Exercise intensified training method, device and equipment and storage medium thereof

Abstract

The embodiment of the invention belongs to the technical field of image processing, is applied to athlete action analysis and intensified training scenes, and relates to an exercise intensified training method, device and equipment and a storage medium thereof. Two-dimensional coordinate information and contour size change information of the target object in each video picture in the target video picture set are obtained, so that dynamic position information of the target object is obtained, a motion track of the target object is determined, and a thermodynamic diagram is constructed, so that the motion tactical habits of a target athlete are analyzed in combination with the thermodynamic diagram, and the motion tactical habits of the target athlete are analyzed. The method has the advantages that the method is simple and convenient to operate, targeted exercise intensified training is achieved according to analysis results, automation and intellectualization are better achieved, meanwhile, coaches can be assisted in strategically analyzing target athletes, accordingly, relevant battle strategies and guidance strategies are formulated, and time consumption during manual analysis is reduced.

Description

Technical Field

[0001] The present application relates to the field of image processing technology, and is applied to athlete motion analysis and intensive training scenarios, and in particular to a sports intensive training method, device, equipment and storage medium thereof. Background Art

[0002] Accurately tracking the body's movements during an action is an important part of sports science. However, the current research focuses on placing markers at predetermined points on the subject's body, which can interfere with the subject's behavior and is only applicable to a limited number of sports. Motion capture has long been a key component of analyzing athlete performance.

[0003] Due to the high cost of motion capture, the current targeted intensive training for athletes still relies heavily on manual methods, which can easily introduce personal subjective factors of coaches and are not intelligent enough. Moreover, the analysis of athlete performance also relies on analysts to watch and mark repeatedly, which is time-consuming and labor-intensive and not scientific enough. Summary of the invention

[0004] The purpose of the embodiments of the present application is to propose a sports intensive training method, device, equipment and storage medium thereof to solve the problem that the existing targeted intensive training for athletes still relies heavily on manual methods and is not intelligent and scientific enough.

[0005] In order to solve the above technical problems, the embodiment of the present application provides a sports strengthening training method, which adopts the following technical solutions:

[0006] A sports strengthening training method comprises the following steps:

[0007] Get batches of videos to be analyzed;

[0008] Perform frame-by-frame segmentation processing on each video to be analyzed in the batch of videos to be analyzed, and obtain a target video picture set corresponding to each video to be analyzed;

[0009] Inputting the target video picture set into a preset object position analysis model to obtain a dynamic position information set of the target object output by the object position analysis model;

[0010] Based on the dynamic location information set of the target object, construct a location information distribution heat map;

[0011] Deploy the position information distribution heat map as reference knowledge into a preset sports training battle model;

[0012] The target robot is controlled according to the sports training and combat model to perform sports intensive training on the target athletes in the batch of videos to be analyzed.

[0013] Furthermore, the step of obtaining a batch of videos to be analyzed specifically includes:

[0014] Using the target athlete's distinguishing identification information as an index field, all sports videos of the target athlete performing the target sports are screened out from a pre-sorted video collection;

[0015] All the motion videos are used as the batch of videos to be analyzed.

[0016] Furthermore, the step of performing frame-by-frame segmentation processing on each video to be analyzed in the batch of videos to be analyzed to obtain a target video picture set corresponding to each video to be analyzed specifically includes:

[0017] Obtaining frame interval information from a preset configuration file, wherein the frame interval information represents time interval information between two consecutive frames of video images;

[0018] Using the frame interval information as a frame parameter, each video to be analyzed in the batch of videos to be analyzed is segmented frame by frame;

[0019] Obtain the target video image set corresponding to each video to be analyzed.

[0020] Furthermore, after executing the step of using the frame interval information as a frame parameter to perform frame segmentation processing on each video to be analyzed in the batch of videos to be analyzed, the method further includes:

[0021] Obtain a preliminary time-sequential frame-by-frame video picture set corresponding to the current video to be analyzed;

[0022] The video pictures after the target athlete exerts a motion action on the target object and the video pictures after the non-target athlete exerts a motion action on the target object are filtered out from the frame-by-frame video picture set by using a preset recognition and filtering rule;

[0023] The selected video pictures after the target athlete exerts motion on the target object are added to the target set in time sequence to generate a target video picture set corresponding to the current video to be analyzed.

[0024] Furthermore, the step of filtering the video images after the target athlete exerts motion on the target object from the frame-by-frame video image set by using a preset recognition and screening rule specifically includes:

[0025] Identifying the types of video pictures in the frame-by-frame video picture set, wherein the types of video pictures include pictures that are generally parallel to the motion trajectory of the target object and pictures that are generally perpendicular to the motion trajectory of the target object;

[0026] If the video picture is a picture that is generally parallel to the motion trajectory of the target object, the target object is identified by the distance between the target object and the target athlete in two consecutive video pictures. If the target object in the previous video picture is closer to the target athlete than the target object in the next video picture, the target object is moving from the target athlete to the non-target athlete.

[0027] If the video picture is an image that is generally perpendicular to the motion trajectory of the target object, the target object is identified by the change in the size of its outline in two consecutive frames of video pictures. If the target object in the previous frame of the video picture appears to be visually larger than the target object in the next frame of the video picture, then the target object is moving from the target athlete to the non-target athlete.

[0028] Furthermore, the step of inputting the target video picture set into a preset object position analysis model to obtain a dynamic position information set of the target object output by the object position analysis model specifically includes:

[0029] Acquire a two-dimensional coordinate system pre-constructed according to the size of the video picture in the target video picture set, wherein the two-dimensional coordinate system includes a set coordinate origin and a unit coordinate value;

[0030] Deploying the two-dimensional coordinate system, the coordinate origin and the unit coordinate value in the two-dimensional coordinate system as position analysis reference knowledge into the preset object position analysis model;

[0031] Obtaining two-dimensional coordinate information of the target object in each video picture in the target video picture set through the preset object position analysis model; and

[0032] Obtaining the outline size change information of the target object in each video picture in the target video picture set through the preset object position analysis model;

[0033] Arrange the two-dimensional coordinate information and contour size change information of the target object corresponding to the same video picture in the target video picture set to obtain the dynamic position information corresponding to the video picture;

[0034] The dynamic position information corresponding to all the video pictures in the target video picture set is sorted in a frame-by-frame order to obtain the dynamic position information set.

[0035] Furthermore, the step of constructing a location information distribution heat map based on the dynamic location information set of the target object specifically includes:

[0036] Identify the outline size and two-dimensional coordinate information of the target object in each video picture in the target video picture set through the dynamic position information set of the target object;

[0037] According to the outline size and the two-dimensional coordinate information, the frequency of occurrence of the target object at different positions is counted to obtain a statistical result;

[0038] The location information distribution heat map is constructed according to the statistical results, wherein the location information distribution heat map follows that the more times the target object stays at the target location, the higher the thermal value of the target location.

[0039] In order to solve the above technical problems, the embodiment of the present application also provides a sports intensive training device, which adopts the following technical solution:

[0040] A sports strengthening training device, comprising:

[0041] The module for acquiring videos to be analyzed is used to acquire batches of videos to be analyzed;

[0042] A target video picture set acquisition module is used to perform frame-by-frame segmentation processing on each video to be analyzed in the batch of videos to be analyzed, and obtain a target video picture set corresponding to each video to be analyzed;

[0043] A dynamic position information set acquisition module, used to input the target video picture set into a preset object position analysis model to obtain a dynamic position information set of the target object output by the object position analysis model;

[0044] A location information distribution heat map construction module, used to construct a location information distribution heat map based on the dynamic location information set of the target object;

[0045] A sports training and combat model deployment module, used to deploy the position information distribution heat map as reference knowledge into a preset sports training and combat model;

[0046] The targeted intensive training module is used to control the target robot to perform intensive sports training on the target athletes in the batch of videos to be analyzed according to the sports training and combat model.

[0047] In order to solve the above technical problems, the embodiment of the present application further provides a computer device, which adopts the following technical solution:

[0048] A computer device includes a memory and a processor, wherein the memory stores computer-readable instructions, and the processor implements the steps of the above-mentioned sports strengthening training method when executing the computer-readable instructions.

[0049] In order to solve the above technical problems, the embodiment of the present application further provides a computer-readable storage medium, which adopts the following technical solution:

[0050] A computer-readable storage medium stores computer-readable instructions, which, when executed by a processor, implement the steps of the sports reinforcement training method as described above.

[0051] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0052] The sports enhancement training method described in the embodiment of the present application obtains a batch of videos to be analyzed, that is, obtains all the archived training videos and / or game videos in which the target athlete has participated in the past, performs image segmentation processing, and obtains the two-dimensional coordinate information of the target object in each video picture in the target video picture set; and, through the preset object position analysis model, obtains the contour size change information of the target object in each video picture in the target video picture set, thereby obtaining the dynamic position information of the target object, determining the motion trajectory of the target object, and constructing a heat map based on the motion trajectory and the position information of the target object, so as to analyze the sports tactical habits of the target athlete in combination with the heat map, and implement targeted sports enhancement training based on the analysis results, which is more automated and intelligent. At the same time, it can also assist coaches in conducting strategic analysis of target athletes, thereby formulating relevant combat strategies and guidance strategies, reducing the time consumption of manual analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the scheme in the present application, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0054] Figure 1 is an exemplary system architecture diagram to which the present application may be applied;

[0055] Figure 2 is a flow chart of an embodiment of a sports strengthening training method according to the present application;

[0056] Figure 3 yes Figure 2 A flowchart of a specific embodiment of step 201 is shown;

[0057] Figure 4 yes Figure 2 A flowchart of a specific embodiment of step 202 is shown;

[0058] Figure 5 It is a flowchart of a specific embodiment of identifying and screening video images after frame-by-frame segmentation processing in the sports intensive training method described in this application;

[0059] Figure 6 yes Figure 5 A flowchart of a specific embodiment of step 502 is shown;

[0060] Figure 7 yes Figure 2 A flowchart of a specific embodiment of step 203 is shown;

[0061] Figure 8 yes Figure 2 A flowchart of a specific embodiment of step 204 is shown;

[0062] Fig. 9 is a structural schematic diagram of an embodiment of a sports intensive training device according to the present application;

[0063] Fig.10 It is a structural diagram of an embodiment of a computer device according to the present application. DETAILED DESCRIPTION

[0064] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0065] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0066] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0067] like Figure 1As shown, the system architecture 100 may include a terminal device 101, a network 102 and a server 103. The terminal device 101 may be a laptop 1011, a tablet computer 1012 or a mobile phone 1013. The network 102 is used to provide a medium for a communication link between the terminal device 101 and the server 103. The network 102 may include various connection types, such as wired, wireless communication links or optical fiber cables.

[0068] The user can use the terminal device 101 to interact with the server 103 through the network 102 to receive or send messages, etc. Various communication client applications can be installed on the terminal device 101, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0069] The terminal device 101 can be any electronic device with a display screen and supporting web browsing. In addition to a laptop computer 1011, a tablet computer 1012 or a mobile phone 1013, the terminal device 101 can also be an e-book reader, an MP3 player (Moving Picture Experts Group Audio Layer III), an MP4 (Moving Picture Experts Group Audio Layer IV), a laptop computer, a desktop computer, etc.

[0070] The server 103 may be a server that provides various services, such as a background server that provides support for web pages displayed on the terminal device 101 .

[0071] It should be noted that the exercise enhancement training method provided in the embodiment of the present application is generally executed by a terminal device, and accordingly, the exercise enhancement training device is generally provided in the terminal device.

[0072] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0073] Continue to refer Figure 2 , shows a flow chart of an embodiment of the sports intensive training method according to the present application. The sports intensive training method comprises the following steps:

[0074] Step 201, obtaining a batch of videos to be analyzed;

[0075] Specifically, the batch of videos to be analyzed refers to all the archived training videos and / or game videos in which the target athlete has participated in the past.

[0076] By obtaining a batch of videos to be analyzed, that is, obtaining all the archived training videos and / or game videos in which the target athlete has participated in the past, it is convenient to conduct a comprehensive analysis of the target athlete's sports tactical habits in the future, and implement targeted sports intensive training based on the analysis results.

[0077] Step 202, performing frame-by-frame segmentation processing on each video to be analyzed in the batch of videos to be analyzed, and obtaining a target video picture set corresponding to each video to be analyzed;

[0078] By performing frame-by-frame segmentation processing on each video to be analyzed in the batch of videos to be analyzed, a target video picture set corresponding to each video to be analyzed is obtained, thereby achieving the acquisition of pictures for action analysis of the target athlete at a frame-by-frame level, thereby ensuring that the result of the action analysis of the target athlete has more reference value and is more accurate.

[0079] Step 203, inputting the target video picture set into a preset object position analysis model to obtain a dynamic position information set of the target object output by the object position analysis model;

[0080] By obtaining the dynamic position information set of the target object output by the object position analysis model, the competitive fighting movements of the target athlete can be analyzed in combination with the motion trajectory of the target object, so as to facilitate targeted intensive training.

[0081] Step 204, constructing a location information distribution heat map based on the dynamic location information set of the target object;

[0082] A position information distribution heat map is constructed through the dynamic position information set of the target object, so as to intuitively display the competitive habits of the target athlete in combination with the position information distribution heat map, thereby conducting targeted intensive training.

[0083] Step 205, deploying the position information distribution heat map as reference knowledge into a preset sports training battle model;

[0084] Step 206: Control the target robot to perform sports intensive training on the target athletes in the batch of videos to be analyzed according to the sports training and combat model.

[0085] By deploying the position information distribution heat map as reference knowledge into a preset sports training and combat model, it is convenient to screen out the high-frequency position points of the target object from the position information distribution heat map, and provide the high-frequency position points as reinforcement training knowledge to the target robot, so that the target robot can perform reinforcement training on the target athlete according to the high-frequency position points, which is more intelligent and scientific, and also reduces the factors of artificial reinforcement training and reduces the time consumption of artificial analysis.

[0086] In this embodiment, by obtaining a batch of videos to be analyzed, that is, obtaining all the archived training videos and / or game videos in which the target athlete has participated in the past, image segmentation processing is performed to obtain the two-dimensional coordinate information of the target object in each video picture in the target video picture set; and, through the preset object position analysis model, the contour size change information of the target object in each video picture in the target video picture set is obtained, thereby obtaining the dynamic position information of the target object, determining the motion trajectory of the target object, and constructing a heat map based on the motion trajectory and the position information of the target object, so as to analyze the sports tactical habits of the target athlete in combination with the heat map, and implement targeted sports intensive training based on the analysis results, which is more automated and intelligent. At the same time, it can also assist coaches in conducting strategic analysis of target athletes, thereby formulating relevant combat strategies and guidance strategies, reducing the time consumption of manual analysis.

[0087] Continue to refer Figure 3 , in some optional implementations, Figure 3 yes Figure 2 The flowchart of a specific embodiment of step 201 shown includes the following steps:

[0088] Step 301, using the distinguishing identification information of the target athlete as an index field, filtering out all sports videos of the target athlete when performing the target sport from a pre-sorted video collection;

[0089] Step 302: taking all the sports videos as the batch of videos to be analyzed.

[0090] Specifically, the distinguishing identification information of the target athlete includes the athlete's name information, the athlete's uniform number information, etc. The target sport includes ball games, such as badminton, table tennis, volleyball, basketball, baseball, etc. The pre-organized video collection includes each game / training video recorded by the self or recorded on the event platform related to the target sport. All sports videos of the target athlete when performing the target sport refer to all archived training videos and / or game videos in which the target athlete has participated in the past.

[0091] By obtaining a batch of videos to be analyzed, that is, obtaining all the archived training videos and / or game videos in which the target athlete has participated in the past, it is convenient to conduct a comprehensive analysis of the target athlete's sports tactical habits in the future, and implement targeted sports intensive training based on the analysis results.

[0092] Continue to refer Figure 4 , in some optional implementations, Figure 4 yes Figure 2 The flowchart of a specific embodiment of step 202 shown includes the following steps:

[0093] Step 401, obtaining frame interval information from a preset configuration file, wherein the frame interval information represents time interval information between two consecutive frames of video images;

[0094] Step 402, using the frame interval information as a frame parameter, and performing frame segmentation processing on each video to be analyzed in the batch of videos to be analyzed;

[0095] Step 403: Obtain a target video picture set corresponding to each video to be analyzed.

[0096] By obtaining frame interval information from a preset configuration file, taking the frame interval information as a frame parameter, performing frame-by-frame segmentation processing on each video to be analyzed in the batch of videos to be analyzed, and obtaining a target video picture set corresponding to each video to be analyzed, it is possible to obtain pictures for action analysis of the target athlete at a frame-by-frame level, thereby ensuring that the result of the action analysis of the target athlete has more reference value and is more accurate.

[0097] Continue to refer Figure 5 In some optional implementations, after step 402 and before step 403, a step of identifying and screening the video images after the frame-by-frame segmentation process is also included. Figure 5 This is a flowchart of a specific embodiment of identifying and screening video images after frame-by-frame segmentation processing in the sports intensive training method described in this application, including the following steps:

[0098] Step 501, obtaining a preliminary time-sequential frame-by-frame video picture set corresponding to the current video to be analyzed;

[0099] Step 502, filtering the video images after the target athlete exerts motion on the target object from the frame-by-frame video image set by using a preset recognition and screening rule;

[0100] Step 503: Add the selected video pictures of the target athlete exerting motion on the target object to the target set in a time-sequential manner to generate a target video picture set corresponding to the current video to be analyzed.

[0101] Specifically, through the preset recognition and screening rules, the video pictures after the target athlete exerts motion on the target object are screened from the frame-by-frame video picture set. For example, the target object is a table tennis ball, and each picture in the video picture set includes athletes from both opposing teams, one of whom is the target athlete and the other is a non-target athlete. The video pictures after the target athlete exerts motion on the target object are screened through the position change of the table tennis ball, for example, based on whether the table tennis ball moves from the target athlete to the non-target athlete.

[0102] By means of preset recognition and screening rules, the video pictures after the target athlete exerts motion on the target object are screened from the frame-by-frame video picture set, and the screened video pictures after the target athlete exerts motion on the target object are added to the target set in chronological order, thereby ensuring that the target video picture set corresponding to each video to be analyzed only contains the video pictures after the target athlete exerts motion on the target object, and eliminates the video pictures after non-target athletes exert motion on the target object, thereby reducing the amount of pictures in the target video picture set, and at the same time, ensuring that each picture in the target video picture set plays a certain role in the analysis of the target athlete's motion tactical habits.

[0103] Continue to refer Figure 6 , in some optional implementations, Figure 6 yes Figure 5 The flowchart of a specific embodiment of step 502 shown includes the following steps:

[0104] Step 601, identifying the types of video pictures in the frame-by-frame video picture set, wherein the types of video pictures include pictures that are generally parallel to the motion trajectory of the target object and pictures that are generally perpendicular to the motion trajectory of the target object;

[0105] Step 603: if the video image is an image that is generally parallel to the motion trajectory of the target object, identification is performed based on the distance between the target object and the target athlete in two consecutive video images. If the target object in the previous video image is closer to the target athlete than the target object in the next video image, the target object is moving from the target athlete to the non-target athlete.

[0106] Step 604: If the video image is an image that is generally perpendicular to the motion trajectory of the target object, the target object is identified by the change in the size of its outline in two consecutive video images. If the target object in the previous video image appears to be visually larger than the target object in the next video image, then the target object is moving from the target athlete to the non-target athlete.

[0107] Continuing with the above table tennis embodiment, there are two determination methods according to whether the table tennis ball moves from the target player to the non-target player.

[0108] One of the judgment methods is that if the video image is an image that is generally parallel to the movement trajectory of the table tennis ball, the distance between the table tennis ball and the target athlete in two consecutive frames of video images is used for identification; if the table tennis ball in the previous frame of the video image is closer to the target athlete than the table tennis ball in the next frame of the video image, then the table tennis ball is moving from the target athlete to the non-target athlete.

[0109] Another way to determine is that if the video image is an image that is generally vertical to the trajectory of the table tennis ball, identification is performed by the change in the size of the outline of the table tennis ball in two consecutive frames of video images. If the table tennis ball in the previous frame of the video image appears to be visually larger than the table tennis ball in the next frame of the video image, then the table tennis ball is moving from the target athlete to the non-target athlete.

[0110] Specifically, since the batch of videos to be analyzed may be videos shot from the side angle of the game table, or may be videos shot from the perspective of the game players' positions, this results in the existence of two different types of video images, one is the image cut out from the video shot from the side angle of the game table, that is, the image is generally parallel to the motion trajectory of the table tennis ball, and the other is the image cut out from the video shot from the perspective of the game players' positions, that is, the image is generally vertical to the motion trajectory of the table tennis ball. By identifying the type of video images in the frame-by-frame video image set, the frame-by-frame video images at different angles can be analyzed to screen out the video images after the target athlete exerts motion on the target object.

[0111] Continue to refer Figure 7 , in some optional implementations, Figure 7 yes Figure 2 The flowchart of a specific embodiment of step 203 shown includes the following steps:

[0112] Step 701, obtaining a two-dimensional coordinate system pre-constructed according to the size of the video pictures in the target video picture set, wherein the two-dimensional coordinate system includes a set coordinate origin and a unit coordinate value;

[0113] Step 702, deploying the two-dimensional coordinate system, the coordinate origin and the unit coordinate value in the two-dimensional coordinate system as position analysis reference knowledge into the preset object position analysis model;

[0114] Step 703, obtaining two-dimensional coordinate information of the target object in each video picture in the target video picture set through the preset object position analysis model; and

[0115] Step 704, obtaining the outline size change information of the target object in each video picture in the target video picture set through the preset object position analysis model;

[0116] Step 705, sorting the two-dimensional coordinate information and contour size change information of the target object corresponding to the same video picture in the target video picture set to obtain the dynamic position information corresponding to the video picture;

[0117] Step 706: sort the dynamic position information corresponding to all the video pictures in the target video picture set in a frame-by-frame order to obtain the dynamic position information set.

[0118] Specifically, the preset object position analysis model is used to obtain the two-dimensional coordinate information of the target object in each video picture in the target video picture set; and the contour size change information of the target object in each video picture in the target video picture set is obtained through the preset object position analysis model. A frame-by-frame video picture comparison method can be used to obtain the change in the two-dimensional coordinate information of the target object, and the contour size change information of the target object between the frame-by-frame video pictures can be combined to obtain the dynamic position information of the target object and determine the motion trajectory of the target object.

[0119] The object position analysis model includes a two-dimensional coordinate information labeling component and a target object contour size comparison component, wherein the two-dimensional coordinate information labeling component is used to label the two-dimensional coordinate value of the target object in two consecutive video frames, and the target object contour size comparison component is used to compare the contour size of the target object in two consecutive video frames.

[0120] Continuing with the above-mentioned table tennis embodiment as an example, for example: the two-dimensional coordinate information of the table tennis ball in two consecutive video frames are (X=10, Y=10) and (X=11, Y=9), and the outline of the table tennis ball gradually becomes larger in the two consecutive video frames. The motion trajectory of the target object can be predicted by two coordinate points and one target object outline size change information.

[0121] Through the preset object position analysis model, the two-dimensional coordinate information of the target object in each video picture in the target video picture set is obtained; and through the preset object position analysis model, the outline size change information of the target object in each video picture in the target video picture set is obtained to determine the motion trajectory of the target object, so as to analyze the competitive combat actions of the target athlete in combination with the motion trajectory of the target object, so as to facilitate targeted intensive training.

[0122] Continue to refer Figure 8 , in some optional implementations, Figure 8 yes Figure 2 The flowchart of a specific embodiment of step 204 shown includes the following steps:

[0123] Step 801, identifying the outline size and two-dimensional coordinate information of the target object in each video picture in the target video picture set through the dynamic position information set of the target object;

[0124] Step 802, counting the frequency of occurrence of the target object at different positions according to the outline size and the two-dimensional coordinate information to obtain a statistical result;

[0125] Step 803: construct the location information distribution heat map according to the statistical results, wherein the location information distribution heat map follows that the more times the target object stays at the target location, the higher the thermal value of the target location.

[0126] By using the outline size and two-dimensional coordinate information, the frequency of the target object appearing at different positions is counted to obtain statistical results, thereby identifying the motion trajectory and position information of the target object when the target athlete exerts motion on the target object. When the target object is characterized on a position information distribution heat map, it is convenient to combine the position information distribution heat map to intuitively display the competitive habits of the target athlete, thereby conducting targeted intensive training.

[0127] Theoretically speaking, the more similar (balanced) the thermal values ​​or thermal representation colors of each point in the position information distribution heat map are, the more stable the competitive level of the target athlete is. Therefore, the purpose of the targeted intensive training is to make the position information distribution heat map obtained when analyzing the target athlete in the future more uniform.

[0128] In some optional implementations, the step of controlling the target robot to perform intensive sports training on the target athletes in the batch of videos to be analyzed according to the sports training battle model specifically includes: screening out high-frequency position points of the target object from the position information distribution heat map, and providing the high-frequency position points as intensive training knowledge to the target robot, so that the target robot can perform intensive training on the target athlete according to the high-frequency position points, wherein the target robot can be understood as a simulated person who performs sports battles with the target athlete, for example: an electronic intelligent athlete in table tennis competitions.

[0129] Specifically, by obtaining a batch of videos to be analyzed, that is, obtaining all the archived training videos and / or game videos in which the target athlete has participated in the past, image segmentation processing is performed to obtain the two-dimensional coordinate information of the target object in each video image in the target video image set; and, through the preset object position analysis model, the outline size change information of the target object in each video image in the target video image set is obtained, thereby obtaining the dynamic position information of the target object, determining the motion trajectory of the target object, and constructing a heat map based on the motion trajectory and the position information of the target object, so as to analyze the sports tactical habits of the target athlete in combination with the heat map, and realize targeted sports intensive training based on the analysis results, which is more automated and intelligent. At the same time, it can also assist coaches in conducting strategic analysis of target athletes, thereby formulating relevant combat strategies and guidance strategies, reducing the time consumption of manual analysis.

[0130] The present application obtains batches of videos to be analyzed, that is, obtains all the archived training videos and / or game videos in which the target athlete has participated in the past, performs image segmentation processing, and obtains the two-dimensional coordinate information of the target object in each video picture in the target video picture set; and, through the preset object position analysis model, obtains the outline size change information of the target object in each video picture in the target video picture set, thereby obtaining the dynamic position information of the target object, determining the motion trajectory of the target object, and constructing a heat map according to the motion trajectory and the position information of the target object, so as to analyze the sports tactical habits of the target athlete in combination with the heat map, and implement targeted sports intensive training according to the analysis results, which is more automated and intelligent. At the same time, it can also assist coaches in conducting strategic analysis of target athletes, thereby formulating relevant combat strategies and guidance strategies, reducing the time consumption of manual analysis.

[0131] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0132] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0133] In an embodiment of the present application, by obtaining a batch of videos to be analyzed, that is, obtaining all the archived training videos and / or game videos in which the target athlete has participated in the past, image segmentation processing is performed to obtain the two-dimensional coordinate information of the target object in each video picture in the target video picture set; and, through the preset object position analysis model, the contour size change information of the target object in each video picture in the target video picture set is obtained, thereby obtaining the dynamic position information of the target object, determining the motion trajectory of the target object, and constructing a heat map based on the motion trajectory and the position information of the target object, so as to analyze the sports tactical habits of the target athlete in combination with the heat map, and implement targeted sports intensive training based on the analysis results, which is more automated and intelligent. At the same time, it can also assist coaches in conducting strategic analysis of target athletes, thereby formulating relevant combat strategies and guidance strategies, reducing the time consumption of manual analysis.

[0134] Further references Fig. 9 , as a response to the above Figure 2 In order to realize the method shown in the figure, the present application provides an embodiment of a sports strengthening training device, and the device embodiment is Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0135] like Fig. 9 As shown, the sports intensive training device 900 described in this embodiment includes: a video acquisition module 901 to be analyzed, a target video picture set acquisition module 902, a dynamic position information set acquisition module 903, a position information distribution heat map construction module 904, a sports training battle model deployment module 905 and a targeted intensive training module 906. Among them:

[0136] The video acquisition module 901 to be analyzed is used to acquire a batch of videos to be analyzed;

[0137] The target video picture set acquisition module 902 is used to perform frame-by-frame segmentation processing on each video to be analyzed in the batch of videos to be analyzed, and obtain the target video picture set corresponding to each video to be analyzed;

[0138] A dynamic position information set acquisition module 903 is used to input the target video picture set into a preset object position analysis model to obtain a dynamic position information set of the target object output by the object position analysis model;

[0139] A location information distribution heat map construction module 904 is used to construct a location information distribution heat map based on the dynamic location information set of the target object;

[0140] A sports training and combat model deployment module 905 is used to deploy the position information distribution heat map as reference knowledge into a preset sports training and combat model;

[0141] The targeted intensive training module 906 is used to control the target robot to perform intensive sports training on the target athletes in the batch of videos to be analyzed according to the sports training and combat model.

[0142] The present application obtains batches of videos to be analyzed, that is, obtains all the archived training videos and / or game videos in which the target athlete has participated in the past, performs image segmentation processing, and obtains the two-dimensional coordinate information of the target object in each video picture in the target video picture set; and, through the preset object position analysis model, obtains the outline size change information of the target object in each video picture in the target video picture set, thereby obtaining the dynamic position information of the target object, determining the motion trajectory of the target object, and constructing a heat map according to the motion trajectory and the position information of the target object, so as to analyze the sports tactical habits of the target athlete in combination with the heat map, and implement targeted sports intensive training according to the analysis results, which is more automated and intelligent. At the same time, it can also assist coaches in conducting strategic analysis of target athletes, thereby formulating relevant combat strategies and guidance strategies, reducing the time consumption of manual analysis.

[0143] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through computer-readable instructions, and the computer-readable instructions can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0144] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0145] To solve the above technical problems, the present application also provides a computer device. Fig.10 , Fig.10 This is a basic structural block diagram of the computer device in this embodiment.

[0146] The computer device 10 includes a memory 10a, a processor 10b, and a network interface 10c which are interconnected and communicated via a system bus. It should be noted that: Fig.10Only a computer device 10 having a component memory 10a, a processor 10b, and a network interface 10c is shown, but it should be understood that it is not required to implement all the components shown, and more or fewer components may be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to a microprocessor, an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), a digital processor (DSP), an embedded device, etc.

[0147] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with a user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.

[0148] The memory 10a includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 10a can be an internal storage unit of the computer device 10, such as a hard disk or memory of the computer device 10. In other embodiments, the memory 10a can also be an external storage device of the computer device 10, such as a plug-in hard disk equipped on the computer device 10, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. Of course, the memory 10a can also include both the internal storage unit of the computer device 10 and its external storage device. In this embodiment, the memory 10a is generally used to store the operating system and various application software installed on the computer device 10, such as a computer-readable instruction of a sports strengthening training method, etc. In addition, the memory 10a can also be used to temporarily store various types of data that have been output or are to be output.

[0149] The processor 10b may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chip in some embodiments. The processor 10b is generally used to control the overall operation of the computer device 10. In this embodiment, the processor 10b is used to run the computer-readable instructions or process data stored in the memory 10a, such as running the computer-readable instructions of the sports intensive training method.

[0150] The network interface 10c may include a wireless network interface or a wired network interface. The network interface 10c is generally used to establish a communication connection between the computer device 10 and other electronic devices.

[0151] The computer device proposed in this embodiment belongs to the field of image processing technology and is applied to athlete motion analysis and intensive training scenarios. This application obtains batches of videos to be analyzed, that is, obtains all the training videos or / and game videos that the target athlete has participated in, performs image segmentation processing, and obtains the two-dimensional coordinate information of the target object in each video picture in the target video picture set; and, through the preset object position analysis model, obtains the contour size change information of the target object in each video picture in the target video picture set, thereby obtaining the dynamic position information of the target object, determining the motion trajectory of the target object, and constructing a heat map according to the motion trajectory and the position information of the target object, so as to facilitate the analysis of the sports tactical habits of the target athlete in combination with the heat map, and realizes targeted sports intensive training according to the analysis results, which is more automated and intelligent. At the same time, it can also assist coaches in strategically analyzing the target athletes, thereby formulating relevant battle strategies and guidance strategies, reducing the time consumption during manual analysis.

[0152] The present application also provides another embodiment, namely, providing a computer-readable storage medium, wherein the computer-readable storage medium stores computer-readable instructions, and the computer-readable instructions can be executed by a processor to enable the processor to perform the steps of the sports enhancement training method as described above.

[0153] The computer-readable storage medium proposed in this embodiment belongs to the field of image processing technology and is applied to athlete motion analysis and intensive training scenarios. This application obtains batches of videos to be analyzed, that is, obtains all the training videos or / and game videos that the target athlete has participated in, performs image segmentation processing, and obtains the two-dimensional coordinate information of the target object in each video picture in the target video picture set; and, through the preset object position analysis model, obtains the contour size change information of the target object in each video picture in the target video picture set, thereby obtaining the dynamic position information of the target object, determining the motion trajectory of the target object, and constructing a heat map according to the motion trajectory and the position information of the target object, so as to facilitate the analysis of the target athlete's sports tactical habits in combination with the heat map, and realize targeted sports intensive training according to the analysis results, which is more automated and intelligent. At the same time, it can also assist coaches in strategically analyzing the target athletes, thereby formulating relevant battle strategies and guidance strategies, reducing the time consumption during manual analysis.

[0154] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0155] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to perform equivalent replacement of some of the technical features therein. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.

Claims

1. A method for strengthening sports training, characterized in that: The steps include: Get batches of videos to be analyzed; Perform frame-by-frame segmentation processing on each video to be analyzed in the batch of videos to be analyzed, and obtain a target video picture set corresponding to each video to be analyzed; Inputting the target video picture set into a preset object position analysis model to obtain a dynamic position information set of the target object output by the object position analysis model; Based on the dynamic location information set of the target object, construct a location information distribution heat map; Deploy the position information distribution heat map as reference knowledge into a preset sports training battle model; The target robot is controlled according to the sports training and combat model to perform sports intensive training on the target athletes in the batch of videos to be analyzed.

2. The exercise strengthening training method according to claim 1, characterized in that: The step of obtaining a batch of videos to be analyzed specifically includes: Using the target athlete's distinguishing identification information as an index field, all sports videos of the target athlete performing the target sports are screened out from a pre-sorted video collection; All the motion videos are used as the batch of videos to be analyzed.

3. The exercise strengthening training method according to claim 1 or 2, characterized in that: The step of performing frame-by-frame segmentation processing on each video to be analyzed in the batch of videos to be analyzed to obtain a target video picture set corresponding to each video to be analyzed specifically includes: Obtaining frame interval information from a preset configuration file, wherein the frame interval information represents time interval information between two consecutive frames of video images; Using the frame interval information as a frame parameter, each video to be analyzed in the batch of videos to be analyzed is segmented frame by frame; Obtain the target video image set corresponding to each video to be analyzed.

4. The exercise strengthening training method according to claim 3, characterized in that: After executing the step of using the frame interval information as a frame parameter to perform frame segmentation processing on each video to be analyzed in the batch of videos to be analyzed, the method further includes: Obtain a preliminary time-sequenced frame-by-frame video picture set corresponding to the current video to be analyzed; The video pictures after the target athlete exerts a motion action on the target object and the video pictures after the non-target athlete exerts a motion action on the target object are filtered out from the frame-by-frame video picture set by using a preset recognition and filtering rule; The selected video pictures after the target athlete exerts motion on the target object are added to the target set in time sequence to generate a target video picture set corresponding to the current video to be analyzed.

5. The exercise strengthening training method according to claim 4, characterized in that: The step of filtering the video images after the target athlete exerts motion on the target object from the frame-by-frame video image set by using a preset recognition and screening rule specifically includes: Identifying the types of video pictures in the frame-by-frame video picture set, wherein the types of video pictures include pictures that are generally parallel to the motion trajectory of the target object and pictures that are generally perpendicular to the motion trajectory of the target object; If the video picture is a picture that is generally parallel to the motion trajectory of the target object, the target object is identified by the distance between the target object and the target athlete in two consecutive video pictures. If the target object in the previous video picture is closer to the target athlete than the target object in the next video picture, the target object is moving from the target athlete to the non-target athlete. If the video picture is an image that is generally perpendicular to the motion trajectory of the target object, the target object is identified by the change in the size of its outline in two consecutive frames of video pictures. If the target object in the previous frame of the video picture appears to be visually larger than the target object in the next frame of the video picture, then the target object is moving from the target athlete to the non-target athlete.

6. The exercise strengthening training method according to claim 1, characterized in that: The step of inputting the target video picture set into a preset object position analysis model to obtain a dynamic position information set of the target object output by the object position analysis model specifically includes: Acquire a two-dimensional coordinate system pre-constructed according to the size of the video picture in the target video picture set, wherein the two-dimensional coordinate system includes a set coordinate origin and a unit coordinate value; Deploying the two-dimensional coordinate system, the coordinate origin and the unit coordinate value in the two-dimensional coordinate system as position analysis reference knowledge into the preset object position analysis model; Obtaining two-dimensional coordinate information of the target object in each video picture in the target video picture set through the preset object position analysis model; and Obtaining the outline size change information of the target object in each video picture in the target video picture set through the preset object position analysis model; Arrange the two-dimensional coordinate information and contour size change information of the target object corresponding to the same video picture in the target video picture set to obtain the dynamic position information corresponding to the video picture; The dynamic position information corresponding to all the video pictures in the target video picture set is sorted in a frame-by-frame order to obtain the dynamic position information set.

7. The exercise strengthening training method according to claim 6, characterized in that: The step of constructing a location information distribution heat map based on the dynamic location information set of the target object specifically includes: Identify the outline size and two-dimensional coordinate information of the target object in each video picture in the target video picture set through the dynamic position information set of the target object; According to the outline size and the two-dimensional coordinate information, the frequency of occurrence of the target object at different positions is counted to obtain a statistical result; The location information distribution heat map is constructed according to the statistical results, wherein the location information distribution heat map follows that the more times the target object stays at the target location, the higher the thermal value of the target location.

8. A sports strengthening training device, characterized in that: include: The module for acquiring videos to be analyzed is used to acquire batches of videos to be analyzed; A target video picture set acquisition module is used to perform frame-by-frame segmentation processing on each video to be analyzed in the batch of videos to be analyzed, and obtain a target video picture set corresponding to each video to be analyzed; A dynamic position information set acquisition module, used to input the target video picture set into a preset object position analysis model to obtain a dynamic position information set of the target object output by the object position analysis model; A location information distribution heat map construction module, used to construct a location information distribution heat map based on the dynamic location information set of the target object; A sports training and combat model deployment module, used to deploy the position information distribution heat map as reference knowledge into a preset sports training and combat model; The targeted intensive training module is used to control the target robot to perform intensive sports training on the target athletes in the batch of videos to be analyzed according to the sports training and combat model.

9. A computer device, characterized in that: The method comprises a memory and a processor, wherein the memory stores computer-readable instructions, and the processor implements the steps of the sports strengthening training method as described in any one of claims 1 to 7 when executing the computer-readable instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by a processor, the steps of the sports strengthening training method according to any one of claims 1 to 7 are implemented.

Images