Photographing control device and photographing control method, and imaging system

Abstract

To provide a photographing control device and a photographing control method capable of automatic photographing control with a higher degree of freedom, while achieving power saving.SOLUTION: A photographing control device acquires information from the state of or images from a main camera, of a plurality of cameras. The photographing control device controls the operation of a sub camera, of the plurality of cameras, on the basis of the information and a role set to the sub camera. The photographing control device acquires, as the information, information on a target subject of the main camera and information on the angle of view of the main camera. The photographing control device controls the photographing direction and angle of view of the sub camera on the basis of the information and the role set to the sub camera.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to an imaging control device, an imaging control method, and an imaging system, and more particularly to a technique for controlling a plurality of imaging devices. [Background technology]

[0002] Patent Document 1 describes an imaging system in which a plurality of cameras are divided into main cameras and sub-cameras, and the sub-cameras are controlled so as to capture the same subject as that of the main camera. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2020-25248 A Summary of the Invention [Problem to be solved by the invention]

[0004] In Patent Document 1, since the shooting of the sub-camera can be automatically controlled, labor saving can be realized. However, there is room for improvement in the degree of freedom of the shooting control of the sub-camera.

[0005] Therefore, in one aspect, the present invention provides an imaging control device and an imaging control method that realize labor saving and enable automatic imaging control with a higher degree of freedom. [Means for solving the problem]

[0006] In one aspect, the present invention provides a shooting control device having an acquisition means for acquiring information from the state or image of a main camera among a plurality of cameras, and a control means for controlling the operation of a sub-camera among the plurality of cameras based on a role set for the sub-camera and the information, wherein the acquisition means acquires, as information, information on a subject of interest of the main camera and information on the angle of view of the main camera, and the control means controls the shooting direction and angle of view of the sub-camera based on the role and information set for the sub-camera. Effect of the Invention

[0007] According to the present invention, it is possible to provide an imaging control device and an imaging control method that realize labor saving and enable automatic imaging control with a higher degree of freedom. [Brief description of the drawings]

[0008] [Figure 1] Schematic diagram of an imaging system according to a first embodiment. [Diagram 2] FIG. 1 is a block diagram showing an example of the functional arrangement of each device in an imaging system according to a first embodiment; [Diagram 3] FIG. 2 is a diagram illustrating the main operations and signal flows of the imaging control device according to the embodiment. [Figure 4] FIG. 13 is a diagram showing an example of roles and control contents that can be set for a sub-camera in an embodiment. [Diagram 5] Flowchart of role determination process in the first embodiment [Figure 6] 1 is a flowchart showing the operation of each device in an imaging system according to an embodiment of the present invention; [Figure 7] FIG. 1 is a diagram for explaining coordinate conversion in an embodiment. [Figure 8] FIG. 1 is a diagram relating to subject detection and coordinate transformation in an embodiment. [Figure 9] Schematic diagram of the operation control of the sub-camera in the first embodiment. [Figure 10] FIG. 13 is a schematic diagram of another operational control of the sub camera in the first embodiment; [Figure 11]FIG. 1 is a diagram for explaining pan value calculation in an embodiment; [Figure 12] FIG. 1 is a diagram for explaining tilt value calculation in an embodiment; [Figure 13] FIG. 13 is a diagram showing an example of mapping of zoom values ​​between the main camera and the sub camera in the first embodiment; [Figure 14] 11 is a flowchart for determining the control content according to the role of the sub-camera in the first embodiment. [Figure 15] Schematic diagram of control according to the role of the sub-camera in the first embodiment. [Figure 16] Schematic diagram of control according to the role of the sub-camera in the first embodiment. [Figure 17] FIG. 13 is a schematic diagram of a tracking operation of a plurality of subjects in a modified example of the first embodiment; [Figure 18] Schematic diagram of an imaging system according to a second embodiment. [Figure 19] FIG. 11 is a diagram showing an example of roles and control contents that can be set in the second embodiment. [Figure 20] FIG. 13 is a schematic diagram showing an example of control regarding a tracking subject of a sub camera in the second embodiment; DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] The present invention will be described in detail below based on its exemplary embodiments with reference to the accompanying drawings. Note that the following embodiments do not limit the invention according to the claims. In addition, although multiple features are described in the embodiments, not all of them are necessarily essential to the invention, and multiple features may be combined arbitrarily. Furthermore, in the accompanying drawings, the same reference numbers are used for the same or similar configurations, and duplicated explanations are omitted.

[0010] <First embodiment> (Overview of the multi-camera imaging system) 1 is a schematic diagram showing an example of the configuration of a multi-camera imaging system 10 (hereinafter simply referred to as an imaging system) according to this embodiment. The imaging system 10 has multiple cameras 300, 400, 500, an imaging control device 100, and a role control device 600. The multiple cameras 300, 400, 500, the imaging control device 100, and the role control device 600 are communicatively connected via a communication network 700.

[0011] The communication network 700 complies with known wired or wireless communication standards such as the IEEE802.3 series, IEEE802.11 series, etc. Each of the multiple cameras 300, 400, 500, the shooting control device 100, and the role control device 600 has a communication interface that complies with the standard of the communication network 700.

[0012] Of the multiple cameras 300, 400, and 500, camera 300 captures the entirety of a predetermined shooting range. The shooting range is set as a range in which a subject to be shot may exist in a studio, for example. Therefore, the video of camera 300 captures all of the subjects within the shooting range.

[0013] The purpose of the camera 300 is to capture an image for detecting a subject of the shooting target present within the shooting range. Therefore, the shooting direction and angle of view of the camera 300 are determined according to the position of the camera 300 and the shooting range, and are basically fixed during shooting. In addition, it is preferable that the camera 300 captures the entire shooting range so that it is not hidden by objects outside the shooting range. Therefore, the camera 300 is installed in a position where it overlooks the entire shooting range. In order to distinguish the camera 300 from the other cameras 400 and 500 whose shooting direction and angle of view during shooting are not basically fixed, the camera 300 will be referred to as an overhead camera below. However, the installation position of the camera 300 is not limited to a position where it overlooks the shooting range. The operation of the overhead camera 300 can be controlled by the shooting control device 100.

[0014] The cameras 400 and 500 are, for example, PTZ cameras, and their operations, including the shooting direction (pan and tilt angles) and the angle of view (zoom), can be controlled from an external device. Here, it is assumed that the user of the imaging system controls the operation of the camera 500, and the shooting control device 100 controls the operation of the camera 400. In the following, the camera 500 is called the main camera and the camera 400 is called the sub-camera, since the shooting control device 100 controls the operation of the camera 400 based on the state of the camera 500. For ease of explanation and understanding, only one sub-camera 400 is shown, but there may be more than one sub-camera. The main camera 500 may be directly operated by the user. The cameras 400 and 500 may be configured so that the shooting direction (pan and tilt angles) can be controlled by attaching the camera body to a tripod head. The cameras 400 and 500 may be configured so that a zoomable interchangeable lens is attached to the camera body.

[0015] Here, in this embodiment, it is assumed that the role control device 600 has an operator. The shooting control device 100 may also have an operator (user), but this is not essential. The operator of the role control device 600 may be the user of the shooting control device 100. Since the shooting of the overhead camera 300 and the sub camera 400 is controlled by the shooting control device 100, a photographer is not required. It is assumed that the main camera 500 has an operator or photographer. In this way, a configuration that does not require operators or photographers for some devices can achieve labor saving.

[0016] 1 shows that all signals are communicated through the communication network 700, but for example, the video signal and the control signal may be communicated in a different manner. For example, each of the multiple cameras 300, 400, 500 may directly supply the video signal to the shooting control device 100 via a cable. The cameras 300, 400, 500 and the shooting control device 100 have a communication circuit according to the standard of the video signal. The standard of the video signal is, for example, the SDI (Serial Digital Interface) standard or the HDMI (High-Definition Multimedia Interface) (registered trademark), but is not limited to these.

[0017] The photography control device 100 detects a subject from a video signal received from the overhead camera 300. The photography control device 100 determines the photography direction and angle of view of the sub-camera based on the subject detection result, the state of the main camera 500, and the role set for the sub-camera. The photography control device 100 transmits a control command including the determined photography direction and angle of view to the sub-camera 400. By changing the role setting, the method of determining the photography direction and angle of view of the sub-camera 400 can be changed, and the degree of freedom of the operation control of the sub-camera 400 can be increased.

[0018] (Example of functional configuration of each device) Fig. 2 is a block diagram showing an example of the functional configuration of each device constituting the multi-camera imaging system shown in Fig. 1. The configuration expressed as a functional block in the drawing can be realized by an integrated circuit such as an ASIC or an FPGA, by a discrete circuit, or by a combination of a memory and a processor that executes a program stored in the memory. Also, one functional block may be realized by multiple integrated circuit packages, or multiple functional blocks may be realized by one integrated circuit package. Also, the same functional block may be implemented in different configurations depending on the operating environment, required capabilities, etc.

[0019] (Photography control device 100) First, a functional configuration example of the imaging control device 100 will be described. The imaging control device 100 may be a general-purpose computer device such as a personal computer or a workstation. The imaging control device 100 has a configuration in which a CPU 101, a RAM 102, a ROM 103, an inference unit 104, a network interface (I / F) 105, a user input unit 106, and a display unit 108 are mutually connected via an internal bus 110.

[0020] The CPU 101 is a microprocessor capable of executing programmed instructions. The CPU 101, for example, loads a program stored in a ROM 103 into a RAM 102 and executes the program to realize the functions of the imaging control device 100, which will be described later. The CPU 101, for example, can realize the functions of the imaging control device 100 by executing an imaging control application that runs on an operating system (OS).

[0021] The RAM 102 is used to load programs executed by the CPU 101 and to temporarily store data to be processed by the CPU 101, data currently being processed, etc. Furthermore, a part of the RAM 102 may be used as a video memory for the display unit 108.

[0022] The ROM 103 is a rewritable non-volatile memory, and stores the programs (OS and applications) executed by the CPU 101, user data, and the like.

[0023] The inference unit 104 executes a detection process of a subject area using a machine learning model for the image of the overhead camera 300. The inference unit 104 can be implemented using a hardware circuit capable of executing the calculation of the machine learning model at high speed, such as a GPU (Graphics Processing Unit) or an NPU (Neural network Processing Unit). Alternatively, the inference unit 104 may be implemented using a reconfigurable logic circuit such as an FPGA (Field-Programmable Gate Array). The CPU 101 may execute a program to realize the function of the inference unit 104.

[0024] The machine learning model may be a convolutional neural network (CNN) trained according to the type of subject to be detected. Here, the inference unit 104 detects a human body region or a human face region as a subject region from an input image. The inference unit 104 outputs the position and size of a rectangular region inscribed in the subject region and the detection reliability for each detected subject region. Note that, a plurality of types of machine learning models may be used to execute detection processing of different types of subject regions for the same input image. Note that the inference unit 104 may execute detection processing of the subject region by a known method that does not use a machine learning model. The inference unit 104 can detect the subject region by using, for example, a method using local features such as SIFT or SURF, or a method using pattern matching.

[0025] The network I / F 105 is an interface for connecting the photography control device 100 to the communication network 700. The photography control device 100 (CPU 101) can communicate with external devices on the communication network 700, such as the overhead camera 300, the sub camera 400, the main camera 500, and the role control device 600, through the network I / F 105. The photography control device 100 may communicate with external devices through other communication interfaces (USB, Bluetooth (registered trademark), etc.) not shown.

[0026] To communicate with each device (overhead camera 300, sub camera 400, main camera 500, role control device 600) on communication network 700, CPU 101 acquires the network address of each device at any timing and stores it in RAM 102. CPU 101 also acquires information about each device (device type, model name, etc.) at any timing (for example, at the time of the first communication) and stores it in RAM 102. In this way, CPU 101 is assumed to know at least the identification information and device type of overhead camera 300, sub camera 400, main camera 500, and role control device 600. Note that the user may be allowed to give any name to each device.

[0027] The user input unit 106 is an input device (not shown) such as a mouse, a keyboard, a touch panel, etc. The imaging control device 100 receives instructions from a user through the user input unit 106.

[0028] The display unit 108 is a display device such as a liquid crystal display (LCD), etc. The display unit 108 displays a GUI screen provided by the OS, a shooting control application, etc.

[0029] (Overhead camera 300) Next, an example of the functional configuration of the overhead camera 300 will be described. The CPU 301 is a microprocessor capable of executing programmed instructions. For example, the CPU 301 loads a program stored in the ROM 303 into the RAM 302 and executes the program to control the operation of each functional block and realize the function of the overhead camera 300, which will be described later.

[0030] The RAM 302 is used to load programs executed by the CPU 301 and to temporarily store data to be processed by the CPU 301, data being processed, etc. The RAM 302 may also be used as a buffer for video signals obtained by shooting.

[0031] The ROM 308 is a rewritable non-volatile memory. The ROM 308 stores the programs executed by the CPU 301, the setting values ​​of the overhead camera 300, user data, etc. The ROM 308 can also be used as a recording destination for video signals. The ROM 308 may include an internal memory and a removable memory card.

[0032] The image sensor 307 has a photographing optical system and an image sensor. The image sensor may be, for example, a known CCD or CMOS color image sensor having a primary color Bayer array color filter. The image sensor has a pixel array in which a plurality of pixels are arranged two-dimensionally, and a peripheral circuit for reading out signals from each pixel. Each pixel accumulates electric charge according to the amount of incident light by photoelectric conversion. A pixel signal group (analog image signal) representing the subject image formed on the imaging surface is obtained by reading out from each pixel a signal having a voltage according to the amount of electric charge accumulated during the exposure period.

[0033] The image processing unit 306 applies predetermined signal processing and image processing to the analog image signal output by the image sensor 307 to generate signals and image data according to the application, and to obtain and / or generate various types of information.

[0034] The processes applied by the image processing unit 306 can include, for example, pre-processing, color interpolation, correction, detection, data processing, evaluation value calculation, and special effect processing. Pre-processing may include A / D conversion, signal amplification, reference level adjustment, defective pixel correction, etc. Color interpolation processing is performed when a color filter is provided on the image sensor 307, and is processing for interpolating values ​​of color components that are not included in the individual pixel data that constitutes the image data. Color interpolation processing is also called demosaic processing. The correction processing can include white balance adjustment, gradation correction, correction of image degradation caused by optical aberration of the imaging optical system (image restoration), correction of the effect of peripheral light falloff of the imaging optical system, color correction, and the like. The data processing may include processes such as cutting out (trimming), compositing, scaling, encoding and decoding, generating header information (generating a data file), etc. The data processing also includes the generation of a video signal to be output to the outside and video data to be recorded in the ROM 308. The evaluation value calculation process may include processes such as generation of a signal and evaluation value used in automatic focus detection (AF), generation of an evaluation value used in automatic exposure control (AE), etc. AF and AE are executed by the CPU 301. The special effects processing may include adding a blur effect, changing color tones, relighting, and the like. Note that these are merely examples of processes that the image processing unit 306 can apply, and do not limit the processes that the image processing unit 306 can apply. The image processing unit 306 outputs the acquired or generated information and data to the CPU 301, RAM 302, etc. depending on the purpose.

[0035] The type and settings of the processing applied by the image processing unit 306 can be controlled by sending commands from the photography control device 100 to the overhead camera 300.

[0036] The network I / F 305 is an interface for connecting the overhead camera 300 to the communication network 700. The overhead camera 300 (CPU 301) can communicate with external devices on the communication network 700, such as the shooting control device 100, the sub camera 400, the main camera 500, and the role control device 600, via the network I / F 305. The overhead camera 300 may communicate with external devices via other communication interfaces (USB, Bluetooth, etc.) not shown.

[0037] (Sub-camera 400) Next, a description will be given of an example of the functional configuration of the sub-camera 400. It is assumed that functional blocks with the same names in the sub-camera 400 and the overhead camera 300 have the same functions, and the description will be omitted.

[0038] As described above, the sub-camera 400 is a PTZ camera, and the shooting direction and angle of view can be controlled externally. Therefore, the sub-camera 400 has a driving unit 409 capable of panning, tilting, and zooming, and a driving I / F 408. The driving I / F 408 is a communication interface between the driving unit 409 and the CPU 401.

[0039] The driving unit 409 has a pan / tilt mechanism that supports the sub-camera 400 so that it can pan and tilt, a zoom mechanism that changes the angle of view of the photographing optical system, and a motor that drives these mechanisms. The zoom mechanism may use the image enlargement / reduction by the image processing unit 406. The driving unit 409 drives the motor according to instructions received from the CPU 401 via the driving I / F 408, and adjusts the optical axis direction and the angle of view of the photographing optical system.

[0040] (Main camera 500) Next, an example of the functional configuration of the main camera 500 will be described. It is assumed that functional blocks with the same names in the main camera 500 and the sub camera 400 have the same functions, and their description will be omitted. The main camera 500 is operated by a user. Here, it is assumed that the user remotely controls the main camera 500 by transmitting commands through the communication network 700. However, when the main camera 500 is not a PTZ camera, the user may directly operate the main camera 500.

[0041] The shooting control device 100 (CPU 101) can obtain information on the shooting direction and angle of view of the sub camera 400 and the main camera 500 from the sub camera 400 and the main camera 500 via the network I / F 505. The shooting direction may be the pan and tilt angles of the driving units 409 and 509 with a predetermined reference direction set to 0°. The reference direction may be the direction directly facing the shooting range.

[0042] (Role control device 600) Next, an example of the functional configuration of the role control device 600 will be described. The CPU 601 is a microprocessor capable of executing programmed instructions. For example, the CPU 601 loads a role setting program stored in the ROM 603 into the RAM 602 and executes the program to control the operation of each functional block and realize the functions of the role control device 600.

[0043] The RAM 602 is used for loading programs executed by the CPU 601 and for temporarily storing data to be processed by the CPU 601, data being processed, etc. In addition, a part of the RAM 602 may be used as a video memory for the display unit 608.

[0044] The ROM 603 is a rewritable non-volatile memory, and stores the programs executed by the CPU 601, the setting values ​​of the role control device 600, user data, and the like.

[0045] The user input unit 611 is an input device such as a button, a dial, a joystick, a touch panel, etc. The role control device 600 receives, via the user input unit 611, a user's instruction regarding the setting of the role of the sub-camera 400.

[0046] The network I / F 605 is an interface for connecting the role control device 600 to the communication network 700. The role control device 600 (CPU 601) can communicate with external devices on the communication network 700, such as the overhead camera 300, the sub camera 400, and the shooting control device 100, through the network I / F 605. The role control device 600 may also communicate with external devices through other communication interfaces (USB, Bluetooth, etc.) not shown.

[0047] The display unit 608 is a display device such as a liquid crystal display (LCD), etc. The display unit 608 displays a GUI screen provided by the OS, a role setting application, etc.

[0048] The role control device 600 stores role setting information, for example, in the ROM 603. The role setting information is information in which identification information of the sub camera 400 is associated with information indicating the role that has been set. The CPU 601 executes a role setting application to display a role setting screen on the display unit 608. The role setting screen displays, for example, identification information of the sub camera 400 (such as a network address and a name set by the user) and the name of the currently set role in association with each other. The initial value of the currently set role may be a default role that has been set in advance. The user can change the current role that is displayed in association with a desired sub camera 400 by operating the user input unit 611.

[0049] When a user operation indicating the end of the setting operation, such as an operation of an OK button included in the role setting screen, is detected, the CPU 601 updates the role setting information stored in the ROM 103 according to the content of the role setting screen.

[0050] When the CPU 601 receives a role acquisition command via the network I / F 605, it reads out the role setting information stored in the ROM 103 and transmits it to the sender of the role acquisition command.

[0051] 1 and 2, the role control device 600 is described as an independent device, but for example, a shooting control application executed by the shooting control device 100 may provide a function similar to that of the role control device 600. Also, a role may be set directly to the sub-camera 400, and the shooting control device 100 may acquire the role assigned to the sub-camera 400 from the sub-camera 400.

[0052] The role that can be set for the sub camera 400 is a predetermined role that determines how information obtained from the main camera 500 is used to control the operation of the sub camera 400. As an example, the information from the main camera is used to control the tracking subject and zoom operation of the sub camera 400.

[0053] Fig. 4 shows an example of types of roles that can be set for the sub camera 400 and control contents associated with the roles. The control contents for each role can be stored in the ROM 603 of the role control device 600 and the ROM 103 of the shooting control device 100 in the table format shown in Fig. 4, for example. Here, it is assumed that any of "main follow", "main counter", "assist follow", and "assist counter" can be set as the role ROLE. When there are multiple sub cameras 400, a role can be set for each sub camera.

[0054] For the sub-camera 400 with the role "main follow", the photography control device 100 (CPU 101) sets the same tracking subject as the main camera 500, and when the main camera 500 is zoomed, the photography control device 100 (CPU 101) performs zoom control of the sub-camera 400 in the same phase. Here, "in phase" means that the zoom direction (telephoto direction or wide-angle direction) is the same, that is, the direction of the angle of view change is the same. On the other hand, "opposite phase" means that the zoom direction (telephoto direction or wide-angle direction) is the opposite direction, that is, the direction of the angle of view change is the opposite direction. Note that even if the zoom direction is in the same phase, the angle of view does not have to be the same as the main camera 500, and whether in the same phase or opposite phase, the degree of zoom change (such as the speed or rate of change) does not have to be the same as the main camera 500.

[0055] For the sub-camera 400 whose ROLE is "main counter", the photography control device 100 (CPU 101) sets the same tracking subject as the main camera 500, and when the main camera 500 is zoomed, the photography control device 100 (CPU 101) controls the sub-camera 400 to zoom down when the main camera 500 is zoomed up. Note that zooming up refers to changing the zoom in the telephoto direction (telephoto end direction), and zooming down refers to changing the zoom in the wide-angle direction (wide end direction). When zoom control is performed by the image processing unit 406, zooming up refers to making the area cut out from the image smaller and the magnification rate of the cut out area larger than before the area change. On the other hand, zooming down refers to making the area cut out from the image larger and the magnification rate of the cut out area smaller than before the area change.

[0056] For the sub-camera 400 whose ROLE is "assist follow", the photography control device 100 (CPU 101) sets a tracking subject different from that of the main camera 500, and when the main camera 500 is zoomed, the photography control device 100 (CPU 101) performs zoom control of the sub-camera 400 in the same phase.

[0057] For the sub-camera 400 whose ROLE is "assist counter", the photography control device 100 (CPU 101) sets a tracking subject different from that of the main camera 500. In addition, when the main camera 500 is zoomed, the photography control device 100 performs zoom control of the sub-camera 400 in the opposite phase.

[0058] Here, for the sub-camera 400 with the role of "assist follow" and "assist counter", a subject existing on the left side of the subject other than the subject of interest of the main camera 500 in the image is set as the tracking subject of the sub-camera 400. The tracking subject of the sub-camera 400 may be set according to other conditions. For example, a subject existing on the right side, upper side, or lower side of the subject other than the subject of interest of the main camera 500 in the image may be set as the tracking subject of the sub-camera. Alternatively, a subject existing on the front or back of the subjects other than the subject of interest of the main camera 500 may be set as the tracking subject of the sub-camera 400.

[0059] Also, only one of setting the subject to be tracked and zoom control may be performed, or another control item may be added.

[0060] In the role setting information stored in the ROM 603 by the role control device 600, information indicating the role ROLE (such as the above-mentioned type name or a number assigned to the type) is associated with identification information of the sub camera 400. The CPU 101 of the photography control device 100 acquires the role setting information from the role control device 600, and executes operation control of the sub camera 400 according to the type of role ROLE set to the sub camera 400.

[0061] The role control device 600 may notify an external device (for example, the shooting control device 100) when there is a change in the role setting for the sub-camera 400. This allows the change in the role setting to be immediately reflected in the operation control of the sub-camera 400.

[0062] <Explanation of the operation of each device> Next, the operation of each device in the multi-camera imaging system will be described. Here, the imaging control device 100 automatically controls the imaging operation of the sub-camera 400 based on the image of the overhead camera 300, information obtained from the main camera 500, and the role set for the sub-camera 400.

[0063] 3 is a diagram showing a series of processes performed by the photography control device 100 when controlling the operation of the sub-camera 400, focusing on the main operations and signal flows. The functional blocks shown in the photography control device 100 show the main operations in a schematic manner, and correspond to the main functions provided by the photography control application. Each functional block in FIG. 3 is realized by a combination of the CPU 101 that executes the photography control application and one or more of the functional blocks of the photography control device 100 shown in FIG. 2.

[0064] Fig. 5 is a flowchart showing the operation of CPU 101 as role determination section 120. Fig. 6(a) to Fig. 6(d) are flowcharts relating to the operation of shooting control device 100, overhead camera 300, main camera 500, and sub-camera 400, respectively.

[0065] In the following description, it is assumed that the three-dimensional coordinate values ​​of the viewpoint position and the shooting direction (optical axis direction) of the overhead camera 300 are known to the shooting control device 100. It is also assumed that known position information, such as the three-dimensional coordinate values ​​of the viewpoint positions of the sub camera 400 and the main camera 500 and the coordinate values ​​of markers arranged in the shooting range, is stored in advance in the ROM 103 as default position information REF_POSI. It is also assumed that the coordinate system of the position is predetermined depending on the type of position.

[0066] (Operation of role determination unit 120) First, the operation of the CPU 101 as the role determination section 120 in Fig. 3 will be described with reference to the flowchart shown in Fig. 5. The operation described below is realized by the CPU 101 executing a shooting control application.

[0067] 5 is not particularly limited to the timing for starting the operations shown in the flowchart of Fig. 5, but the operations are executed at least before starting control of the shooting operation of the sub-camera 400. The operations are also executed when a notification is received from the role control device 600 via the network I / F 105 that the role setting for the sub-camera 400 has been changed.

[0068] In S101, the CPU 101 as the role determination unit 120 acquires a role ROLE (role setting information) corresponding to the sub camera 400 from the role control device 600. The CPU 101 can acquire the above-mentioned role setting information from the role control device 600 by transmitting a role acquisition command to the role control device 600 via the network I / F 105, for example. The CPU 101 stores the acquired role setting information in the RAM 102.

[0069] In S103, CPU 101 refers to the role setting information stored in RAM 102 based on the identification information of sub camera 400, and acquires operation control content for sub camera 400. Then, CPU 101 as role determination section 120 transmits the acquired operation control content (CAMERA_ROLE) to tracking subject determination section 123. In practice, CPU 101 stores the operation control content in a specific area of ​​RAM 102, and refers to it when functioning as tracking subject determination section 123.

[0070] In S104, the CPU 101 as the role determination unit 120 transmits the acquired operation control content (CAMERA_ROLE) to the zoom value calculation unit 125. In practice, the CPU 101 stores the operation control content in a specific area of ​​the RAM 102 and refers to it when functioning as the zoom value calculation unit 125.

[0071] (Operation of the imaging control device 100) Next, the operation of the shooting control device 100 to control shooting by the sub-camera 400 will be described with reference to Fig. 3 and Fig. 6(a). The operation described below corresponds to the operation of the CPU 101 as the recognition unit 121, the target subject determination unit 122, the tracking subject determination unit 123, the pan / tilt value calculation unit 124, and the zoom value calculation unit 125 in Fig. 3. Note that the operation described below is realized by the CPU 101 executing a shooting control application.

[0072] In S201, CPU 101 transmits a shooting instruction command in a predetermined protocol to overhead camera 300 through network I / F 105. In response to this command, overhead camera 300 starts supplying a video signal (moving image data) IMG to video input unit 107. CPU 101 starts storing the video signal received by video input unit 107 in RAM 102, and then executes S202.

[0073] In S202, CPU 101 acquires information ANGLE indicating the shooting direction from main camera 500. Specifically, CPU 101 transmits a shooting direction acquisition command to main camera 500 via network I / F 105 in a predetermined protocol. In response to the shooting direction acquisition command, CPU 501 of main camera 500 transmits information ANGLE indicating the current shooting direction of main camera 500 to shooting control device 100. Information ANGLE may be, for example, the pan and tilt angles of drive unit 509. CPU 101 stores the acquired information ANGLE in RAM 102.

[0074] In S203, the recognition unit 121 executes the following process. (1) Apply subject area detection processing to the input frame image and store the detection results. (2) For each detected subject area, the position information (image coordinates) is converted. (3) Apply classification processing to each detected subject region to identify the classification information (if a new subject is detected, add classification processing information). (4) For each detected subject area, the identification information ID[n] and the position information POSITION[n] are associated and stored.

[0075] The recognition unit 121 is mainly realized by the CPU 101 and the inference unit 104. The CPU 101 reads one frame of the image received from the overhead camera 300 from the RAM 102 and inputs it to the inference unit 104.

[0076] The operation of the recognition unit 121 will be explained step by step below. (1) First, the inference unit 104 inputs a frame image into a machine learning model to detect a subject region. The inference unit 104 stores in the RAM 102 the position and size of each detected subject region, which are output by the machine learning model as a detection result, and the detection reliability. The position and size of the subject region may be any information capable of identifying the position and size of a rectangular region inscribed by the subject region. Here, the center coordinate of the bottom side, and the width and height of the rectangular region are used as the position and size of the subject region.

[0077] Furthermore, inference unit 104 stores the detection result for the first frame image in RAM 102 in association with the subject identification information ID[n]. Here, n is the subject number and is an integer ranging from 1 to the total number of detected subject regions. Furthermore, inference unit 104 stores the subject regions detected from the first frame image in RAM 102 in association with the subject identification information ID[n] as templates for identifying individual subjects. If template matching is not used to identify subjects, it is not necessary to store templates.

[0078] Fig. 8(a) shows an example of the result of subject detection processing by inference unit 104 for the image captured by overhead camera 300 shown in Fig. 7(a). Here, the areas of human subjects A to C present within shooting range 20 are detected, and the coordinates (foot coordinates) of the center of the bottom side of a rectangular area inscribed with the subject areas are output as the position.

[0079] For coordinate conversion, which will be described later, when a marker is placed at a known position within the shooting range 20 as shown in FIG. 7(b), the CPU 101 detects the image of the marker included in the frame image (FIG. 7(a)) and stores the position in the RAM 102. The detection of the marker image may also be performed by the inference unit 104. The detection of the marker image may be performed by any known method, such as pattern matching using a marker template. The marker image may also be detected using a pre-stored machine learning model for marker detection.

[0080] (2) Next, we will explain the coordinate conversion executed by the inference unit 104. Fig. 7(a) shows a schematic diagram of the image captured by the overhead camera 300, and Fig. 7(b) shows a schematic diagram of the image capture range 20 as viewed from directly above its center. The inference unit 104 converts the position of the subject area in the coordinate system of the overhead camera into values ​​in a coordinate system (planar coordinate system) when the image capture range 20 is viewed from directly above its center.

[0081] The reason for converting the coordinates into values ​​in the plane coordinate system here is that it is convenient to calculate a pan value (a movement angle in a horizontal plane) for shooting a specific subject with the sub-camera 400. Note that this is based on the premise that the sub-camera 400 is installed so that the driving unit 409 performs a panning operation in a horizontal plane parallel to the floor of the shooting range 20.

[0082] Coordinate conversion can be performed in various ways, but here, markers are placed at multiple known positions on the floor of the shooting range 20, and coordinate conversion is performed from the overhead camera coordinate system to the planar coordinate system based on the marker positions in the image captured by the overhead camera 300. Note that coordinate conversion may also be performed without using markers, for example, by using the viewpoint position and shooting direction of the overhead camera 300.

[0083] The coordinate transformation can be performed using a homography transformation matrix H according to Equation 1 below.

number

[0084] The homography transformation matrix can be calculated by substituting the coordinates of the four markers detected from the video and the coordinates (known) of the four markers arranged in the shooting range 20 into Equation 1 and solving the simultaneous equations. When the positional relationship between the shooting range 20 and the overhead camera 300 is fixed, the homography transformation matrix H can be calculated in advance during test shooting and stored in, for example, ROM 103.

[0085] CPU 101 sequentially reads out the positions of the subject regions from RAM 102 and converts the coordinates into values ​​in a planar coordinate system. Fig. 8(b) shows a schematic diagram of the state in which the foot coordinates (x, y) of each subject region detected in the overhead camera 300 video shown in Fig. 8(a) are converted into coordinate values ​​(X, Y) in a planar coordinate system using Equation 1 and the homography transformation matrix H stored in ROM 103. CPU 101 stores the converted foot coordinates in RAM 102 as POSITION[n].

[0086] (3) Next, the operation of the inference unit 104 to identify the identification information ID[n] of the subject will be described. Here, the subject is identified using template matching. The subject is identified for the processing results of the second and subsequent subject detections. For the first processing result, a new identification information ID[n] can be assigned to the subject region.

[0087] The inference unit 104 identifies the identification information ID[n] of the detected object region by template matching using the template stored in the RAM 102. This identifies the object within the shooting range. For example, the inference unit 104 calculates an evaluation value representing the correlation of each template for each detected object region. Then, the inference unit 104 identifies the identification information ID[n] corresponding to the template having a certain degree of correlation or higher and having the highest correlation as the identification information ID[n] of the object region. For the evaluation value, a known value such as the sum of absolute differences of pixel values ​​can be used.

[0088] Note that, for a subject region that does not have a certain level of correlation with all the templates, the inference unit 104 assigns new identification information ID[n] and adds the image of the subject region to the template.

[0089] In addition, the inference unit 104 may update an existing template using a subject area detected in a most recent frame image, or delete a template in which a subject area having a certain degree of correlation or more has not existed for a certain period of time. Furthermore, the inference unit 104 may store in the ROM 103 templates corresponding to frequently appearing identification information ID[n].

[0090] Note that the subject may be identified by a method other than template matching. For example, the subject may be identified as the same identification information ID[n] as the subject area having the closest immediately preceding detection position and / or size. Alternatively, the position in the current frame image may be predicted by a Kalman filter or the like from the transition of positions in multiple past detection results associated with the same identification information, and the same identification information ID may be identified as the subject area that is closest to the predicted position. These methods may also be combined. By not using template matching, it is possible to improve the accuracy of identifying different subjects that look similar.

[0091] (4) The inference unit 104 associates the specified identification information ID[n] with the position (planar coordinate system) POSITION[n] of the corresponding subject region and stores them in the RAM 102.

[0092] Of the processes (1) to (4), the processes other than the subject detection may be executed by the CPU 101 instead of the inference unit 104.

[0093] Here, the image from the overhead camera 300 is used to determine the identification information ID[n] and position POSITION[n] of the subject within the shooting range 20. However, the image from the sub camera 400 may also be used. When there are multiple sub cameras 400, the CPU 101 executes the operation shown in the flowchart of FIG. 6(a) for each sub camera 400. The position of the subject area is output as a value in the coordinate system for each sub camera 400. Thus, although the overhead camera 300 is not essential, it is considered that the use of the overhead camera 300 provides better subject detection accuracy.

[0094] Returning to the explanation of Fig. 6(a), in S204, CPU 101 as the subject of interest determination unit 122 in Fig. 3 determines a subject of interest as a tracking subject of main camera 500. CPU 101 can determine a subject of interest of main camera 500 from among the subjects detected in S203, based on the shooting direction of main camera 500 acquired in S202. CPU 101 stores identification information ID[n] corresponding to the subject area determined as the subject of interest of main camera 500 in RAM 102 as identification information MAIN_SUBJECT of the subject of interest.

[0095] For example, CPU 101 can determine that the subject closest to the shooting direction of main camera 500 in the planar coordinate system is the subject of interest of main camera 500. Note that, when there are multiple subjects whose distance from the shooting direction of main camera 500 is equal to or less than a threshold, the user may be allowed to select the subject of interest from among them.

[0096] When allowing the user to select a subject of interest, CPU 101 displays on display unit 108 or an external display device the frame image to which subject detection processing has been applied in S202, together with an indicator indicating the shooting direction and an indicator indicating a subject area that is a candidate for a subject of interest. The indicator for the subject area may be, for example, a rectangular frame indicating the outer edge of the subject area as shown in Fig. 8(a), but may be another indicator. CPU 101 may also display on display unit 108 a message prompting the user to select a subject of interest within the image.

[0097] The user can select a subject area corresponding to a desired subject of interest by operating the user input unit 106 (input device). There are no particular limitations on the selection method, but the selection method may be an operation of operating a mouse or keyboard to specify the desired subject area.

[0098] When the CPU 101 detects a user operation for designating a subject region, the CPU 101 stores in the RAM 102 the identification information ID[n] corresponding to the designated subject region as identification information MAIN_SUBJECT of the target subject.

[0099] Next, in S205, CPU 101 as tracking subject determination unit 123 in Fig. 3 acquires control content CAMERA_ROLE according to the role set for sub camera 400. Specifically, CPU 101 reads out control content CAMERA_ROLE acquired in the role determination process described with reference to Fig. 5 and stored in RAM 102. Note that, if there are multiple sub cameras 400, CPU 101 executes the processes of S205 to S207 for each sub camera.

[0100] In S206, the CPU 101 as the tracking subject determination unit 123 determines a subject to be tracked and photographed by the sub camera 400 in accordance with the control content CAMERA_ROLE. The CPU 101 determines a tracking subject of the sub camera 400 in accordance with the tracking subject rule (FIG. 4) included in the control content CAMERA_ROLE.

[0101] When the tracking subject of the sub camera 400 is to be the same as the target subject of the main camera 500, the CPU 101 sets the identification information MAIN_SUBJECT of the target subject determined in S203 as the identification information SUBJECT_ID of the tracking subject of the sub camera 400.

[0102] When the tracking subject of the sub camera 400 is a subject located on the left side of the subject other than the target subject of the main camera 500, the CPU 101 detects a subject area located on the left edge of the subject area other than the target subject from among the subject areas detected in S203. Then, the CPU 101 sets the identification information ID[n] corresponding to the detected subject area as the identification information SUBJECT_ID of the tracking subject of the sub camera 400.

[0103] CPU 101 writes the identification information SUBJECT_ID of the determined tracking subject to RAM 102. If the tracking subject may differ depending on the sub camera, CPU 101 stores the identification information SUBJECT_ID of the tracking subject in association with the identification information of the sub camera. Note that if the tracking subject changes, CPU 101 retains the information of the previous tracking subject in RAM 102 without erasing it.

[0104] Here, the operation when the role set for the sub camera 400 is "main follow" will be described with reference to Fig. 9. The photography control device 100 controls the sub camera 400 set for the role "main follow" so as to track the subject of interest of the main camera 500.

[0105] Therefore, when the subject of interest of the main camera 500 is determined to be subject B as shown in Fig. 9(a), the CPU 101 determines subject B as the subject to be tracked by the sub camera 400. Thereafter, when the subject of interest of the main camera 500 is determined to have changed to subject A as shown in Fig. 9(b), the CPU 101 changes the subject to be tracked by the sub camera 400 to subject A. Similarly, when the subject of interest of the main camera 500 is determined to have changed to subject C as shown in Fig. 9(c), the CPU 101 changes the subject to be tracked by the sub camera 400 to subject C.

[0106] The operation of the sub camera 400 when the role set for the sub camera 400 is "assist follow" will be described with reference to Fig. 10. For the sub camera 400 set for the role "assist follow", the photography control device 100 controls the sub camera 400 so that it tracks a subject located on the left side of the subject other than the subject of interest of the main camera 500.

[0107] Therefore, when the subject of interest of the main camera 500 is determined to be subject B as shown in Fig. 10(a), the CPU 101 determines the subject A on the left side of subjects A and C as the subject to be tracked by the sub camera 400. Thereafter, when the subject of interest of the main camera 500 is determined to have changed to subject A as shown in Fig. 10(b), the CPU 101 changes the subject to be tracked by the sub camera 400 to subject B on the left side of subjects B and C. Also, when the subject of interest of the main camera 500 is determined to have changed to subject C as shown in Fig. 10(c), the CPU 101 changes the subject to be tracked by the sub camera 400 to subject A on the left side of subjects A and B.

[0108] By dynamically changing the role set for the sub-camera 400 using the role control device 600, the subject tracked by the sub-camera 400 can be changed, enabling flexible automatic shooting.

[0109] Returning to Fig. 6(a), in S207, CPU 101 as pan / tilt value calculation unit 124 calculates the change amounts of pan angle and tilt angle required for sub camera 400 to track and photograph the tracking subject determined in S206. CPU 101 as zoom value calculation unit 125 calculates the zoom value of sub camera 400 according to the change in angle of view of main camera 500. Although the following describes a case where there is one sub camera 400, when there are multiple sub cameras 400, calculation of the change amounts of pan angle and tilt angle and calculation of the zoom value are executed for each sub camera.

[0110] First, there will be described the operation of the CPU 101 as the pan / tilt value calculation unit 124. Here, it is assumed that the following information is stored in advance in the ROM 103 as default position information REF_POSI for each sub camera 400. - 3D coordinates of the installation location (values ​​in a planar coordinate system) -Shooting direction corresponding to the initial values ​​of the pan and tilt angles of the drive unit Controllable range of pan and tilt angles

[0111] The CPU 101 reads out the position information POSITION_OH corresponding to the identification information SUBJECT_ID of the subject being tracked by the sub camera 400 from the RAM 102. Then, the CPU 101 first determines the pan angle from the position information POSITION_OH and the installation position of the sub camera 400.

[0112] 11 is a diagram showing an example of the positional relationship between the sub camera 400 and a tracking subject in a plane coordinate system. Here, a pan angle θ for directing the optical axis direction of the sub camera 400 toward the subject position is determined. The CPU 101 calculates the pan angle θ using the following formula 2.

number

[0113] In Equation 2, px and py are the horizontal and vertical coordinates of the position information POSITION_OH corresponding to the identification information SUBJECT_ID of the tracking subject. Also, subx and suby are the horizontal and vertical coordinates of the installation position of the sub-camera. Here, it is assumed that the current pan angle is the initial value of 0° and the optical axis direction is the vertical direction (Y-axis direction). If the current optical axis direction is not the vertical direction, the angle difference between the current optical axis direction and the vertical direction may be reflected in the angle obtained by Equation 2. Also, if subx > px, the pan direction is counterclockwise; if subx < px, the pan direction is clockwise.

[0114] Next, with reference to FIG. 12, a method for determining the tilt angle will be described. FIG. 8 shows a state in which the sub-camera and the tracking subject are viewed from the side. It is assumed that the current optical axis of the sub-camera 400 is in the horizontal direction and the height is h1, and the height of the face of the tracking subject facing the optical axis is h2. Let ρ be the angle difference (tilt angle) in the height direction between the current optical axis direction and the target optical axis direction. The CPU 101 calculates the tilt angle ρ using the following Equations 3 and 4.

Equation

[0115] The coordinate values used in Equation 4 are the same as the coordinate values used in Equation 2. It is assumed that h1 and h2 are input in advance to the shooting control application and stored in the RAM 102. In this case, the identification number associated with h2 for each subject is made equal to the identification number assigned in the subject detection process. Alternatively, h2 may be a value measured in real time using a sensor (not shown).

[0116] Here, it is assumed that the current tilt angle is the initial value of 0° and the optical axis direction is the horizontal direction (constant height). If the current optical axis direction is not the horizontal direction, the angle difference between the current optical axis direction and the horizontal direction may be reflected in the angle obtained by Equation 4. Also, if h1 > h2, the tilt direction is downward; if h1 < h2, the tilt direction is upward.

[0117] CPU 101 periodically communicates with sub-camera 400 via communication network 700, acquires the current optical axis direction (pan angle and tilt angle of the drive unit), and stores it in RAM 102. The communication cycle can be set to, for example, the reciprocal of the frame rate or less. Alternatively, CPU 101 may hold in RAM 102 the sum of the pan angle and tilt angle controlled from the initial state for sub-camera 400, and use it as the current optical axis direction.

[0118] In this way, CPU 101 calculates the amount of change in the pan angle and tilt angle of sub camera 400, and stores the amount of change in RAM 102. If there are multiple sub cameras 400, CPU 101 calculates the amount of change in the pan angle and tilt angle for each sub camera.

[0119] The change amount of the pan angle and tilt angle may be the angular velocity for the sub camera 400 to rotate in the direction of the tracking subject. For example, CPU 101 acquires the current pan angle and tilt angle from sub camera 400 through communication network 700. Then, CPU 101 calculates the angular velocity of the pan proportional to the difference between the pan angle θ read from RAM 102 and the current pan angle. CPU 101 also calculates the angular velocity of the tilt proportional to the difference between the tilt angle ρ read from RAM 102 and the current tilt angle. CPU 101 stores the angular velocity calculated in this manner in RAM 102.

[0120] The change amount of the pan angle and the tilt angle may be calculated using the image of the sub camera 400 instead of the image of the overhead camera 300. In this case, the CPU 101 may calculate the change amount of the pan angle from the horizontal difference between the current optical axis direction and the direction of the tracked subject in the coordinate system of the sub camera 400, and may calculate the change amount of the tilt angle from the vertical difference. Also, the imaging system may change the shooting direction to track and shoot the tracked subject in only one of the pan direction and the tilt direction, and in such an imaging system, the change amount of only one of the pan angle and the tilt angle may be calculated.

[0121] Next, a description will be given of the operation of CPU 101 as zoom value calculation unit 125. CPU 101 as zoom value calculation unit 125 periodically acquires information MAIN_ZOOM indicating the angle of view of main camera 500, and stores it in RAM 102. Then, when the information MAIN_ZOOM changes, CPU 101 calculates a zoom value Z_VALUE for sub camera 400 according to control content CAMERA_ROLE according to the role set for sub camera 400.

[0122] CPU 101 can determine the zoom operation and its phase of main camera 500, for example, by detecting a change in the angle of view of the image of main camera 500. For example, the change in the angle of view may be detected from a change over time in the size or interval of the subject area.

[0123] 13 shows an example of mapping of zoom values ​​of the main camera and the sub camera. Here, it is assumed that the main camera 500 and the sub camera 400 optically change the angle of view (the photographing optical system has a zoom function). However, a similar function may be realized by digital zoom using the image processing units 406 and 506.

[0124] The zoom value is a parameter having a value corresponding to the angle of view, and in this embodiment, the smaller (narrower) the angle of view, the smaller the zoom value, and the zoom value on the telephoto side is smaller than the zoom value on the wide-angle side. The sub-camera 400 and the main camera 500 are capable of controlling the photographing optical system to an angle of view corresponding to the zoom value by transmitting a command specifying the zoom value. That is, the zoom value is information related to the angle of view and is information representing the zoom state. The zoom value may be, for example, the focal length (mm) of the photographing optical system corresponding to a 35 mm full-size image sensor, in which case the zoom value on the telephoto side is larger than the zoom value on the wide-angle side.

[0125] 13, the range of the zoom value MAIN_ZOOM of the main camera 500 is from main_min to main_max. The zoom range of the sub camera 400 is from sub_min to sub_max. main_min and sub_min are the zoom values ​​corresponding to the telephoto ends of the main camera 500 and the sub camera 400, respectively, and main_max and sub_max are the zoom values ​​corresponding to the wide-angle ends of the main camera 500 and the sub camera 400, respectively. FIG. 13 shows an example in which the range of the zoom value of the main camera 500 is wider than the range of the zoom value of the sub camera 400 at both the telephoto end and the wide-angle end.

[0126] When controlling the zoom value SUB_ZOOM of the sub camera 400 to be in phase with the zoom value MAIN_ZOOM of the main camera 500, the CPU 101 calculates SUB_ZOOM corresponding to the current MAIN_ZOOM using the following formula 5.

number

[0127] On the other hand, when controlling the zoom value SUB_ZOOM of the sub camera 400 to be in the opposite phase to the zoom value MAIN_ZOOM of the main camera 500, the SUB_ZOOM corresponding to the current MAIN_ZOOM is calculated using the following formula 6. Specifically, the CPU 101 calculates the SUB_ZOOM corresponding to the current MAIN_ZOOM by substituting the SUB_ZOOM calculated using formula 5 into the right side of the following formula 6. SUB_ZOOM=sub_max-(SUB_ZOOM-sub_min) (Formula 6)

[0128] When the main camera 500 performs digital zoom and controls the angle of view by cropping, the CPU 101 can determine the zoom value SUB_ZOOM of the sub camera 400 according to the size of the range to be cropped by the main camera 500. Specifically, the CPU 101 sets the zoom value SUB_ZOOM smaller (higher magnification) as the size of the range to be cropped by the main camera 500 becomes smaller, and sets the zoom value SUB_ZOOM larger (lower magnification) as the size becomes larger.

[0129] In addition, the content of the zoom control associated with the role of the sub camera 400 is not limited to the control in the same phase or opposite phase to the main camera 500. For example, a zoom operation independent of the change in the angle of view of the main camera 500 may be associated with the role. For example, an auto-zoom operation that maintains the size of a tracking subject constant may be associated with the role. Also, the angle of view of the sub camera 400 may be fixed to a specific angle of view. By adding roles associated with these zoom controls to the control contents for each role shown in FIG. 4, or by changing the content of the zoom control of the role shown in FIG. 4, various zoom controls for the sub camera 400 are possible.

[0130] Returning to FIG. 6(a), in S207, CPU 101 reads out the change amounts of the pan and tilt angles calculated in S206 and the zoom value from RAM 102. Then, CPU 101 generates a control command PT_VALUE that instructs sub camera 400 to change the pan angle and tilt angle corresponding to these change amounts. CPU 101 also generates a control command Z_VALUE that instructs sub camera 400 to change the angle of view corresponding to the zoom value. The format of the control command is predefined. CPU 101 stores the generated control commands PT_VALUE and Z_VALUE in RAM 102. Note that S207 may be skipped when it is not necessary to generate a control command, such as when the tracking subject is stationary or when the angle of view of main camera 500 does not change.

[0131] Then, the CPU 101 reads out the control commands PT_VALUE and Z_VALUE from the RAM 102, and transmits them to the communication network 700 via the network I / F 105. The sub-camera 400 receives the control commands PT_VALUE and Z_VALUE via the network I / F 405.

[0132] The CPU 101 executes the process from S201 on the next frame image of the video captured by the overhead camera 300. Note that the process shown in Fig. 6(a) does not necessarily have to be executed for every frame.

[0133] (Operation of overhead camera 300) Next, the operation of the overhead camera 300 will be described with reference to Fig. 6(b). The operation described below is realized by the CPU 301 executing a program.

[0134] When the overhead camera 300 is powered on, each functional block is initialized by the CPU 301, and the camera enters a shooting standby state. In the shooting standby state, the CPU 301 may start a video shooting process for live view display, and output display image data generated by the image processing unit 306 to the shooting control device 100 via the network I / F 305.

[0135] In the shooting standby state, the CPU 301 waits for reception of a control command through the network I / F 305. When the CPU 301 receives a control command, it executes an operation according to the control command. Here, an operation when a shooting command is received as a control command from the shooting control device 100 will be described.

[0136] In S301 , the CPU 301 receives an imaging command from the imaging control device 100 via the network I / F 305 .

[0137] The shooting command may specify shooting parameters such as frame rate, resolution, etc. Also, the shooting command may include settings related to the processing to be applied by the image processing unit 306.

[0138] In S302, in response to receiving the shooting command, the CPU 301 starts a moving image shooting process for supplying the image to the shooting control device 100. In this moving image shooting process, a moving image with higher image quality is shot than that of the moving image shooting process for live view display. For example, at least one of the resolution of the moving image and the shooting frame rate is higher than that of the moving image for live view display. The image processing unit 306 applies processing to the image based on the settings for the moving image to be supplied to the shooting control device 100. The image processing unit 306 sequentially stores the generated moving image data in the RAM 302.

[0139] In S303, the CPU 101 reads the video data from the RAM 302, and transmits it to the shooting control device 100 via the network I / F 305. After that, the process from shooting to supply of video data is continued until a control command to stop shooting is received.

[0140] (Operation of main camera 500) Next, the operation of the main 500 will be described with reference to Fig. 6(c). The operation described below is realized by the CPU 501 executing a program.

[0141] When the main camera 500 is powered on, each functional block is initialized by the CPU 501, and then moving image shooting processing for supplying to the shooting control device 100 is started. The image processing unit 506 applies processing to the analog image signal obtained from the image sensor 507 based on the settings for moving images to be supplied to the shooting control device 100. The image processing unit 506 sequentially stores the generated moving image data in the RAM 502. The CPU 501 reads the moving image data from the RAM 502 and supplies it to the shooting control device 100 via the network I / F 505.

[0142] The CPU 501 waits for a control command via the network I / F 305 while supplying video data to the shooting control device 100. When the CPU 501 receives a control command, it executes an operation according to the control command. Here, an operation when a shooting direction acquisition command is received will be described. When a pan / tilt control command PT_VALUE or a zoom control command Z_VALUE is received, the CPU 501 drives the drive unit 509 according to the command.

[0143] In S501, the CPU 501 receives a shooting direction obtaining command via the network I / F 505. The CPU 501 stores the received shooting direction obtaining command in the RAM 502.

[0144] In S502 , in response to receiving the shooting direction acquisition command, the CPU 501 acquires the current pan angle and tilt angle from the drive unit 509 via the drive I / F 508 , and stores them in the RAM 502 .

[0145] In S503, the CPU 501 reads out the current pan angle and tilt angle from the RAM 502, and transmits them to the shooting control device 100 via the network I / F 305 as shooting direction information ANGLE.

[0146] (Operation of sub camera 400) Next, the operation of the sub-camera 400 will be described with reference to Fig. 6(d). The operation described below is realized by the CPU 401 executing a program.

[0147] When the sub-camera 400 is powered on, each functional block is initialized by the CPU 401, and then moving image capturing processing for supplying to the shooting control device 100 is started. The image processing unit 406 applies processing to an analog image signal obtained from the image sensor 407 based on settings for moving images to be supplied to the shooting control device 100. The image processing unit 406 sequentially stores the generated moving image data in the RAM 402. The CPU 401 reads the moving image data from the RAM 402 and supplies it to the shooting control device 100 via the network I / F 405.

[0148] The CPU 401 waits for a control command via the network I / F 305 while supplying video data to the shooting control device 100. When the CPU 401 receives a control command, it executes an operation according to the control command. Here, an operation when a pan / tilt control command PT_VALUE and a zoom control command Z_VALUE are received from the shooting control device 100 will be described.

[0149] In S401, the CPU 401 receives at least one of a pan / tilt control command PT_VALUE and a zoom control command Z_VALUE from the shooting control device 100 via the network I / F 405. The CPU 401 stores the received control command in the RAM 402.

[0150] In S402, the CPU 401 reads out the operation direction and the corresponding operation amount from the control command stored in the RAM 402, and stores them in the RAM 402. Here, in the case of a pan / tilt control command PT_VALUE, the operation direction is the pan and / or tilt direction, and the operation amount is the target angle. Also, in the case of a zoom control command Z_VALUE, the operation amount is the zoom value, and since the operation direction can be specified from the zoom value, there is no need to read out and store the operation direction.

[0151] In S403, the CPU 401 generates drive parameters for the drive unit 409 based on the operation direction and operation amount read out in S403. For example, the CPU 401 may obtain drive parameters according to a combination of the operation direction and operation amount by using a table previously stored in the ROM 403. Note that when the operation amount is given as a target value (target angle or zoom value), the CPU 410 obtains the drive parameters from the difference with the current value.

[0152] In S404, the CPU 401 controls the drive unit 409 through the drive I / F 408 based on the drive parameters acquired in S404. As a result, the drive unit 409 changes the shooting direction of the sub-camera 400 to the operation direction and angle specified by the pan / tilt control command PT_VALUE. In addition, the drive unit 409 changes the angle of view of the shooting optical system to the zoom value specified by the zoom control command Z_VALUE.

[0153] Next, the operation of the shooting control device 100 to control the shooting direction (pan and tilt) and the angle of view (zoom value) of the sub-camera in accordance with the role set for the sub-camera 400 will be described in more detail with reference to the flowchart shown in Fig. 14. The operation shown in the flowchart in Fig. 14 is executed as part of the operation of S205 to S207 in Fig. 6(a).

[0154] S601 corresponds to S205, and the CPU 101 reads out the control content CAMERA_ROLE stored in the RAM 102 in S103 of FIG.

[0155] S602 to S607 are performed in S206, for example. In S602, CPU 101 determines whether the definition of the tracking subject of sub camera 400 included in the control content CAMERA_ROLE indicates the tracking subject (target subject) of main camera 500. For example, if the definition of the tracking subject of sub camera 400 has a value indicating "same as main", CPU 101 determines that the definition of the tracking subject of sub camera 400 indicates the tracking subject of main camera 500 and executes S603. On the other hand, if the definition of the tracking subject of sub camera 400 has a value indicating "different from main (left side)", CPU 101 determines that the definition of the tracking subject of sub camera 400 does not indicate the tracking subject of main camera 500 and executes S604.

[0156] In S603, CPU 101 determines to control the shooting direction of sub camera 400 so as to track a tracking subject (target subject) of main camera 500. In S604, CPU 101 determines to control the shooting direction of sub camera 400 so as to track a subject located on the left side of the subject other than the subject of interest of main camera 500.

[0157] In S605, CPU 101 determines whether the zoom control provision of sub camera 400 included in the control content CAMERA_ROLE indicates control in the same phase as main camera 500. For example, if the zoom control provision of sub camera 400 has a value indicating "same phase as main", CPU 101 determines that the zoom control provision of sub camera 400 indicates control in the same phase as main camera 500 and executes S606. On the other hand, if the tracking subject provision of sub camera 400 has a value indicating "opposite phase to main", CPU 101 determines that the zoom control provision of sub camera 400 does not indicate control in the same phase as main camera 500 and executes S607.

[0158] In S606, CPU 101 determines to control the zoom value (angle of view) of sub camera 400 in the same phase as the change in the zoom value of main camera 500. In S607, CPU 101 determines to control the zoom value (angle of view) of sub camera 400 in the opposite phase to the change in the zoom value of main camera 500.

[0159] An example of control of the sub-camera when the role set for the sub-camera 400 is "main follow" will be described with reference to FIG. 15. FIG. 15 shows a schematic diagram of how the shooting control device 100 controls the shooting direction and angle of view of the sub-camera 400 when the target subject and angle of view of the main camera 500 change over time during shooting. In the figure, time passes from left to right. In FIG. 15, the zoom state is shown in three stages: "telephoto end", "middle", and "wide-angle end". This is because the range of the zoom value may differ between the sub-camera and the main camera as shown in FIG. 13. "Telephoto end" corresponds to a state where the zoom is zoomed up to the telephoto end, "wide-angle end" corresponds to a state where the zoom is zoomed down to the wide-angle end, and "middle" corresponds to a zoom state between the telephoto end and the wide-angle end, but the actual zoom value may differ between the sub-camera and the main camera. For example, when the zoom state is "telephoto end", the zoom value of the main camera is main_min, and the zoom value of the sub-camera is sub_min.

[0160] Initially, the subject of interest (tracking subject) of main camera 500 is subject B, and the zoom state is "medium." Therefore, CPU 101 determines the subject to be tracked by sub camera 400 to be subject B, and controls the shooting direction so that sub camera 400 tracks subject B. CPU 101 also controls the zoom state of sub camera 400 to be "medium."

[0161] After that, the subject of interest of main camera 500 is changed from subject B to subject A, and the zoom state is changed to the "telephoto end." In response to this, CPU 101 changes the subject being tracked by sub camera 400 from subject B to subject A, and controls the shooting direction so that sub camera 400 tracks subject A. CPU 101 also controls the zoom state of sub camera 400 to the "telephoto end."

[0162] After that, the subject of interest of main camera 500 is changed from subject A to subject C, and the zoom state is changed to "wide-angle end." In response to this, CPU 101 changes the subject being tracked by sub camera 400 from subject A to subject C, and controls the shooting direction so that sub camera 400 tracks subject C. CPU 101 also controls the zoom state of sub camera 400 to "wide-angle end."

[0163] In this way, when the role of the sub camera 400 is "main follow", the CPU 101 automatically changes the tracking subject and zoom value of the sub camera 400 so as to follow the change in the focus subject and angle of view (zoom value) of the main camera 500. In the example shown in FIG. 15, the sub camera 400 is controlled so that the degree of change in the zoom state is equal to the degree of change in the zoom state of the main camera 500, but the actual zoom value may be different as long as the direction of change in the zoom value is in phase. For example, when the zoom state of the main camera 500 is at the telephoto end, the zoom state of the main camera 500 does not have to be at the telephoto end. Whether or not to match the zoom value of the sub camera 400 to the zoom value of the main camera 500 may be settable using role setting information.

[0164] Next, an example of control of the sub-camera when the role set for the sub-camera 400 is "assist counter" will be described with reference to FIG. 16 which is similar to FIG.

[0165] Initially, the subject of interest (tracking subject) of main camera 500 is subject B, and the zoom state is "telephoto end." Therefore, CPU 101 determines the subject to be tracked by sub camera 400 to be subject A on the left side out of subjects A and C other than subject B, and controls the shooting direction so that sub camera 400 tracks subject A. CPU 101 also controls the zoom state of sub camera 400 to the "wide-angle end" which is in the opposite phase to main camera 500.

[0166] Thereafter, the focus subject of main camera 500 is changed from subject B to subject A, and the zoom state is changed to "middle". In response to this, CPU 101 changes the tracking subject of sub camera 400 to subject B on the left side of subjects B and C other than subject B, and controls the shooting direction so that sub camera 400 tracks subject B. In addition, since the zoom state of main camera 500 has changed from "telephoto end" to "middle", CPU 101 controls the zoom state of sub camera 400 from "wide-angle end" to "middle" (in the opposite phase).

[0167] After that, the subject of interest of main camera 500 is changed from subject A to subject C, and the zoom state is changed to "wide-angle end." In response to this, CPU 101 changes the subject being tracked by sub camera 400 to subject A on the left side of subjects A and B other than subject C, and controls the shooting direction so that sub camera 400 tracks subject A. In addition, because the zoom state of main camera 500 has changed from "middle" to "wide-angle end," CPU 101 controls the zoom state of sub camera 400 from "middle" to "telephoto end" (in the opposite phase).

[0168] In this way, when the role of sub camera 400 is "assist counter", CPU 101 automatically changes the tracking subject of sub camera 400 to a subject other than the subject of interest of main camera 500 in response to a change in the subject of interest of main camera 500. CPU 101 also automatically changes the zoom value of sub camera 400 in the opposite direction to the change in the angle of view (zoom value) of main camera 500.

[0169] 16, the zoom state of the sub camera 400 is controlled at a degree of change equal to that of the main camera 500, but the amount of change in the zoom value may be different as long as the direction of change in the zoom value is in the opposite phase. For example, when the zoom state of the main camera 500 is at the telephoto end, the zoom state of the main camera 500 does not have to be at the wide-angle end. The degree of change in the zoom state of the sub camera 400 relative to the degree of change in the zoom state of the main camera 500 may be set using role setting information.

[0170] (Modification) So far, we have described an example of automatically controlling the tracking subject and zoom value of the sub camera 400 based on the target subject and zoom value of the main camera 500. In the above example, the sub camera is automatically controlled to track a single subject, but it can also be automatically controlled to track multiple subjects within the shooting range.

[0171] When the role set for the sub-camera 400 is "assist follow", examples of control in the case where the sub-camera 400 is made to track a single subject and in the case where the sub-camera 400 is made to track multiple subjects will be described with reference to FIG. 17. For ease of understanding and explanation, a case will be described in which the angle of view of the main camera 500 does not change and only the control of the subject to be tracked is executed. Also, it is assumed that the angle of view of the sub-camera 400 is always capable of photographing all subjects within the photographing range 20 regardless of the photographing direction. Note that the photographing direction of the sub-camera 400 shown in the top row of FIG. 17 indicates the photographing direction when a single subject is tracked.

[0172] As in FIG. 16, initially, the subject of interest (tracking subject) of the main camera 500 is subject B. Therefore, the CPU 101 determines the tracking subject of the sub camera 400 to be subject A on the left side among subjects A and C other than subject B, and controls the shooting direction so that the sub camera 400 tracks subject A. If the shooting direction is controlled so that the tracking subject is located at the center of the screen, as shown in the second row from the bottom, the image of the sub camera 400 will be an image in which subjects A to C are shifted to the right, resulting in poor balance. Therefore, when multiple subjects including the tracking subject are present in the image of the sub camera 400, the shooting direction can be controlled so that the multiple subjects are tracked. For example, the CPU 101 can control the shooting direction so that the center of gravity of the positions of the multiple subjects A to C included in the image of the sub camera 400 is tracked. As a result, the sub camera 400 shoots an image as shown in the bottom row.

[0173] In the example shown in FIG. 17, even if the sub-camera 400 tracks any one of the subjects A to C, all of the subjects A to C are captured, so the capturing direction of the sub-camera 400 remains almost constant even if the subject of interest of the main camera 500 changes.

[0174] (Variation 2) Also, after determining the tracking subject of the sub camera 400, the CPU 101 may control the sub camera 400 to focus on the tracking subject. Basically, the CPU 401 continuously controls the focusing distance so that the sub camera 400 focuses on the designated tracking subject, but the AF frame of the sub camera 400 can be set to the position of the tracking subject from the shooting control device 100. This allows the sub camera 400 to quickly and reliably focus on the tracking subject. Note that if the AF frame is set when the pan speed slows down (below the threshold), there is a high possibility that the tracking target will be located in the center of the screen, and therefore the time required for focusing can be shortened.

[0175] (Variation 3) Also, the sub camera 400 can be controlled without using the overhead camera 300. In this case, the shooting direction of the sub camera 400 can be determined from the installation positions of the main camera 500 and the sub camera 400 and the shooting direction of the main camera 500 (the orientation of the main camera 500 with respect to the tracking subject). The main camera 500 executes a subject detection process, and the CPU 101 acquires and uses the result to control the sub camera 400. For example, the CPU 101 acquires an image of the subject area from the main camera 500 as a result of the subject detection process. Then, the CPU 101 can control the sub camera 400 to execute a subject tracking process using the acquired image as a template. Alternatively, the CPU 101 may use the acquired image as a template and control the sub camera 400 to track a subject area with a low correlation with the template.

[0176] (Variation 4) Although the shooting control device 100, the role control device 600, and the main camera 500 have been described as independent devices, the functions of the shooting control device 100 and the role control device 600 can also be incorporated into the main camera 500. In this case, the video of the overhead camera 300 is supplied to the main camera 500. With this configuration, it is possible to reduce the number of devices required to realize a multi-camera imaging system.

[0177] As described above, according to this embodiment, when the operation of the sub camera is automatically controlled based on the state and image of the main camera, automatic control is executed according to the role set for the sub camera. Therefore, the photography control device of this embodiment can realize automatic photography control with a higher degree of freedom while realizing labor saving.

[0178] <Second embodiment> Next, a second embodiment of the present invention will be described. In this embodiment, a tracking subject of a sub camera is determined taking into account information based on the state or image of the main camera, the role set for the sub camera, and the image of the sub camera.

[0179] Fig. 18 is a schematic diagram showing a configuration example of an imaging system 10' according to this embodiment. In Fig. 18, the same components as those in the imaging system 10 according to the first embodiment are given the same reference numerals as those in Fig. 1, and the description thereof will be omitted. The imaging system 10' according to this embodiment has two sub-cameras, a sub-camera A800 and a sub-camera B900. The functional configurations of the sub-camera A800 and the sub-camera B900 are similar to those of the sub-camera 400 described in the first embodiment, and therefore the description thereof will be omitted.

[0180] In this embodiment, a role is set in the shooting control device 100 from the role control device 600, and the role setting information includes different control contents for each sub camera. The CPU 101 controls the operation of each sub camera according to the role set in the shooting control device 100. Fig. 19 is a diagram showing an example of role setting information in this embodiment. Here, only the role "assist follow" and the corresponding control contents for each sub camera are shown as an example. However, the types of roles that can be set in the shooting control device 100 and the control contents corresponding to the types of roles are not limited to the example shown in Fig. 19.

[0181] Here, it is stipulated that the sub camera A800 is controlled to set the left subject of the subjects different from the main camera's tracking subject as the tracking subject and to focus on the tracking subject. Also, it is stipulated that the sub camera B900 is controlled to set the right subject of the subjects different from the main camera's tracking subject as the tracking subject and to focus on the tracking subject. Here, since it is known in advance that the total number of subjects is 3, it is stipulated as the left or right of two people, but it may simply be stipulated as the left or right. Note that zoom control may be stipulated as in the first embodiment, but zoom control is omitted for the sake of simplicity of explanation.

[0182] 19 is stored in advance in the ROM 103 of the shooting control device 100. Alternatively, the role setting information may be supplied from the role control device 600 to the shooting control device 100, and the CPU 101 may store it in the RAM 102.

[0183] Using FIG. 20, a description will be given of how the shooting control device 100 controls the sub-camera A 800 and the sub-camera B 900 based on the role setting information.

[0184] Fig. 20(a) shows the positional relationship between shooting range 20, main camera 500, sub camera A 800, and sub camera B 900 at the start of shooting, and subjects A to C within shooting range 20. Fig. 20(b) shows a state in which, after shooting starts, subject A moves from the left side to the right side of subject B, and subject C moves from the right side to the left side of subject B.

[0185] At the stage of Fig. 20(a), the CPU 101 of the shooting control device 100 controls the operations of the sub-camera A800 and the sub-camera B900 based on the role setting information shown in Fig. 19. That is, the CPU 101 determines that of the subjects A and C other than the target subject (subject B) of the main camera 500, the subject A on the left side is the subject to be tracked by the sub-camera A800, and the subject C on the right side is the subject to be tracked by the sub-camera B900.

[0186] The CPU 101 controls the shooting directions of the sub-camera A 800 and the sub-camera B 900 so as to track the determined tracking subject, and also controls the sub-camera A 800 and the sub-camera B 900 so as to focus on the determined tracking subject.

[0187] In the state of FIG. 20(b), the subject A tracked by the sub camera A800 does not satisfy the condition of "subject on the left side" (other than the subject of interest of the main camera 500). Therefore, the CPU 101 changes the subject tracked by the sub camera A800 to subject C on the left side of subjects A and C other than the subject of interest of the main camera 500 (subject B). Similarly, the subject C tracked by the sub camera B900 does not satisfy the condition of "subject on the right side". Therefore, the CPU 101 changes the subject tracked by the sub camera B900 to subject A on the right side of subjects A and C other than the subject of interest of the main camera 500 (subject B). The CPU 101 also controls the sub camera A800 and the sub camera B900 to focus on the determined subject to be tracked.

[0188] When a subject moves significantly, as in Fig. 20(b), there is a high possibility that another subject exists in front, making it easier for the subject to be tracked to be hidden. By setting the sub-camera positioned to the left of the shooting range 20 to track a subject that exists on the left side, it is possible to specify that the tracking subject is effectively changed when the tracking subject moves significantly to the right. The same applies to the sub-camera positioned to the right of the shooting range 20.

[0189] In this embodiment, it is possible to define the control contents so that each sub-camera with the same role tracks a different subject. Therefore, according to the shooting control device 100 of this embodiment, it is possible to automatically control the sub-camera so that it shoots images tracking various subjects based on the state of the main camera and information obtained from the image.

[0190] (Modification) In this embodiment, the shooting direction of the sub-camera for tracking a specific subject is estimated by performing coordinate conversion on the position of the subject area detected from the image of the overhead camera 300. However, a similar estimation may be performed based on the images of the sub-camera A800 and the sub-camera B900. In this case, although the processing load of the shooting control device 100 increases, since coordinate conversion is not required, the accuracy of the control of the shooting direction of the sub-camera can be improved.

[0191] (Variation 2) In the present embodiment, the pan / tilt values ​​for controlling the sub-camera A800 and the sub-camera B900 are calculated so as to automatically track the tracking target. However, automatic tracking is not essential. For example, the role setting information may specify that the pan values ​​of the sub-camera A800 and the sub-camera B900 are controlled according to the zoom value of the main camera 500.

[0192] As an example, when the zoom state of the main camera 500 is the "wide-angle end", the sub-camera A800 can be controlled to face in a direction diagonally 45 degrees to the left, and the sub-camera B900 can be controlled to face in a direction diagonally 45 degrees to the right. On the other hand, when the zoom state of the main camera 500 is the "telephoto end", both the sub-camera A800 and the sub-camera B900 can be controlled to face in the center 0 degree direction.

[0193] By performing such control, it becomes possible to control the shooting directions of the multiple sub-cameras in synchronization with the zoom state of the main camera 500, and the performance effect can be enhanced. For example, when the main camera 500 zooms in on a specific subject, the sub-cameras A800 and B900 can change the shooting directions while zooming in on the same subject in conjunction with the main camera 500. By performing such control, it becomes possible to simultaneously view multiple images shot by multiple cameras that are synchronously controlled in a performance in which multiple camera images are displayed on multiple monitors. In addition, by automatically controlling each camera with the same role, the variation in the time change in the angle of view between the cameras is smaller than when each camera is manually operated, and the sense of unity of the angle of view change is stronger, and a performance effect that enhances the sense of realism can be expected.

[0194] (Variation 3) In the present embodiment, the main camera 500 is controlled as the master, and the sub-camera A800 and the sub-camera B900 are controlled as the slaves. However, the master-slave relationship between the main camera 500 and the sub-camera A800 may be dynamically changed. For example, the camera capturing the main line video among the main camera 500, the sub-camera A800, and the sub-camera B900 may be controlled as the master, and the other cameras may be controlled as the slaves. In this case, the shooting control device 100 may obtain information indicating which camera's video is selected as the main line video from an external device such as a switcher that selects the video, or may determine the information based on a tally signal. The same control may be performed not only when the main line video is selected as the video related to the viewer's viewing or recording, such as the video for recording.

[0195] The master-slave relationship between the cameras may be switched when the sub-camera A 800 or the sub-camera B 900 is manually operated. In this case, when the user manually operates one of the sub-cameras, the control of the other cameras is started with the sub-camera as the master, which is convenient.

[0196] (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.

[0197] The disclosure of the present embodiment includes the following imaging control device, imaging control method, imaging system, and program. (Item 1) An acquisition means for acquiring information from a state or image of a main camera among the plurality of cameras; a control unit that controls an operation of a sub-camera among the plurality of cameras based on a role set for the sub-camera and the information; the acquiring means acquires, as the information, information on a subject of interest of the main camera and information on an angle of view of the main camera; The control means controls a shooting direction and an angle of view of the sub-camera based on the role set for the sub-camera and the information. 13. An imaging control device comprising: (Item 2) The photographing control device according to item 1, characterized in that the control means determines the target subject or a subject other than the target subject as a tracking subject of the sub-camera according to a role set for the sub-camera, and controls the photographing direction of the sub-camera so as to track the tracking subject. (Item 3) 3. The photographing control device according to item 2, wherein the control means controls the photographing direction of the sub-camera so as to track a plurality of subjects including the tracking subject. (Item 4) The photographing control device according to item 3, characterized in that when controlling the photographing direction of the sub-camera so as to track a plurality of subjects including the tracking subject, the control means controls the photographing direction of the sub-camera so as to track the center of gravity of the positions of the plurality of subjects. (Item 5) 5. The photographing control device according to any one of items 1 to 4, wherein, when the sub-camera is multiple, the control means determines different tracking subjects for the multiple sub-cameras. (Item 6) 6. The imaging control device according to any one of items 1 to 5, characterized in that the main camera and the sub camera can be dynamically changed. (Item 7) 7. The photographing control device according to item 6, characterized in that when the sub-camera is manually operated, the main camera and the sub-camera are switched. (Item 8) 7. The imaging control device according to item 6, wherein among the plurality of cameras, a camera whose video is selected by an external device is set as the main camera. (Item 9) The shooting control device according to any one of items 1 to 8, characterized in that the control means determines the shooting direction of the sub-camera based on an image captured by a camera other than the multiple cameras, which captures the entire shooting range of the multiple cameras. (Item 10) 10. The imaging control device according to any one of items 1 to 9, wherein the sub-camera is capable of controlling pan and tilt operations from an external device. (Item 11) The control means controls the angle of view of the sub camera in the same phase as the change in the angle of view of the main camera or in an opposite phase according to the role set for the sub camera. 11. The imaging control device according to any one of items 1 to 10, (Item 12) The information regarding the angle of view of the main camera is information indicating a zoom state of the main camera, 12. The photographing control device according to claim 1, wherein the control means controls the zoom operation of the sub-camera based on a role set for the sub-camera and information indicating a zoom state of the main camera. (Item 13) 13. The photographing control device according to any one of items 1 to 12, wherein the sub-camera has an externally controllable zoom operation. (Item 14) An imaging control device according to any one of items 1 to 13, The plurality of cameras; a communication network that communicably connects the photography control device and the plurality of cameras; An imaging system comprising: (Item 15) A photographing control method executed by a photographing control device, Obtaining information from a state or image of a main camera among the multiple cameras; and controlling an operation of a sub-camera among the plurality of cameras based on a role set for the sub-camera and the information; The acquiring includes acquiring, as the information, information on a subject of interest of the main camera and information on an angle of view of the main camera, The controlling comprises: and controlling a shooting direction and an angle of view of the sub-camera based on a role set for the sub-camera and the information. (Item 16) A program for causing a computer to function as each of the means possessed by the imaging control device according to any one of items 1 to 13.

[0198] The present 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. Therefore, the following claims are appended to disclose the scope of the invention. [Explanation of symbols]

[0199] 100: control device, 300: overhead camera, 400: sub-camera, 500: main camera, 600: role control device, 101: CPU, 102: RAM, 103: ROM, 104: inference unit, 105: network I / F, 106: user input unit

Claims

1. An acquisition means for acquiring information from a state or image of a main camera among the plurality of cameras; a control unit that controls an operation of a sub-camera among the plurality of cameras based on a role set for the sub-camera and the information; the acquiring means acquires, as the information, information on a subject of interest of the main camera and information on an angle of view of the main camera; The control means controls a shooting direction and an angle of view of the sub-camera based on the role set for the sub-camera and the information.

13. An imaging control device comprising:

2. 2. The photographing control device according to claim 1, wherein the control means determines the target subject or a subject other than the target subject as a tracking subject of the sub-camera according to a role set for the sub-camera, and controls the photographing direction of the sub-camera so as to track the tracking subject.

3. 3. The photographing control device according to claim 2, wherein the control means controls the photographing direction of the sub-camera so as to track a plurality of subjects including the tracked subject.

4. The photographing control device according to claim 3, characterized in that, when controlling the photographing direction of the sub-camera so as to track a plurality of subjects including the tracking subject, the control means controls the photographing direction of the sub-camera so as to track the center of gravity of the positions of the plurality of subjects.

5. 2 . The photographing control device according to claim 1 , wherein, when the sub-camera is plural, the control means determines different tracking subjects for the plural sub-cameras.

6. 2. The imaging control device according to claim 1, wherein the main camera and the sub-camera can be dynamically changed.

7. 7. The photographing control device according to claim 6, wherein the main camera and the sub camera are switched when the sub camera is manually operated.

8. 7. The imaging control device according to claim 6, wherein a camera from which an image is selected by an external device among the plurality of cameras is set as the main camera.

9. The imaging control device according to claim 1, characterized in that the control means determines the imaging direction of the sub-camera based on an image captured by a camera other than the multiple cameras, which captures the entire imaging range of the multiple cameras.

10. 2. The photographing control device according to claim 1, wherein the sub-camera is capable of controlling pan and tilt operations from an external device.

11. The control means controls the angle of view of the sub camera in the same phase as the change in the angle of view of the main camera or in an opposite phase according to the role set for the sub camera.

2. The imaging control device according to claim 1 .

12. The information regarding the angle of view of the main camera is information indicating a zoom state of the main camera, 2. The photographing control device according to claim 1, wherein the control means controls a zoom operation of the sub-camera based on a role set for the sub-camera and information indicating a zoom state of the main camera.

13. 2. The photographing control device according to claim 1, wherein the sub-camera has an externally controllable zoom operation.

14. The imaging control device according to any one of claims 1 to 13, The plurality of cameras; a communication network that communicably connects the photography control device and the plurality of cameras; An imaging system comprising:

15. A photographing control method executed by a photographing control device, Obtaining information from a state or image of a main camera among the multiple cameras; and controlling an operation of a sub-camera among the plurality of cameras based on a role set for the sub-camera and the information; The acquiring includes acquiring, as the information, information on a subject of interest of the main camera and information on an angle of view of the main camera, The controlling comprises: and controlling a shooting direction and an angle of view of the sub-camera based on a role set for the sub-camera and the information.

16. A program for causing a computer to function as each of the means included in the imaging control device according to any one of claims 1 to 13.

Images