Automatic tracking shooting method and device for net-separated confrontation sports

Abstract

The present application discloses an automatic tracking shooting method for net confrontation sports, including: based on a target recognition algorithm, identifying human targets in the real-time shooting screen of an automatic tracking shooting device, obtaining the target frames of each human target, and obtaining a first target frame set; calculating the foot point coordinates of each target frame in the first target frame set; based on the foot point coordinates of each target frame, filtering out the target frames whose foot point coordinates are above the net from the first target frame set to obtain a second target frame set; based on the foot point coordinates of each target frame in the second target frame set, identifying the first positions of the number of target frames of the target to be tracked closest to the lower part of the real-time shooting screen; when the first position is in a preset area at the left and right edges of the real-time shooting screen, the automatic tracking shooting device rotates a preset angle in the corresponding direction. This method can effectively track and shoot the athletes on the concerned side while shooting the complete game screen.

Description

Technical Field

[0001] Embodiments of the present application relate to the technical field of intelligent sports shooting, and particularly to an automatic tracking shooting method for net-separated confrontation sports. Background Art

[0002] In the field of sports shooting, common technical solutions usually involve large-field sports with full-court running, such as basketball, football, and ice hockey. In these sports, the shooter will specifically track a certain player, and the running distance is usually large. The rotation of automatic tracking is relatively frequent and the angle is relatively large, so the technology is complex. However, in net-separated confrontation sports, such as badminton, volleyball, tennis, or the recently emerging pickleball, etc., since the movement area of the players is relatively limited, and the shooter usually only needs to shoot the players or teams on one side. Therefore, in the current prior art, single-point fixed-angle shooting or multiple camera positions are used to shoot badminton games, or face recognition is used to track and shoot specified players. CN112354166A discloses a badminton sports capture system and a capture method, which is to control the pan-tilt head by analyzing the tracking signal of the face to capture athletes. But this method must shoot the players from the front or the side front. The characteristic of net-separated sports is the head-on movement of both athletes. Therefore, if shooting from the front, the camera must be installed on the other side of the court and requires sufficient height; if shooting from the side front, the movement pictures of the opponents cannot be shot at all, lacking the sense of reality of competitive games. Therefore, a technical solution that can be easily set up, can shoot the complete game pictures, and can effectively track and shoot the athletes on the concerned side is needed. Summary of the Invention

[0003] In view of this, the present application provides an automatic tracking shooting method for net-separated confrontation sports. The shooting device can be installed on one side of the target to be tracked, so as to track and shoot the movement of the target to be tracked while being able to shoot the entire game court.

[0004] In the first aspect of the present application, an automatic tracking shooting method for net-separated confrontation sports is provided. This method is executed in an automatic tracking shooting device, and the automatic tracking shooting device is installed behind the court on the side where the target to be tracked is located. The method includes:

[0005] Based on the target recognition algorithm, identify the human targets in the real-time shooting picture of the automatic tracking shooting device, obtain the target box of each human target, and obtain the first target box set;

[0006] Calculate the foot point coordinates of each target box in the first target box set;

[0007] Based on the foot point coordinates of each target box, filter out the target boxes whose foot point coordinates are above the net from the first target box set to obtain the second target box set;

[0008] Based on the foot point coordinates of each target frame in the second target frame set, identifying the first positions of the target frames of the number of targets to be tracked closest to the bottom of the real-time shooting picture;

[0009] The first position is used as the tracking center position. When the tracking center position is located in the preset area on the left and right edges of the real-time shooting picture, the automatic tracking shooting device rotates in the corresponding direction by a preset angle.

[0010] According to an embodiment of the present application, the net confrontation sport is a single-player confrontation mode, the preset number is 1, and the first position is the foot point coordinates of the target frame of the target to be tracked.

[0011] According to an embodiment of the present application, the net confrontation sport is a team confrontation mode, the preset number is the number of team members, and the first position is the average value of the foot point coordinates of the target frames of the preset number of targets closest to the bottom of the screen. Preferably, when the number of all target frames in the second target frame set is less than the number of team members, the first position is the average value of the foot point coordinates of all target frames.

[0012] According to an embodiment of the present application, when calculating the foot point coordinates of each target frame in the first target frame set, if the target frame only displays the upper half, the foot point coordinates of the target frame are predicted by the average value of the aspect ratios of other target frames.

[0013] In a second aspect of the present application, another automatic tracking shooting method for mesh-resistance motion is provided. The method is performed in an automatic tracking shooting device, which is installed behind a field on one side where the target to be tracked is located and is suitable for horizontal rotation motion, and the method includes:

[0014] Based on the target recognition algorithm, human targets in the real-time shooting picture of the automatic tracking shooting device are identified, and a target frame of each human target is obtained to obtain a first target frame set;

[0015] Calculate the foot point coordinates of each target frame in the first target frame set;

[0016] Based on the foot point coordinates of each target frame, the target frames whose foot point coordinates are located above the net are filtered out from the first target frame set to obtain a second target frame set;

[0017] Calculating the area of ​​each target frame in the second target frame set, and identifying the second positions of the target frames of the largest number of targets to be tracked in the real-time shooting picture;

[0018] The second position is used as the tracking center position. When the tracking center position is located in the preset area on the left and right edges of the real-time shooting picture, the automatic tracking shooting device rotates in the corresponding direction by a preset angle.

[0019] According to an embodiment of the present application, the net-separated confrontation sport is a single-person confrontation mode, the preset quantity is 1, and the second position is the foot point coordinates of the target box of the target to be tracked.

[0020] According to an embodiment of the present application, the net-separated confrontation sport is a team confrontation mode, the preset quantity is the number of team members, and the second position is the average value of the foot point coordinates of the target boxes of the preset quantity of targets with the largest area. Preferably, when the total number of target boxes in the second target box set is less than the number of team members, the second position is the average value of the foot point coordinates of all target boxes.

[0021] According to an embodiment of the present application, when calculating the foot point coordinates of each target box in the first target box set, if the target box only shows the upper half, the foot point coordinates of the target box are predicted by the average value of the aspect ratios of the widths and heights of other target boxes.

[0022] According to an embodiment of the present application, when calculating the area of each target box in the second target box set, if the target box only shows the upper half, the area of the target box is predicted by the average value of the aspect ratios of the widths and heights of other target boxes.

[0023] In the third aspect of the present application, an automatic tracking shooting device is provided, including a shooting module, an analysis module, and a rotation module. The shooting module is physically connected to the rotation module. The rotation module is adapted to rotate horizontally. The shooting module is adapted to continuously obtain real-time shooting images and send the real-time shooting images to the analysis module. The analysis module is adapted to execute the method of the first aspect or the second aspect of the present application and send a rotation instruction to the rotation module. The rotation module is adapted to change the angle of the shooting module according to the rotation instruction. Preferably, the automatic tracking shooting device is installed directly behind the side of the field where the target to be tracked is located. When rotating, the maximum rotation angle of the rotation module is limited to the difference between the arctangent of the quotient of half of the field width divided by the distance between the automatic tracking shooting device and the bottom line of the side of the field where the target to be tracked is located, and half of the field of view angle of the automatic tracking device.

[0024] In the fourth aspect of the present application, an automatic tracking shooting system is provided, including:

[0025] An intelligent terminal, adapted to continuously obtain real-time shooting images, execute the method of the first aspect or the second aspect of the present application, and send a rotation instruction to the intelligent cloud platform;

[0026] An intelligent cloud platform, adapted to change the angle of the intelligent terminal according to the rotation instruction.

[0027] In the fifth aspect of the present application, an electronic device is provided, including a memory and a processor. A computer program is stored on the memory. When the processor executes the computer program, the method of the first aspect or the second aspect of the present application is implemented.

[0028] In a sixth aspect of the present application, there is provided a computer-readable storage medium having stored thereon a computer program, which when executed by a processor, implements the method according to the first aspect or the second aspect of the present application.

[0029] The automatic tracking and shooting method for net confrontation sports provided by the embodiments of the present application identifies human targets in the real-time captured image through a target recognition algorithm, obtains target frames and calculates the coordinates of the foot points, filters the target frames above the net based on the coordinates of the foot points, and identifies the positions of several target frames closest to the camera in the image based on the target frame parameters in the filtered set of target frames, and realizes the automatic tracking of the targets based on the change of the positions.

[0030] It should be understood that the content described in the Summary of the Invention section is not intended to limit the key or important features of the embodiments of the present application, nor to limit the scope of the present application. Other features of the present application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In conjunction with the accompanying drawings and with reference to the following detailed description, the above and other features, advantages and aspects of the embodiments of the present application will become more apparent. In the drawings, the same or similar reference numerals denote the same or similar elements, where:

[0032] Figure 1 is a flowchart of an automatic tracking and shooting method for net confrontation sports according to an embodiment of the present application;

[0033] Figure 2 is a schematic diagram of the recognition result of a target recognition algorithm according to an embodiment of the present application;

[0034] Figure 3 is a flowchart of the calculation of the tracking center position according to an embodiment of the present application;

[0035] Figure 4 is a block diagram of an automatic tracking and shooting device 400 according to an embodiment of the present application;

[0036] Figure 5 is a schematic diagram of the calculation of the rotation angle of the automatic tracking and shooting device 400 according to an embodiment of the present application;

[0037] Figure 6 is a schematic diagram of the structure of a terminal device or a server suitable for implementing the embodiments of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0038] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the following will clearly and completely describe the technical solutions in the embodiments of this application with reference to the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are some, but not all, of the embodiments of this application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in this application without creative efforts shall fall within the protection scope of this application.

[0039] In addition, the term "and / or" in this document is merely a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B may represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in this document generally represents an "or" relationship between the associated objects before and after.

[0040] Secondly, in the embodiments in this document, the coordinate system is established in a common manner in the field of computer vision, that is, the origin of coordinates is at the upper left corner of the screen, the horizontal direction is the x-axis, and the vertical direction is the y-axis. Those of ordinary skill in the art should be aware that other similar embodiments obtained by other coordinate system establishment methods will have opposite embodiments in the description of specific direction changes and numerical increases and decreases. These embodiments can be obtained without creative efforts and all fall within the protection scope of this application.

[0041] Figure 1 For the automatic tracking shooting method of net-separated confrontation sports according to the embodiments of this application, this method is executed in the automatic tracking shooting device 400, and the automatic tracking shooting device 400 is installed behind the venue on the side where the target to be tracked is located. The sports scenario targeted by this application is net-separated confrontation sports, such as badminton, volleyball, tennis, pickleball, etc. The venue for net-separated confrontation sports is a rectangular venue with the line where the net is located as the axis of symmetry, and both sides of the game occupy one side of the venue. As described in the background art, the tracking shooting in the prior art usually uses the face recognition method for tracking. Therefore, the device must be installed at a position where the face of the target to be tracked can be photographed. In this application, the automatic tracking shooting device 400 is installed behind the venue on the side where the target to be tracked is located, which can not only reduce the installation height but also photograph the entire venue at the same time. At the same time, preferably, the automatic tracking shooting device 400 is also suitable for vertical rotation movement and roll movement to achieve a better tracking effect on the target. In this application, this method includes:

[0042] S101: Based on the target recognition algorithm, identify the human targets in the real-time shooting screen of the automatic tracking shooting device 400, obtain the target frame of each human target, and obtain the first target frame set.

[0043] Among them, the target recognition algorithm is used to identify and locate the position information of the human body in the image. In this application, the specific selection of the target recognition algorithm is not limited: the YOLOv8 (You Only Look Once version 8) model can be used, or other recognition algorithms such as CNN (Convolutional Neural Network) and ViT (Vision Transformer) can also be used.

[0044] In S101, the target boxes of all human body targets in the real-time captured image are recognized to obtain the first target box set. In a possible implementation, the target boxes recognized by the target recognition algorithm are represented by four parameters (x, y, w, h), where x and y respectively represent the horizontal and vertical coordinates of the center point of the target box; w represents the width of the target box, and h represents the height of the target box.

[0045] S102: Calculate the foot point coordinates of each target box in the first target box set.

[0046] Among them, the foot point of the target box refers to the position of the foot of the target in the target box. Figure 2 It is a schematic diagram of the recognition result of a target recognition algorithm. As Figure 2 shown, in a possible implementation, a target box 202 is recognized in the real-time captured image 201, and four parameters of the target box 202 are given: the width is w1, the height is h1, and the coordinates of the center point 203 are (x1, y 1） . The midpoint 204 of the bottom edge of the target box is approximately used as the foot point, that is, the foot point coordinates are (x1, y1 + h1 / 2); in another possible implementation, the error value σ of the target box can be introduced. The error value is the mean value statistically calculated from multiple frames of stationary targets, generally 5% of the height of the target box. Then, the point 205 at the position of σ height above the midpoint 204 of the bottom edge of the target box is used as the foot point, that is, the foot point coordinates are (x1, y1 + h1 / 2 - σ).

[0047] In Figure 2 , only the upper half of the second target box 206 appears in the real-time captured image 201. In a possible implementation, by calculating the average value of the width-to-height ratios of all other complete target boxes, the width-to-height ratio of the second target box 206 is predicted, so as to predict the foot point position of the second target box 206. In an example as Figure 2 shown, the width-to-height ratios of the four complete target boxes are w1 / h1, w2 / h2, w3 / h3, w4 / h4, and their geometric mean is ; then the predicted width-to-height ratio of the second target box 206 is . If the center point coordinates of the second target box 206 are shown as (x2, y 2） in the real-time captured image 201, then the predicted actual foot point position of the second target box 206 is 。

[0048] S103: Filter out the target bounding boxes whose foot point coordinates are above the net from the first target bounding box set based on the foot point coordinates of each of the target bounding boxes, to obtain a second target bounding box set;

[0049] Among them, in a possible implementation, accept the dots or lines drawn by the user on the shooting screen, record the position of the net, and exclude all target bounding boxes whose coordinates fall above the net line. Specifically, the specific implementation manner for determining the coordinates falling outside the net line can adopt the quadratic function substitution method. Let the equation of the net line be ax + by + c = 0, then set the function f(x, y) = ax + by, substitute the foot point coordinates of each of the target bounding boxes into f(x, y), if the function value is less than 0, then determine that the foot point coordinates fall above the line.

[0050] In another possible implementation, when installing the automatic tracking shooting device 400, prompt and monitor the user to adjust the shooting angle of the device until the position of the net in the picture is placed at a preset position on the screen; after starting shooting, filter out the target bounding boxes whose foot point coordinates are above the preset position from the first target bounding box set, to obtain a second target bounding box set. In a specific implementation manner, the preset position can be located at the central horizontal line of the screen.

[0051] After step S103, the present application calculates a preset number of targets closest to the shooting device through an algorithm and tracks them.

[0052] In a possible implementation, determine whether the target in the target bounding box is closer to the shooting device by judging the position of the foot point coordinates of the target bounding box.

[0053] S1041: Identify the first positions of a preset number of target bounding boxes closest to the lower part of the real-time shooting picture based on the foot point coordinates of each of the target bounding boxes in the second target bounding box set, where the preset number is the number of targets to be tracked.

[0054] Among them, the larger the ordinate of the foot point of the target bounding box, the more it is determined that the target bounding box is closer to the lower part of the picture; according to the relationship between the shooting device and the shooting target in the shooting picture, the closer the target bounding box is to the lower part of the picture, the closer the target in the target bounding box is to the shooting device in reality.

[0055] S1051: Use the first position as the tracking center position.

[0056] In another possible implementation, determine whether the target in the target bounding box is closer to the screen by judging the area size of the target bounding box.

[0057] S1042: Calculate the area of each target box in the second target box set, and identify the second positions of a preset number of target boxes with the largest areas in the real-time captured image. The preset number is the number of targets to be tracked;

[0058] Among them, the area of a target box is the product of the width (w) and height (h) of the target box. According to the perspective principle, the larger the area of a target box, the closer the target in the target box is to the shooting device in reality.

[0059] S1052: Use the second position as the tracking center position.

[0060] After determining the tracking center position, the shooting angle of the automatic tracking shooting device 400 is adjusted in a timely manner by real-time tracking and judgment of the tracking center position.

[0061] S106: When the tracking center position is within a preset area at the left or right edge of the real-time captured image, the automatic tracking shooting device 400 rotates by a preset angle in the corresponding direction.

[0062] When the tracking center position is at the left or right edge of the real-time captured image, it means that the target to be tracked has left the center position of the screen and moved to the edge of the image. At this time, the automatic tracking shooting device 400 will rotate left or right by a preset angle accordingly. Specifically, in a possible implementation, when the tracking center position is in the left 1 / 4 area of the real-time captured image, control the automatic tracking shooting device 400 to rotate to the left, and the rotation angle is set to 1 / 4 of the viewing angle of the automatic tracking shooting device 400; when the tracking center position is in the right 1 / 4 area of the real-time captured image, control the automatic tracking shooting device 400 to rotate to the right, and the rotation angle is set to 1 / 4 of the viewing angle of the automatic tracking shooting device 400. For example, if the viewing angle of the iPhone camera is about 60°, then when it is detected that the tracking center position is in the left 1 / 4 area of the real-time captured image, control the automatic tracking shooting device 400 to rotate 15° to the left.

[0063] Figure 3 It is a flowchart for calculating the coordinates of the tracking center position according to an embodiment of the present application. As Figure 3 shown, the net confrontation sports can be classified according to the number of confrontants into two types: single-person confrontation mode and team confrontation mode. The single-person confrontation mode includes, but is not limited to, singles matches of badminton, tennis, and pickleball; the team confrontation mode includes, but is not limited to, doubles matches of badminton, tennis, and pickleball, and multi-person confrontation matches such as volleyball and sepak takraw.

[0064] In the single-person confrontation mode, there is only 1 target to be tracked. In the second target box set filtered by step S103:

[0065] If there are more than one target, it indicates that there are unfiltered opponent players or off-court interference targets among them. Therefore, detect one target closest to the automatic tracking shooting device 400, and use the foot point coordinates thereof as the coordinates of the tracking center position. Among them, detect one target closest to the automatic tracking shooting device 400 by the method described in step S1041 or S1042;

[0066] If there is only one target in the second target box set, it can be considered that this target is the target to be tracked, and directly use the foot point coordinates of the target box where this target is located as the coordinates of the tracking center position;

[0067] If there is no target in the second target box set, it indicates that a target loss has occurred during the tracking process. Considering that players tend to return to the center of the court during the game, therefore, at this time, restore the shooting angle of the automatic tracking shooting device 400 to make it return to the middle position, that is, return to the center.

[0068] In the multi-player confrontation mode, there are multiple targets to be tracked. For example, in various doubles matches, two targets need to be tracked simultaneously; in volleyball matches, five targets need to be tracked simultaneously. Considering that players usually run and gather around the ball during the game, therefore, select the average value of the foot point coordinates of the targets to be tracked as the coordinates of the tracking center position. Specifically, in the second target box set filtered through step S103:

[0069] If the number of target boxes in the second target box set exceeds the number of players in the team N, it indicates that there are unfiltered opponent players or off-court interference targets among them. Therefore, detect N targets closest to the automatic tracking shooting device 400, and use the average value of their foot point coordinates as the coordinates of the tracking center position. Among them, detect N targets closest to the automatic tracking shooting device 400 by the method described in step S1041 or S1042;

[0070] If there are only N targets in the second target box set, or less than N targets but the number is not zero, it can be considered that all these targets are valid targets to be tracked, and directly use the average value of the foot point coordinates of the target boxes where these targets are located as the coordinates of the tracking center position;

[0071] If there is no target in the second target box set, it indicates that a target loss has occurred during the tracking process. Considering that players tend to return to the center of the court during the game, therefore, at this time, restore the shooting angle of the automatic tracking shooting device 400 to make it return to the middle position, that is, return to the center.

[0072] The method of the embodiment of the present application is described above, and the device of the embodiment of the present application is provided below.

[0073] It can be understood that, in order to implement the functions in the foregoing method embodiments, the device provided in the embodiments of the present application includes corresponding hardware structures, software units, or combinations of hardware structures and software structures for executing various functions. Those skilled in the art should easily realize that, for the units and algorithm steps of each example described in combination with the embodiments disclosed herein, the embodiments of the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a certain function is executed in the form of hardware or computer software driving the hardware depends on the specific application and design constraints of the technical solution. Professional technicians can use different device implementation methods in different usage scenarios to implement the foregoing method embodiments, and different implementation methods of the device should not be considered to exceed the scope of the embodiments of the present application.

[0074] The embodiments of the present application can perform a functional unit division on the device. For example, each functional unit can be corresponding to each function, or two or more functions can be integrated into one functional unit. The above integrated module can be implemented in the form of hardware or in the form of a software functional unit. It should be noted that the division of units in the embodiments of the present application is illustrative, only a logical function division, and there can be other division methods in actual implementation.

[0075] Figure 4 It is a block diagram of an automatic tracking shooting device 400 according to an embodiment of the present application. As Figure 4 shown, the automatic tracking shooting device 400 includes a shooting module 401, an analysis module 402, and a rotation module 403. The automatic tracking shooting device 400 is used to implement the foregoing automatic shooting tracking method.

[0076] Optionally, the automatic tracking shooting device 400 can be an independent device, or a component included in an independent device, or a combination of multiple different independent devices. In a possible implementation manner, the shooting module 401 is implemented as an independent intelligent terminal or camera, the analysis module 402 is implemented as another independent intelligent terminal or intelligent hardware, and the rotation module 403 is implemented as a pan-tilt or rotatable bracket. In another possible implementation manner, the shooting module 401 is implemented as a camera module in an intelligent terminal, the analysis module 402 is implemented as a computing module in the same intelligent terminal, and the rotation module 403 is implemented as an intelligent pan-tilt or rotatable bracket. In yet another possible implementation manner, the shooting module 401 is implemented as a camera module in an integrated intelligent imaging device, the analysis module 402 is implemented as a computing module in the same integrated intelligent imaging device, and the rotation module 403 is implemented as a motion mechanism in the same integrated intelligent imaging device.

[0077] Among them, the shooting module 401 is physically connected to the rotation module 403. The shooting module 401 is adapted to continuously obtain real-time shooting images and send the real-time shooting images to the analysis module 402. Optionally, the shooting module 401 may not have an active information sending function, but the analysis module 402 actively obtains the real-time shooting images from the shooting module 402. The analysis module 402 is adapted to execute the method in the embodiments of the present application based on the real-time shooting images Figure 1 or Figure 2 to perform real-time calculation and judgment on the tracking center position, and send a rotation instruction to the rotation module 403 according to the judgment condition. The rotation module 403 is adapted to rotate horizontally, that is, rotate around the vertical axis (z-axis). The rotation module 403 is adapted to change the angle of the shooting module 401 according to the rotation instruction.

[0078] As described in the method of the embodiment Figure 1 previously, the automatic tracking shooting device 400 is adapted to be installed behind the venue on the side where the target to be tracked is located. Preferably, the automatic tracking shooting device 400 is installed directly behind the venue on the side where the target to be tracked is located, that is, on the extension line of the center line of the venue on the side where the target to be tracked is located.

[0079] In a possible implementation, the rotation module limits the maximum rotation angle when rotating. During a game, there are occasionally scenarios where players leave the field to pick up the ball, change the ball, take a break, or receive coaching from the sidelines, etc., and at this time, it is not necessary to continue tracking the players who have left the field. Therefore, the embodiments of the present application limit the maximum rotation angle to prevent the automatic tracking shooting device 400 from rotating at too large an angle, so as to prevent image jitter or dizziness, and at the same time reduce the acquisition of irrelevant images.

[0080] Figure 5 is a schematic diagram of the rotation angle calculation of the automatic tracking shooting device 400 according to the embodiment of the present application. In a possible implementation, the rectangle ABCD is the entire venue for net confrontation sports, and the lower half is the half where the target to be tracked is located. The automatic tracking shooting device 400 is installed at point O, and point O is on the extension line of the center line of the venue backward and the distance to the bottom line is h. In the initial state, the field of view of the automatic tracking shooting device 400 is within the range of ∠EOF, and ∠EOF is the field of view angle of the automatic tracking shooting device 400. The field of view angles of different camera devices or lenses are different, which can be directly obtained through the interface provided by the camera device or obtained by looking up the table by reading the model of the camera device.

[0081] In a possible implementation, the maximum rotation angle of the automatic tracking shooting device 400 is set at the angle of the line segment OC, that is, the rotation angle is ∠EOC. At this time, the entire right side of the venue is within the camera's field of view, and there is no need to continue moving to the right. Similarly, the processing method for the left side of the venue is completely symmetrical and will not be elaborated here. Let the width of the venue be w, the distance between the automatic tracking shooting device 400 and the bottom line be h, and the field of view angle ∠EOF of the automatic tracking shooting device 400 be α. Through simple calculation in plane geometry, it can be obtained that ∠EOC = arctan(w / 2h) - α / 2, that is, the maximum rotation angle is the arctangent of the quotient of half of the venue width divided by the distance between the automatic tracking shooting device 400 and the bottom line of the side of the target to be tracked, minus half of the field of view angle of the automatic tracking device.

[0082] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working process of the described module can refer to the corresponding process in the foregoing method embodiment and will not be elaborated here.

[0083] Figure 6 The structural schematic diagram of a terminal device or a server suitable for implementing the embodiments of the present application is shown.

[0084] As Figure 6 shown, the terminal device or the server includes a central processing unit (CPU) 601, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 602 or the program loaded from the storage section 608 into the random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the terminal device or the server are also stored. The CPU 601, the ROM 602, and the RAM 603 are connected to each other through a bus 604. The input / output (I / O) interface 605 is also connected to the bus 604.

[0085] The following components are connected to the I / O interface 605: an input section 606 including a keyboard, a mouse, etc.; an output section 607 including, for example, a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a LAN card, a modem, etc. The communication section 609 performs communication processing via a network such as the Internet. The drive 610 is also connected to the I / O interface 605 as required. A removable medium 611, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 610 as required, so that the computer program read from it can be installed into the storage section 608 as required.

[0086] In particular, according to an embodiment of the present application, the above method flow steps can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a machine-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 609, and / or installed from the removable medium 611. When the computer program is executed by the central processing unit (CPU) 601, the above functions defined in the system of the present application are executed.

[0087] It should be noted that the computer-readable medium shown in the present application can be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of the computer-readable storage medium can include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, the computer-readable storage medium can be any tangible medium that contains or stores a program, and the program can be used by or in combination with an instruction execution system, apparatus, or device. And in the present application, the computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, in which the computer-readable program code is carried. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer-readable signal medium can also be any computer-readable medium other than the computer-readable storage medium, and the computer-readable medium can send, propagate, or transmit a program for use by or in combination with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted by any suitable medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0088] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagram may represent a module, a segment of a program, or a part of code, and the foregoing module, segment of a program, or part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in an order different from that marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and the combination of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system that performs the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0089] The units or modules described in the embodiments of the present application can be implemented in software or in hardware. The described units or modules can also be provided in a processor. Among them, the names of these units or modules do not constitute a limitation to the units or modules themselves in some cases.

[0090] On the other hand, the present application also provides a computer-readable storage medium, which can be included in the electronic device described in the above embodiments; or can exist separately without being assembled into the electronic device. The above computer-readable storage medium stores one or more programs, and when the foregoing programs are executed by one or more processors, they implement the methods described in the present application.

[0091] The above description is only the preferred embodiments of the present application and the explanation of the applied technical principles. Those skilled in the art should understand that the scope of the application involved in the present application is not limited to the technical solutions formed by the specific combination of the above technical features, and should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the foregoing application concept. For example, the technical solutions formed by mutually replacing the above features with other technical features having similar functions (but not limited to) described in the present application.

Claims

1. An automatic tracking shooting method for net confrontation sports, which is executed in an automatic tracking shooting device. The automatic tracking shooting device is installed behind the field on the side where the target to be tracked is located, and is characterized in that, The method includes: Based on a target recognition algorithm, identifying human targets in the real-time captured image of the automatic tracking shooting device, obtaining the target bounding box for each human target, and obtaining a first set of target bounding boxes; Calculating the foot point coordinates of each target bounding box in the first set of target bounding boxes; Based on the foot point coordinates of each target bounding box, filtering out the target bounding boxes whose foot point coordinates are above the net from the first set of target bounding boxes, and obtaining a second set of target bounding boxes; Based on the foot point coordinates of each target bounding box in the second set of target bounding boxes, identifying the first positions of a preset number of target bounding boxes closest to the lower part of the real-time captured image, where the preset number is the number of targets to be tracked; wherein, when the preset number is 1, the first position is the foot point coordinates of the target bounding box of the target to be tracked; when the preset number is greater than 1, the first position is the average value of the foot point coordinates of the preset number of target bounding boxes closest to the lower part of the image; Taking the first position as the tracking center position; when the tracking center position is in a preset area at the left and right edges of the real-time captured image, the automatic tracking shooting device rotates by a preset angle in the corresponding direction.

2. The method according to claim 1, characterized in that, When the net confrontation movement is in a team confrontation mode, the preset number is the number of team members. When the total number of all target bounding boxes in the second set of target bounding boxes is less than the number of team members, the first position is the average value of the foot point coordinates of all target bounding boxes.

3. The method according to claim 1, wherein Calculating the foot point coordinates of each target bounding box in the first set of target bounding boxes includes: When only the upper half of the target bounding box is displayed, predicting the foot point coordinates of the target bounding box based on the average value of the aspect ratios of other target bounding boxes.

4. An automatic tracking shooting device, characterized in that, It includes a shooting module, an analysis module, and a rotation module. The shooting module is physically connected to the rotation module. The rotation module is suitable for horizontal rotation. The shooting module is suitable for continuously obtaining a real-time captured image and sending the real-time captured image to the analysis module; the analysis module is suitable for executing the method according to any one of claims 1-3, and sending a rotation instruction to the rotation module: the rotation module is suitable for changing the angle of the shooting module according to the rotation instruction.

5. The automatic tracking shooting device according to claim 4, characterized in that, The automatic tracking shooting device is installed directly behind the side of the field where the target to be tracked is located. When the rotation module rotates horizontally, the maximum rotation angle is limited to the difference between the arctangent of the quotient of half of the field width divided by the distance between the automatic tracking shooting device and the bottom line of the side of the field where the target to be tracked is located, and half of the field of view angle of the automatic tracking shooting device.

6. An automatic tracking and shooting system, characterized in that, It includes: An intelligent terminal, suitable for continuously obtaining a real-time captured image, executing the method according to any one of claims 1-3, and sending a rotation instruction to the intelligent cloud platform; An intelligent cloud platform, suitable for changing the angle of the intelligent terminal according to the rotation instruction.

7. An electronic device, comprising a memory and a processor, wherein a computer program is stored on the memory, characterized in that When the processor executes the computer program, it implements the method according to any one of claims 1-3.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the method according to any one of claims 1-3.

Images