Motion Information Processing Method, Apparatus, and Computer Device

Abstract

The present disclosure relates to a motion information processing method, apparatus, and computer equipment, the method comprising: obtaining pressure data of a motion subject's motion location in real time; obtaining video information of the motion subject in real time; judging whether the motion subject's current motion satisfies a first force condition based on the pressure data; judging whether the motion subject's current motion satisfies a range condition based on the video information; and recording the motion subject's current motion as a valid motion if the judgment result is that the motion subject's current motion satisfies both the first force condition and the range condition. The present disclosure can comprehensively collect and record the motion information of the motion subject based on sensors and computer vision, and can timely analyze the motion subject's running behavior and judge whether the motion subject's current motion is a valid motion, thereby greatly improving the efficiency of sports training and reducing manual scoring errors in sports competitions.

Description

Technical Field

[0001] The present disclosure relates to the technical field of motion information processing, and in particular to a motion information processing method, apparatus, and computer equipment. Background Art

[0002] my country is currently implementing its national fitness strategy, with a gradual increase in fitness venues and facilities. The public's enthusiasm for improving their health through fitness is growing. To improve the level of scientific fitness guidance services, promote high-quality development of the sports industry, and provide intelligent fitness services for all, the collection of sports data is particularly important in competitions, training, and athlete selection.

[0003] In current sports training and competitions, the processing of athletic information primarily relies on manual scoring. Even when video recording is used, manual interpretation is still necessary. For example, in the sport of boxing, current products and academic research are limited to capturing punching force during the sport. However, match scoring information is manually collected, resulting in a low level of informatization in the training process and a limited selection of athletes. Summary of the Invention

[0004] Based on this, it is necessary to provide a motion information processing method, apparatus, computer equipment, storage medium and computer program product that can... address the above technical issues.

[0005] In a first aspect, the present disclosure provides a motion information processing method. The method comprises:

[0006] Obtain real-time pressure data of the movement subject's movement location;

[0007] Acquiring video information of the moving subject in real time;

[0008] determining, based on the pressure data, whether the current action of the moving subject satisfies a first force condition;

[0009] determining, based on the video information, whether the current action of the moving subject satisfies a range condition;

[0010] If the judgment result is that the current action of the moving subject satisfies the first force condition and the range condition, the current action of the moving subject is recorded as a valid action.

[0011] In one embodiment, the method further comprises:

[0012] Acquiring acceleration data of the movement location of the moving subject in real time;

[0013] determining, based on the acceleration data, whether the current motion of the moving subject satisfies a second force condition;

[0014] When the judgment result is that the current action of the moving subject satisfies the first force condition and the range condition, recording the current action of the moving subject as a valid action includes:

[0015] If the judgment result is that the current action of the moving subject satisfies the first force condition, the second force condition, and the range condition at the same time, the current action of the moving subject is recorded as a valid action.

[0016] In one embodiment, determining whether the current action of the moving subject satisfies a second force condition based on the acceleration data includes:

[0017] Obtaining acceleration components of the moving body on the x-axis, y-axis, and z-axis of a spatial rectangular coordinate system respectively according to the acceleration data;

[0018] Inputting the acceleration component into a preset algorithm model, and the algorithm model outputs a result after calculation;

[0019] When the output result of the algorithm model is true, it is determined that the current action of the moving subject meets the second force condition.

[0020] In one embodiment, determining whether the current action of the moving subject satisfies a range condition based on the video information includes:

[0021] Inputting the video information into a preset machine learning model;

[0022] The machine learning model determines whether a key event currently occurs in the moving subject based on the video information;

[0023] When the output result of the machine learning model is that a key event currently occurs to the moving subject, it is determined that the current action of the moving subject meets the range condition.

[0024] In one embodiment, the machine learning model determines whether a key event has occurred in the moving subject based on the video information, including:

[0025] The machine learning model determines whether a key event currently occurs in the moving subject based on computer vision to obtain a first result;

[0026] The machine learning model marks key parts of the moving subject and extracts the marked points of the moving subject;

[0027] Determining whether a key event currently occurs on the moving subject based on the marked points to obtain a second result;

[0028] constructing a three-dimensional model of the moving subject according to the annotated points of the moving subject, and determining whether a key event has currently occurred in the moving subject according to the three-dimensional model to obtain a third result;

[0029] The machine learning model outputs a final result of whether a key event has occurred in the moving subject based on the first result, the second result, and the third result.

[0030] In one embodiment, determining whether a key event currently occurs in the moving subject based on the three-dimensional model includes:

[0031] Performing a first dyeing on the movement-occurring portion of the moving subject, and performing a second dyeing on the effective range where the movement of the moving subject occurs;

[0032] Whether a key event currently occurs in the moving subject is determined based on whether the first dyed portion currently contacts the second dyed portion.

[0033] In a second aspect, the present disclosure further provides a motion information processing device. The device comprises:

[0034] The pressure module is used to obtain the pressure data of the movement site of the moving subject in real time;

[0035] A video module, used for acquiring video information of the moving subject in real time;

[0036] a first force determination module, configured to determine whether the current action of the moving subject satisfies a first force condition based on the pressure data;

[0037] A range judgment module, configured to judge whether the current action of the moving subject satisfies a range condition based on the video information;

[0038] The valid action module is used to record the current action of the moving subject as a valid action when a judgment result shows that the current action of the moving subject meets the first force condition and the range condition.

[0039] In one embodiment, the apparatus further comprises:

[0040] An acceleration module, used to obtain acceleration data of the movement location of the moving subject in real time;

[0041] a second force determination module, configured to determine whether the current motion of the moving subject satisfies a second force condition based on the acceleration data;

[0042] When the judgment result is that the current action of the moving subject satisfies the first force condition and the range condition, the effective action module records the current action of the moving subject as a valid action, including: when the judgment result is that the current action of the moving subject satisfies the first force condition, the second force condition, and the range condition at the same time, recording the current action of the moving subject as a valid action.

[0043] In one embodiment, the second force determination module includes:

[0044] a component unit, configured to obtain acceleration components of the moving subject on the x-axis, y-axis, and z-axis of a spatial rectangular coordinate system respectively according to the acceleration data;

[0045] an algorithm unit, configured to input the acceleration component into a preset algorithm model, and the algorithm model outputs a result after calculation;

[0046] An algorithm output unit is used to determine whether the current action of the moving subject meets the second force condition when the output result of the algorithm model is true.

[0047] In one embodiment, the range determination module includes:

[0048] A video input unit, configured to input the video information into a preset machine learning model;

[0049] A key event unit, configured for the machine learning model to determine whether a key event has currently occurred in the moving subject based on the video information;

[0050] A model output unit is used to determine whether the current action of the moving subject meets the range condition when the output result of the machine learning model is that a key event has currently occurred on the moving subject.

[0051] In one embodiment, the key event unit includes:

[0052] A first result subunit is configured to determine, using the machine learning model based on computer vision, whether a key event has currently occurred on the moving subject, and obtain a first result;

[0053] A labeling subunit, configured to use the machine learning model to label key parts of the moving subject and extract labeling points of the moving subject;

[0054] A second result subunit is configured to determine whether a key event has currently occurred on the moving subject based on the marked points, and obtain a second result;

[0055] A third result subunit is configured to construct a three-dimensional model of the moving subject based on the annotated points of the moving subject, and determine whether a key event has currently occurred on the moving subject based on the three-dimensional model to obtain a third result;

[0056] The final result subunit is used for the machine learning model to output the final result of whether a key event has occurred in the moving subject at present based on the first result, the second result, and the third result.

[0057] In one embodiment, the third result subunit includes:

[0058] a dyeing component for performing a first dyeing on the movement-occurring portion of the moving subject and a second dyeing on the effective range where the movement of the moving subject occurs;

[0059] The part judgment component is used to judge whether a key event currently occurs in the moving subject according to whether the first dyed part currently contacts the second dyed part.

[0060] In a third aspect, the present disclosure further provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the motion information processing method when executing the computer program.

[0061] In a fourth aspect, the present disclosure further provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of the motion information processing method described above when executed by a processor.

[0062] In a fifth aspect, the present disclosure further provides a computer program product, which includes a computer program that implements the steps of the motion information processing method when executed by a processor.

[0063] The above-mentioned motion information processing method, apparatus, computer device, storage medium and computer program product have at least the following beneficial effects:

[0064] The present invention can comprehensively collect and record the motion information of an athlete based on sensors and computer vision, and can promptly analyze the athlete's running behavior and determine whether the athlete's current action is valid. This can greatly improve the efficiency of sports training and reduce manual scoring errors in sports competitions. In particular, for boxing, the present invention can accurately judge the force and landing point of punches during competitions. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the traditional technology, the following briefly introduces the drawings required for use in the embodiments or the description of the traditional technology. Obviously, the drawings described below are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0066] Figure 1 A diagram illustrating an application environment of a motion information processing method according to an embodiment;

[0067] Figure 2 1 is a flow chart of a motion information processing method according to an embodiment;

[0068] Figure 3 is another flowchart of a motion information processing method according to an embodiment;

[0069] Figure 4 is a schematic diagram of a flow chart for determining whether a second force condition is satisfied based on acceleration data in one embodiment;

[0070] Figure 5 1 is a flow chart of determining whether a range condition is met based on video information in one embodiment;

[0071] Figure 6 A schematic diagram of a process for determining the occurrence of a key event using a machine learning model in one embodiment;

[0072] Figure 7 This is a schematic diagram of video information before annotation;

[0073] Figure 8 Schematic diagram of video information after annotation;

[0074] Figure 9 is a schematic diagram of a process for obtaining a third result based on a three-dimensional model in one embodiment;

[0075] Figure 10 is a schematic diagram of a dyed region of a three-dimensional model in one embodiment;

[0076] Figure 11 is another flowchart of a motion information processing method according to an embodiment;

[0077] Figure 12 A schematic diagram showing a visual display of motion information of a moving subject in one embodiment;

[0078] Figure 13 is a structural block diagram of a motion information processing device in one embodiment;

[0079] Figure 14 is another structural block diagram of a motion information processing device according to an embodiment;

[0080] Figure 15 is a structural block diagram of a second force determination module in one embodiment;

[0081] Figure 16 is a structural block diagram of a range determination module in one embodiment;

[0082] Figure 17 is a structural block diagram of a key event unit in one embodiment;

[0083] Figure 18 is a structural block diagram of the third result subunit in one embodiment;

[0084] Figure 19 FIG. 1 is a block diagram of the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0085] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0086] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art in the art of the present disclosure. The terms used herein in the specification of the present disclosure are only for the purpose of describing specific embodiments and are not intended to limit the present disclosure.

[0087] It should be noted that the terms "first," "second," and the like in the specification and claims of the present disclosure and the accompanying drawings are used to distinguish similar items and are not necessarily used to describe a specific order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than that illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Rather, they are merely examples of apparatuses and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims. The terms "comprise," "include," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, product, or apparatus comprising a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, product, or apparatus. Without further limitation, this does not preclude the presence of additional identical or equivalent elements in the process, method, product, or apparatus comprising the elements. For example, the use of terms such as "first," "second," and the like are intended to indicate names and do not imply any specific order.

[0088] As used herein, the singular forms "a," "an," and "the" may also include the plural forms, unless the context clearly indicates otherwise. It should also be understood that the terms "include," "comprising," "having," and the like specify the presence of stated features, integers, steps, operations, components, parts, or combinations thereof, but do not preclude the presence or addition of one or more other features, integers, steps, operations, components, parts, or combinations thereof. Also, in this specification, the term "and / or" includes any and all combinations of the relevant listed items.

[0089] The motion information processing method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the terminal 102 or the server 104, or it can be placed on the cloud or other network servers. Among them, the terminal 102 can be but is not limited to various personal computers, laptops, smart phones, tablets, Internet of Things devices and portable wearable devices. The server 104 can be implemented as an independent server or a server cluster consisting of multiple servers. The terminal 102 is connected to a video acquisition device and a sensor device. The terminal 102 can process the information collected by the video acquisition device and the sensor device, and display it through a display device. The data of the processing process can be stored locally or in the cloud.

[0090] In some embodiments of the present disclosure, Figure 2 As shown, a motion information processing method is provided, which is applied to Figure 1 The following steps are used as an example to illustrate the terminal in the figure:

[0091] Step S10: Acquire the pressure data of the movement-occurring part of the moving subject in real time.

[0092] Specifically, the subject can be a natural person or an intelligent machine device, and pressure data is collected at the site of the subject's movement. For example, in the sport of boxing, the subject can be a natural person. A soft pressure sensor can be placed at the fist peak of a boxing glove. When the subject strikes an object during boxing, the pressure sensor transmits the pressure data to the terminal via Bluetooth or other wireless communication methods.

[0093] Step S30: Acquire video information of the moving subject in real time.

[0094] Specifically, video capture equipment is installed around the area where the moving subject is operating. In this embodiment, four monocular cameras are deployed around the area to capture video information. The monocular cameras are calibrated to ensure time synchronization between the multiple cameras. Real-time video information is acquired in sync with pressure data acquisition.

[0095] Step S50: determining whether the current action of the moving subject satisfies a first force condition based on the pressure data.

[0096] Specifically, based on the real-time acquired pressure data, a determination is made as to whether the current action of the subject meets a first force condition based on the current pressure data. The current pressure data is compared with a preset threshold value, and if the current pressure data is greater than or equal to the preset threshold value, the current action of the subject is determined to meet the first force condition. In boxing, one factor determining whether a strike is effective is whether the strike force meets the preset threshold value.

[0097] Step S70: Determine whether the current action of the moving subject meets the range condition based on the video information.

[0098] Specifically, based on the collected video information, a judgment is made according to the current frame, or based on the current frame and the preset number of frames closest to the current time. The behavioral actions of the moving subject are identified, and whether the current action of the moving subject meets the range condition is judged. Taking boxing as an example, another factor determining whether the striking action is effective is whether the striking foothold is within the effective range. In single-player training, the effective range may be the range of the practice pile; in two-player confrontation, the effective range may be the front of the opponent's body. The effective range can be set according to the properties of the sport and the rules of the game. This embodiment uses video information to determine whether the striking foothold of the moving subject falls within the effective range, and then determines whether the current action meets the range condition.

[0099] Step S90: When the judgment result is that the current action of the moving subject satisfies the first force condition and the range condition, the current action of the moving subject is recorded as a valid action.

[0100] Specifically, the current action of the moving subject is determined to be synchronous based on the pressure data and video information. If the current action satisfies the first force condition and the range condition, the current action can be determined to be a valid action, and the valid action can be recorded or marked. In this embodiment, the acquired pressure data, video information, and the judgment results based on the pressure data and video information are all stored locally or in the cloud. This facilitates the subsequent export of data for analysis and training of the moving subject's movements, and also facilitates scoring based on the recorded valid actions, reducing human errors during competitions.

[0101] The above-mentioned motion information processing method can comprehensively collect and record the motion information of the athlete, and can timely analyze the athlete's running behavior and determine whether the athlete's current action is valid. This can greatly improve the efficiency of sports training and reduce manual scoring errors in sports competitions. In particular, for boxing, this method can accurately judge the force and landing point of punches during competitions.

[0102] In some embodiments of the present disclosure, Figure 3 As shown, the method further includes:

[0103] Step S20: Acquire acceleration data of the movement location of the moving subject in real time.

[0104] Specifically, taking boxing as an example, the athlete can be a natural person. An acceleration sensor can be installed on the athlete's wrist. When the athlete performs boxing movements and the hand moves, the acceleration sensor transmits acceleration data to the terminal via Bluetooth or other wireless communication methods.

[0105] Step S60: determining whether the current action of the moving subject satisfies a second force condition based on the acceleration data.

[0106] Specifically, based on the acceleration data acquired in real time, it is determined whether the current action of the moving subject meets the second force condition according to the current acceleration data.

[0107] When the judgment result is that the current action of the moving subject satisfies the first force condition and the range condition, recording the current action of the moving subject as a valid action includes:

[0108] Step S92: When the judgment result is that the current action of the moving subject satisfies the first force condition, the second force condition, and the range condition at the same time, the current action of the moving subject is recorded as a valid action.

[0109] Specifically, the current action of the moving subject is judged to be performed synchronously based on the pressure data, acceleration data, and video information. When the current action is judged to meet the first force condition based on the pressure data, and the current action is judged to meet the second force condition based on the acceleration data, and the current action meets the range condition, the current action can be determined to be a valid action, and the valid action can be recorded or marked.

[0110] This embodiment improves the accuracy of determining effective actions by synchronously analyzing and judging the acquired pressure data, acceleration data, and video information, and comprehensively determining effective actions.

[0111] In some embodiments of the present disclosure, Figure 4As shown, the above step S60 includes:

[0112] Step S62: Obtain the acceleration components of the moving body on the x-axis, y-axis, and z-axis of the spatial rectangular coordinate system according to the acceleration data.

[0113] Step S64: inputting the acceleration component into a preset algorithm model, and the algorithm model outputs a result after calculation.

[0114] Specifically, based on the acceleration data acquired in real time, the acceleration components of the moving subject on the x-axis, y-axis, and z-axis of the spatial rectangular coordinate system are obtained, and the acceleration components in the three directions are input into the preset algorithm model. In this embodiment, a large amount of temporal correlation data of acceleration and force values can be obtained by collecting the punching acceleration and load force of professional athletes or ordinary athletes. The algorithm model is obtained by fitting the data using the least squares method. The algorithm model can also be obtained by other calculation methods. The algorithm model is used to calculate the strength of the current action of the moving subject based on the acceleration component, and then compare the calculated strength with the preset threshold. When the calculated strength is greater than or equal to the preset threshold, the algorithm model outputs a true result. The preset threshold in this embodiment can be the same as the preset threshold for pressure data, or different thresholds can be set according to the performance of the sensor.

[0115] Step S66: When the output result of the algorithm model is true, determine that the current action of the moving subject meets the second force condition.

[0116] Specifically, when the output result of the algorithm model is true, it can be determined that the current action of the moving subject meets the second force condition.

[0117] This embodiment obtains acceleration data, calculates the strength of the current action of the moving subject based on the acceleration component, and then judges whether the current action of the moving subject meets the second strength condition based on the preset threshold set for the acceleration data, and verifies it with the first strength condition, thereby improving the accuracy of the strength judgment of the current action.

[0118] In some embodiments of the present disclosure, Figure 5 As shown, the above step S70 includes:

[0119] Step S72: Input the video information into a preset machine learning model.

[0120] Specifically, the collected video information is synchronously input into a preset machine learning model. The machine learning model in this embodiment is a well-trained model. Taking boxing as an example, the machine learning model is trained by studying a large number of boxing training videos and boxing match videos.

[0121] Step S74: The machine learning model determines whether a key event has occurred in the moving subject based on the video information.

[0122] Specifically, the machine learning model analyzes and processes video information to determine whether a key event has occurred in the subject. Key events are selected based on the characteristics of the movement. For example, in boxing, key events might include a hit to the chest, head, or ribs. By identifying key events, the model determines whether the punch's landing point meets the range conditions.

[0123] Step S76: When the output result of the machine learning model is that a key event has currently occurred in the moving subject, determine whether the current action of the moving subject meets the range condition.

[0124] Specifically, the machine learning model outputs the result of whether a key event has occurred at present in the moving subject. The output result of the machine learning model is that when a key event has occurred at present in the moving subject, it is determined that the current action of the moving subject meets the range condition.

[0125] In some embodiments of the present disclosure, Figure 6 As shown, the above step S74 includes:

[0126] Step S7402: The machine learning model determines whether a key event has occurred in the moving subject based on computer vision to obtain a first result.

[0127] Specifically, the machine learning model, based on computer vision, directly determines whether a key event has occurred in the moving subject by comparing features of the video information, thereby obtaining a first result. If a key event has occurred in the moving subject, the first result is true; otherwise, the first result is false.

[0128] Step S7404: The machine learning model marks the key parts of the moving subject and extracts the marked points of the moving subject.

[0129] Specifically, the machine learning model processes the video information, extracts the key parts of the moving subject in the video information, and annotates them. It extracts the annotation points of the moving subject. Taking boxing as an example, the boxer’s joints can be annotated, as well as the head and hands. Figure 7 The video information before marking is shown. Figure 8 The video information after marking.

[0130] Step S7406: Determine whether a key event has currently occurred in the moving subject based on the marked points to obtain a second result.

[0131] Specifically, based on the annotated video information, the annotated points are calculated and processed to determine whether a key event has occurred in the moving subject, thereby obtaining a second result. If a key event has occurred in the moving subject, the second result is true; otherwise, the second result is false.

[0132] Step S7408: constructing a three-dimensional model of the moving subject according to the marked points of the moving subject, and determining whether a key event has currently occurred in the moving subject according to the three-dimensional model to obtain a third result.

[0133] Specifically, based on the annotated video information, the annotated points are extracted to construct a three-dimensional model of the moving subject. Based on the constructed three-dimensional model of the moving subject, it is determined whether a key event has currently occurred with the moving subject, thereby obtaining a third result. If it is determined that a key event has currently occurred with the moving subject, the third result is true; otherwise, the third result is false.

[0134] Step S7410: The machine learning model outputs a final result of whether a key event has occurred in the moving subject based on the first result, the second result, and the third result.

[0135] Specifically, the first, second, and third results are all obtained based on time-synchronized video information. Based on these results, a final result can be determined by performing AND / OR logic calculations, or by using a weighted calculation, to determine whether a key event has occurred in the subject. The machine learning model then outputs the final result.

[0136] The machine learning model of this embodiment obtains the final result through multiple parallel judgment branches, which improves the accuracy of judging key events and avoids the omission of key events.

[0137] In some embodiments of the present disclosure, Figure 9 As shown, the above step S7408 includes:

[0138] Step A10: performing a first dyeing on the portion where the movement of the moving subject occurs, and performing a second dyeing on the effective range where the movement of the moving subject occurs.

[0139] Specifically, based on the constructed three-dimensional model, the action location and effective range of the motion subject are distinguished by coloring. Taking boxing as an example, based on the constructed three-dimensional model of the boxer, the boxer's hands are first colored, for example, red; and the effective striking range of the front side of the boxer's body is second colored, for example, green. Figure 10As shown in the figure, the shaded area represents the first dyed area, and the shaded area represents the second dyed area. Furthermore, the colors of the first dyed area and the second dyed area are not limited to red and green, and can be other colors. The greater the color difference between the two, the more helpful it is for subsequent judgment of whether a key event has occurred in the moving subject.

[0140] Step A20: determining whether a key event currently occurs in the moving subject based on whether the first dyed portion currently contacts the second dyed portion.

[0141] Specifically, based on the dyed moving subject, by judging whether the first dyed part contacts the second dyed part, and the specific contact position, it can be determined whether a key event currently occurs in the moving subject.

[0142] This embodiment constructs a three-dimensional model of the moving subject based on video information, performs a first dyeing on the part where the moving subject's action occurs, and performs a second dyeing on the effective range where the moving subject's action occurs, thereby performing a more intuitive visualization of the movement and facilitating the capture of key events occurring in the moving subject.

[0143] This embodiment trains the machine learning model by learning a large number of boxing training videos and boxing match videos to obtain a mature machine learning model. The machine learning model can output whether a key event has occurred at the current time of the moving subject based on real-time video information, and then judge whether the current action of the moving subject meets the range conditions, thereby improving the accuracy of the effective range judgment.

[0144] In some embodiments of the present disclosure, the method can be applied to, but not limited to, physical confrontation sports such as boxing, free fighting, taekwondo, Muay Thai, karate, and fighting. Figure 11 The method specifically includes:

[0145] The sports subject includes two opposing sides. For example, the red and blue players are used as examples. Pressure sensors are set at the fist peak positions of the red and blue players' boxing gloves to obtain pressure data and obtain the punching force N of the sports subject. nt , n∈{rl,rr,bl,br}. Where t represents time, rl represents the left hand of the red player, rr represents the right hand of the red player, bl represents the left hand of the blue player, and br represents the right hand of the blue player.

[0146] The acceleration data is obtained by setting the acceleration sensors on the wrists of the red and blue athletes to obtain the acceleration A of the punching subject. nt , n∈{rl,rr,bl,br}. According to A ntObtain its acceleration Axt, Ayt, Azt on the x-axis, y-axis, and z-axis of the spatial rectangular coordinate system. nt The corresponding Axt, Ayt, Azt input preset algorithm model F nt (x, y, z). Algorithm model F nt (x, y, z) calculates the strength of the current movement of the moving subject, and then compares the calculated strength with the preset threshold. If the calculated strength is greater than or equal to the preset threshold, the algorithm model F nt (x, y, z) outputs true.

[0147] By setting up monocular cameras around the boxing ring, we can obtain synchronized video streams V1, V2, V3, and V4 of multiple perspectives of boxing. Input V1, V2, V3, and V4 into the trained machine learning model to obtain the event K that occurred at time Tvt. vt Where v∈{r,b}, r represents the red player, b represents the blue player; the key event set K = {hit chest, hit head, hit ribs...}.

[0148] At time t, at N nt ≥N min In the case of F nt (x, y, z) output is true, and K vt ∈K, then according to N nt n and K vt The v in the formula can be used to determine whether the strike of one or both players at the current moment is a valid strike, and the score or points that the boxer deserves can be calculated based on n and v.

[0149] In the above steps, including time t, striking force N nt , acceleration data A nt Event K vt The information will be stored locally or in the cloud via storage media. After the boxing round, the round score and points can be obtained from the above information. After the game, the game score and points, as well as the technical analysis report of the entire game can be obtained. For example Figure 12 As shown in Figure 2, the data collected from a boxer during one round.

[0150] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of 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 these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0151] Based on the same inventive concept, embodiments of the present disclosure also provide a motion information processing device for implementing the aforementioned motion information processing method. The solution provided by this device is similar to the solution described in the aforementioned method. Therefore, the specific limitations in one or more of the following embodiments of the motion information processing device can be found in the above-mentioned limitations on the motion information processing method and will not be further elaborated here.

[0152] The device may include a system (including a distributed system), software (application), module, component, server, client, etc. that uses the method described in the embodiments of this specification and is combined with the necessary implementation hardware. Based on the same innovative concept, the device in one or more embodiments provided by the embodiments of the present disclosure is as described in the following embodiments. Since the implementation scheme and method for solving the problem of the device are similar, the implementation of the specific device in the embodiments of this specification can refer to the implementation of the aforementioned method, and the repetitions will not be repeated. As used below, the term "unit" or "module" can implement a combination of software and / or hardware for a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceived.

[0153] In some embodiments of the present disclosure, Figure 13 As shown, a motion information processing device is provided. The device may be the aforementioned terminal, or a server, or a module, component, device, unit, etc. integrated into the terminal. The device Z00 may include:

[0154] Pressure module Z10, used to obtain real-time pressure data of the movement site of the moving subject;

[0155] Video module Z20, used for acquiring video information of the moving subject in real time;

[0156] a first force determination module Z30, configured to determine whether the current movement of the moving subject satisfies a first force condition based on the pressure data;

[0157] a range determination module Z40, configured to determine whether the current motion of the moving subject satisfies a range condition based on the video information;

[0158] The valid action module Z50 is configured to record the current action of the moving subject as a valid action if the judgment result is that the current action of the moving subject satisfies the first force condition and the range condition.

[0159] In some embodiments of the present disclosure, Figure 14 As shown, the device Z00 further includes:

[0160] The acceleration module Z60 is used to obtain acceleration data of the movement location of the moving subject in real time;

[0161] A second force determination module Z70 is configured to determine whether the current motion of the moving subject satisfies a second force condition based on the acceleration data;

[0162] When the valid action module Z50 determines that the current action of the moving subject satisfies the first force condition and the range condition, recording the current action of the moving subject as a valid action includes:

[0163] If the judgment result is that the current action of the moving subject satisfies the first force condition, the second force condition, and the range condition at the same time, the current action of the moving subject is recorded as a valid action.

[0164] In some embodiments of the present disclosure, Figure 15 As shown, the second force judgment module Z70 includes:

[0165] Component unit Z72, used to obtain the acceleration components of the moving body on the x-axis, y-axis, and z-axis of the spatial rectangular coordinate system according to the acceleration data;

[0166] an algorithm unit Z74, configured to input the acceleration component into a preset algorithm model, and the algorithm model outputs a result after calculation;

[0167] The algorithm output unit Z76 is used to determine whether the current action of the moving body meets the second force condition when the output result of the algorithm model is true.

[0168] In some embodiments of the present disclosure, Figure 16 As shown, the range judgment module Z40 includes:

[0169] a video input unit Z42, configured to input the video information into a preset machine learning model;

[0170] A key event unit Z44 is used for the machine learning model to determine whether a key event has currently occurred in the moving subject based on the video information;

[0171] The model output unit Z46 is used to determine whether the current action of the moving subject meets the range condition when the output result of the machine learning model is that a key event has currently occurred on the moving subject.

[0172] In some embodiments of the present disclosure, Figure 17 As shown, the key event unit Z44 includes:

[0173] A first result subunit Z4402 is configured for the machine learning model to determine, based on computer vision, whether a key event has currently occurred on the moving subject, and obtain a first result;

[0174] Annotation subunit Z4404 is used for annotating key parts of the moving subject using the machine learning model and extracting annotated points of the moving subject;

[0175] A second result subunit Z4406 is configured to determine whether a key event has currently occurred on the moving subject based on the marked points, and obtain a second result;

[0176] A third result subunit Z4408 is configured to construct a three-dimensional model of the moving subject based on the annotated points of the moving subject, and determine whether a key event has currently occurred on the moving subject based on the three-dimensional model to obtain a third result;

[0177] The final result subunit Z4410 is used for the machine learning model to output the final result of whether a key event has occurred in the moving subject at present based on the first result, the second result, and the third result.

[0178] In some embodiments of the present disclosure, Figure 18 As shown, the third result subunit Z4408 includes:

[0179] The dyeing component A10 is used to perform a first dyeing on the movement-occurring part of the moving subject and a second dyeing on the effective range where the movement of the moving subject occurs;

[0180] The position determination component A20 is configured to determine whether a key event has occurred in the moving subject according to whether the first dyeing position is currently in contact with the second dyeing position.

[0181] Each module in the above-mentioned motion information processing device can be implemented in whole or in part through software, hardware, or a combination thereof. Each of the above-mentioned modules can be embedded in or independent of the processor in the computer device in hardware form, or can be stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to each of the above modules. It should be noted that the division of modules in the embodiments of the present disclosure is schematic and is only a logical functional division. In actual implementation, other division methods may be used.

[0182] Based on the above-mentioned embodiment description of the motion information processing method, in another embodiment provided by the present disclosure, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 19 As shown. The computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a motion information processing method is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad provided on the computer device housing, or an external keyboard, touchpad or mouse.

[0183] Those skilled in the art will understand that the structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0184] Based on the description of the embodiment of the motion information processing method above, in another embodiment provided in the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0185] Based on the description of the embodiment of the motion information processing method above, in another embodiment provided by the present disclosure, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0186] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties.

[0187] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processor involved in the various embodiments provided herein may be, but are not limited to, a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, and the like.

[0188] Throughout this specification, references to terms such as "some embodiments," "other embodiments," and "desired embodiments" indicate that a particular feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. Although these terms are used interchangeably throughout this specification, they do not necessarily refer to the same embodiment or example.

[0189] It is understood that the various embodiments of the above method in this specification are described in a progressive manner. The same / similar parts between the various embodiments can be referred to in detail. Each embodiment focuses on the differences from other embodiments. For related parts, please refer to the description of other method embodiments.

[0190] The technical features of the above-mentioned embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features of the above-mentioned embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0191] The above-described embodiments merely represent several implementation methods of the present disclosure. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the patent application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present disclosure, all of which fall within the scope of protection of the present disclosure. Therefore, the scope of protection of the patent disclosed herein shall be determined by the appended claims.

Claims

1. A motion information processing method, characterized in that: The method comprises: Obtain real-time pressure data of the movement subject's movement location; Acquiring video information of the moving subject in real time; determining, based on the pressure data, whether the current action of the moving subject satisfies a first force condition; determining, based on the video information, whether the current action of the moving subject satisfies a range condition; If the result of the judgment is that the current action of the moving subject satisfies the first force condition and the range condition, recording the current action of the moving subject as a valid action; The determining, based on the video information, whether the current action of the moving subject satisfies a range condition includes: Inputting the video information into a preset machine learning model; The machine learning model determines whether a key event currently occurs in the moving subject based on computer vision to obtain a first result; The machine learning model marks key parts of the moving subject and extracts the marked points of the moving subject; Determining whether a key event currently occurs on the moving subject based on the marked points to obtain a second result; constructing a three-dimensional model of the moving subject according to the annotated points of the moving subject, and determining whether a key event has currently occurred in the moving subject according to the three-dimensional model to obtain a third result; The machine learning model outputs a final result of whether a key event currently occurs to the moving subject based on the first result, the second result, and the third result; When the output result of the machine learning model is that a key event currently occurs to the moving subject, it is determined that the current action of the moving subject meets the range condition.

2. The method according to claim 1, characterized in that The method further comprises: Acquiring acceleration data of the movement location of the moving subject in real time; determining, based on the acceleration data, whether the current motion of the moving subject satisfies a second force condition; When the judgment result is that the current action of the moving subject satisfies the first force condition and the range condition, recording the current action of the moving subject as a valid action includes: If the judgment result is that the current action of the moving subject satisfies the first force condition, the second force condition, and the range condition at the same time, the current action of the moving subject is recorded as a valid action.

3. The method according to claim 2, characterized in that The determining, based on the acceleration data, whether the current motion of the moving subject satisfies the second force condition includes: Obtaining acceleration components of the moving body on the x-axis, y-axis, and z-axis of a spatial rectangular coordinate system respectively according to the acceleration data; Inputting the acceleration component into a preset algorithm model, and the algorithm model outputs a result after calculation; When the output result of the algorithm model is true, it is determined that the current action of the moving subject meets the second force condition.

4. The method according to claim 1, wherein The determining, based on the three-dimensional model, whether a key event currently occurs on the moving subject comprises: Performing a first dyeing on the movement-occurring portion of the moving subject, and performing a second dyeing on the effective range where the movement of the moving subject occurs; Whether a key event currently occurs in the moving subject is determined based on whether the first dyed portion currently contacts the second dyed portion.

5. A motion information processing device, characterized in that: The device comprises: The pressure module is used to obtain the pressure data of the movement site of the moving subject in real time; A video module, used for acquiring video information of the moving subject in real time; a force determination module, configured to determine whether the current action of the moving subject satisfies a first force condition based on the pressure data; A range judgment module, configured to judge whether the current action of the moving subject satisfies a range condition based on the video information; a valid action module, configured to record the current action of the moving subject as a valid action if a judgment result shows that the current action of the moving subject satisfies the first force condition and the range condition; Wherein, the range judgment module includes: A video input unit, configured to input the video information into a preset machine learning model; Key incident units include: A first result subunit is configured to determine, using the machine learning model based on computer vision, whether a key event has currently occurred on the moving subject, and obtain a first result; A labeling subunit, configured to use the machine learning model to label key parts of the moving subject and extract labeling points of the moving subject; A second result subunit is configured to determine whether a key event has currently occurred on the moving subject based on the marked points, and obtain a second result; A third result subunit is configured to construct a three-dimensional model of the moving subject based on the annotated points of the moving subject, and determine whether a key event has currently occurred on the moving subject based on the three-dimensional model to obtain a third result; A final result subunit, configured for the machine learning model to output a final result of whether a key event has currently occurred on the moving subject based on the first result, the second result, and the third result; A model output unit is used to determine whether the current action of the moving subject meets the range condition when the output result of the machine learning model is that a key event has currently occurred on the moving subject.

6. The device according to claim 5, characterized in that The device further comprises: An acceleration module, used to obtain acceleration data of the movement location of the moving subject in real time; a second force determination module, configured to determine whether the current motion of the moving subject satisfies a second force condition based on the acceleration data; When the valid action module determines that the current action of the moving subject satisfies the first force condition and the range condition, recording the current action of the moving subject as a valid action includes: If the judgment result is that the current action of the moving subject satisfies the first force condition, the second force condition, and the range condition at the same time, the current action of the moving subject is recorded as a valid action.

7. The device according to claim 6, characterized in that The second strength judgment module includes: a component unit, configured to obtain acceleration components of the moving subject on the x-axis, y-axis, and z-axis of a spatial rectangular coordinate system respectively according to the acceleration data; an algorithm unit, configured to input the acceleration component into a preset algorithm model, and the algorithm model outputs a result after calculation; An algorithm output unit is used to determine whether the current action of the moving subject meets the second force condition when the output result of the algorithm model is true.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 4 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 4 are implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 4 are implemented.

Images