and enlarges a portion of the captured image data, or a combination of optical zoom and digital zoom.

[0065] [Control process] Next, with reference to Figures 3 to 10, a control process for tracking a tracking subject by switching between a mode in which WS100 controls the sub-camera 400 based on an overhead image and a mode in which EB200 controls the sub-camera 400 based on a sub-image will be described.

[0066] First, the functional configuration of the WS 100 and the EB 200 for implementing the control process of this embodiment will be described with reference to FIGS.

[0067] Each function of the WS 100 and the EB 200 is realized by hardware and / or software. If the functional units shown in Fig. 3 are configured by hardware instead of by software, it is sufficient to have a circuit configuration corresponding to each functional unit in Fig. 3.

[0068] The WS 100 includes an image recognition unit 121, an object of interest determination unit 122, a tracking target determination unit 123, a control information generation unit 124, a feature information determination unit 125, and a tracking state determination unit 126. Software for realizing these functions is stored in the non-volatile memory 103, and the control unit 101 loads it into the volatile memory 102 and executes it.

[0069] The EB 200 includes an image recognition unit 221, a tracking target determination unit 222, and a control information generation unit 223. These pieces of software are stored in the non-volatile memory 203, and the control unit 201 loads them into the volatile memory 202 and executes them.

[0070] Fig. 4(a) is a flowchart showing the basic operation of the WS 100. Fig. 4(b) is a flowchart showing the basic operation of the EB 200. Fig. 4(c) is a flowchart showing the operation of the overhead camera 300. Fig. 4(d) is a flowchart showing the operation of the sub-camera 400.

[0071] First, the software functions and basic operations of the WS 100 will be described with reference to FIG. 3 and FIG. 4(a).

[0072] In step S101, the control unit 101 transmits a shooting command to the overhead camera 300 using a predetermined protocol via the communication unit 105, receives an overhead image from the overhead camera 300, stores it in the volatile memory 102, and advances the process to step S102.

[0073] In step S102, the control unit 101 executes the function of the image recognition unit 121 in FIG. 3, and the process proceeds to step S103.

[0074] The image recognition unit 121 controls the inference unit 104, the volatile memory 102, and the non-volatile memory 103, and performs the following object recognition process.

[0075] The image recognition unit 121 receives the overhead image IMG of the overhead camera 300 read from the volatile memory 102 and reference position information REF_POSI of the overhead camera 300. The position information REF_POSI of the overhead camera 300 includes information on the position of the overhead camera 300 and marker coordinates. The image recognition unit 121 detects the subject and calculates feature information based on the overhead image IMG of the overhead camera 300 and the reference position information REF_POSIREF_POSI. The image recognition unit 121 then outputs coordinate information POSITION[n] indicating the position of the detected subject, ID[n] indicating identification information of the detected subject, and STAT[n] indicating feature information of the detected subject. The position of the overhead camera 300 is a position in a coordinate space in which the shooting area of ​​the overhead camera 300 is viewed from directly above, and is known in advance by being measured by a user operation or a sensor (not shown). The marker coordinates are position information of a marker placed in a coordinate space in which the shooting area of ​​the overhead camera 300 is viewed from directly above in order to calculate a homography transformation matrix (described later), and are known values ​​measured in advance manually or by a sensor (not shown). The marker is a mark having a color different from the color of the floor, ground, etc., and may be any type as long as it can be measured by a user operation or a sensor (not shown). For example, if the sensor (not shown) is a camera, the marker position is obtained by extracting the color of the marker from an image captured by making the marker a mark of any color. The position of the overhead camera 300 and the marker coordinates may be input by the user via the operation unit 106 of the WS 100, and the control unit 101 may store them in the volatile memory 102. The reference position information REF_POSI and the subject coordinate information POSITION[n] are expressed in a coordinate system converted into a coordinate space in which the shooting area of ​​the overhead camera 300 is viewed from directly above. n is an index indicating the number of subjects detected, and for example, when the inference unit 104 detects three people, the POSITION, ID, and STAT for the three people are output as the inference result. The control unit 101 stores the subject recognition result by the image recognition unit 121 in the volatile memory 102. The subject detection process and the feature information calculation process will be described in detail later.

[0076] Here, a method for calculating the subject coordinate information POSITION by the image recognition unit 121 will be described.

[0077] First, with reference to FIG. 5, the relationship between the coordinate system of the overhead image of the overhead camera 300 and the coordinate system when the shooting area of ​​the overhead camera 300 is viewed from directly above will be described.

[0078] In order to calculate a pan value such that the shooting direction of the sub camera 400 is the direction of the tracking subject, the calculation is simplified by calculating the angle in a plane coordinate space perpendicular to the axis along which the sub camera 400 performs the panning operation. For example, when the sub camera 400 is installed perpendicular to a ground surface (reference position) such as a floor or the ground, the coordinate space perpendicular to the axis along which the sub camera 400 performs the panning operation is a coordinate space parallel to the reference position (a coordinate space in which the space in which the sub camera 400 and the subject are located is viewed from directly above) shown in FIG. 5(b). In this embodiment, it is assumed that the sub-camera 400 is installed perpendicular to the reference position, and the pan value is calculated in a coordinate system in which the shooting area of ​​the overhead camera 300 is viewed from directly above. That is, the subject position detected in the coordinate system of the overhead image of the overhead camera 300 shown in Fig. 6(a) (hereinafter, overhead camera coordinate system) is converted to a coordinate system in which the shooting area of ​​the overhead camera 300 is viewed from directly above (hereinafter, planar coordinate system) shown in Fig. 5(b). The coordinate conversion is performed using the homography conversion matrix H according to the following formula 1. (Formula 1) TIFF2025038858000002.tif19155In Equation 1, x and y are the horizontal and vertical coordinates in the overhead camera coordinate system, and X and Y are the horizontal and vertical coordinates in the plane coordinate system.

[0079] The control unit 101 reads out the reference position information REF_POSI from the volatile memory 102, and substitutes the marker coordinates Mark_A to Mark_D shown in FIGS. 5(a) and 5(b) included in the reference position information REF_POSI into Equation 1 to calculate the homography transformation matrix H. The marker coordinates are values ​​in a planar coordinate system. By using Equation 1, any coordinate in the overhead camera coordinate system of FIG. 4(a) can be mapped to any coordinate in the planar coordinate system of FIG. 4(b). In the example of FIG. 4, the control unit 101 can grasp the positions of the subjects A, B, and C included in the overhead image IMG of the overhead camera 300 in the planar coordinate system of FIG. 4(b). The control unit 101 stores the homography transformation matrix H calculated by the above Equation 1 in the volatile memory 102.

[0080] Next, a method for detecting the subject position using an inference model for subject detection and a method for converting the subject position into a planar coordinate system will be described.

[0081] In this embodiment, subject detection is performed by performing image recognition processing using a trained inference model for subject detection that has been created by performing machine learning such as deep learning.

[0082] The inference model for subject detection receives an overhead image as input and outputs coordinate information on the image of the subject contained in the overhead image.

[0083] The control unit 101 detects subjects by performing image recognition processing using an inference model for subject detection with the inference unit 104 using the overhead image IMG of the overhead camera 300 as input. Fig. 6(a) shows an example in which subjects detected by the inference unit 104 are displayed in rectangular frames. As shown in Fig. 6(a), the coordinates of rectangular parts circumscribing subjects A, B, and C detected from the overhead image are detected as subject positions. The control unit 101 stores coordinate information of the subject detected from the overhead image in the volatile memory 102. Note that, in the present embodiment, an example of subject detection by inference processing using a trained model has been described, but the present invention is not limited to this. For example, a method called the SIFT method, which detects by matching local feature points in an image, or a template matching method, which detects by calculating the similarity with a template image, may be used.

[0084] Furthermore, the control unit 101 converts the bottom end of the rectangular part of the subject detected in the overhead camera coordinate system shown in Fig. 6(a) into the planar coordinate system shown in Fig. 6(b) as the subject detection position (the coordinates of the person's feet in the example of Fig. 6). For example, the control unit 101 reads out the homography transformation matrix H from the volatile memory 102 and substitutes the coordinates (xa, ya) of the feet of subject A in the overhead camera coordinate system into x and y in Equation 1, thereby making it possible to convert the coordinates into the foot coordinates (XA, YA) in the planar coordinate system. Similarly, it is possible to calculate the foot coordinates (XB, YB) of subject B and the foot coordinates (XC, YC) of subject C in the plane coordinate system for the foot coordinates (xb, yb) of subject B and the foot coordinates (xc, yc) of subject C. The control unit 101 writes the foot coordinates in the volatile memory 102 as the position coordinates POSITION of the subject.

[0085] Next, a method for generating identification information ID and feature information STAT of a subject by image recognition unit 121 will be described.

[0086] The control unit 101 inputs the subject coordinate information POSITION, which is the inference result of the inference model for subject detection, and the overhead image of the overhead camera 300 into the learned inference model for subject identification created by machine learning such as deep learning using the inference unit 104, and outputs identification information ID and feature information STAT by performing inference processing. The inference model for subject identification is different from the inference model for subject detection.

[0087] Here, we will explain the inference model for subject identification.

[0088] The inference model for subject identification in this embodiment is a trained model that has been trained to increase the similarity of feature information for images of the same subject using training data that is a collection of data associating a set of images of a specific subject taken from multiple different shooting directions with information that can identify the specific subject, the number of which is equal to the number of subjects.By inputting an image of the subject cut out based on the coordinate position POSITION of the subject, which is the output of the inference model for subject detection, into the inference model for subject identification, feature information STAT is output. When an image of the same subject taken with a different camera is input, the output feature information has a higher similarity to the feature information STAT compared to when an image of a different subject is input. Feature information can be a multidimensional vector of the response of the convolution layer of a convolutional neural network. Similarity will be discussed later.

[0089] The inference model for subject detection and the inference model for subject identification are stored in the non-volatile memory 103 before the control process of this embodiment is started.

[0090] The image recognition unit 121 also assigns identification information ID of the subject corresponding to the feature information that is the inference result of the inference model for identifying the subject. Furthermore, the image recognition unit 121 calculates the similarity of the feature information of each image of the subject obtained by inputting the image of each subject detected by the inference model for detecting the subject using the images of the current frame and the past frame as input to the inference model for identifying the subject. The similarity is calculated using cosine similarity. The more similar the multidimensional vectors, which are the feature information of each subject image, the closer the cosine similarity is to 1, and the more different they are, the closer the cosine similarity is to 0. The same ID is assigned to subjects with the closest similarity between the past and current frames. Note that the method of calculating the similarity is not limited to this, and any method may be used as long as it outputs a higher value when the feature information is closer and outputs a lower value when the feature information is more distant. In this embodiment, feature information is used to assign IDs, but the present invention is not limited to this. A method may be used in which the position and size of the rectangular information of the detected subject is compared between the current frame and the past frame using rectangular information of the subject obtained by an inference model for subject detection, and the same ID is assigned to the subject that is closest to the position of the rectangular information, by predicting the position of the rectangular information of the current frame from the transition of the position of the rectangular information for the same ID in the past few frames using a Kalman filter or the like, and assigning the same ID to the subject that is closest to the position of the predicted rectangular information. An ID may be assigned by combining these methods. By using this method, it is possible to improve the accuracy of ID assignment when a similar-looking subject suddenly enters the shooting field of view.

[0091] As described above, the image recognition unit 121 performs inference processing using an inference model for subject detection with the overhead image of the overhead image 300 as input, outputs the coordinate position POSITION of the subject, and stores it in the volatile memory 102. The image recognition unit 121 also inputs the subject coordinate information POSITION, which is the inference result of the inference model for subject detection, and the overhead image of the overhead camera 300 to an inference model for subject identification to perform inference processing. Then, the image recognition unit 121 outputs the identification information ID and feature information STAT as the result of the inference processing, and stores it in the volatile memory 102.

[0092] Returning to the description of FIG. 4, in step S103, the control unit 101 executes the function of the target subject determination unit 122 in FIG. 3, and advances the process to step S104.

[0093] The target subject determining unit 122 determines a target subject MAIN_SUBJECT from operation information input by the user via the operation unit 106 and coordinate information of the subject, which is the subject recognition result by the image recognition unit 121 read from the volatile memory 102 .

[0094] The control unit 101 displays the overhead image captured by the overhead camera 300 and the subject recognition results in the volatile memory 102 on the display unit 111 of the WS 100. The control unit 101 allows the user to select a subject of interest from among the subjects displayed as subject recognition results via the operation unit 106. For example, if the operation unit 106 is a mouse, the user can click and select one of the subjects displayed on the display unit 111. The control unit 101 saves the identification information ID corresponding to the subject of interest selected by the user in the volatile memory 102 as the subject of interest MAIN_SUBJECT.

[0095] In step S104, the control unit 101 executes the function of the tracking target determination unit 123 in FIG. 3, and advances the process to step S105.

[0096] The tracking target determining unit 123 determines a tracking subject SUBJECT_ID of the sub camera 400 from the target subject MAIN_SUBJECT determined by the target subject determining unit 122 .

[0097] Here, a method for determining a subject to be tracked by the sub camera 400 will be described.

[0098] The control unit 101 reads out the target subject MAIN_SUBJECT determined by the target subject determination unit 122 from the volatile memory 102, and determines the target subject MAIN_SUBJECT as the tracking subject SUBJECT_ID of the sub camera 400. In this way, by setting the same subject as the target subject MAIN_SUBJECT selected by the user as the tracking subject SUBJECT_ID of the sub camera 400, it is possible to control the sub camera 400 with the subject selected by the user as the tracking target.

[0099] The method of determining the tracking subject is not limited to the above method, and may be determined using information on the target subject MAIN_SUBJECT and identification information ID read from the volatile memory 102. For example, when multiple subjects are included in the overhead image of the overhead camera 300 and multiple sub-cameras 400 are installed, one sub-camera may track the same subject as the target of interest, and another sub-camera may track a different subject from the target of interest. By determining the tracking subject in this way, multiple subjects included in the overhead image of the overhead camera 300 can be tracked comprehensively for each sub-camera. There is also a method of reading out the coordinate information POSITION, identification information ID, and REF_POSI including the sub camera position of the subject from the volatile memory 102, and determining the subject closest to the sub camera among the subjects detected from the overhead image of the overhead camera 300 as the tracking subject. By determining the tracking subject in this manner, it is possible to set the subject that is easiest to fit into the angle of view from the position of the sub camera as the tracking target. The control unit 101 stores the tracking subject SUBJECT_ID determined as described above in the volatile memory 102, and also stores the identification ID of the tracking subject before it was stored in the volatile memory 102 as the past tracking subject ID.

[0100] In step S105, the control unit 101 executes the function of the feature information determination unit 125 to transmit feature information corresponding to the tracking subject of the sub camera 400 to the EB 200. In addition, the control unit 101 executes the function of the tracking state determination unit 126 to update the tracking state information STATE, store it in the volatile memory 102, and proceeds to step S106.

[0101] The tracking state information STATE includes any one of the following information: "Tracking by WS100" and "Tracking by EB200". "Tracking by WS100" indicates a state in which WS100 is tracking a tracking subject by controlling the sub-camera 400. "Tracking by EB200" indicates a state in which EB200 is tracking a tracking subject by controlling the sub-camera 400. The process of step S105 will be described later in detail.

[0102] In step S106, the control unit 101 reads the tracking state information STATE from the volatile memory 102, and determines whether "tracking by WS100" or "tracking by EB200" based on the tracking state information STATE. If the control unit 101 determines that "tracking by WS100" is true, the process proceeds to step S107, and if the control unit 101 determines that "tracking by EB200" is true, the process returns to step S101.

[0103] In step S107, the control unit 101 executes the function of the control information generating unit 124 in FIG. 3, and the process proceeds to step S108.

[0104] The control information generating unit 124 calculates pan / tilt values ​​PT_VALUE of the sub camera 400 for tracking the tracking subject SUBJECT_ID determined by the tracking target determining unit 123 by the sub camera 400. The control unit 101 reads out coordinate information of the sub camera 400 in a planar coordinate system included in the reference position information REF_POSI and coordinate information POSITION of the detected subject from the volatile memory 102. Then, the control unit 101 calculates pan / tilt values ​​such that the shooting direction of the sub camera 400 is the direction of the tracking subject from the coordinate information of the subject corresponding to the tracking subject SUBJECT_ID.

[0105] Here, a method for calculating the pan value will be described with reference to FIG.

[0106] As shown in FIG. 7, the angle θ between a line extending from the center of the optical axis of the sub-camera 400 and a line connecting the sub-camera 400 and the tracking subject SUBJECT_ID can be calculated by the following formula 2. (Formula 2) TIFF2025038858000003.tif19155 In Equation 2, px and py are the horizontal and vertical coordinates of the position of the tracked subject, and subx and suby are the horizontal and vertical coordinates of the position of the sub-camera 400. px and py can be found from the coordinate information POSITION of the detected subject by referring to the coordinate information corresponding to the tracked subject SUBJECT_ID.

[0107] The control information generator 124 calculates the pan value of the sub camera 400 based on the angle θ.

[0108] Next, a method for calculating the tilt control value will be described with reference to FIG.

[0109] As shown in FIG. 8, the height h1 of the optical axis of the sub-camera 400 is taken as the angle ρ between a line extending from the center of the optical axis of the sub-camera 400 and a line extending toward the height h2 of a specific part of the tracked subject (in the case of a person, the height of the face), and the angle ρ can be calculated using the following equations 3 and 4. (Formula 3) TIFF2025038858000004.tif13155 (Formula 4) TIFF2025038858000005.tif19155 In formula 4, h1 is the height of the sub-camera 400 from the ground surface, and h2 is the height from the ground surface to a predetermined part of the tracking subject (in the case of a person, the face). h1 and h2 may be stored in the volatile memory 102 in advance, or may be measured in real time using a sensor (not shown).

[0110] The control information generator 124 calculates a tilt control value for the sub camera 400 based on the angle ρ.

[0111] The pan value / tilt value may be a speed value for directing the sub camera 400 toward the tracking subject. The method of calculating the pan value / tilt value is as follows: first, the control unit 101 acquires the current pan value / tilt value of the sub camera 400 from the EB 200. Next, the control unit 101 calculates a pan angular velocity proportional to the difference with the pan value θ read from the volatile memory 102. The control unit 101 also calculates a tilt angular velocity proportional to the difference with the tilt control value ρ read from the volatile memory 102. Then, the control unit 101 stores the calculated control value in the volatile memory 102.

[0112] In step S108, the control unit 101 reads the pan value / tilt value from the volatile memory 102, converts them into control commands according to a predetermined protocol for controlling the sub camera 400, stores them in the volatile memory 102, and proceeds to step S109.

[0113] In step S109, the control unit 101 transmits a control command according to the pan value / tilt value calculated in step S108 to the sub-camera 400 via the communication unit 105, and returns the process to step S101.

[0114] The above is the basic operation of the WS100.

[0115] Next, the function and basic operation of the EB 200 will be described with reference to FIG. 3 and FIG. 4(b).

[0116] In step S201, the control unit 201 transmits a shooting command to the sub-camera 400 via the communication unit 205, receives a captured sub-image from the sub-camera 400, stores the captured sub-image in the volatile memory 202, and advances the process to step S202.

[0117] In step S202, the control unit 201 executes the function of the image recognition unit 221 in FIG. 3, and advances the process to step S203.

[0118] The image recognition unit 221 has the same functions as the image recognition unit 121 of the WS 100. The control unit 201 inputs the sub-image of the sub-camera 400 read from the volatile memory 202 by the inference unit 204 into a trained model created by performing machine learning such as deep learning, and performs inference processing. The inference result includes coordinate information POSITION of the subject detected from the sub-image of the sub-camera 400, feature information STAT_SUB[m], and identification information ID for each subject, and is stored in the volatile memory 202. Note that the trained model used for the inference processing of the image recognition unit 221 is a common model (inference model for subject detection, inference model for subject identification) with the trained model used by the image recognition unit 121 of the WS 100.

[0119] In step S203, the control unit 201 receives the feature information STAT of the subject from the WS 100 via the communication unit 205, and compares it with the feature information STAT_SUB calculated from the sub-image of the sub-camera 400 using the function of the tracking target determination unit 222 in Fig. 3. If a subject having a high similarity between the feature information STAT and the feature information STAT_SUB is present within the shooting angle of view of the sub-camera 400, the control unit 201 determines the identification information ID of the subject as the identification information ID of the subject to be tracked by the sub-camera 400 = SUBJECT_ID, stores it in the volatile memory 102, and proceeds to step S204. The method of calculating the similarity will be described in detail later.

[0120] In step S204, the control unit 201 checks the communication state for the WS 100 to stop tracking or continue tracking via the communication unit 205, performs processing according to the communication content, and proceeds to step S205. The processing in step S204 will be described in detail later.

[0121] In step S205, the control unit 201 determines whether or not information on the SUBJECT_ID of the tracking subject is stored in the volatile memory 202. If the control unit 201 determines that information on the SUBJECT_ID of the tracking subject is stored in the volatile memory 202, that is, that the identification information ID of the tracking subject of the sub camera 400 is stored in the volatile memory 102, the process proceeds to step S206. If the control unit 201 determines that information on the SUBJECT_ID of the tracking subject is not stored in the volatile memory 202, that is, that the identification information ID of the tracking subject of the sub camera 400 is not stored in the volatile memory 102, the process returns to step S201.

[0122] In step S206, the control unit 201 reads out the identification information ID for each subject, which is the subject recognition result in step S202, from the volatile memory 202, and determines whether or not the tracking subject SUBJECT_ID exists in the sub-image of the sub-camera 400. If the control unit 201 determines that the tracking subject SUBJECT_ID exists in the sub-image, the process proceeds to step S207, and if it determines that the tracking subject SUBJECT_ID does not exist, the process returns to step S201.

[0123] In step S207, the control unit 101 executes the function of the control information generating unit 223 in FIG. 3, and proceeds to step S208.

[0124] The control information generating unit 223 has a function of calculating the pan value / tilt value of the sub camera 400. The control unit 201 reads out the subject coordinate information POSITION and the tracking subject SUBJECT_ID from the volatile memory 202, and specifies the current position of the tracking subject corresponding to the tracking subject SUBJECT_ID. The control unit 201 reads out the past positions of the tracking subject within the shooting angle of view from the volatile memory 202, and calculates the angular velocity of the pan to be larger if there is a large difference in the horizontal direction between the current position of the tracking subject and the past position of the tracking subject, and calculates the angular velocity of the tilt to be larger if there is a large difference in the vertical direction. The control unit 201 saves the pan value / tilt value in the volatile memory 202.

[0125] In step S208, the control unit 201 converts the pan / tilt values ​​read from the volatile memory 202 into control commands in accordance with a predetermined protocol for controlling the sub camera 400, stores the control commands in the volatile memory 202, and proceeds to step S209.

[0126] In step S209, the control unit 201 transmits a control command corresponding to the pan value / tilt value calculated in step S208 to the sub-camera 400 via the communication unit 205, and returns the process to step S101.

[0127] The above is the basic operation of the EB200.

[0128] As described above, WS100 performs image recognition processing on the overhead image of overhead camera 300, and controls the panning / tilting operations of sub camera 400 when the tracking state information STATE is "tracking by WS100". It does not control the panning / tilting operations of sub camera 400 when it is "tracking by EB200". EB200 performs image recognition processing on the sub image of sub camera 400, and controls the panning / tilting operations of sub camera 400 when a tracking subject is set and detected from the sub image. It does not control the panning / tilting operations of sub camera 400 when a tracking subject is not set. 9, it is possible to switch between the WS 100 and the EB 200 controlling the sub-camera 400 by updating the tracking state information STATE and the settings of the tracked subject. Note that by transmitting the pan / tilt values ​​only from one device controlling the sub-camera 400 and not transmitting them when the other device is in control, it is possible to reduce the amount of communication compared to transmitting the pan / tilt values ​​for each process in FIGS. 4(a) and (b).

[0129] Next, the operation of the overhead camera 300 when a shooting command is received from the WS 100 will be described with reference to FIG.

[0130] In step S301, the control unit 301 receives a shooting command from the WS 100 via the communication unit 305, and the process proceeds to step S302.

[0131] In step S302, the control unit 301 starts an image capturing process in response to receiving an image capturing command via the communication unit 305, and proceeds to step S303. The control unit 301 captures an image using the imaging unit 306, and stores the generated image data in the volatile memory 302 after performing predetermined image processing using the image processing unit 307.

[0132] In step S 303 , the control unit 301 reads the image data from the volatile memory 302 , and transmits it to the WS 100 via the communication unit 305 .

[0133] The operation of the overhead camera 300 has been described above.

[0134] Next, the operation of the sub-camera 400 that receives a control command from the WS 100 or the EB 200 will be described with reference to FIG.

[0135] In step S401, the control unit 401 receives a control command via the communication unit 405, stores the control command in the volatile memory 402, and advances the process to step S402.

[0136] In step S402, the control unit 401 reads out the pan / tilt values ​​from the volatile memory 402 in response to receiving a control command from the communication unit 405, and advances the process to step S403.

[0137] In step S403, the control unit 401 calculates drive parameters for controlling the pan operation / tilt operation at a desired speed in a desired direction based on the pan value / tilt value read from the nonvolatile memory 403, and proceeds to step S404. The drive parameters are parameters for controlling the actuators for the pan / tilt directions included in the PTZ drive unit 409, and the pan value / tilt value included in the control command is converted into the drive parameters by referring to a conversion table stored in the nonvolatile memory 403.

[0138] In step S404, the control unit 401 controls the optical unit 408 by the PTZ driving unit 409 based on the driving parameters obtained in step S403, and changes the shooting direction of the sub camera 400. The PTZ driving unit 409 changes the shooting direction of the sub camera 400 by driving the optical unit 408 in the pan / tilt direction based on the driving parameters.

[0139] The operation of the sub-camera 400 has been described above.

[0140] Next, the control process of the WS 100 will be described with reference to FIG.

[0141] FIG. 9(a) shows the control process of the WS 100, and shows the detailed process of step S105 in FIG. 4(a).

[0142] Part of the processing in FIG. 9(a) is realized by the control unit 101 executing the function of the tracking state determination unit 126 in FIG.

[0143] The tracking state determination unit 126 has a function of updating the tracking state information STATE stored in the volatile memory 102 .

[0144] In step S110, the control unit 101 reads out from the volatile memory 102 the SUBJECT_ID of the tracking subject of the sub camera 400 calculated in step S104 in Fig. 4A and the identification information ID indicating the previous tracking subject. Then, the control unit 101 compares the identification information read out from the volatile memory 102 to determine whether or not the tracking subject of the sub camera 400 has changed. If the control unit 101 determines that the tracking subject of the sub camera 400 has changed, the process proceeds to step S111, and if the control unit 101 determines that the tracking subject has not changed, the process proceeds to step S113.

[0145] In step S111, the control unit 101 transmits a tracking stop command to the EB 200 via the communication unit 105, and the process proceeds to step S112.

[0146] In step S112, the control unit 101 executes the function of the tracking state determination unit 126 in FIG. 3, and changes the tracking state information STATE to "tracking by WS 100".

[0147] When the tracking subject of the sub camera 400 is changed, there is a high possibility that the tracking subject is not present within the shooting angle of view of the sub camera 400. In this case, by performing the processes of steps S111 and S112, the WS 100 controls the sub camera 400 based on the overhead image of the overhead camera 300 instead of the sub camera 400.

[0148] In step S113, the control unit 101 reads the tracking state information STATE from the volatile memory 102, and determines whether "tracking by WS100" or "tracking by EB200" based on the tracking state information STATE. If the control unit 101 determines that "tracking by WS100" is true, the process proceeds to step S117, and if the control unit 101 determines that "tracking by EB200" is true, the process proceeds to step S114.

[0149] In step S114, the control unit 101 transmits a tracking continuation confirmation request to the EB200 via the communication unit 105, and inquires whether the EB200 can continue tracking the tracked subject. The response from the EB200 is "Continue tracking OK" or "Continue tracking NG." If the control unit 101 receives a notification of "Continue tracking OK" from the EB200, the process returns to step S101, and if the control unit 101 receives a notification of "Continue tracking NG" from the EB200, the process proceeds to step S115.

[0150] In step S115, the control unit 101 transmits a tracking stop command to the EB 200 via the communication unit 105, and the process proceeds to step S116.

[0151] In step S116, the control unit 101 executes the function of the tracking state determination unit 126 in FIG. 3, updates the tracking state information STATE to "tracking by WS 100", and ends the process.

[0152] By performing the processes from steps S114 to S116, when the tracking state is "tracking by EB200", tracking can be continued by WS100 even if the EB200 becomes unable to perform tracking.

[0153] In step S117, the control unit 101 determines whether or not a tracking subject is present within the shooting angle of view of the sub camera 400. If the control unit 101 determines that a tracking subject is present within the shooting angle of view of the sub camera 400, the control unit 101 advances the process to step S118. If the control unit 101 determines that a tracking subject is not present within the shooting angle of view of the sub camera 400, the control unit 101 ends the process. Whether or not a tracked subject is present within the shooting angle of view of the sub-camera 400 can be determined by comparing the current pan / tilt values ​​acquired by the control unit 101 from the sub-camera 400 with the new pan / tilt values ​​calculated in step S107 of Figure 4(a). When the current pan value / tilt value is sufficiently close to the new pan value / tilt value, it can be determined that the tracking subject is present within the shooting angle of view of the sub camera 400. Alternatively, when the pan / tilt speed value calculated in step S108 is sufficiently small, it can be determined that the tracking subject is present within the shooting angle of view of the sub camera 400 because the current pan value / tilt value is approaching the new pan value / tilt value.

[0154] In step S118, the control unit 101 acquires shooting information from the sub camera 400 to determine whether or not to trim the overhead image and the subject area to be trimmed, and proceeds to step S119. The details of the trimming process will be described later. Here, for the sake of simplicity, the description will be continued assuming that the trimming process is not performed.

[0155] In step S119, the control unit 101 executes the function of the feature information determining unit 125 in FIG. 3, and advances the process to S120.

[0156] The feature information determination unit 125 has a function of determining feature information of a subject being tracked by the sub camera 400, that is, feature information of the subject to be transmitted to the EB 200. The feature information determination unit 125 reads out feature information STAT[n] of the subject detected by the image recognition unit 121 from the overhead image of the overhead camera 300 from the volatile memory 102. The feature information determination unit 125 also reads out identification information SUBJECT_ID of the subject being tracked determined by the tracking target determination unit 123 from the volatile memory 102. Then, the feature information determination unit 125 determines feature information STAT[i] corresponding to the subject being tracked from the feature information STAT[n], and stores it in the volatile memory 102. i is an index indicating the subject being tracked.

[0157] In step S120, the control unit 101 transmits a tracking start command and feature information STAT[i] of the tracked subject to the EB 200 via the communication unit 105, and the process proceeds to step S121.

[0158] By the processing of steps S117 to S120, a tracking start command and feature information of the tracking subject can be transmitted to the EB200 only when there is a high possibility that the tracking subject is present within the shooting angle of view of the sub-camera 400. This makes it possible to reduce the amount of communication compared to the case where information is transmitted for each process of Fig. 4(a) and Fig. 9(a).

[0159] In step S121, control unit 101 receives the comparison result of the subject from EB 200 via communication unit 105. If control unit 101 receives match information from EB 200 indicating that the subjects match, the process proceeds to step S122, and if control unit 101 receives mismatch information indicating that the subjects do not match, the process ends.

[0160] In step S122, the control unit 101 executes the function of the tracking state determination unit 126 in FIG. 3, changes the tracking state information STATE to "Tracking by EB200", and ends the process.

[0161] Next, the control process of the EB 200 will be described with reference to FIGS.

[0162] FIG. 9B shows the control process of the EB 200, and shows the detailed process of step S203 in FIG.

[0163] In step S210, control unit 201 determines whether or not it has received from WS 100, via communication unit 205, a tracking start command and feature information STAT[i] of the tracking subject obtained from the overhead image of overhead camera 300. If control unit 201 has received the tracking start command and feature information STAT[i] of the tracking subject from WS 100, it proceeds to step S211;

[0164] In steps S211 to S214, the control unit 201 executes the function of the tracking target determination unit 222 in FIG. 3, and determines whether the feature information STAT[i] received from the WS 100 and the feature information STAT_SUB[m] obtained from the sub-image of the sub-camera 400 satisfy a predetermined condition.

[0165] The tracking target determination unit 222 has a function of calculating a similarity between the feature information STAT[i] received from the WS 100 and the feature information STAT_SUB[m] obtained from the sub-image of the sub-camera 400. The tracking target determination unit 222 also has a function of comparing a threshold value stored in the volatile memory 102 with the similarity of the feature information and storing the comparison result in the volatile memory 102. For example, when two people are present in the sub-image of the sub-camera 400, the tracking target determination unit 222 calculates the similarity between the feature information of the two people (STAT_SUB[1], STAT_SUB[2]) and the feature information STAT[i] received from the WS 100. The similarity is calculated as the cosine similarity between the feature information vectors, and a value between 1 and 0 is obtained as the similarity. The control unit 201 stores the similarities calculated for the m subjects in the volatile memory 202.

[0166] In step S211, the control unit 201 executes the function of the tracking target determination unit 222 in FIG. 3 to perform a comparison process of the feature information, and proceeds to step S212.

[0167] In step S212, control unit 201 determines whether or not a subject with highly similar feature information exists, based on the comparison result in step S211. The existence of a subject with highly similar feature information means that the same subject is photographed by overhead camera 300 and sub camera 400. If control unit 201 determines that a subject with highly similar feature information exists, control unit 201 proceeds to step S214, and if control unit 201 determines that a subject with highly similar feature information does not exist, control unit 201 proceeds to step S213.

[0168] The control unit 201 reads a predetermined threshold value from the volatile memory 202, and determines that a subject with high similarity in feature information exists if the similarity is equal to or greater than the threshold value as a predetermined condition, or if a subject with a higher similarity exists, or if the subjects match, and stores the identification information ID of the subject in the volatile memory 202. Furthermore, the control unit 201 updates information MATCH, which indicates whether or not there is a subject with high similarity in feature information, and stores the information in the volatile memory 202. In this embodiment, if the value of MATCH is 0, there is no subject with high similarity in feature information, i.e., the subjects do not match between the overhead camera 300 and the sub camera 400. If the value of MATCH is 1, there is a subject with high similarity in feature information, i.e., the subjects match between the overhead camera 300 and the sub camera 400. If a subject with highly similar feature information is present, the control unit 201 stores MATCH=1 in the volatile memory 202 and proceeds to step S214. If a subject with highly similar feature information is not present, the control unit 201 stores MATCH=0 in the volatile memory 202 and proceeds to step S213.

[0169] Here, the similarity of feature information of a subject detected from the overhead image captured by the overhead camera 300 and the sub-image captured by the sub camera 400 will be described with reference to FIG.

[0170] Fig. 10(a) shows the positional relationship between the shooting position and shooting direction of the overhead camera 300 and the shooting position and shooting direction of the sub camera 400. Fig. 10(b) shows the subject detected from the overhead image of the overhead camera 300 and the tracked subject.

[0171] Assume that subjects A, B, and C are detected from the overhead image of overhead camera 300, and the subject being tracked by sub camera 400 is subject C. The feature information of the subject being tracked by sub camera 400 transmitted from sub camera 400 to WS 100 is information corresponding to subject C. Figures 10(c) and (e) show the sub-images of sub camera 400, and Figures 10(d) and (f) show the similarity between the feature information of the subject being tracked by sub camera 400 and the feature information of the subject detected from the sub-image.

[0172] As shown in Fig. 10(c), when the sub camera 400 is photographing subjects A and B, the similarity is calculated between the feature information of subject C in the overhead image of the overhead camera 300 and each feature information of subject A or subject B in the sub image of the sub camera 400. As shown in Fig. 10(d), the similarity is low between the feature information of subject C in the overhead image of the overhead camera 300 and the feature information of subject A or subject B in the sub image of the sub camera 400. In this case, for example, when the threshold value of the subject similarity is 0.7, the result is that both subjects A and B do not match.

[0173] 10(e), when sub camera 400 is capturing images of subjects B and C, the similarity is calculated between feature information of subject C in the overhead image of overhead camera 300 and feature information of subject B or subject C in the sub-image of sub camera 400. Subject C in the overhead image of overhead camera 300 and subject C in the sub-image of sub camera 400 have different shapes in the images because the camera shooting positions and directions are different. For example, when subject C faces or faces toward overhead camera 300, subject C faces forward in the overhead image of overhead camera 300, and faces closer to the side in the sub-image of sub-camera 400. The inference model for identifying the subject in image recognition unit 121 of WS100 and image recognition unit 221 of EB200 is a model that learns images of the same subject photographed from multiple different directions. For this reason, the similarity of feature information is high even if the same subject photographed by multiple cameras with different shooting positions and directions has different morphology in each photographed image. 10(f), the similarity between the feature information of subject C in the overhead image captured by overhead camera 300 and the feature information of subject C in the sub-image captured by sub camera 400 becomes high. As a result, for example, when the threshold value of the subject similarity is 0.7, subject B is determined to be a mismatch and subject C is determined to be a match, and subject C can be determined to be the same subject.

[0174] Returning to the explanation of FIG. 9B, in step S213, the control unit 201 reads MATCH=0 from the volatile memory 202, transmits it to the WS 100 via the communication unit 205, and ends the process.

[0175] In step S214, the control unit 201 reads out the identification information ID of the subject for which the highest similarity has been calculated from the volatile memory 102, stores it in the volatile memory 102 as the tracking subject SUBJECT_ID, and proceeds to step S215. By selecting the subject for which the highest similarity has been calculated, even if there are subjects wearing similar clothes, for example, the most likely subject among them can be set as the tracking target.

[0176] In step S215, the control unit 201 reads MATCH=1 from the volatile memory 202, transmits it to the WS 100 via the communication unit 205, and ends the process.

[0177] FIG. 9C shows the control process of the EB 200, and shows the detailed process of step S204 in FIG.

[0178] In step S220, the control unit 201 determines whether or not a tracking stop command has been received from the WS 100 via the communication unit 205. If a tracking stop command has been received from the WS 100, the control unit 201 proceeds to step S221, and if not, the control unit 201 proceeds to step S223.

[0179] In step S221, the control unit 201 transmits a control command to stop the panning / tilting operation to the sub-camera 400 via the communication unit 205, and the process proceeds to step S222.

[0180] In step S222, the control unit 201 deletes the tracking subject SUBJECT_ID stored in the volatile memory 202, and the process proceeds to step S201.

[0181] In step S223, the control unit 201 determines whether or not a tracking continuation confirmation request has been received from the WS 100 via the communication unit 205. If a tracking continuation confirmation request has been received from the WS 100, the control unit 201 proceeds to step S224, and if not, the control unit 201 ends the process.

[0182] In step S224, the control unit 201 reads out the subject recognition result by the image recognition unit 221 from the volatile memory 202, and determines whether or not the tracking subject SUBJECT_ID is detected. If the control unit 201 determines that the tracking subject SUBJECT_ID is detected by the image recognition unit 221, the process proceeds to step S226, and if not, the process proceeds to step S225.

[0183] In step S225, the control unit 201 transmits "Continue tracking NG" to the WS 100 via the communication unit 205, and the process returns to step S201.

[0184] In step S226, the control unit 201 transmits "Continue tracking OK" to the WS 100 via the communication unit 205, and ends the process.

[0185] The above is the detailed control process of the EB200.

[0186] Next, the trimming process in step S118 in Fig. 9(a) will be described. Fig. 11 is a diagram for explaining the relationship between the subject to be tracked and the shooting angle of view, and a method for calculating the amount of trimming of the overhead image so that the size of the subject to be tracked in the overhead image and the size of the subject to be tracked in the sub-image match will be described. In this embodiment, an example in which control is performed based on the vertical size as the size of the subject to be tracked will be described.

[0187] As shown in FIG. 11(a), in the overhead image of overhead camera 300, the entire tracking subject C is within the shooting angle of view of overhead camera 300, whereas in the sub-image of sub camera 400 shown in FIG. 11(c) where only a portion of tracking subject C is within the shooting range (where a portion of the subject is outside the shooting angle of view (the subject is cut off), there is a possibility that the similarity between the characteristic information of the tracking subject extracted from the overhead image of overhead camera 300 and the characteristic information of the tracking subject extracted from the sub-image of sub camera 400 will decrease. For example, this is the case where characteristic information of the entire body of a person as the tracking subject is extracted from the overhead image of overhead camera 300, whereas characteristic information is extracted only from the face of the tracking subject from the sub-image of sub camera 400.

[0188] When there is a large difference between the size of the tracked subject in the overhead image of overhead camera 300 (hereinafter, the tracked subject size in the overhead image) and the size of the tracked subject in the sub-image of sub camera 400 (hereinafter, the tracked subject size in the sub-image), the similarity of the feature information described in Figure 10(f) decreases, and there is a possibility that subjects that actually match will be determined to be mismatched.

[0189] Therefore, in this embodiment, when the difference between the size of the tracking subject in the overhead image and the size of the tracking subject in the sub-image is large, the amount of trimming of the overhead image is controlled so that the size of the tracking subject in the overhead image and the size of the tracking subject in the sub-image become closer to each other. This makes it possible to prevent the subject from being cut off, thereby reducing the decrease in similarity of the feature information due to the subject being cut off.

[0190] FIG. 11(b) shows the relationship between the tracking subject and the shooting angle of view of the overhead camera 300. FIG. 11(d) shows the relationship between the tracking subject and the shooting angle of view of the sub-camera 400. In FIG. 11, the camera height is hcam, the vertical angle of view is φ, the vertical field of view is H, the distance to the tracking subject is L, and the height of the entire subject (the actual height of the subject in real space) is hobj. In FIG. 11(b), the vertical field of view H includes the ground at the position of the subject, so if the entire height hobj of the subject is less than the vertical field of view H, a part of the subject does not fall outside the field of view. In FIG. 11(d), the vertical field of view H does not reach the ground at the position of the subject, so a part of the subject falls outside the field of view. In FIG. 11, the height hview of the subject in the vertical field of view, which is the size of the tracking subject of the overhead camera 300 and the sub-camera 400, can be calculated by the following formula 5. (Formula 5) In this embodiment, the amount of trimming is determined from the relationship between the size information hview of the subject in the vertical field of view H and the overall size information hobj of the subject in the above formula 5. This makes it possible to determine the subject area for calculating feature information according to the size information of the subject in the vertical field of view H.

[0191] FIG. 12 illustrates the trimming process in step S118 of FIG.

[0192] In step S123, control unit 101 reads out subject information from volatile memory 102. The subject information is the overall height hobj of the subject described in FIG. 11. The subject information is set in advance by a user operation via operation unit 106 or a setting instruction via communication unit 105, and is stored in volatile memory 102. Note that the subject information may be read out from volatile memory 102 or non-volatile memory 103 so as to be automatically selected according to the type of subject. Control unit 101 stores the subject information in volatile memory 102, and proceeds to step S124.

[0193] In step S124, the control unit 101 acquires shooting information from the overhead camera 300 and the sub camera 400 via the communication unit 105. The shooting information is information for calculating the vertical field of view H shown in FIG. 11. The vertical field of view H can be calculated using the following formulas 6 and 7. The distance L can be calculated using the above formula 3, and the vertical angle of view φ can be calculated from the vertical size s of the image sensors of the overhead camera 300 and the sub camera 400 and the focal length f at the time of acquiring the information. Therefore, the control unit 101 can calculate the vertical field of view H by acquiring information on the vertical size s and focal length f of the image sensors from the overhead camera 300 and the sub camera 400. (Formula 6) TIFF2025038858000007.tif13155 (Formula 7) TIFF2025038858000008.tif13155 The control unit 101 stores the subject information acquired from the overhead camera 300 and the sub-camera 400 in the volatile memory 102, and the process proceeds to step S125.

[0194] In step S125, the control unit 101 compares the overall size information hobj of the subject with the size information hview of the subject in the vertical field of view H. The control unit 101 reads out the information saved in steps S123 and S124 from the volatile memory 102, and calculates the vertical field of view H. Next, the control unit 101 calculates the height hview of the subject within the field of view using the vertical field of view H. The control unit 101 then calculates the ratio of the height hview of the subject to the height hobj of the subject as the degree of agreement r with the overhead image using the following Equation 8, saves the calculated degree of agreement r with the overhead image in the volatile memory 102, and proceeds to step S126. (Formula 8) TIFF2025038858000009.tif13155 In step S126, the control unit 101 determines the amount of trimming based on the table read out from the non-volatile memory 103, according to the degree of match r with the overhead image.

[0195] Here, a table showing the relationship between the degree of matching r with an overhead image and the amount of trimming, and a method for determining the amount of trimming will be described with reference to FIG.

[0196] In FIG. 13(a), when the degree of agreement r with the overhead image is 1 / 2 or more and 1 or less, it is determined that more than half of the entire subject is within the field of view, and the amount of trimming is set to 0. When the degree of agreement r with the overhead image is 1 / 3 or more and less than 1 / 2, it is determined that more than half of the entire subject is outside the field of view, and the amount of trimming is set to up to half of the entire subject, as shown in FIG. 13(b). When the degree of agreement r with the overhead image is less than 1 / 3, it is determined that more than two-thirds of the subject is outside the field of view, and the amount of trimming is set to up to two-thirds of the entire subject. In this embodiment, since the sub-camera 400 captures a person's face as the subject, the direction of trimming is set to the vertical upward direction starting from the feet.

[0197] Depending on the characteristics of the subject and the shooting method, multiple trimming directions may be set in consideration of the horizontal width of the subject. Also, the trimming amount may be dynamically calculated from the subject area by defining it as a ratio according to the degree of agreement r with the overhead image, rather than the degree of agreement r with the overhead image. For example, the trimming amount may be calculated by the following formula 9, where T is the trimming amount. (Formula 9) TIFF2025038858000010.tif7155 The control unit 101 stores the trimming amount determined as described above in the volatile memory 102, and the process proceeds to step S127.

[0198] In step S127, the control unit 101 determines whether or not to perform trimming based on the result of the trimming amount determination process in step S126. If the trimming amount determined in step S126 has not been stored in the volatile memory 102, the control unit 101 determines that trimming will not be performed, terminates the process of Fig. 12, and proceeds to step S119 in Fig. 9(a). If the trimming amount determined in step S126 has been stored in the volatile memory 102, the control unit 101 determines that trimming will be performed, and proceeds to step S128.

[0199] In step S128, the control unit 101 performs subject detection using the inference model for subject detection described above, using the inference unit 104. That is, as shown in Fig. 6(a), the control unit 101 acquires the coordinates of a circumscribing rectangle of the subject from the overhead image of the overhead camera 300. The control unit 101 performs a trimming process on the circumscribing rectangle using the image processing unit 307, as shown in Fig. 13, based on the trimming amount determined in step S126.

[0200] The image processing unit 307 generates a subject image by cutting out a portion of the subject that is out of the field of view from the entire subject as shown in Fig. 11(c), and inputs the generated subject image to the image recognition unit 121. The control unit 101 stores the coordinate information of the subject in the subject image that has been subjected to the trimming process in the volatile memory 102, ends the process of Fig. 12, and proceeds to step S119 in Fig. 9(a). In this embodiment, the description will proceed assuming that the amount of trimming determined in step S126 is 1 / 2.

[0201] Returning to the explanation of Fig. 9(a), in step S119, the control unit 101 reads out from the volatile memory 102 the subject image that has been subjected to the trimming process in step S128, if any, and executes the function of the feature information determination unit 125. The trimmed subject image is input, and the control unit 101 reads out from the volatile memory 102 the feature information STAT[n] of the subject and the identification information SUBJECT_ID of the tracking subject determined by the tracking target determination unit 123. The control unit 101 determines STAT[i] corresponding to the tracking subject from the feature information STAT[n], stores it in the volatile memory 102, and proceeds to the process of step S120.

[0202] The processing of steps S123 to S128 in Fig. 12 and step S119 in Fig. 9(a) makes it possible to calculate feature information of a part of the subject on which trimming processing has been performed. The control unit 201 of the EB200 receives the feature information of the part of the subject on which trimming processing has been performed from the WS100, and performs the same processing as in Fig. 4. Then, the control unit 201 of the EB200 compares it with the feature information of the subject detected by the sub-camera 400 in a state in which a part of the subject is out of the field of view of the sub-camera 400 as shown in Fig. 11(c).

[0203] For example, if the overhead image of the overhead camera 300 is shown in Fig. 13(c) and the sub-image of the sub camera 400 is shown in Fig. 13(d), the subject portion above the dashed line is cut out by performing a trimming process on the overhead image of Fig. 13(c). This makes it closer to the subject image of Fig. 13(d), and then calculates the feature information of the subject and compares it with the feature information of the subject of the sub-image of Fig. 13(d).

[0204] In the example of Figure 13(e), when no cropping is performed, the similarity of the feature information is 0.4, but when cropping is performed with the cropping amount reduced to 1 / 2, the similarity of the feature information becomes 0.8, and it is determined that the subjects match between the overhead image and the sub-image.

[0205] According to the above-described first embodiment, the same subject can be recognized by the multiple cameras 300 and 400 with different shooting positions and shooting directions. Therefore, a specific subject can be tracked by appropriately switching between the control of the sub-camera 400 by the WS 100 and the control of the sub-camera 400 by the EB 200.

[0206] When the subject to be tracked does not exist in the sub-image of the sub-camera 400, the WS 100 controls the sub-camera 400, and when the subject to be tracked exists in the shooting angle of view of the sub-camera 400, the control of the sub-camera 400 can be handed over from the WS 100 to the EB 200. Also, when the subject to be tracked moves at high speed and is lost, or when the subject to be tracked is changed, tracking can be continued by controlling the sub-camera 400 with the WS 100.

[0207] In the first embodiment, the WS100 and the EB200 switch whether or not to transmit the pan value / tilt value to the sub camera 400, but the present invention is not limited to this example. For example, the pan value / tilt value may be transmitted from the WS100 and the EB200 to the sub camera 400 regardless of the tracking state, and the sub camera 400 may control which device the pan value / tilt value received from to perform the pan operation / tilt operation. In this case, the process of the WS100 may omit the process of step S106 in FIG. 4(a), and before the process of step S107 in FIG. 4(a), the control unit 101 may add a process of transmitting tracking state information STATE to the sub camera 400. The process of the EB200 may omit the processes of steps S205 and S206 in FIG. 4(b) and step S221 in FIG. 9(c).

[0208] When the tracking state information STATE received from WS100 is "tracking by EB200", the sub-camera 400 controls to perform a panning operation / tilting operation in response to a control command received from EB200. When the tracking state information STATE received from WS100 is "tracking by WS100", the sub-camera 400 controls to perform a panning operation / tilting operation in response to a control command received from WS100.

[0209] [Embodiment 2] In the first embodiment, the feature information of the subject transmitted from the WS 100 to the EB 200 is one piece of feature information of the tracked subject. In the second embodiment, an example will be described in which the WS 100 generates multiple candidates for feature information and transmits them to the EB 200, and the feature information is compared in the EB 200.

[0210] In the first embodiment, the amount of trimming is determined by the process in Fig. 12, and feature information is calculated for the subject image that has been subjected to the trimming process in step S119. In the second embodiment, a plurality of subject images that have been subjected to the trimming process based on a plurality of preset trimming amounts are created, and feature information is calculated from each of the subject images.

[0211] The following description will focus on the differences from the first embodiment.

[0212] First, the operation of the WS 100 will be described.

[0213] The WS 100 executes the trimming process in step S118 in FIG. 9A regardless of the subject information and the shooting information of the sub-camera 400 acquired in steps S123 and S124 in FIG.

[0214] In step S118, the control unit 101 creates subject images according to three patterns of trimming amounts for the table shown in FIG.

[0215] In step S119, the control unit 101 calculates feature information of the three patterns of subject images created in step S118. In the first embodiment, one piece of feature information STAT[i] is determined for the tracking subject, but in the second embodiment, three pieces of feature information, STAT[i][0], STAT[i][1], and STAT[i][2], are determined for one subject. The amount of trimming is not limited to three patterns, and any number of patterns may be set. For example, when there are p patterns of the amount of trimming, and the number of detected subjects is n, the number of feature information will be n×p. Therefore, for a specific tracking subject SUBJECT_ID=i, feature information STAT[i][0] to STAT[i][p-1] is calculated.

[0216] In step S120, the control unit 101 transmits a tracking start instruction and the feature information STAT[i][0] to STAT[i][2] to the EB 200 via the communication unit 105.

[0217] Next, the operation of the EB 200 will be described.

[0218] The second embodiment differs in that a plurality of pieces of feature information are received and collated in the process of FIG. 9(b).

[0219] In step S210, control unit 201 determines whether or not it has received a tracking start command and feature information STAT[i][0] to STAT[i][2] of the tracked subject in the overhead image of overhead camera 300 from WS 100 via communication unit 205. If control unit 201 determines that it has received a tracking start command and feature information STAT[i][0] to STAT[i][2] of the tracked subject in the overhead image of overhead camera 300 from WS 100, it proceeds to step S211, and if it has not received them, it ends the process.

[0220] In step S211, the control unit 201 executes the function of the tracking target determination unit 222 in Fig. 3. Unlike the first embodiment, the tracking target determination unit 222 compares the characteristic information STAT[i][0] to STAT[i][2] received in step S210 with the characteristic information STAT_SUB.

[0221] In step S212, the control unit 201 determines whether or not a subject with highly similar feature information exists based on the result of the comparison in step S211, as shown in Fig. 13(e). If the control unit 201 determines that a subject with highly similar feature information exists, the control unit 201 proceeds to step S214, and if the control unit 201 determines that a subject with highly similar feature information does not exist, the control unit 201 proceeds to step S213.

[0222] According to the above-described second embodiment, by calculating feature information according to a plurality of trimming amount patterns without using subject information or shooting information of the sub-camera 400, it is possible to obtain the same effect as in the first embodiment.

[0223] [Embodiment 3] In the first and second embodiments, the overhead image is subjected to a trimming process so that the characteristic information of the subject detected from the overhead image of the overhead camera 300 approaches the characteristic information of the subject detected from the sub-image of the sub camera 400.

[0224] In the third embodiment, an example will be described in which, when the feature information of the tracked subject does not match between the overhead camera 300 and the sub camera 400, zoom control is performed so that a part of the subject does not go out of the shooting angle of view of the sub camera 400. In this way, by changing the shooting angle of view of the sub camera 400 and recalculating the feature information of the subject, it is possible to obtain feature information of the entire subject from the sub image. This control is effective when the tracking of the subject is more important than the change in the shooting angle of view.

[0225] The control process of the third embodiment will be described with reference to FIGS.

[0226] The processing from steps S110 to S122 in FIG. 14 is similar to the processing from steps S110 to S122 in FIG.

[0227] In step S121, if the control unit 101 receives mismatch information from the EB 200 indicating that the subjects do not match, the control unit 101 advances the process to step S130.

[0228] Here, the zoom control of the sub-camera 400 in step S130 in FIG. 14 will be described with reference to FIG.

[0229] In step S134, the control unit 101 reads the subject information from the volatile memory 102, similar to step S123, and the process proceeds to step S135.

[0230] In step S135, the control unit 101 acquires shooting information from the overhead camera 300 and the sub-camera 400 via the communication unit 105, and proceeds to step S136.

[0231] In step S136, the control unit 101 calculates a zoom value of the sub-camera 400 such that the shooting angle of view of the sub-camera 400 approaches the shooting angle of view of the overhead camera 300 capturing the tracked subject. The control unit 101 calculates the vertical field of view H of the overhead camera 300 based on the information acquired in steps S134 and S135.

[0232] Next, the control unit 101 calculates the height hview of the subject within the field of view of the overhead camera 300 based on the vertical field of view H of the overhead camera 300. The control unit 101 calculates the vertical field of view H of the sub camera 400 such that the difference between the size information hview of the tracking subject in the vertical field of view H of the overhead camera 300 and the size information hview of the subject of the sub camera 400 matches, using the above formula 5.

[0233] Furthermore, the control unit 101 calculates the focal length f from the vertical field of view H of the sub-camera 400 and the above formulas 6 and 7, and calculates the zoom value corresponding to the focal length f. The control unit 101 stores the zoom value in the volatile memory 102, and the process proceeds to step S137.

[0234] The height hview of the subject within the field of view of the sub-camera 400 does not necessarily have to be equal to the height hview of the subject within the field of view of the overhead camera 300, and may be closer (so that the difference is smaller) than before the start of processing. Also, when multiple subjects are present in the shooting angle of view of the sub-camera 400, the control unit 101 selects the subject closest to the center of the angle of view as the tracking subject.

[0235] In step S137, the control unit 101 reads out from the volatile memory 102 the zoom value calculated in step S136, the focal length f of the sub camera 400 acquired in step S135, and a threshold value previously stored in the volatile memory 102. The control unit 101 calculates the difference between the zoom value corresponding to the focal length f of the sub camera 400 acquired in step S135 and the zoom value calculated in step S136. If the control unit 101 determines that the calculated difference is less than the threshold value, it advances the process to step S131 in Fig. 14, and if the control unit 101 determines that the calculated difference is equal to or greater than the threshold value, it advances the process to step S138.

[0236] In step S138, the control unit 101 reads out the zoom value calculated in step S136 from the volatile memory 102, and transmits a zoom control command corresponding to the zoom value from the WS 100 to the sub-camera 400 via the communication unit 105. When the control unit 401 of the sub-camera 400 receives the zoom control command via the communication unit 405, it controls the PTZ driving unit 409 to achieve the received zoom value.

[0237] This makes it possible to bring the shooting angle of the sub-camera 400 closer to the shooting angle of the overhead camera 300 capturing the tracked subject, that is, closer to the state of Fig. 11(a) from the state of Fig. 11(c). Therefore, the difference in size of the tracked subject between the overhead image of the overhead camera 300 and the sub-image of the sub-camera 400 becomes smaller, and it becomes possible to track a specific subject in cooperation with the multiple cameras even if the shooting positions and shooting directions of the multiple cameras are arranged apart, and part of the subject is outside the shooting angle of view or the subject is too small.

[0238] The trimming process performed prior to the zoom process can deal to some extent with cases where a part of a specific subject is outside the shooting angle of view in an image captured by only one of the overhead camera 300 and the sub-camera 400 (usually the sub-camera). However, the inventors of the present application have found that, for example, when the entire body of a specific subject is captured small by the overhead camera 300 and the face of the same subject is captured by the sub-camera 400, the similarity of the feature information may decrease even if the trimming process is performed. Therefore, in this embodiment, if the subjects still do not match even after the trimming process (NO in step S121), the zoom process is performed, thereby increasing the possibility that the subjects will match if the same subject is being photographed. Also, by changing the zoom value only when the difference between the current zoom value of the sub-camera 400 and the zoom value of the sub-camera 400 at which the size information hview of the tracking subject in the vertical field of view H of the overhead camera 300 matches the size information hview of the subject of the sub-camera 400 exceeds a threshold, it is possible to change the shooting angle of view of the sub-camera 400 only when the difference in subject size is so large that it is likely to affect the determination of the similarity of the feature information.

[0239] After transmitting the zoom control command, the control unit 101 ends the process in FIG. 15, and proceeds to step S131.

[0240] The processing in steps S131 to S133 is similar to the processing in steps S119 to S121 in FIG.

[0241] According to the above-described third embodiment, the imaging angle of view of the sub-camera 400 is controlled so that the subject does not leave the field of view, thereby making it possible to acquire feature information of the entire subject.

[0242] [Embodiment 4] In the first to third embodiments, an example has been described in which either the WS 100 or the EB 200 controls the sub-camera 400. In the fourth embodiment, an example will be described in which the EB 200 is omitted and the WS 100 controls the sub-camera 400 based on the overhead image of the overhead camera 300 and the sub-image of the sub-camera 400.

[0243] In the fourth embodiment, the sub camera 400 is controlled using either the pan value / tilt value calculated based on the overhead image of the overhead camera 300 or the pan value / tilt value calculated based on the sub image of the sub camera 400.

[0244] 1 without the EB 200, and differs from the first embodiment in that a sub-image from the sub-camera 400 is input to the WS 100. Operations other than those of the WS 100 are the same as those of the first embodiment.

[0245] In basic operation, the overhead camera 300 transmits an overhead image to the WS 100. The sub-camera 400 transmits a sub-image to the WS 100. The sub-camera 400 also has a PTZ function.

[0246] WS100 detects a subject from the overhead image of overhead camera 300 and the sub-image of sub camera 400, and changes the imaging direction of sub camera 400 to the direction of the tracked subject based on the subject recognition result. WS100 controls sub camera 400 based on the subject recognition result of the overhead image of overhead camera 300 until the imaging direction of sub camera 400 becomes the direction of the tracked subject. After the shooting direction of sub camera 400 becomes the direction of the tracked subject, WS 100 calculates feature information of the tracked subject from the overhead image of overhead camera 300, and calculates feature information of the subject from the sub-image of sub camera 400. Then, based on this feature information, WS 100 controls sub camera 400. The feature information is information that can identify that the same subject is captured by multiple cameras with different shooting positions and / or shooting directions.

[0247] According to the fourth embodiment, the sub camera 400 can be controlled based on the subject recognition result of either the overhead image of the overhead camera 300 or the sub image of the sub camera 400, to track the subject to be tracked.

[0248] The hardware configurations of the WS 100, the overhead camera 300, and the sub-camera 400 are the same as those in FIG. 2 of the first embodiment.

[0249] First, the functional configuration of the WS 100 for implementing the control process of this embodiment will be described with reference to FIG.

[0250] The functions of the WS 100 are realized by hardware and / or software. If the functional units shown in Fig. 16 are configured by hardware instead of by software, it is sufficient to have a circuit configuration corresponding to each of the functional units in Fig. 16.

[0251] WS100 includes an image recognition unit 121, an object of interest determination unit 122, a tracking target determination unit 123, a control information generation unit 124, a feature information determination unit 125, a tracking state determination unit 126, an image recognition unit 127, and a tracking target determination unit 128. Software for realizing these functions is stored in non-volatile memory 103, and the control unit 101 loads it into volatile memory 102 and executes it.

[0252] The functions of the image recognition unit 121, the target subject determination unit 122, the tracking target determination unit 123, and the feature information determination unit 125 are similar to those in FIG. 3 of the first embodiment.

[0253] The functions and basic operations of the WS 100 will be described with reference to FIGS.

[0254] The processes from step S501 to step S504 are similar to those from step S101 to S104 in FIG. 4(a) of the first embodiment.

[0255] In step S505, the control unit 101 transmits a shooting command to the sub-camera 400 via the communication unit 105, receives the captured sub-image from the sub-camera 400, stores it in the volatile memory 102, and proceeds to step S506.

[0256] In step S506, the control unit 101 executes the function of the image recognition unit 127 in FIG. 16, and advances the process to step S507.

[0257] The functions of the image recognition unit 127 can be achieved by replacing the control unit 201 with the control unit 101, the volatile memory 202 with the volatile memory 102, and the non-volatile memory 203 with the non-volatile memory 103 in the description of the image recognition unit 221 of the EB 200 of the first embodiment.

[0258] 16, compares the feature information calculated in steps S502 and S506, and updates the tracking state information STATE. Furthermore, the control unit 101 stores the tracking subject SELECT_ID and the tracking state information STATE in the volatile memory 102, and the process proceeds to step S508.

[0259] The tracking state information STATE includes information on either "tracking using overhead image" or "tracking using sub-image." "Tracking using overhead image" indicates a state in which the tracking subject is tracked by controlling sub-camera 400 based on the subject recognition result of the overhead image of overhead camera 300. "Tracking using sub-image" indicates a state in which the tracking subject is tracked by controlling sub-camera 400 based on the subject recognition result of the sub-image of sub-camera 400. The process of step S507 will be described in detail later.

[0260] The processes in steps S508 to S510 are executed by the function of the control information generating unit 124 in FIG.

[0261] In step S508, the control unit 101 reads the tracking state information STATE from the volatile memory 102, and determines whether "tracking using an overhead image" or "tracking using a sub-image" based on the tracking state information STATE. If the control unit 101 determines that "tracking using an overhead image" is in progress, the process proceeds to step S510, and if the control unit 101 determines that "tracking using a sub-image is in progress", the process proceeds to step S509.

[0262] In step S509, the control unit 101 calculates the pan value / tilt value of the sub camera 400 based on the subject recognition result of the sub image of the sub camera 400, and proceeds to step S511. The process of step S509 can be performed by replacing the control unit 201 with the control unit 101 and the volatile memory 202 with the volatile memory 102 in the process of the control information generation unit 223 in FIG.

[0263] In step S510, the control unit 101 calculates the pan value / tilt value of the sub camera 400 based on the subject recognition result of the overhead image of the overhead camera 300, and proceeds to step S511. The process of step S510 can be performed by replacing the control unit 201 with the control unit 101 and the volatile memory 202 with the volatile memory 102 in the process of the control information generation unit 223 in FIG.

[0264] In step S511, the control unit 101 executes the function of the control information generating unit 124 in FIG. 3, and advances the process to step S512.

[0265] The processes in steps S511 and S512 are similar to those in steps S108 and S109 in FIG.

[0266] The above is the basic operation of the WS100.

[0267] Next, the control process of the WS 100 will be described with reference to FIG.

[0268] FIG. 18 shows the control process of the WS 100, and shows the detailed process of step S507 in FIG.

[0269] The process of step S520 is similar to that of step S110 in FIG.

[0270] In step S521, the control unit 101 executes the function of the tracking state determination unit 126 in FIG. 16, and changes the tracking state information STATE to "tracking using an image from an overhead camera".

[0271] The tracking state determination unit 126 has a function of updating the tracking state information STATE stored in the volatile memory 102 .

[0272] In step S522, the control unit 101 reads the tracking state information STATE from the volatile memory 102, and determines whether "tracking using an overhead image" or "tracking using a sub-image" is in progress based on the tracking state information STATE. If the control unit 101 determines that "tracking using an overhead image" is in progress, the process proceeds to step S525, and if the control unit 101 determines that "tracking using a sub-image is in progress", the process proceeds to step S523.

[0273] The process of step S523 can be achieved by replacing the control unit 201 with the control unit 101 and the volatile memory 202 with the volatile memory 102 in the process of step S224 in FIG. 9B.

[0274] In step S524, the control unit 101 executes the function of the tracking state determination unit 126 in FIG. 16, and changes the tracking state information STATE to "tracking using overhead image".

[0275] The processes in steps S525, S526a, and S527 are similar to those in steps S117, S118, and S119 in FIG.

[0276] The process of steps S528 to S530 can be achieved by replacing the control unit 201 with the control unit 101 and the volatile memory 202 with the volatile memory 102 in the process of steps S211 to S214 in FIG. 9B.

[0277] In step S531, the control unit 101 executes the function of the tracking state determination unit 126 in FIG. 16 to change the tracking state information STATE to "tracking using sub-image", and ends the process.

[0278] According to the above-mentioned embodiment 4, WS 100 switches whether to control sub camera 400 based on the subject recognition result of the overhead image of overhead camera 300 or the sub image of sub camera 400. This makes EB 200 of embodiment 1 unnecessary, and the same effect as embodiment 1 can be obtained with a simplified system configuration.

[0279] [Embodiment 5] In the first to fourth embodiments, the overhead image is subjected to a trimming process to control the feature information of the subject detected from the overhead image of the overhead camera 300 to be closer to the feature information of the subject detected from the sub-image of the sub camera 400. In the fifth embodiment, an example will be described in which zoom control is performed so that a part of the subject does not fall outside the shooting angle of view of the sub camera 400.

[0280] The following description will focus on the differences from embodiments 1 to 4. First, the operation of the WS 100 will be described.

[0281] The control process of the fifth embodiment will be described with reference to FIG.

[0282] The processes in steps S110 to S117 and S119 to S122 in FIG. 19 are similar to the processes in steps S110 to S117 and S119 to S122 in FIG.

[0283] In step S150, the control unit 101 acquires subject information of the tracked subject included in the overhead image, subject information included in the sub-image, and shooting information from the sub-camera 400 to determine the zoom value of the sub-camera 400 and perform zoom control of the sub-camera 400.

[0284] Here, a method of calculating a zoom value of the sub camera 400 such that the size of the tracked subject in the overhead image and the size of the tracked subject in the sub image match in the zoom control in step S150 in Fig. 19 will be described with reference to Fig. 11. In this embodiment, an example of performing zoom control based on the vertical size as the size of the tracked subject will be described.

[0285] In this embodiment, when the difference between the size of the tracked subject in the overhead image and the size of the tracked subject in the sub-image is large, the zoom value of the sub-camera 400 is controlled so that the size of the tracked subject in the overhead image and the size of the tracked subject in the sub-image become closer to each other. This makes it possible to prevent the subject from being cut off, thereby reducing the decrease in similarity of the feature information due to the subject being cut off.

[0286] In this embodiment, the zoom value of the sub camera 400 is calculated so that the size of the tracking subject in the sub image matches the size of the tracking subject in the overhead image. Then, the calculated zoom value is compared with the current zoom value of the sub camera 400, and when the difference between the calculated zoom value and the current zoom value of the sub camera 400 exceeds a threshold, the zoom value of the sub camera 400 is controlled so that the size of the tracking subject in the sub image approaches the size of the tracking subject in the overhead image. Note that the term "approaching" the size of the tracking subject in the sub image to the size of the tracking subject in the overhead image includes "matching." This reduces the possibility of erroneously determining that a subject that actually matches is not matched.

[0287] In this embodiment, the zoom value of the sub-camera 400 is controlled so that the difference between the size information hview of the tracked subject in the vertical field of view H of the overhead camera 300 and the size information hview of the subject in the vertical field of view H of the sub-camera 400, calculated by the above formula 5, does not become too large.

[0288] When the difference between the zoom value of sub-camera 400 at which size information hview of the tracking subject in the vertical field of view H of overhead camera 300 matches size information hview of the subject in the vertical field of view H of sub-camera 400, and the current zoom value, exceeds a threshold value, the zoom value of sub-camera 400 is controlled so that the difference becomes equal to or less than the threshold value. On the other hand, when the difference between the zoom value of sub-camera 400 and the current zoom value is equal to or less than the threshold value, the zoom value of sub-camera 400 is not controlled. This makes it possible to control the shooting angle of view of sub-camera 400 only when there is a large difference between the feature information of the tracking subject detected from the overhead image and the feature information of the subject detected from the sub-image, which affects the determination of the similarity.

[0289] The zoom control process of the sub-camera 400 in step S150 in FIG. 19 is as described with reference to FIG.

[0290] The zoom control of this embodiment makes it possible to control the shooting angle of view of the sub-camera 400 so that the difference between the size of the tracked subject in the overhead image and the size of the tracked subject in the sub-image does not become too large. Therefore, even if the shooting positions and shooting directions of the multiple cameras are arranged apart and part of the subject is outside the shooting angle of view or the subject is too small, it becomes possible to track a specific subject in cooperation with the multiple cameras.

[0291] In addition, after determining the similarity of the feature information of the subject, or when the similarity of the feature information of the subject is high, the zoom value of the sub-camera 400 may be returned to the zoom value before the change. In this case, when the zoom value of the sub-camera 400 is changed in step S138, the zoom value before the change is saved, and the zoom value before the change is transmitted to the sub-camera 400 before the processing of step S122, so that tracking can be started with the zoom value before the change.

[0292] In this case, the control unit 101 acquires the current zoom value of the sub camera 400 in step S135 and stores it in the volatile memory 102, and before starting the process of step S122, reads out the zoom value stored in step S135 from the volatile memory 102 and transmits it to the sub camera 400. This makes it possible to start tracking after returning the shooting angle of view changed to increase the similarity of the feature information of the subject to the shooting angle of view before the change.

[0293] Furthermore, when the zoom value changed to increase the similarity of the feature information of the subject is returned to the zoom value before the change, the sub-camera 400 may notify the WS100 or EB200 that the control to the zoom value before the change has been completed. In this case, when the control unit 401 of the sub-camera 400 receives a notification from the PTZ driving unit 409 that the zoom operation has been completed, the control unit 401 notifies the WS100 or EB200 that the zoom operation has been completed via the communication unit 405. This allows the image output to the WS100 or EB200 to be quickly switched to the sub-image of the sub-camera 400 after the zoom control of the sub-camera 400 is completed. Also, the image output from the WS100 or EB200 to an external device to be quickly switched to the sub-image of the sub-camera 400.

[0294] Alternatively, instead of restoring the zoom value before the change, the WS100 or EB200 may store the zoom value before the change and create a sub-image with the zoom value before the change by performing a trimming process. In this case, the WS100 or EB200 acquires a sub-image from the sub-camera 400, calculates an image area according to the shooting angle of view corresponding to the zoom value before the change, and performs a trimming process for the sub-image by the image processing units 307 and 407. This allows the image output to the WS100 or EB200 to be quickly switched to the sub-image of the sub-camera 400 after the zoom control of the sub-camera 400 is completed. Also, the image output to an external device from the WS100 or EB200 can be quickly switched to the sub-image of the sub-camera 400.

[0295] The above trimming process may be performed by the sub-camera 400. In this case, the WS100 or EB200 instructs the sub-camera 400 to perform the trimming process. This allows the image output to the WS100 or EB200 to be quickly switched to the sub-image of the sub-camera 400 after the zoom control of the sub-camera 400 is completed. Also, the image output from the WS100 or EB200 to an external device can be quickly switched to the sub-image of the sub-camera 400.

[0296] According to the above-described fifth embodiment, the same subject can be recognized by the multiple cameras 300 and 400 with different shooting positions and shooting directions. Therefore, a specific subject can be tracked by appropriately switching between the control of the sub-camera 400 by the WS 100 and the control of the sub-camera 400 by the EB 200.

[0297] When the subject to be tracked does not exist in the sub-image of the sub-camera 400, the WS 100 controls the sub-camera 400, and when the subject to be tracked exists in the shooting angle of view of the sub-camera 400, the control of the sub-camera 400 can be handed over from the WS 100 to the EB 200. Also, when the subject to be tracked moves at high speed and is lost, or when the subject to be tracked is changed, tracking can be continued by controlling the sub-camera 400 with the WS 100.

[0298] In the fifth embodiment, an example has been described in which the WS100 and the EB200 switch whether or not to transmit pan / tilt values ​​to the sub-camera 400, but the present invention is not limited to this example. For example, the pan / tilt values ​​may be transmitted from the WS100 and the EB200 to the sub-camera 400 regardless of the tracking state, and control may be performed as to which device the sub-camera 400 receives the pan / tilt values ​​to use when performing the pan / tilt operation.

[0299] In this case, the process of step S106 in Fig. 4(a) is omitted from the process of WS100, and a process of the control unit 101 transmitting tracking state information STATE to the sub camera 400 is added before the process of step S107 in Fig. 4(a). The process of EB200 is omitted from the processes of steps S205 and S206 in Fig. 4(b) and step S221 in Fig. 9(c).

[0300] When the tracking state information STATE received from WS100 is "tracking by EB200", the sub-camera 400 controls to perform a panning operation / tilting operation in response to a control command received from EB200. When the tracking state information STATE received from WS100 is "tracking by WS100", the sub-camera 400 controls to perform a panning operation / tilting operation in response to a control command received from WS100.

[0301] In the present embodiment, the example of controlling the size of the tracking subject in the sub-image to approach the size of the tracking subject in the overhead image has been described, but the present invention is not limited to this example. For example, when the overhead camera 300 includes an optical unit and a PTZ driving unit, the shooting angle of view of the overhead camera 300 may be controlled to control the size of the tracking subject in the sub-image to approach the size of the tracking subject in the overhead image.

[0302] In the present embodiment, the example of controlling the size of the tracking subject in the sub-image to approach the size of the tracking subject in the overhead image has been described, but the present invention is not limited to this example. For example, when the overhead camera 300 includes an optical unit and a PTZ driving unit, the shooting angle of view of the overhead camera 300 may be controlled to control the size of the tracking subject in the overhead image to approach the size of the tracking subject in the sub-image.

[0303] In the present embodiment, an example has been described in which the WS 100 calculates the height hview of the subject by performing inference processing to recognize the subject based on the overhead image from the overhead camera 300 and the sub-image from the sub-camera 400, but the present invention is not limited to this example. For example, the overhead camera 300 and the sub-camera 400 may perform inference processing to recognize the subject, and the WS 100 may obtain the subject detection result from the inference processing from the overhead camera 300 and the sub-camera 400 via the communication unit 105, and calculate the height hview of the subject.

[0304] In the present embodiment, an example has been described in which a threshold is set for the difference between the zoom value of the sub-camera 400 and the current zoom value such that the difference between the size of the tracked subject in the overhead image and the size of the tracked subject in the sub-image coincides, but the present invention is not limited to this. Other forms may be used as long as the difference in the height hview of the tracked subject within the vertical field of view of the overhead camera 300 and the sub-camera 400 can be controlled to be small. For example, a threshold may be set for the difference between the size information hview of the tracked subject in the overhead image and the size information hview of the subject in the sub-camera 400, and the zoom value of the sub-camera 400 may be controlled when the difference in the size information hview of the subject exceeds this threshold.

[0305] Furthermore, in this embodiment, the zoom value of the sub camera 400 is controlled using the vertical size as the size of the tracked subject of the overhead camera 300 and the sub image, but the zoom value may be controlled using the horizontal size.

[0306] [Embodiment 6] In the fifth embodiment, an example was described in which either the WS 100 or the EB 200 controls the sub-camera 400. In the sixth embodiment, similar to the fourth embodiment, an example is described in which the EB 200 is omitted and the WS 100 controls the sub-camera 400 based on the overhead image of the overhead camera 300 and the sub-image of the sub-camera 400.

[0307] Next, the control process of the WS 100 will be described with reference to FIG.

[0308] FIG. 20 shows the control process of the WS 100, and shows the detailed process of step S507 in FIG.

[0309] The process in step S520 is similar to that in step S110 in FIG.

[0310] In step S521, the control unit 101 executes the function of the tracking state determination unit 126 in FIG. 16, and changes the tracking state information STATE to "tracking using an image from an overhead camera".

[0311] The tracking state determination unit 126 has a function of updating the tracking state information STATE stored in the volatile memory 102 .

[0312] In step S522, the control unit 101 reads the tracking state information STATE from the volatile memory 102, and determines whether "tracking using an overhead image" or "tracking using a sub-image" is in progress based on the tracking state information STATE. If the control unit 101 determines that "tracking using an overhead image" is in progress, the process proceeds to step S525, and if the control unit 101 determines that "tracking using a sub-image is in progress", the process proceeds to step S523.

[0313] The process of step S523 can be achieved by replacing the control unit 201 with the control unit 101 and the volatile memory 202 with the volatile memory 102 in the process of step S224 in FIG. 9B.

[0314] In step S524, the control unit 101 executes the function of the tracking state determination unit 126 in FIG. 16, and changes the tracking state information STATE to "tracking using overhead image".

[0315] The processes in steps S525, S526b, and S527 are similar to those in steps S117, S150, and S119 in FIG.

[0316] The process of steps S528 to S530 can be achieved by replacing the control unit 201 with the control unit 101 and the volatile memory 202 with the volatile memory 102 in the process of steps S211 to S214 in FIG. 9B.

[0317] In step S531, the control unit 101 executes the function of the tracking state determination unit 126 in FIG. 16 to change the tracking state information STATE to "tracking using sub-image", and ends the process.

[0318] According to the above-mentioned sixth embodiment, the WS 100 switches whether to control the sub-camera 400 based on the subject recognition result of the overhead image of the overhead camera 300 or the sub-image of the sub-camera 400. This makes the EB 200 of the fifth embodiment unnecessary, and the same effect as that of the fifth embodiment can be obtained with a simplified system configuration.

[0319] [Embodiment 7] In the first to sixth embodiments, an example of a system including the overhead camera 300 and the sub-camera 400 has been described.

[0320] In the seventh embodiment, an example of a system including a main camera 500 in addition to an overhead camera 300 and a sub-camera 400 will be described.

[0321] FIG. 21 is a system configuration diagram of the seventh embodiment.

[0322] The seventh embodiment differs from the first to sixth embodiments in that a main camera 500 is provided, and a subject to be tracked by the sub camera 400 is determined based on a main image captured by the main camera 500. The following description will focus on the differences from the first to sixth embodiments.

[0323] In the seventh embodiment, the main camera 500 has a PTZ function. The target subject determination unit 122 of the WS 100 determines (estimates) a target subject of the main camera 500 from the shooting range of the main camera 500, and determines a tracking subject of the sub camera 400 based on the target subject of the main camera 500. The tracking subject of the sub camera 400 may be the same subject as the target subject of the main camera 500, or may be a different subject.

[0324] Next, an example of determining a tracking subject of the sub camera 400 based on a role (ROLE) set to the sub camera 400 will be described.

[0325] The role of the sub-camera 400 indicates the subject of interest in the main camera 500, the subject to be tracked by the sub-camera 400 associated with the zoom operation, and the control content of the zoom operation. The role of the sub-camera 400 can be set by the user via an operation unit provided in the WS100 or the EB200.

[0326] Furthermore, if multiple sub-cameras are installed, any one of the multiple sub-cameras can be set as the main camera, and the main camera settings may be set by the user using an operation unit provided on the WS 100 or EB 200. The role of the sub-camera 400 and the method of setting the main camera are not limited to the above-mentioned method. Any method may be used.

[0327] FIG. 22 shows an example of roles and contents that can be set for the sub-camera 400.

[0328] When the role (ROLE) is "main follow", the role (CAMERA_ROLE) of the sub camera 400 is to track the same subject as the subject that the main camera 500 is focusing on, and to perform zoom control in the same phase as the zoom operation of the main camera 500. Based on this role (CAMERA_ROLE), the zoom control value of the sub camera 400 is calculated. Here, the same phase in the zoom operation means that the zoom operations of the main camera 500 and the sub camera 400 are controlled in the same direction. For example, when the zoom control value of the main camera 500 is changed from the wide-angle side to the telephoto side, the zoom of the sub camera 400 is also changed from the wide-angle side to the telephoto side.

[0329] When the role (ROLE) is "main counter", the role (CAMERA_ROLE) of the sub camera 400 is to track the same subject as the subject that the main camera 500 is focusing on, and to perform zoom control in the opposite phase to the zoom operation of the main camera 500. The PTZ value of the sub camera 400 is calculated based on this role (CAMERA_ROLE). Here, the opposite phase in the zoom operation means that the zoom operations of the main camera 500 and the sub camera 400 are controlled in the opposite directions. For example, when the zoom control value of the main camera 500 is changed from the wide-angle side to the telephoto side, the zoom of the sub camera 400 is changed from the telephoto side to the wide-angle side.

[0330] When the role (ROLE) is "assist follow", the sub camera 400 tracks a subject other than the subject that the main camera 500 is focusing on, and performs zoom control in the same phase as the zoom operation of the main camera 500. Based on this role (CAMERA_ROLE), the zoom control value of the sub camera 400 is calculated.

[0331] When the role (ROLE) is "assist counter", the sub camera 400 tracks a subject other than the subject that the main camera 500 is focusing on, and performs zoom control in the opposite phase to the zoom operation of the main camera 500. Based on this role (CAMERA_ROLE), the zoom control value of the sub camera 400 is calculated. In the example of FIG. 22, "separate from main (left side)" is exemplified as the control content of the tracking subject for "assist follow" and "assist counter", but there may be "assist follow" and "assist counter" in which the tracking subject is "separate from main (right side)".

[0332] In addition, when the tracking subject is "separate from the main subject", it may also serve the role of tracking a subject in a position other than left and right (up and down, or front and back).

[0333] When there are multiple sub-cameras, a role may be set for each sub-camera.

[0334] In addition, in the seventh embodiment, an example has been described in which the control contents of the tracking subject and zoom are set as roles, but the control contents of only the tracking subject may be set as a role, or other items may be added.

[0335] In the seventh embodiment, a tracking subject of the sub camera 400 is set based on the main image of the main camera 500, and an example is described in which the seventh embodiment is combined with the first to fifth embodiments. However, the seventh embodiment may also be combined with the sixth embodiment.

[0336] [Embodiment 8] In the eighth embodiment, an example will be described in which a dummy area is added to the sub-image so as to become a subject area corresponding to the overhead image, thereby bringing characteristic information of the subject of the sub-image closer to characteristic information of the subject of the overhead image. In this embodiment, the dummy area is called a "letter", and combining the dummy area with the subject area is called "adding a letter". Note that in the eighth embodiment, an all-black image is exemplified as the dummy area, but this is not limiting.

[0337] The control process of the eighth embodiment will be described with reference to FIGS.

[0338] The processes of steps S110 to S122 in FIG. 23(a) except for steps S140 to S142 are similar to the processes of steps S110 to S122 in FIG. 9(a).

[0339] First, the letter adding process of the sub camera in step S140 of FIG. 23 will be described with reference to FIG.

[0340] In step S143, similarly to step S123, the control unit 101 reads the subject information from the volatile memory 102, and the process proceeds to step S144.

[0341] In step S144, the control unit 101 acquires shooting information from the overhead camera 300 and the sub-camera 400 via the communication unit 105, and proceeds to step S145. In the sixth embodiment, the information acquired from the sub-camera 400 includes information on the subject area where the subject is detected by the control unit 201 performing image recognition processing using an inference model for subject detection.

[0342] In step S145, the control unit 101 calculates the letter size based on the ratio of the subject area included in the overhead image to the subject area included in the sub-image within the shooting angle of view.

[0343] Now, with reference to FIG. 25, the process of calculating the letter size will be described.

[0344] FIG. 25(a) illustrates an example of a subject area in an overhead image, with a size of wо (horizontal)×hо (vertical). FIG. 25(b) and FIG. 25(c) illustrate an example of a subject area in a sub-image, with a size of wc1 (horizontal)×hc1 (vertical) and wc2 (horizontal)×hc2 (vertical). In the eighth embodiment, the face of the subject is photographed, so it is necessary to add letters downward. When photographing the feet, it is necessary to add letters upward, and the letters may be added in a direction according to a specific part of the subject. The direction in which the letters are added may be determined according to the position of the subject area. As shown in FIG. 25(c), when the subject area is in contact with the bottom side of the sub-image, the letters are added downward, and when the subject area is in contact with the right side of the sub-image, the letters are added rightward. The sizes hr and wr of the letters to be added can be calculated by the following formula 10. In step S145, control unit 101 stores the calculation result of the letter size in volatile memory 102, and the process proceeds to step S141 in FIG. 23(a). (Formula 10) TIFF2025038858000011.tif25156 Alternatively, the degree of match r may be calculated using the above-mentioned formula 8, and the letter size may be calculated using the following formula 11. (Formula 11) TIFF2025038858000012.tif8161 In step S141, the control unit 101 executes the function of the feature information determining unit 125 in FIG. 3, similarly to step S119 in FIG. 9(a), and advances the process to step S142.

[0345] In step S141, control unit 101 transmits a tracking start command and feature information STAT[i] of the tracking subject to EB 200 via communication unit 105, and proceeds to step S121. Here, control unit 101 reads the letter size calculated in step S145 from volatile memory 102. If the letter size is a positive number, control unit 101 transmits the letter size to EB 200 via communication unit 105. If the letter size is 0 or less, the letter is not necessary and is not transmitted.

[0346] Next, the control of the EB 200 will be described with reference to FIG.

[0347] The eighth embodiment differs in that letter size is received and processed in the process of FIG. 23(b).

[0348] In step S230, control unit 201 determines whether or not it has received a tracking start command, feature information STAT[i] of the tracking subject obtained from the overhead image of overhead camera 300, and further letter size from WS 100 via communication unit 205. If control unit 201 has received a tracking start command and feature information STAT[i] of the tracking subject from WS 100, it proceeds to step S231, and if not, it ends the process. If control unit 201 has received letter size, it stores it in volatile memory 102, but if not, it does nothing and proceeds to step S231.

[0349] In step S231, the control unit 201 reads the volatile memory 102 to determine whether a letter-sized document was received in step S230. If it has been received, the process proceeds to step S231; if it has not been received, the process proceeds to step S233.

[0350] In step 232, control unit 201 executes the function of image recognition unit 221, but unlike step S202 in FIG. 4(b), it executes the letter adding process described in FIG. 24 for the subject area in the sub-image. Control unit 201 determines the direction in which the subject area in the sub-image contacts the sub-image. For the determined direction, control unit 201 calculates feature information STAT_SUB[m] for the subject area to which the letter is added based on the letter size information received from WS 100. Control unit 201 overwrites volatile memory 102 with the newly calculated feature information STAT_SUB[m] and proceeds to step S233.

[0351] In steps S233 to S237, the control unit 201 performs the same processes as steps S211 to S214 in Fig. 9(b) by executing the function of the tracking target determination unit 222 in Fig. 3, and determining whether or not the feature information STAT[i] received from the WS 100 and the feature information STAT_SUB[m] obtained from the sub-image of the sub-camera 400 satisfy a predetermined condition.

[0352] According to the above-described eighth embodiment, by calculating feature information from the subject area to which letters are added based on the shooting information of the sub-camera 400, it is possible to obtain the same effects as those of the first to fifth embodiments.

[0353] [Embodiment 9] In the first to eighth embodiments, the height hview of the subject is calculated from the height hcam of the overhead camera 300 and the sub camera 400, the vertical angle of view φ, the vertical field of view H, the distance L to the tracked subject, and the overall height hobj of the subject, as described in Fig. 11. In the ninth embodiment, an example will be described in which skeletal information of the subject is calculated instead of calculating the height hview of the subject.

[0354] FIG. 26 illustrates an example of skeletal information of a subject.

[0355] FIG. 26(a) illustrates an example of a subject of an overhead image. FIG. 26(b) illustrates an example of a result of executing a skeleton estimation process on the subject of FIG. 26(a). The skeleton estimation process is added as a function of the image recognition unit 121. The control unit 101 inputs an image read from the volatile memory 102 by the inference unit 104 into a trained model for skeleton estimation created by performing machine learning such as deep learning, and performs an inference process. The inference result is the coordinates of each part of the body in the image and a score indicating the likelihood of the coordinates, as illustrated in FIG. 26(c). For a nose, the coordinates are oxnose and oynose, and the score is osnose. It is assumed that the EB200 also has a similar function.

[0356] Similarly, Fig. 26(d) illustrates an example of a subject in a sub-image. Fig. 26(e) illustrates the result of executing a skeleton estimation process on the subject in Fig. 26(d). Since the lower body of the subject in Fig. 26(d) is outside the angle of view, the coordinates and score information shown in Fig. 26(f) only cover the waist.

[0357] In the first to eighth embodiments, the height hview of the subject is calculated, but in the ninth embodiment, skeletal information as shown in Fig. 26(c) and Fig. 26(f) is calculated. That is, the height hview of the subject in Fig. 11(d) can be replaced with the difference in coordinates of each part of the skeletal information in Fig. 26.

[0358] For example, in FIG. 26(c), let us assume that the difference between the y coordinate of the nose, oynose, and the y coordinate of the left ankle, oyLankle, is the largest. In the image shown in FIG. 26(e), which includes only the waist, let us assume that the difference between the y coordinate of the nose, cynose, and the y coordinate of the left waist, cyLwaist, is the largest. In this case, the degree of agreement r obtained by Equation 8 can be calculated by the following Equation 12. (Formula 12) TIFF2025038858000013.tif12161 An example of the trimming amount T obtained from the above formula 12 and formula 9 is shown in Fig. 27(a). By trimming the overhead image in Fig. 27(a) using the skeleton information in Fig. 26(c) and Fig. 26(f), an image of the same range as the sub-image in Fig. 27(b) is obtained.

[0359] Similarly, for the letter size calculated in the eighth embodiment, the letter size hr shown in FIG. 27(c) can be calculated using the above formula 11.

[0360] In the ninth embodiment, the amount of trimming can be calculated by replacing the coordinate information of each part according to the change in posture of the subject. However, in consideration of the case where the skeleton estimation fails, it is desirable to also calculate the amount of trimming in the first to fourth embodiments and check the consistency with the amount of trimming calculated in the eighth and ninth embodiments. Also, although the inference model used in this embodiment was a skeleton estimation for a person, the same process may be performed for animals and objects by replacing it with a corresponding model.

[0361] [Other embodiments] The present invention can also be realized by a process in which a program for implementing one or more of the functions of the above-described embodiments is supplied to a system or device via a network or a storage medium, and one or more processors in a computer of the system or device read and execute the program. The present invention can also be realized by a circuit (e.g., ASIC) that implements one or more of the functions.

[0362] The invention is not limited to the above-described embodiments, and various modifications and variations are possible without departing from the spirit and scope of the invention. Accordingly, the following claims are appended to apprise the public of the scope of the invention.

[0363] The disclosure of this specification includes the following system, control device, and program. [Configuration 1] A system including a first imaging device and a second imaging device having different shooting directions, and a first control device and a second control device that control the second imaging device so as to track a predetermined subject based on a first image captured by the first imaging device or a second image captured by the second imaging device, The first control device includes: a first determination means for determining the predetermined subject from subjects included in the first image; an image processing means for cutting out a first region of the predetermined subject included in the first image based on a shooting range of the second image acquired from the second imaging device; a first generating means for generating first feature information of the first region of the predetermined subject; a first control means for controlling the second imaging device so as to track the predetermined subject; having The second control device includes: a second generating means for generating second feature information of a subject included in the second image; a second determination means for determining the predetermined subject based on the first feature information and the second feature information acquired from the first control device; A second control means for controlling the second imaging device so as to track the predetermined subject; A system comprising: [Configuration 2] The system described in configuration 1, characterized in that the image processing means determines an amount of cropping for cropping the first region based on first size information indicating an overall size of the specified subject and second size information indicating a size of the subject within a shooting range of the second imaging device. [Configuration 3] The system according to configuration 2, wherein the image processing means acquires the second size information based on the first size information and position information and imaging range of the second imaging device. [Configuration 4] The system described in configuration 3, wherein the first size information is a height of the subject from a reference position, the second size information is a height of the subject in a shooting range of the second imaging device, and the shooting range is a vertical angle of view of the second imaging device. [Configuration 5] The system described in any one of configurations 2 to 4, characterized in that the image processing means determines the cropping amount based on a table that associates a ratio of the second size information to the first size information with the cropping amount. [Configuration 6] 5. The system according to any one of configurations 2 to 4, wherein the cutout amount is calculated from a ratio of the second size information to the first size information. [Configuration 7] the image processing means sets a plurality of cropping amounts, generates a plurality of pieces of first feature information of a plurality of first regions cropped by the plurality of cropping amounts, and transmits the plurality of pieces of first feature information to the second control device; The second control device includes: The system according to any one of configurations 1 to 6, characterized in that the plurality of first characteristic information received from the first control device is compared with the second characteristic information. [Configuration 8] The second control device compares the first characteristic information generated by the first control device with the second characteristic information generated by the second generation means, the first feature information and the second feature information are information that can identify an identical subject when the same subject is photographed by a plurality of image capturing devices having different photographing directions, The system described in any one of configurations 1 to 7, characterized in that the first control device switches between a first state in which the first control device controls the second imaging device to track the specified subject based on the first feature information and a second state in which the second control device controls the second imaging device to track the specified subject based on the second feature information, based on a result of a comparison between the first feature information and the second feature information. [Configuration 9] The first control device transmits the first characteristic information to the second control device; the first control means switches to the second state when the first characteristic information and the second characteristic information satisfy a predetermined condition based on a result of the comparison in the second control device; The system according to configuration 8, wherein if the first characteristic information and the second characteristic information do not satisfy the predetermined condition, the system switches to the first state. [Configuration 10] the predetermined condition is that a similarity between the first feature information and the second feature information is equal to or greater than a threshold value; The second control device determines a similarity between the first feature information and the second feature information; The system according to configuration 9, further comprising notifying the first control device of the result of the determination. [Configuration 11] The system described in configuration 9 or 10, wherein the first control means, when the first feature information and the second feature information do not satisfy the specified condition, controls the shooting angle of view of the second imaging device to approach the shooting angle of view of the first imaging device capturing the first image including the specified subject. [Configuration 12] The system described in configuration 11, characterized in that the first control means controls the shooting angle of view of the second imaging device so as to reduce the difference between the size of the specified subject included in the first image and the size of the subject included in the second image. [Configuration 13] the second control means controls the second imaging device to track the predetermined object when the predetermined object is present within a shooting range of the second imaging device; When the predetermined object is no longer present within a shooting range of the second imaging device, notify the first control device that tracking of the predetermined object cannot be continued; 13. The system according to any one of configurations 8 to 12, wherein the first control means receives the notification and switches from the second state to the first state. [Configuration 14] 14. The system according to any one of configurations 8 to 13, characterized in that, when the specified subject is changed, the first control means switches from the second state to the first state. [Configuration 15] 15. The system of claim 14, wherein when the specified subject is changed, the first control means switches from the first state to the second state if the first feature information and the second feature information satisfy a specified condition. [Configuration 16] The first control device includes: a feature information determining means for determining the first feature information of the predetermined object and transmitting the first feature information to the second control device; a first control information generating means for generating first control information for controlling the second control device so as to track the predetermined subject; The second control device includes: and a second control information generating means for generating second control information for controlling the second control device so as to track the specified subject. [Configuration 17] 17. The system of claim 16, wherein the control information includes at least one of a pan value and a tilt value. [Configuration 18] The first generation means generates the first feature information by performing an inference process using a trained model with the first image as an input; The system according to any one of configurations 1 to 17, wherein the second generation means generates the second feature information by performing inference processing using a trained model with the second image as an input. [Configuration 19] The trained model includes a first model for object detection and a second model for object identification; the first generating means generates first information indicating a position of a subject included in the first image by performing an inference process using the first model with the first image as an input; generating feature information of a subject included in the first image by performing an inference process using the second model with the first image and the first information as input; the second generating means generates second information indicating a position of a subject included in the second image by performing an inference process using the first model with the second image as an input; The system described in configuration 18, characterized in that it generates feature information of the subject contained in the second image by performing inference processing using the second model with the second image and the second information as input. [Configuration 20] The second model for identifying a subject is obtained by photographing a plurality of subjects from a plurality of different photographing directions. The captured images are used as learning data, and images of the same subject are compared based on the similarity of their feature information. The system according to configuration 19, characterized in that the model is a trained model that has been trained to achieve the above. [Configuration 21] A system including a first imaging device and a second imaging device having different shooting directions, and a first control device and a second control device that control the second imaging device so as to track a predetermined subject based on a first image captured by the first imaging device or a second image captured by the second imaging device, The first control device includes: a first determination means for determining the predetermined subject from subjects included in the first image; A first generating means for generating first feature information of the predetermined subject; a first control means for controlling the second imaging device so as to track the predetermined subject; having The second control device includes: a second generating means for generating second feature information of a subject included in the second image; a second determination means for determining the predetermined subject based on the first feature information and the second feature information acquired from the first control device; A second control means for controlling the second control device so as to track the predetermined subject; having a control unit for controlling a shooting angle of the second imaging device in accordance with a size of the specified subject included in the first image when generating the first feature information to be transmitted to the second control device; [Configuration 22] The system described in configuration 21, characterized in that the first control means controls the shooting angle of view of the second imaging device so as to reduce the difference between the size of the specified subject included in the first image and the size of the subject included in the second image. [Configuration 23] The system described in configuration 22, wherein the first control means calculates a shooting angle of view of the second imaging device such that a difference between a size of the specified subject included in the first image and a size of the subject included in the second image is small, and controls the shooting angle of view of the second imaging device such that a difference between the calculated shooting angle of view and a current shooting angle of the second imaging device is equal to or less than a threshold value. [Configuration 24] 24. The system according to configuration 22 or 23, wherein the size of the subject is a height of the subject in a shooting angle of view of the imaging device, and the shooting angle of view is a vertical angle of view of the imaging device. [Configuration 25] 25. The system according to configuration 24, wherein the height of the subject is calculated from the overall height of the subject, the height position of the imaging device, and the vertical angle of view. [Configuration 26] 26. The system according to any one of configurations 21 to 25, wherein the subject included in the second image is the subject closest to a center of the angle of view of the second image. [Configuration 27] The second control device compares the first characteristic information generated by the first control device with the second characteristic information generated by the second generation means, the first feature information and the second feature information are information that can identify an identical subject when the same subject is photographed by a plurality of image capturing devices having different photographing directions, the first control means stores a photographing angle of view of the second imaging device before the photographing angle of view is changed; 27. The system according to any one of configurations 21 to 26, wherein after the comparison is performed, the imaging angle of view of the second imaging device is returned to the imaging angle before it was changed. [Configuration 28] The system described in Configuration 27, wherein the first control means, when the result of the comparison shows that the similarity between the first feature information and the second feature information is equal to or greater than a threshold, returns the angle of view of the second imaging device to the angle of view before it was changed. [Configuration 29] 29. The system according to any one of configurations 21 to 28, wherein the first control means controls the photographing angle of view by a zoom function. [Configuration 30] The system described in any one of configurations 27 to 29, characterized in that the second imaging device notifies the first control device and / or the second control device that the shooting angle of view of the second imaging device has returned to the shooting angle of view before it was changed. [Configuration 31] An image processing means for cutting out a part of an image, the first control means stores the photographing angle of view of the second image pickup device before the change; 29. The system according to claim 27 or 28, wherein after the comparison is performed, the image processing means creates the second image with the shooting angle of view of the second imaging device before the change. [Configuration 32] The system described in any one of configurations 21 to 31, characterized in that the first control device switches between a first state in which the first control device controls the second imaging device to track the specified subject based on the first feature information and a second state in which the second control device controls the second imaging device to track the specified subject based on the second feature information based on a result of a comparison between the first feature information and the second feature information. [Configuration 33] The first control device transmits the first characteristic information to the second control device; the first control means switches to the second state when the first characteristic information and the second characteristic information satisfy a predetermined condition based on a result of the comparison; 33. The system according to configuration 32, characterized in that if the first characteristic information and the second characteristic information do not satisfy the predetermined condition, the system switches to the first state. [Configuration 34] the predetermined condition is that a similarity between the first feature information and the second feature information is equal to or greater than a threshold value; The system described in configuration 33, wherein the second control means determines the similarity between the first feature information and the second feature information and notifies the first control device of the result of the determination. [Configuration 35] the second control means controls the second imaging device to track the predetermined object when the predetermined object is present in a photographing angle of view of the second imaging device; When the predetermined object is no longer present in the imaging angle of view of the second imaging device, notify the first control device that tracking of the predetermined object cannot be continued; 33. The system according to configuration 32, wherein the first control means receives the notification and switches from the second state to the first state. [Configuration 36] 36. The system of any one of configurations 32 to 35, wherein the first control means switches from the second state to the first state when the specified subject is changed. [Configuration 37] 37. The system of claim 36, wherein when the specified subject is changed, the first control means switches from the first state to the second state if the first feature information and the second feature information satisfy a specified condition. [Configuration 38] The first control device includes: a feature information determining means for determining the first feature information of the predetermined object and transmitting the first feature information to the second control device; a first control information generating means for generating first control information for controlling the second control device so as to track the predetermined subject; The second control device includes: and a second control information generating means for generating second control information for controlling the second control device to track the specified subject. [Configuration 39] 39. The system of claim 38, wherein the control information includes at least one of a pan value and a tilt value. [Configuration 40] The first generation means generates the first feature information by performing an inference process using a trained model with the first image as an input; The system according to any one of configurations 21 to 39, wherein the second generation means generates the second feature information by performing inference processing using a trained model with the second image as input. [Configuration 41] The trained model includes a first model for object detection and a second model for object identification; the first generating means generates first information indicating a position of a subject included in the first image by performing an inference process using the first model with the first image as an input; generating feature information of a subject included in the first image by performing an inference process using the second model with the first image and the first information as input; the second generating means generates second information indicating a position of a subject included in the second image by performing an inference process using the first model with the second image as an input; The system described in configuration 40, characterized in that it generates feature information of the subject contained in the second image by performing inference processing using the second model with the second image and the second information as input. [Configuration 42] The system described in configuration 41, wherein the second model for identifying a subject is a trained model that has been trained using images of a plurality of subjects taken from a plurality of different shooting directions as training data, so as to increase the similarity of feature information for images of the same subject. [Configuration 43] A control device that controls a second imaging device to track a predetermined subject based on a first image captured by a first imaging device or a second image captured by a second imaging device having a shooting direction different from that of the first imaging device, A determination means for determining the predetermined subject from subjects included in the first image; an image processing means for cutting out a first region of the predetermined subject included in the first image based on a shooting range of the second image acquired from the second imaging device; A generating means for generating first feature information of the first region of the predetermined subject; a control unit for controlling the second imaging device so as to track the predetermined subject; The control device, wherein the control means transmits the first feature information to an external device that controls the second imaging device. [Configuration 44] A control device that controls a second imaging device so as to track a predetermined subject based on a second image captured by the second imaging device having a different imaging direction from that of the first imaging device, A generating means for generating second feature information of a subject included in the second image; a determination means for determining the predetermined subject based on first feature information of the predetermined subject included in a first image captured by the first imaging device and acquired from an external device, and the second feature information; a control unit for controlling the second imaging device so as to track the predetermined subject; The control device, characterized in that the first feature information is feature information of a first region of the specified subject cut out from the first image based on a shooting range of the second image. [Configuration 45] A control device that controls a second imaging device to track a predetermined subject based on a first image captured by a first imaging device or a second image captured by a second imaging device having a shooting direction different from that of the first imaging device, a first determination means for determining the predetermined subject from subjects included in the first image; an image processing means for cutting out a first region of the predetermined subject included in the first image based on a shooting range of the second image acquired from the second imaging device; a first generating means for generating first feature information of the first region of the predetermined subject; a second generating means for generating second feature information of a subject included in the second image; a second determination means for determining the predetermined subject based on the first feature information and the second feature information; and a control unit that controls the second imaging device so as to track the predetermined subject based on the first feature information or the second feature information. [Configuration 46] A control device that controls a second imaging device to track a predetermined subject based on a first image captured by a first imaging device or a second image captured by a second imaging device having a shooting direction different from that of the first imaging device, A determination means for determining the predetermined subject from subjects included in the first image; A generating means for generating first feature information of the predetermined subject; a control unit for controlling the second imaging device so as to track the predetermined subject; The control device is characterized in that, when generating the first feature information to be transmitted to an external device that controls the second imaging device, the control means controls the shooting angle of view of the second imaging device in accordance with the size of the specified subject included in the first image. [Configuration 47] A control device that controls a second imaging device so as to track a predetermined subject based on a second image captured by the second imaging device having a different imaging direction from that of the first imaging device, A generating means for generating second feature information of a subject included in the second image; a determination means for determining the predetermined subject based on first feature information of the predetermined subject included in a first image captured by the first imaging device and acquired from an external device, and the second feature information; and a control unit that controls the second imaging device so as to track the predetermined subject. [Configuration 48] A control device that controls a second imaging device to track a predetermined subject based on a first image captured by a first imaging device or a second image captured by a second imaging device having a shooting direction different from that of the first imaging device, a first generating means for generating first feature information of the predetermined object included in the first image; a second generating means for generating second feature information of a subject included in the second image; a control unit that controls the second imaging device so as to track the predetermined subject based on the first feature information or the second feature information, The control device is characterized in that, when generating the second feature information from the second image, the control means controls the shooting angle of view of the second imaging device in accordance with the size of the specified subject included in the first image. [Configuration 49] A system including a first imaging device and a second imaging device having different shooting directions, and a first control device and a second control device that control the second imaging device so as to track a predetermined subject based on a first image captured by the first imaging device or a second image captured by the second imaging device, The first control device includes: a first determination means for determining the predetermined subject from subjects included in the first image; a calculation means for calculating an imparting area based on a ratio between the predetermined object included in the first image and an object included in the second image within a photographing angle of view; a first generating means for generating first feature information of a first region of the predetermined subject; a first control means for controlling the second imaging device so as to track the predetermined subject; having The second control device includes: a second generating means for generating second feature information of a subject included in the second image; an image processing means for generating information in which an area of ​​a subject included in a second image is expanded in accordance with the added area acquired from the first control device; a second determination means for determining the predetermined subject based on the first feature information and the second feature information acquired from the first control device; A second control means for controlling the second imaging device so as to track the predetermined subject; A system comprising: [Configuration 50] The system described in configuration 49, characterized in that the calculation means, the image processing means, calculates a ratio indicating the second area relative to the first area and an assigned area based on first size information indicating an overall size of the specified subject and second size information indicating the size of the subject in the shooting range of the second imaging device. [Configuration 51] The system described in configuration 50, characterized in that the first size information is a height of the subject from a reference position, the second size information is a height of the subject in a shooting range of the second imaging device, and the shooting range is a vertical angle of view of the second imaging device. [Configuration 52] The system described in configuration 50, characterized in that the first size information is a width or height of the subject in the image captured by the first imaging device, and the second size information is a width or height of the subject in the image captured by the second imaging device. [Configuration 53] The first control device includes: a first estimation means for estimating a bone structure of a subject in an image captured by the first imaging device; The second control device includes: a second estimation means for estimating a bone structure of a subject in an image captured by the second imaging device; The system described in configuration 1, wherein the image processing means determines the cutout amount based on the skeletal information obtained by the first estimation means and the skeletal information obtained by the second estimation means. [Configuration 54] The first control device includes: a first estimation means for estimating a bone structure of a subject in an image captured by the first imaging device; The second control device includes: a second estimation means for estimating a bone structure of a subject in an image captured by the second imaging device; The system described in any one of configurations 49 to 52, characterized in that the calculation means determines the imparting area based on skeletal information obtained by the first estimation means and skeletal information obtained by the second estimation means. [Configuration 55] A program for causing a computer to function as a control device according to any one of configurations 43 to 48. [Explanation of symbols]

[0364] 100...first control device (workstation / WS), 200...second control device (edge ​​box / EB), 300...first imaging device (overhead camera), 400...second imaging device (sub-camera), 101, 201, 301, 401...control unit

Claims

1. A system including a first imaging device and a second imaging device having different shooting directions, and a first control device and a second control device that control the second imaging device so as to track a predetermined subject based on a first image captured by the first imaging device or a second image captured by the second imaging device, The first control device includes: a first determination means for determining the predetermined subject from subjects included in the first image; an image processing means for cutting out a first area of ​​the predetermined subject included in the first image based on a shooting range of the second image acquired from the second imaging device; a first generating means for generating first feature information of the first region of the predetermined subject; a first control means for controlling the second imaging device so as to track the predetermined subject; having The second control device includes: a second generating means for generating second feature information of a subject included in the second image; a second determination means for determining the predetermined subject based on the first feature information and the second feature information acquired from the first control device; A second control means for controlling the second imaging device so as to track the predetermined subject; A system comprising:

2. The system according to claim 1, characterized in that the image processing means determines an amount of cropping for cropping the first region based on first size information indicating an overall size of the specified subject and second size information indicating a size of the subject within a shooting range of the second imaging device.

3. 3. The system according to claim 2, wherein the image processing means acquires the second size information based on the first size information and position information and a photographing range of the second image pickup device.

4. 4. The system according to claim 3, wherein the first size information is a height of the subject from a reference position, the second size information is a height of the subject in a shooting range of the second imaging device, and the shooting range is a vertical angle of view of the second imaging device.

5. 3. The system according to claim 2, wherein said image processing means determines said cut-out amount based on a table in which a ratio of said second size information to said first size information corresponds to said cut-out amount.

6. The system according to claim 2 , wherein the cutout amount is calculated from a ratio of the second size information to the first size information.

7. the image processing means sets a plurality of cropping amounts, generates a plurality of pieces of the first feature information of a plurality of the first regions cropped by the plurality of cropping amounts, and transmits the plurality of pieces of the first feature information to the second control device; The second control device includes:

2. The system of claim 1, further comprising: comparing the plurality of first characteristic information received from the first control device with the second characteristic information.

8. The second control device compares the first characteristic information generated by the first control device with the second characteristic information generated by the second generation means, the first feature information and the second feature information are information that can identify an identical subject when the same subject is photographed by a plurality of image capturing devices having different photographing directions, The system according to claim 1, characterized in that the first control device switches between a first state in which the first control device controls the second imaging device to track the specified subject based on the first feature information and a second state in which the second control device controls the second imaging device to track the specified subject based on the second feature information, based on a result of a comparison between the first feature information and the second feature information.

9. The first control device transmits the first characteristic information to the second control device; the first control means switches to the second state when the first characteristic information and the second characteristic information satisfy a predetermined condition based on a result of the comparison in the second control device; The system according to claim 8 , wherein the system switches to the first state if the first characteristic information and the second characteristic information do not satisfy the predetermined condition.

10. the predetermined condition is that a similarity between the first feature information and the second feature information is equal to or greater than a threshold value; 10. The system according to claim 9, wherein the second control device determines a similarity between the first feature information and the second feature information, and notifies the first control device of a result of the determination.

11. The system according to claim 9, characterized in that, when the first feature information and the second feature information do not satisfy the specified condition, the first control means controls the shooting angle of view of the second imaging device to approach the shooting angle of view of the first imaging device capturing the first image including the specified subject.

12. The system according to claim 11, wherein the first control means controls the shooting angle of view of the second imaging device so as to reduce a difference between a size of the specified subject included in the first image and a size of the subject included in the second image.

13. the second control means controls the second imaging device to track the predetermined object when the predetermined object is present within a shooting range of the second imaging device; When the predetermined object is no longer present within a shooting range of the second imaging device, notify the first control device that tracking of the predetermined object cannot be continued; 9. The system according to claim 8, wherein the first control means receives the notification and switches from the second state to the first state.

14. 9. The system of claim 8, wherein said first control means switches from said second state to said first state when said predetermined subject is changed.

15. The system described in claim 14 , wherein when the specified subject is changed, the first control means switches from the first state to the second state if the first feature information and the second feature information satisfy a specified condition.

16. The first control device includes: a feature information determining means for determining the first feature information of the predetermined subject and transmitting the first feature information to the second control device; a first control information generating unit configured to generate first control information for controlling the second control device so as to track the predetermined subject; The second control device includes:

9. The system according to claim 8, further comprising: second control information generating means for generating second control information for controlling said second control device so as to track said predetermined subject.

17. 17. The system of claim 16, wherein the control information includes at least one of a pan value and a tilt value.

18. The first generating means generates the first feature information by performing an inference process using a trained model with the first image as an input; The system according to claim 1, characterized in that the second generation means generates the second feature information by performing inference processing using a trained model with the second image as input.

19. The trained model includes a first model for object detection and a second model for object identification, the first generating means generates first information indicating a position of a subject included in the first image by performing an inference process using the first model with the first image as an input; performing an inference process using the second model with the first image and the first information as inputs to generate feature information of a subject included in the first image; the second generating means generates second information indicating a position of a subject included in the second image by performing an inference process using the first model with the second image as an input; The system described in claim 18, characterized in that the second image and the second information are used as inputs to perform inference processing using the second model, thereby generating feature information of the subject contained in the second image.

20. The system described in claim 19, characterized in that the second model for subject identification is a trained model that has been trained using images of multiple subjects taken from multiple different shooting directions as learning data, so as to increase the similarity of feature information for images of the same subject.

21. A system including a first imaging device and a second imaging device having different shooting directions, and a first control device and a second control device that control the second imaging device so as to track a predetermined subject based on a first image captured by the first imaging device or a second image captured by the second imaging device, The first control device includes: a first determination means for determining the predetermined subject from subjects included in the first image; a first generating means for generating first feature information of the predetermined subject; a first control means for controlling the second imaging device so as to track the predetermined subject; having The second control device includes: a second generating means for generating second feature information of a subject included in the second image; a second determination means for determining the predetermined subject based on the first feature information and the second feature information acquired from the first control device; A second control means for controlling the second control device so as to track the predetermined subject; having The system is characterized in that the first control means controls the shooting angle of view of the second imaging device in accordance with the size of the specified subject contained in the first image when generating the first feature information to be transmitted to the second control device.

22. The system according to claim 21, wherein the first control means controls the shooting angle of view of the second imaging device so as to reduce a difference between a size of the specified subject included in the first image and a size of the subject included in the second image.

23. The system according to claim 22, wherein the first control means calculates a shooting angle of view of the second imaging device such that a difference between a size of the specified subject included in the first image and a size of the subject included in the second image is small, and controls the shooting angle of view of the second imaging device such that a difference between the calculated shooting angle of view and a current shooting angle of the second imaging device is equal to or smaller than a threshold value.

24. 23. The system according to claim 22, wherein the size of the subject is a height of the subject in a shooting angle of view of the imaging device, and the shooting angle of view is a vertical angle of view of the imaging device.

25. 25. The system according to claim 24, wherein the height of the subject is calculated from the overall height of the subject, the height position of the imaging device, and the vertical angle of view.

26. 22. The system of claim 21, wherein the object included in the second image is the object closest to a center of the angle of view of the second image.

27. The second control device compares the first characteristic information generated by the first control device with the second characteristic information generated by the second generation means, the first feature information and the second feature information are information that can identify an identical subject when the same subject is photographed by a plurality of image capturing devices having different photographing directions, the first control means stores a photographing angle of view of the second imaging device before the photographing angle of view is changed; 22. The system of claim 21, wherein after the comparison is performed, the angle of view of the second image capture device is returned to the angle of view before the change.

28. The system according to claim 27, characterized in that, when the result of the comparison indicates that the similarity between the first feature information and the second feature information is equal to or greater than a threshold, the first control means restores the shooting angle of view of the second imaging device to the shooting angle before it was changed.

29. 22. The system according to claim 21, wherein the first control means controls the photographing angle of view by a zoom function.

30. The system according to claim 27, characterized in that the second imaging device notifies the first control device and / or the second control device that the imaging angle of view of the second imaging device has returned to the imaging angle before it was changed.

31. An image processing means for cutting out a part of an image, the first control means stores the photographing angle of view of the second image pickup device before the change; 28. The system of claim 27, wherein after the comparison is performed, the image processing means creates the second image of the pre-changed photographing angle of view of the second image capture device.

32. The system described in claim 21, characterized in that the first control device switches between a first state in which the first control device controls the second imaging device to track the specified subject based on the first feature information and a second state in which the second control device controls the second imaging device to track the specified subject based on the second feature information, based on a result of a comparison between the first feature information and the second feature information.

33. The first control device transmits the first characteristic information to the second control device; the first control means switches to the second state when the first characteristic information and the second characteristic information satisfy a predetermined condition based on a result of the comparison; 33. The system of claim 32, wherein the system switches to the first state if the first characteristic information and the second characteristic information do not satisfy the predetermined condition.

34. the predetermined condition is that a similarity between the first feature information and the second feature information is equal to or greater than a threshold value; 34. The system according to claim 33, wherein the second control means determines a similarity between the first feature information and the second feature information, and notifies the first control device of a result of the determination.

35. the second control means controls the second imaging device to track the predetermined object when the predetermined object is present in a photographing angle of view of the second imaging device; When the predetermined object is no longer present in the photographing angle of view of the second imaging device, notify the first control device that tracking of the predetermined object cannot be continued; 33. The system of claim 32, wherein the first control means switches from the second state to the first state upon receiving the notification.

36. 33. The system of claim 32, wherein said first control means switches from said second state to said first state when said predetermined subject is changed.

37. The system described in claim 36, wherein when the specified subject is changed, the first control means switches from the first state to the second state if the first feature information and the second feature information satisfy a specified condition.

38. The first control device includes: a feature information determining means for determining the first feature information of the predetermined subject and transmitting the first feature information to the second control device; a first control information generating unit configured to generate first control information for controlling the second control device so as to track the predetermined subject; The second control device includes:

33. The system according to claim 32, further comprising: second control information generating means for generating second control information for controlling said second control device so as to track said predetermined subject.

39. 40. The system of claim 38, wherein the control information includes at least one of pan and tilt values.

40. The first generating means generates the first feature information by performing an inference process using a trained model with the first image as an input; The system according to claim 21, characterized in that the second generation means generates the second feature information by performing inference processing using a trained model with the second image as input.

41. The trained model includes a first model for object detection and a second model for object identification, the first generating means generates first information indicating a position of a subject included in the first image by performing an inference process using the first model with the first image as an input; performing an inference process using the second model with the first image and the first information as inputs to generate feature information of a subject included in the first image; the second generating means generates second information indicating a position of a subject included in the second image by performing an inference process using the first model with the second image as an input; The system described in claim 40, characterized in that an inference process is performed using the second model with the second image and the second information as input, thereby generating feature information of the subject contained in the second image.

42. The system described in claim 41, characterized in that the second model for subject identification is a trained model that has been trained using images of multiple subjects taken from multiple different shooting directions as learning data, so as to increase the similarity of feature information for images of the same subject.

43. A control device that controls a second imaging device to track a predetermined subject based on a first image captured by a first imaging device or a second image captured by a second imaging device having a shooting direction different from that of the first imaging device, a determining means for determining the predetermined subject from subjects included in the first image; an image processing means for cutting out a first area of ​​the predetermined subject included in the first image based on a shooting range of the second image acquired from the second imaging device; A generating means for generating first feature information of the first region of the predetermined subject; a control unit for controlling the second imaging device so as to track the predetermined subject; The control device according to claim 1, wherein the control means transmits the first feature information to an external device that controls the second imaging device.

44. A control device that controls a second imaging device so as to track a predetermined subject based on a second image captured by the second imaging device having a shooting direction different from that of the first imaging device, A generating means for generating second feature information of a subject included in the second image; a determination means for determining the predetermined subject based on first feature information of the predetermined subject included in a first image captured by the first imaging device and acquired from an external device, and the second feature information; a control unit for controlling the second imaging device so as to track the predetermined subject; A control device, characterized in that the first feature information is feature information of a first region of the specified subject cut out from the first image based on a shooting range of the second image.

45. A control device that controls a second imaging device to track a predetermined subject based on a first image captured by a first imaging device or a second image captured by a second imaging device having a shooting direction different from that of the first imaging device, a first determination means for determining the predetermined subject from subjects included in the first image; an image processing means for cutting out a first area of ​​the predetermined subject included in the first image based on a shooting range of the second image acquired from the second imaging device; a first generating means for generating first feature information of the first region of the predetermined subject; a second generating means for generating second feature information of a subject included in the second image; a second determination means for determining the predetermined subject based on the first feature information and the second feature information; and a control unit that controls the second imaging device so as to track the predetermined subject based on the first feature information or the second feature information.

46. A control device that controls a second imaging device to track a predetermined subject based on a first image captured by a first imaging device or a second image captured by a second imaging device having a shooting direction different from that of the first imaging device, a determining means for determining the predetermined subject from subjects included in the first image; A generating means for generating first feature information of the predetermined subject; a control unit for controlling the second imaging device so as to track the predetermined subject; The control device is characterized in that, when generating the first feature information to be transmitted to an external device that controls the second imaging device, the control means controls the shooting angle of view of the second imaging device in accordance with the size of the specified subject included in the first image.

47. A control device that controls a second imaging device so as to track a predetermined subject based on a second image captured by the second imaging device having a shooting direction different from that of the first imaging device, A generating means for generating second feature information of a subject included in the second image; a determination means for determining the predetermined subject based on first feature information of the predetermined subject included in a first image captured by the first imaging device and acquired from an external device, and the second feature information; and a control unit for controlling the second imaging device so as to track the predetermined subject.

48. A control device that controls a second imaging device to track a predetermined subject based on a first image captured by a first imaging device or a second image captured by a second imaging device having a shooting direction different from that of the first imaging device, a first generating means for generating first feature information of the predetermined subject included in the first image; a second generating means for generating second feature information of a subject included in the second image; a control unit that controls the second imaging device so as to track the predetermined subject based on the first feature information or the second feature information, The control device is characterized in that, when generating the second feature information from the second image, the control means controls the shooting angle of view of the second imaging device in accordance with the size of the specified subject contained in the first image.

49. A system including a first imaging device and a second imaging device having different shooting directions, and a first control device and a second control device that control the second imaging device so as to track a predetermined subject based on a first image captured by the first imaging device or a second image captured by the second imaging device, The first control device includes: a first determination means for determining the predetermined subject from subjects included in the first image; a calculation means for calculating an imparting area based on a ratio of the predetermined object included in the first image to an object included in the second image within a photographing angle of view; a first generating means for generating first feature information of a first region of the predetermined subject; a first control means for controlling the second imaging device so as to track the predetermined subject; having The second control device includes: a second generating means for generating second feature information of a subject included in the second image; an image processing means for generating information in which a region of a subject included in a second image is expanded in accordance with the region to be added acquired from the first control device; a second determination means for determining the predetermined subject based on the first feature information and the second feature information acquired from the first control device; A second control means for controlling the second imaging device so as to track the predetermined subject; A system comprising:

50. The system described in claim 49, characterized in that the calculation means, the image processing means, calculates a ratio indicating the second area relative to the first area and an assigned area based on first size information indicating an overall size of the specified subject and second size information indicating the size of the subject in the shooting range of the second imaging device.

51. 51. The system of claim 50, wherein the first size information is a height of the subject from a reference position, the second size information is a height of the subject in a shooting range of the second imaging device, and the shooting range is a vertical angle of view of the second imaging device.

52. The system of claim 50, wherein the first size information is a width or height of a subject in an image captured by the first imaging device, and the second size information is a width or height of a subject in an image captured by the second imaging device.

53. The first control device includes: a first estimation means for estimating a bone structure of a subject in an image captured by the first imaging device; The second control device includes: a second estimation means for estimating a bone structure of a subject in an image captured by the second imaging device; 2. The system according to claim 1, wherein the image processing means determines the cutout amount based on the skeletal information obtained by the first estimating means and the skeletal information obtained by the second estimating means.

54. The first control device includes: a first estimation means for estimating a bone structure of a subject in an image captured by the first imaging device; The second control device includes: a second estimation means for estimating a bone structure of a subject in an image captured by the second imaging device; 53. The system according to claim 49, wherein the calculation means determines the imparting area based on skeletal information obtained by the first estimation means and skeletal information obtained by the second estimation means.

55. A program for causing a computer to function as the control device according to any one of claims 43 to 48.

Images