Method for specifying real-time tracking targets by pausing video.

Abstract

In sports photography, such as soccer, this allows the PTZ camera to accurately select the target to track, even in environments where multiple fast-moving objects are visible. [Solution] For video footage continuously acquired from camera 12, multiple action targets included in each frame are highlighted in a discernible manner, the highlighted video is dynamically displayed at a timing similar to real time, and video footage for a predetermined buffer time prior to real time is kept in a state where it can be recalled, the dynamically displayed video is paused at a specified timing, frames for a predetermined number of seconds before and after the timing of the video are selected and displayed according to the user's input, the system accepts the specification of an action target to be displayed, and a control signal is sent to the camera to track the specified action target.

Description

Technical Field

[0001] This invention relates to a system that continuously tracks and photographs a specific target with a camera in an environment where multiple targets are mixed.

Background Art

[0002] In recent years, while the scenes for shooting videos have increased due to the diversification of content, there is a tendency for a shortage of camera operators with specialized skills. For example, in shooting sports videos where multiple players participate, there are often multiple targets such as players and balls that need to be shot and change frequently, and high-level techniques are required for shooting. However, it is not easy to cultivate highly skilled camera operators, and the demand for automatic shooting technology is increasing.

[0003] In sports such as soccer and basketball where players are particularly mixed, videos that follow a specific shooting target (target) such as a single player or ball are mainstream. Therefore, in automatic shooting, basically, one of the continuously moving targets needs to be specified in real time and the shooting should continue while tracking that target. For this purpose, various techniques for detecting and tracking objects have been studied.

[0004] As an example of a technique for detecting and identifying an object, YOLO (You Only Look Once) provided as open source can be cited. The entire image is divided into fine grid cells and processed collectively, and as an output result, a display that surrounds the range of the detected and identified object in the image with a rectangle (Bounding Box: Bbox) can be obtained in real time.

[0005] As an example of a technique for tracking a target, IOU (intersection-over-union) can be cited. The value obtained by dividing the overlapping part (intersection) in two regions by the area of the union of the two regions is called IOU and is used as an index representing the degree of overlap.

[0006] YOLO calculates the IOU of the Bboxes between two frames of images outputting Bboxes, and tracks by determining that pairs of Bboxes exceeding a threshold are the same subject. This allows the user to select one Bbox and then continuously track Bboxes that are determined to be the same subject. The PTZ camera, which adjusts up, down, left, right, and zoom, automatically adjusts to keep the tracked object within the camera's field of view, enabling automatic recording of footage that continuously tracks the target.

[0007] However, the process of specifying the target to be tracked still largely relies on human judgment. Even deciding which player or ball to focus on in each scene is still left to human judgment. However, during sports, the objects are moving at high speed, making it quite difficult to quickly and accurately specify a target. Patent Document 1 proposes a technique in which a display screen for selecting a target is divided, and the user quickly presses a 10-key keypad or directional keys as an input device to select the target. [Prior art documents] [Patent Documents]

[0008] [Patent Document 1] Japanese Patent Publication No. 2007-233542 [Overview of the project] [Problems that the invention aims to solve]

[0009] However, even with the technology described in Patent Document 1, while the operation itself can be simplified, it is still difficult to make accurate selections when multiple objects are displayed, as the selection must be made while tracking the video in real time. In particular, when trying to select the same object with multiple cameras, it is necessary to consecutively select the target for each camera in the short time that the object is within the field of view of all the cameras, which further increases the time constraint and difficulty.

[0010] Therefore, the purpose of this invention is to enable the camera to accurately select the target object to track, even in environments where multiple objects are displayed moving at high speed. [Means for solving the problem]

[0011] This invention is A video acquisition unit that continuously acquires video footage captured by a camera, A highlighting processing unit that highlights multiple action objects contained within each frame of the acquired video in a way that makes them distinguishable, A video display function unit that dynamically displays the highlighted video in a timing similar to real time, A video storage unit that holds video footage for a predetermined buffer time period prior to real-time in a state that can be retrieved, A pause function unit that pauses the dynamically displayed video at a specified timing, A target designation function unit that selects and displays frames of the aforementioned video for a predetermined number of seconds before, after, or both of the aforementioned timings according to the user's input, and accepts the designation of the target to be displayed. A camera control unit transmits a control signal to the camera to track the specified target, The above problem was solved by the first solution, which involves a device for specifying the target of operation.

[0012] Furthermore, in the first solution, A second solution can be adopted in which, after the target designation function unit receives the designation of the target, it performs a follow-up tracking calculation to track the designated target from the frame in which the target was designated to the frame at the most recent time, determines the location of the designated target in the frame at the most recent time, and transmits this to the camera as the camera control unit.

[0013] Furthermore, in the first solution, The aforementioned highlighting processing unit performs continuous tracking calculations to sequentially track all action targets highlighted in every frame. When the target designation function unit receives the designation of the target to be operated, a third solution can be adopted in which the camera control unit determines the location of the target to be operated, which has been tracked up to the frame at the most recent time, and transmits this information to the camera.

[0014] Furthermore, this invention can employ a fourth solution, which is a program for operating a computer as a target designation device, which is one of the first to third solutions.

[0015] Furthermore, this invention can adopt a fifth solution, which is a system comprising the camera and the first to third solutions, which are device for designating the target of operation.

[0016] Furthermore, this invention also, Steps to continuously acquire video captured by the camera, A step of highlighting multiple objects of action contained within each frame of the acquired video so that they can be identified. The steps include dynamically displaying the highlighted video in a timing similar to real time, The step of continuously retaining video footage for a predetermined buffer time period prior to real-time in a state where it can be retrieved, The steps of pausing the dynamically displayed video at a specified timing, A step of selecting and displaying frames of the aforementioned video for a predetermined number of seconds before, after, or both of the aforementioned timings, according to the operator, and receiving a specification of the action target to be displayed, A step of sending a control signal to the camera to track the specified target, A sixth solution can be adopted, which is a method for specifying the target of the operation to be performed. [Effects of the Invention]

[0017] According to the operation target specifying device, program for operating the same, and operation target specifying method according to the present invention, instead of specifying the operation target while chasing it in real time, it pauses for about several seconds to select a frame at a timing that makes it easy to select the operation target, and the operation target can be specified. Therefore, even in a video where a large number of players such as in soccer or basketball are in a chaotic state, the operator can accurately select the operation target in a short time. This greatly contributes to the fact that by securing a buffer time of about several seconds and displaying the selected video instead of displaying the latest frame in real time, it is possible to select a frame that makes it easy to specify the operation target by moving it back and forth in time at the paused stage.

[0018] Existing methods can be used to track the operation target specified in the specified frame to the latest frame. As a method of tracking only the specified operation target, although a slight time lag occurs until the camera can actually automatically follow, the calculation load of the operation target specifying device itself can be reduced. On the other hand, as a method of continuously tracking all operation targets displayed in all frames in sequence, when an operation target is specified, the camera can be quickly directed to the current position of the operation target from the recording that tracked the operation target, so the time lag can be reduced. However, continuously tracking all operation targets in sequence increases the calculation load of the operation target specifying device itself.

Brief Description of Drawings

[0019] [Figure 1] Schematic diagram showing an embodiment of a system including the operation target specifying device according to the present invention [Figure 2] Example diagram of the arrangement of a soccer field and cameras installed as an example of the environment using the present invention [Figure 3] Functional block diagram of the operation target specifying device according to the present invention [Figure 4] (a) Example diagram of a frame including highlighted display displayed on a display device, (b) Example diagram of a frame in which operation targets with a time difference of several seconds from (a) overlap [Figure 5] Conceptual diagram showing the time-axis behavior of the method for specifying the target of operation according to this invention. [Figure 6] (a) An example of a frame at the point of pause, (b) An image illustrating the process of selecting frames before and after the pause, (c) An image illustrating a camera that receives a control signal and tracks the target object, centering it in the field of view. [Figure 7] An example diagram showing a display screen divided into four sections to simultaneously display images from four cameras. [Figure 8] Flowchart example of a program for operating the target device according to this invention. [Modes for carrying out the invention]

[0020] The present invention will be described in detail below, along with specific embodiments. This invention is a device for specifying an object, a method for specifying an object, and a program therefor, which enable the camera to automatically track and continuously film an object in motion that appears in a video being captured by the camera, in order to easily and accurately specify that object.

[0021] Figure 1 shows a system configuration diagram of an operation target designation system having an operation target designation device 11 according to the first embodiment of the present invention and cameras 12 (12a to 12d) controlled by the operation target designation device 11.

[0022] The target device 11 is a computer equipped with a display device 21 and an input device 22. As hardware, a general-purpose personal computer, tablet, or smartphone equipped with a general-purpose arithmetic unit, memory, and storage device can be used. However, it must have wired or wireless network capabilities in order to connect to and control the camera 12. While Figure 1 shows the target device 11 as a single unit, it may be composed of multiple hardware units. Hardware with the same functionality may be configured in parallel, or the configuration of the target device 11 described later may be implemented by distributing the workload among multiple connected hardware units. For example, the computational load can be distributed by sharing the processing.

[0023] The display device is preferably capable of high-speed color display, and specific examples include liquid crystal monitors and organic EL monitors. The display device may be housed in the same enclosure as the target device 11 itself, or it may be connected externally via a display cable.

[0024] The input device preferably has a pointing device. While it is possible to specify a point using only a keyboard, it is preferable to have a device that allows for quick selection of a target displayed on the display device, such as a mouse, trackball, or touch panel.

[0025] Furthermore, the program that causes a computer to operate as the target device 11 according to this invention is either installed as a dedicated program that performs the following operations, or executed via a web browser or the like.

[0026] The camera 12 controlled by the target device 11 according to this invention must be a PTZ camera, which is a camera that can remotely control horizontal (pan), vertical (tilt), and zoom adjustments. The number of cameras 12 is not particularly limited and can be determined according to the requirements of the content to be filmed. This invention can also be implemented with a single camera 12. The advantage of being able to quickly specify the target is particularly well demonstrated in a system with multiple cameras 12. Here, as an example, we will explain a case in which cameras 12a to 12d are installed at four locations outside the field of a soccer field, as shown in Figure 2.

[0027] Furthermore, the type of video content used to specify the target of action using the action target designation device 11 according to this invention is not particularly limited. In sports, it is particularly suitable for use in sports involving many players, such as basketball, not just soccer. Outside of sports, it is also suitable for use in live performances and other events featuring many performers.

[0028] Figure 3 shows a functional block diagram of the operation target designation device 11 according to this invention connected to a camera 12. Cameras 12a to 12d are described together as camera 12 in this document. If multiple cameras 12 are connected, it is preferable that they be connected in parallel.

[0029] The operation target designation device 11 primarily consists of a calculation unit 31 that performs calculations related to video processing, a UI unit 32 related to the user interface, and a camera control unit 33 related to the control of the camera 12. These functions are realized by programs that are installed or temporarily deployed on the operation target designation device 11 as hardware. The programs are recorded on a tangible, non-temporary recording medium, loaded into memory for execution, and then executed by the calculation unit.

[0030] The target device 11 has a video acquisition unit 41 that continuously acquires video captured by the camera 12. When acquiring the video, it is preferable to continuously receive it from the camera 12 in an environment with as little time lag as possible.

[0031] The target device 11 has a video storage unit 42 that stores at least a portion of the acquired video in a readable format. The storage medium may be the volatile memory, non-volatile memory, or magnetic disk of the target device 11. However, in order to enable high-speed video processing, it is desirable that at least a portion of the video data be stored in an environment that can read and process the video data at high speed, such as non-volatile memory or a Solid State Drive (SSD).

[0032] The object designation device 11 has a highlighting processing unit 43 that highlights multiple objects included in each frame of the acquired video in a discriminable manner. Here, a frame refers to a still image that makes up a video. Videos are generally displayed at a rate of about 30 to 60 frames per second and are perceived as moving by the user. Objects included in a frame basically refer to objects that move relative to the background in the video, and include performers such as athletes and singers, as well as non-human organisms such as horses in horse racing and birds in nature, and balls exchanged on fields or courts, but are not particularly limited. However, this invention is preferably used when multiple objects appear in the video. To highlight in a discriminable manner means to display the object so that the user can clearly distinguish it from the background visually, and so that the object designation device 11 can distinguish which object is being selected when selecting from the input device 22. Specific methods include enclosing the object with a rectangle or circle, or changing the color of the area of ​​the object to distinguish it from the background. One example of a technology that can be used is YOLO, but it is not particularly limited to this. Here, we use a soccer player P as the target of the action, and Figure 4 shows an example of highlighting him by surrounding him with a rectangular line. Figure 4 is a frame showing a part of a soccer field as captured by camera 12, with each player in the frame surrounded by a rectangle.

[0033] The video, in which the target of each frame is highlighted by the highlighting processing unit 43, is preferably stored in the video storage unit 42 and can be recalled. The target of operation designation device 11 has a video display function unit 46 that dynamically displays the highlighted video at a timing similar to real time (the latest time of capture). A timing similar to real time means that the video can be displayed with a delay of only the minimum time lag from the latest time of video acquisition due to the above-mentioned highlighting calculation processing and communication processing. The destination for dynamic display is basically a display device 21 that is stored in the same enclosure as the target of operation designation device 11 or is directly connected to it with minimal time lag. At this time, while dynamically displaying, it is necessary to continuously reserve video from the latest real time for a predetermined buffer time in a high-speed recall area in the video storage unit 42. Specifically, it is desirable to reserve it on non-volatile memory as it is easier for the arithmetic unit to process.

[0034] The predetermined buffer time is approximately 1 to 10 seconds. Here, it will be abbreviated as "a few seconds." While the video display function unit 46 displays video captured by the camera 12 in near real-time, the video storage unit 42 continuously holds video frames from a few seconds prior to real-time (the latest time) so that they can be recalled and displayed according to instructions. Specifically, these frames are continuously buffered in a high-speed recall area within the video storage unit 42. This allows the user to recall frames from the video storage unit 42 immediately after pausing the video they are viewing on the display device 21, thereby rewinding the displayed video chronologically by a few seconds (i.e., to the past). Furthermore, after pausing, the video up to the latest time is also continuously buffered in a high-speed recall area within the video storage unit 42. By making the frames between the moment of pause and the latest time recallable, it is possible to advance the video beyond the paused frame (i.e., to the future).

[0035] The buffer time may be longer than 10 seconds, but if the buffer time is extended beyond 10 seconds, the target object may move too far from the paused frame, and in some cases may even go out of the field of view, thus limiting its effectiveness in assisting the selection of the target object. Furthermore, if too many frames are kept allocated in the area that can be recalled quickly, the amount of execution memory may increase too much, potentially leading to a heavy operational burden. For this reason, a buffer time of 10 seconds or less is preferable, and 5 seconds or less is practically suitable in most cases. On the other hand, if the buffer time is shorter than 1 second, the time window that can be extended back becomes too short, making it not much different from real-time display, and the effects of the present invention will not be fully realized.

[0036] A conceptual diagram of this change on the time axis is shown in Figure 5. The frame displayed on the display device 21 progresses along with the latest time captured by the camera 12, but it remains after the buffer time.

[0037] To achieve the above operation, the target selection device 11 has a pause function unit 47 that pauses the dynamically displayed highlighted video at a specified timing. The timing for this pause is preferably received from the input device 22. The input device 22 can be a mouse or touch panel, which can be used to click or touch buttons on the displayed video or to operate the video. Alternatively, pressing a keyboard, numeric keypad, or other buttons may be accepted as a pause command. This is because it is required that the input be made as quickly as possible at a timing close to the situation desired by the user. If the operation is delayed, it may be difficult to select the target of the operation at a timing that is not desirable. This difference will be explained using a comparison between Figure 4(a) and Figure 4(b) as an example. We want to select the player enclosed by the thick line in the figure. If this can be stopped at the timing in Figure 4(a), selection within the rectangle is easy. However, if the positional relationship becomes like that in Figure 4(b) with a delay of a few seconds, the position will overlap with the player to the right, making it difficult to accurately select the player enclosed by the thick line in the figure. Furthermore, this positional relationship may continue for some time.

[0038] To address this, the target selection device 11 has a target selection function unit 48 that selects and displays frames of a predetermined number of seconds before, after, or both of the pause timing specified by the user in response to the user's operation, and accepts the specification of the target to be displayed. Selecting and displaying in response to the above operation means switching the display to frames that are chronologically in the past or future according to the input from the input device 22. Even if the frame at the pause timing is superimposed with a rectangular display that highlights the player, as in Figure 6(a), there is a high possibility that among the frames that are rewinded to a few seconds before (in the past) the pause timing, there is a frame where the rectangular display that highlights the player does not overlap, as in the very first frame in Figure 6(b). In this way, the display is switched to frames of a few seconds before (in the past), after (in the future), or both of the pause timing. The method for accepting this selection is preferably one that can move forward or backward in the time series by input from the input device 22, which allows for easy fast forward and rewind of the time series. Operations such as moving the mouse wheel forward and backward, or sliding a slider bar displayed on a touch panel forward, backward, left, or right, can be suitably used. Furthermore, accepting the specification of the displayed target means accepting the specification of a target from among the targets displayed in the frame that the camera 12 is to track. A good way to accept the specification is to select the highlighted target (in this case, within the rectangular frame) using the input device 22, which is a pointing device. In Figure 6(b), a finger icon, which is the mouse cursor, is shown as an example. Select a frame that makes it easy to specify the target you want to specify (in this case, player P1 surrounded by a thick frame), move the mouse cursor into the target's frame in the frame, and click to specify the target.

[0039] The target selection device 11 has a tracking function unit 49 that tracks the target specified in the displayed frame to the position shown in the latest image on the camera 12. This is because the designated frame is several seconds in the past, and the position of the target often moves during those seconds, so it is necessary to track the position to which the camera 12 is actually pointed to to the latest position of the specified target. The IOU method described above can be preferably used as a tracking method, but is not particularly limited.

[0040] Tracking methods include a reactive tracking calculation method that tracks only the specified target, and a continuous tracking calculation method that sequentially tracks all targets highlighted by the highlighting processing unit 43. The former has a low computational load but there is a time lag between selection and issuing an instruction to camera 12. The latter has a high computational load but allows for immediate instruction to camera 12 after selection.

[0041] The method of the subsequent tracking calculation described above will now be explained. After the target designation function unit 48 receives the designation of the target, it tracks the designated target from the frame in which the target was designated to the frame at the most recent time. That is, for the designated target, it checks for targets that are determined to be the same subject between the designated frame and the next frame, and checks for targets that are determined to be the same subject between the next frame and the frame after that, and so on, repeating this process until the frame at the most recent time, thereby determining the location (coordinates) of the designated target at the frame at the most recent time.

[0042] Next, the method of the continuous tracking calculation described above will be explained. Without waiting for the target designation function unit 48 to designate an operating target, the highlighting processing unit 43 continuously checks the relationships between operating targets that are determined to be the same subject between each frame for all highlighted operating targets. In other words, the movement of all operating targets is continuously tracked across all frames. This means that, for any past frame, if an operating target is designated in that frame, it is possible to immediately check where that operating target is in the latest frame, as long as it has not gone out of the field of view. For example, each operating target may be identifiable by an ID or similar. Then, when the target designation function unit 48 receives the designation of an operating target, it determines the position (coordinates) of that operating target in the latest frame, for which it has already been tracked up to the latest frame as described above.

[0043] In any of the above methods, the location of the designated target in the latest time frame is determined. The target designation device 11 has a camera control unit 33 that transmits a control signal to the camera 12 to position the coordinates of its location in an appropriate position within the camera 12's field of view. The camera control unit 33 then continues to transmit control signals to the camera 12 to track the designated target. Specifically, the camera control unit 33 includes a control signal calculation unit 50 that calculates the control signals described above, and a control signal transmission unit 51 that transmits the control signals to the camera 12.

[0044] Once the above control signal is transmitted to camera 12, it will automatically operate so that the object being operated on is centered in the image (Figure 6(c)). Camera 12 may operate automatically, or the camera control unit 33 may operate by coordinating with the tracking function unit 49 based on information from the highlighting processing unit 43 to generate and transmit control signals in real time each time.

[0045] The target selection device 11 according to this invention allows for precise and high-speed operation of pausing and selecting a target by moving the camera back and forth to a frame that is easy to select. This enables a single user (operator) to accurately select targets for multiple cameras 12. For example, as shown in Figure 7, the images from multiple cameras 12 (12a to 12d) can be displayed on the screen in a split view. Immediately after a scene changes, the target can be selected for each of the multiple cameras 12, and control signals can be sent to the cameras 12. From then on, the camera can automatically track the target without user intervention until the screen changes significantly. With this invention, even a user without particular skill can select a target for one camera 12 in approximately 2 to 5 seconds.

[0046] A program flow example for operating a system consisting of an action target designation device 11 and a camera 12 will be explained using Figure 8. First, the video acquisition unit 41 continuously acquires video footage captured by the camera 12 (S11). Receiving data transmitted via push from the camera 12 reduces the load on the action target designation device 11. At this time, it is desirable to receive not only the video data for each frame of the video, but also identification information mainly for identifying the camera 12. The highlighting processing unit 43 then highlights multiple action targets contained in each frame of the acquired video so that they can be distinguished (S12).

[0047] Then, the video display function unit 46 of the target device 11, while continuously reserving video for the predetermined buffer time (several seconds) (S13), transmits the highlighted video to the display device 21 at a timing close to real time for dynamic display (S14). The user then observes the video with the target highlighted, which is slightly delayed from real time. Here, S13 and S14 are described with S13 first for convenience, but in reality they are executed almost in parallel. The pause function unit 47 of the target device 11 pauses the video dynamically displayed on the display device 21 at the timing instructed by the user operating the input device 22 (S15).

[0048] The target designation function unit 48 of the target designation device 11 transmits and displays to the display device 21 the frames selected by the user's operation to move forward or backward along the time axis from the input device 22 after a pause (S16). In addition, in (S16), if frames selected by the user within the time elapsed since the pause up to the latest time are also transmitted and displayed to the display device 21 in the same way. The target designation by the input device 22 is accepted from among the displayed frames (S17).

[0049] Here, we will describe the method of reactive tracking calculation as an example. The tracking function unit 49 of the target designation device 11 performs reactive tracking calculation to track the designated target from the frame in which the target was designated up to the frame at the most recent time, and calculates and determines the position coordinates of the designated target in the frame at the most recent time (S21). The camera control unit 33 of the target designation device 11 uses these position coordinates to calculate a control signal to the camera 12, which is a PTZ camera, so that the position coordinates of the designated target are located in the center of the video captured by the camera 12 (S22). This calculated control signal is transmitted to the camera 12 as a signal (S23).

[0050] From this point onward, the camera 12 or the camera control unit 33 continuously controls the position coordinates of the designated target to remain centered in the video captured by the camera 12. [Explanation of Symbols]

[0051] 11. Designated operating device 12, 12a, 12b, 12c, 12d Camera 21 Display device 22 Input devices 31 Arithmetic section 32 UI section 33 Camera Control Unit 41 Video Acquisition Unit 42. Video Memory Unit 43. Highlighting Processing Unit 46 Video display function unit 47 Pause function unit 48 Target Selection Function Unit 49 Tracking Function Unit 50 Control signal calculation unit 51 Control signal transmission unit

Claims

1. A video acquisition unit that continuously acquires video footage captured by a camera, A highlighting processing unit that highlights multiple action objects contained within each frame of the acquired video in a way that makes them distinguishable, A video display function unit that dynamically displays the highlighted video in a timing similar to real time, A video storage unit that holds video footage for a predetermined buffer time period prior to real-time in a state that can be retrieved, A pause function unit that pauses the dynamically displayed video at a specified timing, A target designation function unit that selects and displays frames of the aforementioned video for a predetermined number of seconds before, after, or both of the aforementioned timings according to the user's input, and accepts the designation of the target to be displayed. A camera control unit transmits a control signal to the camera to track the specified target, A device for specifying the target of operation.

2. The target designation device according to claim 1, wherein after the target designation function unit receives the designation of the target, it performs a follow-up tracking calculation to track the designated target from the frame in which the target was designated to the frame at the most recent time, determines the location of the designated target in the frame at the most recent time, and transmits this to the camera as the camera control unit.

3. The aforementioned highlighting processing unit performs continuous tracking calculations to sequentially track all action targets highlighted in every frame. The target designation device according to claim 1, wherein when the target designation function unit receives the designation of the target to be operated, it determines the location of the target to be operated, which has been tracked up to the frame at the most recent time, and transmits this to the camera as the camera control unit.

4. A program for operating a computer as an operating target designated device according to any one of claims 1 to 3.

5. A system comprising the camera and the device for specifying the target of operation according to any one of claims 1 to 3.

6. Steps to continuously acquire video captured by the camera, A step of highlighting multiple objects of action contained within each frame of the acquired video so that they can be identified. The steps include dynamically displaying the highlighted video in a timing similar to real time, The step of continuously retaining video footage for a predetermined buffer time period prior to real-time in a state where it can be retrieved, The steps of pausing the dynamically displayed video at a specified timing, A step of selecting and displaying frames of the aforementioned video for a predetermined number of seconds before, after, or both of the aforementioned timings, according to the operator, and receiving a specification of the action target to be displayed, A step of sending a control signal to the camera to track the specified target, A method for specifying the target of an operation to be performed.

Images