Ball game video analysis method and system, electronic equipment and storage medium

Abstract

The invention discloses a ball game video analysis method and system, electronic equipment and a storage medium, and relates to the technical field of ball game video analysis, and the method comprises the steps: obtaining a target ball game video, each video frame in the target ball game video containing a timestamp; each video frame in the target ball game video is identified, the position of each human body key point of each player at each moment and the position of the ball at each moment are obtained, and the timestamps correspond to the moments in a one-to-one mode. By analyzing the target ball game video, the position of each human body key point of each player and the position of the ball can be accurately and efficiently captured in real time, dependence on manual operation is reduced, instant feedback can be provided for coaches and players, and data support is provided for optimizing training strategies and competition strategies.

Description

Background Art

[0002] In today's professional sports, there is a growing demand for high-precision, real-time sports performance analysis. This demand stems from the continuous pursuit of optimizing player performance, including accurate analysis of technical details, instant adjustment of sports strategies, and effective management of injury prevention. Traditional analysis methods often rely on manual observation and post-data processing, which is not only time-consuming and labor-intensive, but also difficult to achieve the required accuracy and real-time performance. Summary of the invention

[0003] The technical problem to be solved by the present invention is to address the deficiencies of the prior art and specifically provide a ball sports video analysis method, system, electronic device and storage medium, which are as follows:

[0004] 1) In the first aspect, the present invention provides a ball sports video analysis method, and the specific technical solution is as follows:

[0005] Acquire a target ball sports video, wherein each video frame in the target ball sports video contains a timestamp;

[0006] Each video frame in the target ball sports video is identified to obtain the position of each key point of each human body of each player at each moment and the position of the ball at each moment, wherein the timestamp corresponds to the moment one by one.

[0007] The beneficial effects of the ball sports video analysis method provided by the present invention are as follows:

[0008] By analyzing target ball sports videos, it is possible to accurately and efficiently capture the positions of each key point of each player's body and the position of the ball in real time, reducing dependence on manual operations, providing instant feedback to coaches and players, and providing data support for optimizing training strategies and game strategies.

[0009] Based on the above scheme, the ball sports video analysis method of the present invention can also be improved as follows.

[0010] Furthermore, it also includes:

[0011] When the ball hitting detection is triggered, a ball position time sequence within a preset time period is determined based on the target ball sports video or the position of the ball at each moment, the preset time period including the moment when the ball hitting detection is triggered;

[0012] The ball position time series is fitted, and the trough position in the fitted curve is determined as the hitting position.

[0013] The beneficial effect of adopting the above further solution is that the hitting position can be accurately analyzed, providing more data support for optimizing training strategies and game strategies.

[0014] Furthermore, it also includes:

[0015] The release speed and release angle of the ball are calculated based on the hitting position and the position of the ball at the next moment after the hitting position.

[0016] The beneficial effect of adopting the above further solution is that the player can analyze the shooting speed and shooting angle of the ball every time he hits the ball, providing more data support for optimizing training strategies and game strategies.

[0017] Further, the process of determining the ball position time series according to the target ball sports video includes:

[0018] From the target ball sports video, multiple video frames within a preset time period including the moment of triggering the ball hitting detection are obtained and identified to obtain a ball position time series.

[0019] The beneficial effect of adopting the above further solution is that the ball position time series can be quickly acquired, thereby improving the real-time nature of the analysis.

[0020] Further, the process of determining the ball position time series according to the ball position at each moment includes:

[0021] From the position of the ball at each moment, the positions of the ball at multiple moments within a preset time period including the moment of triggering the ball hitting detection are obtained to form a ball position time series.

[0022] The beneficial effect of adopting the above further solution is that the ball position time series can be quickly acquired, thereby improving the real-time nature of the analysis.

[0023] Further, the process of obtaining the target ball sports video includes:

[0024] Shoot the initial ball game video with a camera or camcorder;

[0025] The initial ball sports video is preprocessed to obtain the target ball sports video.

[0026] Furthermore, the initial ball sports video is: a badminton match video, a badminton training video, a table tennis match video, a table tennis training video, a tennis match video or a tennis training video.

[0027] The beneficial effect of adopting the above further solution is that the present invention is applicable to sports videos of various ball games and has strong applicability.

[0028] 2) In the second aspect, the present invention also provides a ball sports video analysis system, and the specific technical solution is as follows:

[0029] It includes a ball sports video acquisition module and a recognition module;

[0030] The ball sports video acquisition module is used to: acquire a target ball sports video, wherein each video frame in the target ball sports video contains a timestamp;

[0031] The recognition module is used to: recognize each video frame in the target ball sports video, obtain the position of each key point of each human body of each player at each moment and the position of the ball at each moment, wherein the timestamp corresponds to the moment one by one.

[0032] Based on the above solution, the ball sports video analysis system of the present invention can also be improved as follows.

[0033] Furthermore, it also includes a ball position time series acquisition module and a ball hitting position determination module;

[0034] The ball position time series acquisition module is used to: when the ball hitting detection is triggered, determine the ball position time series within a preset time period according to the target ball sports video or the position of the ball at each moment, the preset time period including the moment when the ball hitting detection is triggered;

[0035] The hitting position determination module is used to fit the ball position time series and determine the trough position in the fitted curve as the hitting position.

[0036] Furthermore, it also includes a speed angle calculation module, which is used to calculate the ball's release speed and release angle according to the hitting position and the position of the ball at the next moment after the hitting position.

[0037] Furthermore, the ball position time series acquisition module is specifically used for:

[0038] From the target ball sports video, multiple video frames within a preset time period including the moment of triggering the ball hitting detection are obtained and identified to obtain a ball position time series.

[0039] Furthermore, the ball position time series acquisition module is also specifically used for:

[0040] From the position of the ball at each moment, the positions of the ball at multiple moments within a preset time period including the moment of triggering the ball hitting detection are obtained to form a ball position time series.

[0041] Furthermore, the ball sports video acquisition module is specifically used for:

[0042] Shoot the initial ball game video with a camera or camcorder;

[0043] The initial ball sports video is preprocessed to obtain the target ball sports video.

[0044] Furthermore, the initial ball sports video is: a badminton match video, a badminton training video, a table tennis match video, a table tennis training video, a tennis match video or a tennis training video.

[0045] 3) In a third aspect, the present invention further provides an electronic device, comprising a processor, the processor being coupled to a memory, the memory storing at least one computer program, the at least one computer program being loaded and executed by the processor, so that the electronic device implements any one of the above-mentioned ball sports video analysis methods.

[0046] 4) In a fourth aspect, the present invention further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, any of the above-mentioned ball sports video analysis methods is implemented.

[0047] It should be noted that the beneficial effects achieved by the technical solutions of the second to fourth aspects of the present invention and the corresponding possible implementation methods can be found in the above-mentioned technical effects of the first aspect and its corresponding possible implementation methods, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments of the present invention:

[0049] Figure 1 A schematic diagram of a process of analyzing a ball sports video according to an embodiment of the present invention;

[0050] Figure 2 A schematic diagram of a court, players, and non-players in a badminton singles match video;

[0051] Figure 3 Schematic diagram of the ball's release speed and release angle;

[0052] Figure 4 A schematic diagram of the structure of a ball sports video analysis system according to an embodiment of the present invention;

[0053] Figure 5 The figure is a schematic diagram of the structure of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0054] The principles and features of the present invention are described below. The examples given are only used to explain the present invention and are not used to limit the scope of the present invention.

[0055] The technical solution of the present invention and how the technical solution of the present invention solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present invention will be described below in conjunction with the accompanying drawings.

[0056] like Figure 1 As shown, a ball sports video analysis method according to an embodiment of the present invention comprises the following steps:

[0057] S1, obtaining a target ball sports video, wherein each video frame in the target ball sports video contains a timestamp;

[0058] S2. Identify each video frame in the target ball sports video, and obtain the position of each key point of each human body of each player at each moment and the position of the ball at each moment, wherein the timestamp corresponds to the moment one by one.

[0059] By parsing each timestamp, the moment corresponding to each timestamp is obtained.

[0060] A ball sports video analysis method according to an embodiment of the present invention can accurately and efficiently capture the position of each key point of each player's body and the position of the ball in real time by analyzing the target ball sports video, reduce dependence on manual operation, provide instant feedback to coaches and players, and provide data support for optimizing training strategies and game strategies.

[0061] Optionally, in the above technical solution, it also includes:

[0062] S3, when the ball hitting detection is triggered, determining the ball position time sequence within a preset time period according to the target ball sports video or the ball position at each moment, the preset time period including the moment when the ball hitting detection is triggered;

[0063] S4. Fitting the ball position time series, and determining the trough position in the fitted curve as the hitting position.

[0064] Through S3 and S4, the hitting position can be accurately analyzed, providing more data support for optimizing training strategies and game strategies.

[0065] Optionally, in the above technical solution, it also includes:

[0066] S5. Calculate the release speed and release angle of the ball based on the hitting position and the position of the ball at the next moment after the hitting position. Players can analyze the release speed and release angle of the ball every time they hit the ball, providing more data support for optimizing training strategies and game strategies.

[0067] Optionally, in S3, the process of determining the ball position time series according to the target ball sports video includes:

[0068] S30: From the target ball sports video, a plurality of video frames within a preset time period including the moment of triggering the ball hitting detection are obtained and identified to obtain a ball position time series.

[0069] Optionally, in S3, the process of determining the ball position time series according to the ball position at each moment includes:

[0070] From the position of the ball at each moment, the positions of the ball at multiple moments within a preset time period including the moment of triggering the ball hitting detection are obtained to form a ball position time series.

[0071] Optionally, in S1, the process of acquiring the target ball sports video includes:

[0072] S10, shooting an initial ball sports video with a camera or video camera;

[0073] Among them, the camera can be an RGB camera and a high dynamic camera capable of shooting high-definition video, and the camera and video camera can be selected according to actual conditions.

[0074] S11, preprocessing the initial ball sports video to obtain a target ball sports video.

[0075] Optionally, in the above technical solution, the initial ball sports video is: a badminton match video, a badminton training video, a table tennis match video, a table tennis training video, a tennis match video or a tennis training video. The present invention is applicable to sports videos of various ball games and has strong applicability.

[0076] Among them, the badminton match video can be a badminton singles match video or a badminton match video can be a badminton doubles match video, the badminton training video can be a badminton singles match video or a badminton singles training video can be a badminton doubles training video, the table tennis match video can be a table tennis singles match video or a table tennis doubles match video, the table tennis training video can be a table tennis singles training video or a table tennis doubles training video, the tennis match video can be a tennis singles match video or a tennis doubles match video, and the tennis training video can be a tennis singles training video or a tennis doubles training video.

[0077] Taking a badminton singles training video as an example, a ball sports video analysis method of the present invention is described, which includes the following steps:

[0078] S101, placing the camera and its associated equipment (such as a bracket, etc.) at a suitable location outside the court 3, specifically:

[0079] Referring to the main perspective of the BWF match broadcast, the camera is placed directly behind one side of the court 3 and filmed from top to bottom. The direction of the lens is approximately the same as that of the court 3. The camera's filming perspective is fixed. The badminton singles training video filmed will contain the court 3, the net 4, the players and non-players 5, etc. Among them, the non-players 5 include referees, coaches and off-court spectators, etc. Among them, the number of players participating in the game is 2, respectively recorded as the first player 1 and the second player 2. The first player 1 is a player far away from the camera, and the second player 2 is a player close to the camera. Figure 2 shown.

[0080] S102. Filming badminton singles training video:

[0081] Perform data registration on the camera's external parameters, set the timestamp to be added to the video frames taken by the camera, and set the interval between each two adjacent video frames, which can be set to 1 millisecond or 2 milliseconds, etc., according to actual conditions.

[0082] When the first player 1 and the second player 2 are training on the court 3 , a high-definition badminton singles training video can be shot and saved, wherein each video frame in the badminton singles training video has a timestamp.

[0083] S103, pre-processing the badminton singles training video:

[0084] Each video frame in the badminton singles training video is subjected to distortion correction, smoothing and connected boundary area processing to obtain the target ball sports video. The smoothing is performed by the median filtering method based on the cv2.medianBlur function, and the connected boundary area processing is performed by the expansion (based on the cv2.dilate function) and erosion (based on the cv2.erode function).

[0085] S104, identifying each video frame in the target ball sports video, obtaining the position of each key point of each human body of each player at each moment and the position of the ball at each moment, the specific implementation process is as follows:

[0086] 1) Each video frame in the target ball sports video is identified by the trained person detection model to obtain the position of each human body key point of each person in each video frame, and based on the boundary line of the court 3, the position of each human body key point of people outside the court 3 is removed, that is, the position of each human body key point of each non-player 5 is removed to obtain the position of each human body key point of the first player 1 and the position of each human body key point of the second player 2 in each video frame.

[0087] Among them, the key points of the human body include: hands, neck, elbows, shoulders, waist, knees, feet, etc., which can be set according to actual conditions.

[0088] Among them, the process of obtaining a trained person detection model includes: constructing multiple person samples based on historical ball sports videos, the person samples include person images and labels (for example, labeling human images as 1 and non-human images as 0), and then training the first preset network model to obtain a trained person detection model.

[0089] Among them, the first preset network model is YOLOv10, R-CNN network or CNN (convolutional neural network), etc., and other network models can also be selected according to actual conditions.

[0090] In another embodiment, the first preset network model may be directly trained with an existing dataset including multiple pedestrian images to obtain a trained human detection model. The existing dataset including multiple pedestrian images may be the UCF-QNRF dataset released by the University of Florida or the CUHK Occlusion dataset released by the Chinese University of Hong Kong.

[0091] 2) Using the trained ball detection and tracking model, each video frame in the target ball sports video is identified to obtain the position of the ball in each video frame.

[0092] Among them, multiple ball position samples are constructed according to historical ball sports videos, and the ball position samples include ball images and labels. Specifically, the ball positions can be used as labels, and then the second preset network model is trained to obtain a trained ball detection and tracking model.

[0093] Among them, the second preset network model can be TrackNetV2, R-CNN network or CNN (convolutional neural network), DNN (deep neural network), etc., and other deep learning networks can also be selected according to actual conditions.

[0094] The position of each key point of the human body and the position of the ball can be represented by the coordinates in the preset plane coordinate system. The center point of the court 3 can be used as the origin o, and the two directions along the court 3 can be used as the directions of the x-axis and the y-axis to establish a preset plane coordinate system. Then, Represents the coordinates of different key points of the first player 1 at time t, which can be used The coordinates of different key points of the second player 2 at time t can be represented by Represents: The coordinates of the first player 1's hand at time t, expressed as It represents: the coordinates of the neck of the first player 1 at time t. Similarly, different i values ​​are set for different key points of the human body. Time t is the time corresponding to the timestamp of any video frame in the target ball sports video.

[0095] Optionally, the center point of the coordinates of all the key points of the first player 1 at time t is taken as the coordinates of the first player 1 at time t, denoted as The center point of the coordinates of all the key points of the second player 2 at time t is taken as the coordinates of the second player 2 at time t, denoted as

[0096]

[0097] S105, when the ball hitting detection is triggered, determine the ball position time sequence within a preset time period according to the target ball sports video or the ball position at each moment, the preset time period including the moment when the ball hitting detection is triggered.

[0098] When the distance between the coordinates of the ball and the coordinates of the first player 1 or the coordinates of the second player 2 is less than a first preset distance threshold, and within a preset time period, the direction of the ball determined according to the coordinates of the ball changes, the hitting detection is triggered, wherein the first preset distance threshold can be set according to actual conditions, or, when the distance between the coordinates of the ball and the coordinates of the first player 1 or the coordinates of the hand of the second player 2 is less than a second preset distance threshold, and within a preset time period, the direction of the ball determined according to the coordinates of the ball changes, the hitting detection is triggered, wherein the second preset distance threshold can be set according to actual conditions, or, the condition for triggering the hitting detection is set according to experience, and when the condition is met, the hitting detection is triggered.

[0099] The preset time period may also be set according to actual conditions. For example, the preset time period may be the entire time period of the target ball sports video, or the preset time period may be a partial time period of the target ball sports video.

[0100] The time when the ball hitting detection is triggered is recorded as T, and TT can be ′ To T+T ′ The time period between is taken as the preset time period, T ′ Indicates duration, T ′ It can be n milliseconds, where n can be set according to actual conditions. Generally speaking, n is an integer multiple of the interval between two adjacent video frames.

[0101] The process of determining the ball position time series according to the target ball sports video includes:

[0102] Get TT from target ball sports videos ′ To T+T ′ The trained ball detection and tracking model is used to identify the multiple video frames between the two frames and obtain the ball in TT ′ To T+T ′ The position at each moment in between is obtained, thus obtaining the ball position time series.

[0103] The process of determining the ball position time series according to the ball position at each moment includes:

[0104] From the position of the ball at each moment, get the ball at TT ′ To T+T ′ The position at each moment in between constitutes the ball position time series.

[0105] S106, Fitting:

[0106] The ball position time series obtained in S105 is fitted, specifically, a quadratic polynomial fitting is performed, and the trough position in the fitted curve is determined as the hitting position, thereby obtaining the actual hitting point.

[0107] It should be noted that if the preset time period can be the entire time period of the target ball sports video, or the preset time period is a partial time period in the target ball sports video, the fitted curve may include multiple trough positions, thereby obtaining multiple hitting positions, and the hitting positions can also be represented by coordinates in the preset plane coordinate system.

[0108] S107, based on any hitting position and the position of the ball at the next moment after the hitting position, specifically in combination with the above-mentioned preset plane coordinate system, the ball's release speed and release angle at the time of the hitting can be calculated, and by analogy, the ball's release speed and release angle at each hitting can be calculated, such as Figure 3 shown.

[0109] Optionally, the movement of each key point of the human body of the first player 1 is analyzed according to the position of each key point of the human body of the first player 1 at the moment of the hitting position and the next moment after the hitting position, and the movement of each key point of the human body of the second player 2 is analyzed according to the position of each key point of the human body of the second player 2 at the moment of the hitting position and the next moment after the hitting position.

[0110] Optionally, the position of each key point of the human body of each player at each moment, the position of the ball at each moment, the hitting position, the shooting speed and the shooting angle are fed back to a preset smart terminal for display, and the corresponding video clips can also be played for the convenience of coaches and players to view, helping players to improve their hitting movements, thereby increasing the badminton shooting speed and optimizing the shooting angle.

[0111] The beneficial effects of the present invention are as follows:

[0112] 1) The present invention relates to the technical field of sports performance analysis and automated video recording, and is intended to solve key technical problems existing in traditional sports analysis and recording methods. The present invention is committed to improving the accuracy and efficiency of sports data recording, and through the use of advanced vision and artificial intelligence technologies, it is possible to accurately capture and analyze the movements of players in real time. The present invention aims to automate the recording process of sports performance and reduce dependence on manual operations, thereby improving the consistency and objectivity of data collection. The present invention also solves the real-time problem of sports analysis data processing, and provides instant feedback to coaches and players by quickly processing and analyzing data, thereby optimizing training and game strategies.

[0113] 2) The present invention can be applied not only in the field of professional sports to help coaches and players analyze and improve performance, but also in school sports and amateur sports activities to provide technical support for players' training and competition. In addition, these systems can also be integrated into sports technology products, such as smart fitness equipment and sports performance analysis software, to provide scientific and accurate sports analysis services for the majority of users.

[0114] 3) The present invention brings significant performance improvements to related sports analysis and recording products by integrating advanced visual recognition and artificial intelligence technologies. First of all, the application of this technology greatly improves the accuracy and efficiency of data collection, ensuring that every detail of the player's training can be accurately captured and analyzed. This is not only crucial for the optimization of player training and game strategies, but also provides coaches with more detailed and reliable data support. Coaches can use the present invention to help players improve their hitting movements, thereby increasing the speed of badminton shots and optimizing the angle of shots.

[0115] 4) The present invention improves the user experience of the product. The automated data recording and real-time analysis functions reduce the user's reliance on professional knowledge, making it easy for even non-professionals to use, thereby broadening the market application scope of the product. In addition, through real-time feedback and analysis, users can adjust the training method in a timely manner and effectively improve the training effect, which increases the attractiveness and market competitiveness of the present invention.

[0116] In the above embodiments, although the steps are numbered S1, S2, etc., these are only specific embodiments given by the present invention. Those skilled in the art may adjust the execution order of S1, S2, etc. according to actual conditions, which is also within the protection scope of the present invention. It can be understood that in some embodiments, some or all of the above embodiments may be included.

[0117] like Figure 4 As shown, a ball sports video analysis system 200 according to an embodiment of the present invention includes a ball sports video acquisition module 201 and a recognition module 202;

[0118] The ball sports video acquisition module 201 is used to: acquire a target ball sports video, wherein each video frame in the target ball sports video contains a timestamp;

[0119] The recognition module 202 is used to recognize each video frame in the target ball sports video, and obtain the position of each key point of each human body of each player at each moment and the position of the ball at each moment, wherein the timestamp corresponds to the moment one by one.

[0120] Optionally, in the above technical solution, it further includes a ball position time series acquisition module and a ball hitting position determination module;

[0121] The ball position time series acquisition module is used to: when the ball hitting detection is triggered, determine the ball position time series within a preset time period according to the target ball sports video or the position of the ball at each moment, the preset time period including the moment when the ball hitting detection is triggered;

[0122] The hitting position determination module is used to fit the ball position time series and determine the trough position in the fitted curve as the hitting position.

[0123] Optionally, the above technical solution further includes a speed angle calculation module, which is used to calculate the ball's release speed and release angle according to the hitting position and the position of the ball at the next moment after the hitting position.

[0124] Optionally, in the above technical solution, the ball position time series acquisition module is specifically used for:

[0125] From the target ball sports video, multiple video frames within a preset time period including the moment of triggering the ball hitting detection are obtained and identified to obtain a ball position time series.

[0126] Optionally, in the above technical solution, the ball position time series acquisition module is further specifically used for:

[0127] From the position of the ball at each moment, the positions of the ball at multiple moments within a preset time period including the moment of triggering the ball hitting detection are obtained to form a ball position time series.

[0128] Optionally, in the above technical solution, the ball sports video acquisition module 201 is specifically used for:

[0129] Shoot the initial ball game video with a camera or camcorder;

[0130] The initial ball sports video is preprocessed to obtain the target ball sports video.

[0131] Optionally, in the above technical solution, the initial ball sports video is: a badminton match video, a badminton training video, a table tennis match video, a table tennis training video, a tennis match video or a tennis training video.

[0132] In another embodiment, ROS (Robot Operating System) is used to provide a system framework for node management and communication for the system of the present invention. ROS nodes are created for each functional module of the system, including input signal source, ball hitting detection node, motion analysis node and visualization node. Specifically:

[0133] 1) The input signal source uses an RGB camera and a high dynamic camera to synchronously collect badminton training movements in real time and capture real-time motion. The data obtained by the RGB camera node is the same as the observation results of the human eye. The high dynamic camera node can accurately obtain the motion information of athletes and badminton by collecting dynamic images at a high frequency.

[0134] 2) The analysis process mainly includes a hitting detection node and a motion analysis node. The hitting detection node is used to confirm the actual recording start and end time of the video, and the motion analysis is used to analyze the motion image to parse the motion training data.

[0135] 3) Connect the display screen through the visualization node to provide real-time feedback of RGB sports video and training action analysis results to athletes and coaches.

[0136] It should be noted that the beneficial effects of the ball sports video analysis system 200 provided in the above embodiment are the same as the beneficial effects of the ball sports video analysis method described above, which will not be described in detail here. In addition, when the system provided in the above embodiment realizes its functions, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the system can be divided into different functional modules according to actual conditions to complete all or part of the functions described above. In addition, the system and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be described in detail here.

[0137] Among them, the ball sports video analysis system of the present invention can be a computer program (including program code) running in a computer device. For example, the ball sports video analysis system of the present invention is an application software that can be used to execute the corresponding steps in the ball sports video analysis method of the present invention.

[0138] In some embodiments, the ball sports video analysis system of the present invention can be implemented by a combination of software and hardware. As an example, the ball sports video analysis system of the present invention can be a processor in the form of a hardware decoding processor, which is programmed to execute the ball sports video analysis method of the present invention. For example, the processor in the form of a hardware decoding processor can adopt one or more application specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field programmable gate arrays (FPGAs) or other electronic components.

[0139] The modules involved in the embodiments of the present invention may be implemented in software or hardware. The name of a module does not limit the module itself in some cases.

[0140] An electronic device according to an embodiment of the present invention comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, any one of the above-mentioned ball sports video analysis methods is implemented. That is to say, an electronic device according to an embodiment of the present invention may include but is not limited to: a processor and a memory; the memory is used to store the computer program; the processor is used to execute the ball sports video analysis method shown in any embodiment of the present invention by calling the computer program.

[0141] In an alternative embodiment, an electronic device is provided, such as Figure 5 As shown, Figure 5 The electronic device 4000 shown includes: a processor 4001 and a memory 4003. The processor 4001 and the memory 4003 are connected, such as through a bus 4002. Optionally, the electronic device 4000 may also include a transceiver 4004, which may be used for data interaction between the electronic device and other electronic devices, such as data transmission and / or data reception. It should be noted that in actual applications, the transceiver 4004 is not limited to one, and the structure of the electronic device 4000 does not constitute a limitation on the embodiments of the present invention.

[0142] Processor 4001 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of the present invention. Processor 4001 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0143] The bus 4002 may include a path to transmit information between the above components. The bus 4002 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 4002 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 5 In the figure, only one thick line is used to represent the bus 4002, but this does not mean that there is only one bus or one type of bus.

[0144] The memory 4003 can be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited to this.

[0145] The memory 4003 is used to store the application code (computer program) for executing the solution of the present invention, and the execution is controlled by the processor 4001. The processor 4001 is used to execute the application code stored in the memory 4003 to implement the content shown in the above method embodiment.

[0146] Among them, the electronic device can also be a terminal device, and the terminal device can be any device that can install applications, including at least one of a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, a smart TV, and a smart car device.

[0147] It should be noted that Figure 5 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0148] A computer-readable storage medium according to an embodiment of the present invention stores a computer program, and when the computer program is executed by a processor, any of the above-mentioned ball sports video analysis methods is implemented.

[0149] Optionally, the computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a compact disc (CD-ROM), a magnetic tape, a floppy disk, an optical data storage device, and the like.

[0150] In an exemplary embodiment, a computer program product or a computer program is also provided, the computer program product or the computer program includes computer instructions, the computer instructions are stored in a computer-readable storage medium. A processor of an electronic device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the electronic device performs any of the above-mentioned ball sports video analysis methods.

[0151] Computer program code for performing the operations of the present invention may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0152] It should be understood that the flow charts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the method and computer program product according to various embodiments of the present invention. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the module, the program segment, or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a sequence different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0153] The computer-readable storage medium provided by the embodiment of the present invention may be, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or component, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with 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 thereof. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, device, or component.

[0154] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device executes the method shown in the above embodiment.

[0155] The above description is only a preferred embodiment of the present invention and an explanation of the technical principles used. Those skilled in the art should understand that the disclosure scope involved in the present invention is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present invention (but not limited to) by each other.

[0156] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects and represent the definition of a specific order or sequence. The order of use of similar objects can be interchanged where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than the order shown or described.

[0157] Those skilled in the art know that the present invention can be implemented as a system, method or computer program product. Therefore, the present invention can be specifically implemented in the following forms, namely: it can be complete hardware, it can be complete software (including firmware, resident software, microcode, etc.), or it can be a combination of hardware and software, which is generally referred to as "circuit", "module" or "system" herein. In addition, in some embodiments, the present invention can also be implemented in the form of a computer program product in one or more computer-readable media, and the computer-readable medium contains computer-readable program code.

[0158] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. A ball sports video analysis method, characterized in that: include: Acquire a target ball sports video, wherein each video frame in the target ball sports video contains a timestamp; Each video frame in the target ball sports video is identified to obtain the position of each key point of each human body of each player at each moment and the position of the ball at each moment, wherein the timestamp corresponds to the moment one by one.

2. A ball sports video analysis method according to claim 1, characterized in that: Also includes: When the ball hitting detection is triggered, a ball position time sequence within a preset time period is determined based on the target ball sports video or the position of the ball at each moment, wherein the preset time period includes the moment when the ball hitting detection is triggered; The ball position time series is fitted, and the trough position in the fitted curve is determined as the hitting position.

3. A ball sports video analysis method according to claim 2, characterized in that: Also includes: The release speed and release angle of the ball are calculated based on the hitting position and the position of the ball at the next moment after the hitting position.

4. A ball sports video analysis method according to claim 2 or 3, characterized in that: The process of determining the ball position time series according to the target ball sports video includes: From the target ball sports video, a plurality of video frames within a preset time period including the moment of triggering the ball hitting detection are acquired and identified to obtain the ball position time series.

5. A ball sports video analysis method according to claim 2 or 3, characterized in that: The process of determining the ball position time series according to the ball's position at each moment includes: From the position of the ball at each moment, the positions of the ball at multiple moments within a preset time period including the moment of triggering the ball hitting detection are obtained to form the ball position time series.

6. A ball sports video analysis method according to any one of claims 1 to 3, characterized in that: The process of acquiring target ball sports video includes: Shoot the initial ball game video with a camera or camcorder; The initial ball sports video is preprocessed to obtain the target ball sports video.

7. A ball sports video analysis method according to claim 6, characterized in that: The initial ball sports video is: a badminton match video, a badminton training video, a table tennis match video, a table tennis training video, a tennis match video or a tennis training video.

8. A ball sports video analysis system, characterized in that: It includes a ball sports video acquisition module and a recognition module; The ball sports video acquisition module is used to: acquire a target ball sports video, wherein each video frame in the target ball sports video contains a timestamp; The recognition module is used to: recognize each video frame in the target ball sports video, obtain the position of each key point of each human body of each player at each moment and the position of the ball at each moment, wherein the timestamp corresponds to the moment one by one.

9. An electronic device, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, a ball sports video analysis method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the ball sports video analysis method according to any one of claims 1 to 7 is implemented.

Images