Motion capture method and device based on physical training and storage medium

Abstract

The invention provides a motion capture method and device based on physical training and a storage medium. The method comprises the steps that athletes are numbered; collecting action data, analyzing whether the action data is abnormal, if so, performing early warning, otherwise, entering the next step; action quality parameters are collected, and action quality is analyzed; training environment parameters are collected, the environment state is analyzed, and early warning is conducted if the environment is unqualified. According to the invention, abnormity can be early warned in time, the motion quality can be accurately evaluated, and the training effect and safety can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of sports training, and more specifically, to a motion capture method, device and storage medium based on sports training. Background Art

[0002] In the field of sports training, traditional training methods mainly rely on the coach's observation and experience to guide athletes. This subjective evaluation method often fails to accurately capture subtle changes in athletes' movements and cannot detect potential technical problems in a timely manner. With the development of science and technology, motion capture technology has begun to be applied to sports training, collecting athletes' motion data through sensors and other equipment to provide coaches with a more intuitive basis for analysis. However, existing motion capture systems focus more on the surface morphology analysis of movements, lack in-depth evaluation of movement quality, and insufficient consideration of the training environment, which cannot fully guarantee the training effect and the safety of athletes.

[0003] In the process of implementing the embodiments of the present invention, the inventors found that there are at least the following problems or defects in the prior art: First, the detection of movement abnormalities is not accurate enough and cannot effectively distinguish the boundary between normal movements and abnormal movements; second, there is a lack of quantitative standards for the evaluation of movement quality, making it difficult to objectively compare the movement quality of different athletes; third, the impact of the training environment on athlete performance is ignored, and environmental factors are not included in the comprehensive evaluation system. Summary of the invention

[0004] The invention provides a motion capture method, equipment and storage medium based on sports training.

[0005] In a first aspect of the present invention, a motion capture method based on sports training is provided, comprising: Step S1, numbering all athletes participating in sports training, the numbers are: 1, 2, ..., n; Step S2, collecting the changes of the motion data of all athletes over time, and analyzing whether the athlete's motion is abnormal according to the changes of the real-time motion data of each athlete over time; Step S3: If the athlete's action is abnormal or potentially abnormal, an early warning is immediately issued; if the athlete's action is not abnormal or potentially abnormal, the process proceeds to step S4; Step S4, collecting the data of the variation of the movement quality parameters of all athletes over time, and analyzing the movement quality state of each athlete according to the data of the variation of the movement quality parameters of each athlete over time; Step S5: collect the real-time parameters of the training environment of all athletes, and analyze the training environment status of the athletes according to the real-time parameters of the training environment of the athletes. If the training environment of the athletes does not meet the requirements, an early warning is immediately issued.

[0006] Furthermore, the specific method in step S2 includes: Obtain the real-time movement speed and movement range of the ith athlete; compare the real-time movement speed and movement range of the ith athlete with the set standard threshold. If any movement parameter exceeds the standard threshold range, it means that the movement of the ith athlete is abnormal, and an early warning is issued immediately. Otherwise, further analyze whether there is potential abnormality in the movement of the ith athlete.

[0007] Furthermore, the specific process of further analyzing whether the action of the i-th athlete has potential abnormalities includes: Get the i-th athlete in the set time period The internal action speed changes over time data, construct the action speed change function of the i-th athlete over time ; in, is the amplitude, is the angular frequency, is the initial phase, is the time variable within the set time period; Get the i-th athlete in the set time period The internal movement amplitude changes over time data, and the movement amplitude change function of the i-th athlete is constructed ; in, is the amplitude, is the angular frequency, is the initial phase, is the time variable within the set time period; The potential abnormal coefficient of the action of the i-th athlete is calculated by the following formula : In the formula, For function right The derivative of For function right The derivative of To find the maximum value of a function, To find the minimum function, is the standard reference value of the action speed, It is the standard reference value of the range of motion; The potential abnormal coefficient of the action of the i-th athlete The preset threshold value of the potential abnormal coefficient of the action of the i-th athlete For comparison, if the potential abnormal coefficient of the action of the i-th athlete is Greater than or equal to the preset threshold of the potential abnormal coefficient of the action of the i-th athlete , it means that the action of the i-th athlete is potentially abnormal, and an early warning is issued immediately. Otherwise, go to step S4.

[0008] Furthermore, the specific method of step S4 includes: Get the i-th athlete's The quality parameters of the action are within the set time period The data changes over time in the same box, and constructs the i-th athlete’s The function of the quality parameter of each action changing with time; The action quality coefficient of the i-th athlete is calculated by the following formula : ; In the formula, is the function of the j-th action quality parameter of the i-th athlete changing with time, is the standard function of the j-th action quality parameter of the ith athlete changing with time, is the weight coefficient corresponding to the j-th action quality parameter, is the time variable within the set time period, To set the initial detection time point within the time period, To end the detection time point within the set time period; according to the action quality coefficient of the i-th athlete Determine the quality level of the i-th athlete's movements.

[0009] Furthermore, the action quality coefficient of the i-th athlete The specific process of judging the action quality level of the i-th athlete includes: Get the number of athletes in the same event as the i-th athlete , calculate the difference coefficient of the ith athlete according to the following formula: : The i-th athlete's difference coefficient Difference coefficient with the i-th athlete The preset threshold is compared. If the difference coefficient of the i-th athlete Greater than or equal to the i-th athlete's difference coefficient The preset threshold indicates that the action quality level of the i-th athlete is lower than the expected level, and it is recommended to strengthen targeted training, among which, is the movement quality coefficient of the zth athlete in the same event as the ith athlete.

[0010] Furthermore, the specific method of step S5 includes: Obtain various parameter values ​​of the athlete's training environment; Compare the values ​​of various environmental parameters with the set appropriate thresholds respectively: if there are environmental parameter items that exceed the set appropriate threshold range, the athlete's training environment is judged to be unqualified and an early warning is issued immediately; otherwise, the training environment status is judged as a whole based on the overall deviation of the values ​​of various environmental parameters.

[0011] Furthermore, the method for making an overall judgment on the training environment state according to the overall deviation of each environmental parameter value includes: calculating the environmental coefficient of the athlete's training environment by the following formula: : ; in, is the number of environmental parameters detected, is the index of the environment parameter item and , For the The detected value of the environmental parameter, For the Suitable standard values ​​of environmental parameters, For the Suitable reference values ​​for environmental parameters, For the Correlation coefficient of item parameters; According to the environmental coefficient of the athlete's training environment Analyze the status of the training environment.

[0012] Furthermore, the environmental coefficient according to the athlete's training environment Methods for analyzing the state of the training environment include: The environmental factor of the athlete training environment Environmental coefficient thresholds for athlete training environments By comparison, if the environmental coefficient of the athlete's training environment Greater than or equal to the environmental coefficient threshold of the athlete's training environment , then the overall training environment of the athlete is unqualified and an early warning is issued immediately.

[0013] In a second aspect of the present invention, an electronic device is provided, comprising: at least one processor, a memory and an input-output unit; wherein the memory is used to store a computer program, and the processor is used to call the computer program stored in the memory to execute any one of the methods described in the first aspect.

[0014] In a third aspect of the present invention, a computer-readable storage medium is provided, which includes instructions, and when the instructions are executed on a computer, the computer is caused to execute the method according to any one of the first aspects.

[0015] The above-mentioned embodiments of the present invention have at least the following beneficial effects: the method can monitor the athlete's action data in real time, and by comparing with the standard threshold, quickly and accurately identify abnormal situations in the athlete's actions, thereby issuing a warning in time to avoid injuries to the athlete due to wrong actions. At the same time, the method can also quantitatively evaluate the athlete's action quality, by constructing a function of the change of action quality parameters over time, calculating the action quality coefficient, and then judging the athlete's action quality level, providing a scientific training guidance basis for the coach, and helping to improve the athlete's technical level in a targeted manner.

[0016] In addition, this method can also comprehensively consider various parameters of the training environment, and through the calculation and analysis of environmental coefficients, determine whether the training environment meets the requirements, ensure that athletes train in a suitable environment, and further improve training effects and safety. This comprehensive monitoring and evaluation system provides more scientific and accurate technical support for sports training, and helps promote the innovation and development of sports training methods. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood by reading the detailed description below with reference to the accompanying drawings. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, in which: Figure 1 A schematic flow chart of a motion capture method based on sports training provided in accordance with an embodiment of the present invention. DETAILED DESCRIPTION

[0018] The principles and spirit of the present invention will be described below with reference to several exemplary embodiments. It should be understood that these embodiments are provided only to enable those skilled in the art to better understand and implement the present invention, and are not intended to limit the scope of the present invention in any way. On the contrary, these embodiments are provided to make the present invention more thorough and complete, and to fully convey the scope of the present invention to those skilled in the art.

[0019] Those skilled in the art know that the embodiments of the present invention can be implemented as a system, device, apparatus, method or computer program product. Therefore, the present invention can be specifically implemented in the following forms, namely: complete hardware, complete software (including firmware, resident software, microcode, etc.), or a combination of hardware and software.

[0020] It should be noted that any number of elements in the drawings is for illustration rather than limitation, and any naming is only for distinction and does not have any limiting meaning.

[0021] Reference below Figure 1 , Figure 1 Schematic diagram of a flow chart of a motion capture method based on sports training provided by an embodiment of the present invention. Figure 1 As shown, a motion capture method 100 based on sports training includes: Step S1, numbering all athletes participating in sports training, the numbers are: 1, 2, ..., n; Step S2, collecting the changes of the motion data of all athletes over time, and analyzing whether the athlete's motion is abnormal according to the changes of the real-time motion data of each athlete over time; Step S3: If the athlete's action is abnormal or potentially abnormal, an early warning is immediately issued; if the athlete's action is not abnormal or potentially abnormal, the process proceeds to step S4; Step S4, collecting the data of the variation of the movement quality parameters of all athletes over time, and analyzing the movement quality state of each athlete according to the data of the variation of the movement quality parameters of each athlete over time; Step S5: collect the real-time parameters of the training environment of all athletes, and analyze the training environment status of the athletes according to the real-time parameters of the training environment of the athletes. If the training environment of the athletes does not meet the requirements, an early warning is immediately issued.

[0022] It should be noted that all athletes participating in sports training are numbered in the order of 1, 2, ..., n. This process is to facilitate the individual tracking and analysis of the action data of each athlete. Numbering is an identification method used to distinguish different athletes and ensure the accuracy and traceability of data. Through numbering, the collected action data can be matched with a specific athlete, which facilitates subsequent data processing and analysis.

[0023] Specifically, the numbering can be set according to the name, position or other characteristics of the athlete. For example, in a football team, the players can be numbered according to their positions, such as forwards 1 to 3, midfielders 4 to 8, defenders 9 to 12, and goalkeepers 13. This numbering method not only helps to quickly identify athletes, but also allows for classification and analysis of action data based on position characteristics. The numbering should ensure that each athlete has a unique identification to avoid duplication and confusion.

[0024] Preferably, the number can be connected to the athlete's personal information database, so that when collecting action data, the data can be directly associated with the athlete's personal file. For example, when the sensor collects the action data of an athlete, the data can be automatically stored in the athlete's personal training record through the number, including detailed information such as date, time, and training items. In addition, the number can also be used for post-training data analysis, such as counting the training time and number of completed actions of each athlete, providing a basis for formulating personalized training plans.

[0025] More specifically, the changes in the motion data of all athletes over time are collected, and the athletes' motions are analyzed to see if they are abnormal based on the changes in the real-time motion data of each athlete over time. The motion data here includes various body movements of athletes during training, such as speed, amplitude, angle, etc. The collection of motion data can be achieved through a variety of sensors, such as accelerometers, gyroscopes, etc. These sensors can be installed on athletes' clothing or sports equipment to capture athletes' motion information in real time.

[0026] Furthermore, the frequency of motion data collection can be set according to different training items. For example, in track and field training, the collection frequency can be set to 10 to 100 times per second to capture the fast movements of athletes in sprinting, long jump and other events. In gymnastics training, the collection frequency can be appropriately reduced, such as 5 to 20 times per second, to adapt to the rhythm changes of athletes when completing complex movements. The analysis of motion data can determine whether there is an abnormality by setting a threshold. For example, if the athlete's movement speed exceeds the set normal range, or the movement amplitude deviates greatly from the standard movement, it can be considered that the movement is abnormal.

[0027] Preferably, the analysis of motion data can be combined with a machine learning algorithm to establish a motion model by learning a large amount of normal motion data. When there is a significant difference between the motion data collected in real time and the model, it can be judged as abnormal. In addition, an expert system can be introduced, and coaches or sports scientists can evaluate the motion data based on experience to provide more accurate abnormal judgments. For example, for some difficult movements, such as somersaults in gymnastics, the expert system can be used to conduct a comprehensive evaluation of the coherence and stability of the movement, and potential technical problems can be discovered in a timely manner.

[0028] Furthermore, if an athlete's movements are abnormal or potentially abnormal, an early warning is issued immediately. Early warning is a timely feedback mechanism used to alert coaches or athletes to possible problems. Early warning can be carried out in a variety of ways, such as sound alarms, visual signals or vibration prompts. The purpose of early warning is to intervene in time at the early stage of the problem to avoid injuries to athletes due to incorrect movements, and also provide timely feedback to coaches so that they can adjust training plans.

[0029] Specifically, the triggering conditions of the early warning can be set according to the degree of abnormal movement. For example, if the athlete's movement speed exceeds 20% of the normal range, or the movement amplitude deviation exceeds 10%, the early warning will be triggered immediately. The level of the early warning can also be divided according to the severity of the abnormality, such as slight abnormality, moderate abnormality and severe abnormality, and different levels of early warning can use different prompt methods. For example, a slight abnormality can send a notification through a mobile phone application, a moderate abnormality can send a sound alarm through the speaker of the training venue, and a severe abnormality can send a vibration prompt through the coach's handheld device.

[0030] More specifically, the early warning system can be integrated with the training monitoring system to achieve automated training adjustments. For example, when the early warning system detects abnormal movements of athletes, the parameters of the training equipment can be automatically adjusted, such as reducing the difficulty of the training equipment, or adjusting the training rhythm to give athletes more rest time.

[0031] Furthermore, the early warning system can also record the time, location and specific circumstances of the abnormality, providing data support for subsequent analysis and improvement. For example, by analyzing the early warning records, it can be found that certain specific actions or training stages are prone to abnormalities, so as to optimize the training methods and equipment in a targeted manner.

[0032] In some embodiments, the specific method in step S2 includes: Obtain the real-time movement speed and movement range of the ith athlete; compare the real-time movement speed and movement range of the ith athlete with the set standard threshold. If any movement parameter exceeds the standard threshold range, it means that the movement of the ith athlete is abnormal, and an early warning is issued immediately. Otherwise, further analyze whether there is potential abnormality in the movement of the ith athlete.

[0033] It should be noted that the real-time movement speed and movement amplitude of the ith athlete are obtained. This process is to preliminarily determine whether the athlete's movement meets the standard. Movement speed refers to the distance or angle change that the athlete completes the movement in a unit of time, while movement amplitude refers to the range of motion of various parts of the body when the athlete completes the movement. Through these two parameters, the athlete's movement can be basically quantitatively analyzed, providing a basis for subsequent abnormality detection.

[0034] Specifically, the speed of movement can be measured by accelerometers installed on athletes. These sensors can capture the acceleration changes of various parts of the athlete's body in real time and then calculate the speed. The amplitude of movement can be obtained through angle sensors or image recognition technology. Angle sensors can be installed at joints to directly measure the angle of movement of the joints; image recognition technology can capture the athlete's movement image through a camera, and use computer vision algorithms to analyze the position changes of various parts of the athlete's body in the image to calculate the amplitude of movement. In practical applications, appropriate sensors and measurement methods can be selected according to different training items and the characteristics of athletes.

[0035] Preferably, in order to improve the accuracy of the movement speed and amplitude measurement, a variety of sensor fusion methods can be used. For example, by combining an accelerometer and a gyroscope, not only the acceleration but also the angular velocity can be measured, thereby more comprehensively reflecting the athlete's movement state. In addition, a machine learning algorithm can be introduced to calibrate and fuse the sensor data to improve the reliability and accuracy of the data. For example, by training a neural network model, the noise and errors in the sensor data can be automatically identified and corrected, thereby obtaining more accurate movement speed and amplitude values.

[0036] Furthermore, the real-time movement speed and movement amplitude of the ith athlete are compared with the set standard threshold. The standard threshold here is pre-set based on factors such as the athlete's training goals, technical level, and physical condition, and is used to determine whether the athlete's movements are normal. By comparing the real-time data with the standard threshold, abnormal situations in the athlete's movements can be quickly identified and early warnings can be issued in a timely manner.

[0037] More specifically, the setting of the standard threshold can be determined based on the athlete's historical data, the data of outstanding athletes in the same event, and sports science theory. For example, for sprinters, a reasonable speed threshold range can be set based on their personal bests, world records, and research results in sports biomechanics. The threshold of the range of motion can be set based on factors such as the athlete's technical movement specifications and body flexibility. In practical applications, the standard threshold can be a fixed range of values ​​or a dynamically changing function that is adjusted according to the training progress and athlete status.

[0038] Preferably, in order to more accurately judge abnormal movements, statistical methods and machine learning algorithms can be introduced. For example, by analyzing the movement data of a large number of athletes, a statistical model of normal movements is established, and then the real-time data is compared with the model to calculate the abnormal probability. If the abnormal probability exceeds a certain threshold, it can be considered that the athlete's movement is abnormal. In addition, machine learning algorithms can be used to classify and predict real-time data, automatically identify the patterns and characteristics of abnormal movements, and improve the accuracy and timeliness of early warnings.

[0039] Furthermore, if any action parameter exceeds the standard threshold range, it means that the action of the i-th athlete is abnormal, and an early warning is issued immediately. Otherwise, further analysis is conducted to see if there is a potential abnormality in the action of the i-th athlete. The early warning mechanism is to promptly remind coaches and athletes to pay attention to potential risks and take corresponding measures to adjust and correct them. Potential abnormality analysis is to conduct in-depth analysis of those actions that may be risky even though they do not exceed the threshold, so as to discover and solve problems in advance.

[0040] Specifically, early warning can be carried out in a variety of ways, such as sound alarms, visual signals or mobile phone application notifications. Potential anomaly analysis can include time series analysis of motion data, spectrum analysis, etc., through which subtle changes and potential problems in the action can be discovered. For example, by analyzing the time series of movement speed, it can be found whether the athlete has signs of fatigue or unstable technical movements; by analyzing the spectrum of movement amplitude, periodic errors or incoordination in the movement can be identified.

[0041] Preferably, the early warning system can be integrated with the training management system to achieve automated training adjustments and feedback. For example, when the early warning system detects abnormal movements of athletes, it can automatically adjust the training plan, increase rest time or reduce training intensity. At the same time, the results of potential abnormality analysis can be fed back to the coach in real time, and the coach can provide targeted guidance and training adjustments to the athletes based on the analysis results to improve training effectiveness and safety. In addition, the early warning system can also record and analyze the frequency and type of early warning events to provide data support for athletes' training evaluation and improvement.

[0042] In some embodiments, the specific process of further analyzing whether the i-th athlete's action has potential abnormalities includes: Get the i-th athlete in the set time period The internal action speed changes over time data, construct the action speed change function of the i-th athlete over time ; in, is the amplitude, is the angular frequency, is the initial phase, is the time variable within the set time period; Get the i-th athlete in the set time period The internal movement amplitude changes over time data, and the movement amplitude change function of the i-th athlete is constructed ; in, is the amplitude, is the angular frequency, is the initial phase, is the time variable within the set time period; The potential abnormal coefficient of the action of the i-th athlete is calculated by the following formula : In the formula, For function right The derivative of For function right The derivative of To find the maximum value of a function, To find the minimum function, is the standard reference value of the action speed, It is the standard reference value of the range of motion; The potential abnormal coefficient of the action of the i-th athlete The preset threshold value of the potential abnormal coefficient of the action of the i-th athlete For comparison, if the potential abnormal coefficient of the action of the i-th athlete is Greater than or equal to the preset threshold of the potential abnormal coefficient of the action of the i-th athlete , it means that the action of the i-th athlete is potentially abnormal, and an early warning is issued immediately. Otherwise, go to step S4.

[0043] It should be noted that the process of further analyzing whether there are potential abnormalities in the athlete's movements is achieved by constructing a function of the speed and amplitude of the movement over time and calculating the potential abnormality coefficient. The potential abnormality coefficient here is a quantitative indicator used to evaluate the stability and consistency of the athlete's movements. By comparing this coefficient with the preset threshold, it can be determined whether the athlete's movements have potential problems, even if these movements appear normal on the surface.

[0044] Specifically, the function of action speed changing with time is and the time-varying function of the motion amplitude middle, and They represent amplitude, i.e. the maximum speed and magnitude of the movement; and stands for angular frequency, which indicates the rate of periodic change of the action; and Represents the initial phase, which indicates the phase offset at the beginning of the action. These parameters can be obtained by fitting the athlete's action data within a set time period. For example, through mathematical methods such as the least squares method, the optimal values ​​of these parameters can be determined, thereby constructing a function that accurately reflects the athlete's action characteristics.

[0045] Preferably, in order to more accurately calculate the potential anomaly coefficient, higher-order derivatives and more complex mathematical models can be used. For example, in addition to calculating the first-order derivative and In addition, second-order derivatives can be calculated to analyze the acceleration changes of the action. In addition, machine learning algorithms such as support vector machines (SVM) or neural networks can be introduced to classify and predict the action data and automatically identify potential abnormal patterns. For example, a neural network model is trained with the input of the athlete's action data and the output as the potential abnormality coefficient. Through a large amount of training data, the model can accurately identify potential abnormalities.

[0046] Next, by calculating the formula To determine the potential anomaly coefficient Here and The functions are used to obtain the maximum and minimum values ​​of the functions. By comparing the changes in the maximum and minimum values ​​of the speed and amplitude of the movements, the stability and consistency of the athletes' movements can be quantitatively evaluated. Exceeding the preset threshold , it indicates that there is a potential abnormality in the athlete's movement.

[0047] Specifically, the preset threshold The setting can be determined based on the athlete's historical data, the data of outstanding athletes in the same event, and sports science theory. For example, for a specific training event, a reasonable range of potential abnormal coefficients can be determined by analyzing the action data of a large number of outstanding athletes. In addition, the threshold can be dynamically adjusted according to the athlete's training stage and physical condition. For example, in the early stages of training, since the athlete may not have fully mastered the technical movements, the threshold can be appropriately relaxed; as the training progresses, the threshold can be gradually tightened to require the athlete to meet higher standards.

[0048] Preferably, in order to improve the accuracy of potential anomaly detection, multi-dimensional evaluation indicators can be introduced. In addition to speed and amplitude, other factors such as the rhythm and coordination of the movement can also be considered. For example, by analyzing the rhythm changes of the athlete's movements, it can be found whether there is incoherence in the technical movements; by evaluating the coordination of the movements, it can be identified whether the various parts of the body work together. In addition, data fusion technology can be used to comprehensively analyze the data of multiple sensors to obtain more comprehensive athlete movement information. For example, combining the data of accelerometers, gyroscopes, and electromyography (EMG) sensors can more accurately evaluate the quality of athletes' movements and potential anomalies.

[0049] Furthermore, the calculated potential anomaly coefficient With preset threshold For comparison, if Greater than or equal to , it means that the athlete's action is potentially abnormal, and an early warning is issued immediately. Otherwise, proceed to the next step. Early warnings can be issued in a variety of ways, such as sound alarms, visual signals, or mobile phone application notifications, to alert coaches and athletes to potential problems.

[0050] Specifically, the early warning system can be integrated with the training monitoring system to achieve automated training adjustments. For example, when a potential anomaly is detected, the system can automatically adjust the parameters of the training equipment, such as reducing the difficulty of the training equipment, or adjusting the training rhythm to give athletes more rest time. At the same time, the early warning system can record and analyze the frequency and type of early warning events, providing data support for athletes' training evaluation and improvement. For example, by analyzing the early warning records, it can be found that certain specific movements or training stages are prone to potential anomalies, so as to optimize the training methods and equipment in a targeted manner.

[0051] Preferably, the early warning system can provide personalized feedback and suggestions. For example, based on the athlete's specific situation, the system can generate a detailed report, including the specific manifestations of potential abnormalities, possible causes, and improvement suggestions.

[0052] Furthermore, the early warning system can be combined with the athlete's personal training plan to automatically adjust the training plan based on the early warning results, ensuring that the athlete improves his or her technical level in a safe and effective training environment. For example, if an athlete frequently shows potential abnormalities in a certain action, the system can suggest adding special training for that action, or adjusting the intensity and frequency of training.

[0053] In some embodiments, the specific method of step S4 includes: Get the i-th athlete's The quality parameters of the action are within the set time period The data changes over time in the same box, and constructs the i-th athlete’s The function of the quality parameter of each action changing with time; The action quality coefficient of the i-th athlete is calculated by the following formula : ; In the formula, is the function of the j-th action quality parameter of the i-th athlete changing with time, is the standard function of the j-th action quality parameter of the ith athlete changing with time, is the weight coefficient corresponding to the j-th action quality parameter, is the time variable within the set time period, To set the initial detection time point within the time period, To end the detection time point within the set time period; according to the action quality coefficient of the i-th athlete Determine the quality level of the i-th athlete's movements.

[0054] It should be noted that the specific method of step S4 involves obtaining multiple action quality parameters of the athlete, and analyzing these parameters by constructing a function that changes over time, and then calculating the action quality coefficient to evaluate the athlete's action quality level. The action quality parameters here refer to various indicators that can reflect the athlete's action technique, coordination and stability, such as the fluency, accuracy, and force distribution of the action. Through the analysis of these parameters, the athlete's action performance can be fully understood, and scientific training suggestions can be provided to the coach.

[0055] Specifically, the selection of action quality parameters should be determined according to the specific training items and goals. For example, in basketball training, action quality parameters can include shooting accuracy, dribbling stability, defensive footwork speed, etc. These parameters can be collected by various sensors and measuring devices, such as optical motion capture systems, pressure sensors, electromagnetic sensors, etc. The collected data can be analyzed within a set time period. The time period should be adjusted according to the intensity of the training and the physical condition of the athletes, which can usually range from a few minutes to tens of minutes. For example, for high-intensity short-term training, the time period can be set to 5 minutes; for endurance training, the time period can be extended to 30 minutes.

[0056] Preferably, in order to more accurately evaluate the action quality, different weight coefficients can be assigned to each action quality parameter, and these weight coefficients can be set according to the importance of the parameter and the contribution to the training goal. For example, in football shooting training, the accuracy of the shot may be more important than the power of the shot, so the accuracy parameter can be given a higher weight.

[0057] Furthermore, the function of the action quality parameter can adopt a more complex mathematical model, such as a polynomial function or an exponential function, to more accurately describe the trend of the parameter over time. For example, for actions that require rapid explosive power, such as sprint start, an exponential function can be used to describe the rapid change of the strength parameter over time.

[0058] More specifically, by calculating the formula To determine the motion quality factor Here represents the function of the j-th action quality parameter of the i-th athlete changing with time, It represents the standard function of the j-th action quality parameter of the ith athlete changing with time, represents the weight coefficient corresponding to the j-th action quality parameter, and They represent the initial and final detection time points within the set time period. By calculating the deviation integral between the actual parameters and the standard parameters and combining them with the weight coefficient, a comprehensive action quality coefficient can be obtained to evaluate the overall action quality of the athlete.

[0059] Furthermore, the standard function The setting can be determined based on the performance of outstanding athletes or the research results of sports science. For example, for the take-off action of a high jumper, the standard function can be constructed based on the action data of the world's top high jumpers to reflect the changes in parameters such as ideal take-off force, speed and angle over time. The setting should be adjusted according to the degree of influence of each parameter on the overall movement quality, which can be determined through expert evaluation or data analysis. For example, by analyzing the data of a large number of athletes and finding that a certain parameter is highly correlated with competition results, a higher weight can be given to this parameter.

[0060] Preferably, in order to improve the accuracy and reliability of action quality assessment, a machine learning algorithm can be introduced to optimize the setting of the standard function and weight coefficient. For example, by training a regression model, the input is a large number of athletes' action quality parameter data, and the output is the action quality score. The model can automatically learn the optimal weight of each parameter and the form of the standard function.

[0061] In addition, a real-time feedback system can be used to dynamically adjust the standard function and weight coefficient according to the real-time performance of the athlete to adapt to the characteristics and training progress of different athletes. For example, if an athlete performs well in a certain action, the system can automatically improve the standard function of the action parameters to motivate the athlete to continue to improve.

[0062] In some embodiments, the action quality coefficient of the i-th athlete The specific process of judging the action quality level of the i-th athlete includes: Get the number of athletes in the same event as the i-th athlete , calculate the difference coefficient of the ith athlete according to the following formula: : The i-th athlete's difference coefficient Difference coefficient with the i-th athlete The preset threshold is compared. If the difference coefficient of the i-th athlete Greater than or equal to the i-th athlete's difference coefficient The preset threshold indicates that the action quality level of the i-th athlete is lower than the expected level, and it is recommended to strengthen targeted training, among which, is the movement quality coefficient of the zth athlete in the same event as the ith athlete.

[0063] It should be noted that according to the athlete's action quality coefficient The process of judging the quality of their movements involves calculating the athlete's coefficient of variation. The coefficient of variation here is a quantitative indicator that measures the difference between an athlete's movement quality and the average level of other athletes in the same event. By comparing the movement quality coefficient of an individual athlete with the group average, it is possible to assess whether the athlete's movement quality has reached the expected level, thus providing a basis for targeted training.

[0064] Specifically, the coefficient of variation The calculation formula is in, is the action quality coefficient of the ith athlete, is the average value of the movement quality coefficients of all athletes in the same event. is the standard deviation of these coefficients. This formula is standardized so that the coefficient of variation can intuitively reflect the degree of deviation of individual athletes from the group average. For example, if an athlete's coefficient of variation is much higher than the group average, it means that the quality of his movements is excellent; otherwise, he may need to strengthen his training.

[0065] Preferably, in order to more accurately evaluate the level of athletes' movement quality, it is possible to consider introducing a weighted difference coefficient, in which the movement quality coefficients of different athletes can be given different weights according to their roles in the team or training focus. For example, in basketball training, different weights can be given to the movement quality coefficients of main players and substitute players according to their playing time and role in the game, so as to more accurately reflect the overall training level and needs of the team.

[0066] Furthermore, the calculation of the coefficient of variation can combine real-time data with historical data to provide coaches with more comprehensive training feedback by dynamically analyzing the trend of changes in the quality of athletes' movements. For example, if an athlete's coefficient of variation continues to decline in several consecutive training sessions, this may indicate that the athlete needs to adjust his training methods or increase the intensity of training.

[0067] In some embodiments, the specific method of step S5 includes: Obtain various parameter values ​​of the athlete's training environment; Compare the values ​​of various environmental parameters with the set appropriate thresholds respectively: if there are environmental parameter items that exceed the set appropriate threshold range, the athlete's training environment is judged to be unqualified and an early warning is issued immediately; otherwise, the training environment status is judged as a whole based on the overall deviation of the values ​​of various environmental parameters.

[0068] It should be noted that the specific method of step S5 involves obtaining various parameter values ​​of the athlete's training environment, and comparing these parameter values ​​with the set appropriate thresholds to determine whether the training environment is qualified. The training environment parameters here include but are not limited to temperature, humidity, light intensity, air quality, field hardness, etc., which have an important impact on the performance and health of athletes. By monitoring these parameters, it can be ensured that athletes train in the best environment, thereby improving training effects and reducing the risk of injury.

[0069] Specifically, the acquisition of training environment parameters can be achieved through various sensors. For example, temperature and humidity sensors can be installed in the training venue to monitor the temperature and humidity of the environment in real time; light intensity sensors can be used to measure the lighting conditions of the training venue; air quality monitors can detect the concentration of pollutants in the air. The data of these sensors can be transmitted to the central control system in real time and compared with the preset appropriate thresholds. The setting of appropriate thresholds should be based on the research results of sports science and human physiology. For example, for indoor track and field training, the appropriate temperature range may be 15-25 degrees Celsius, humidity 40%-60%, and light intensity 500-1000 lux. If any parameter exceeds the set appropriate threshold range, the system will judge that the training environment is unqualified.

[0070] Preferably, in order to more comprehensively evaluate the training environment status, a comprehensive environmental coefficient can be used to quantify the overall quality of the environment. The calculation formula of the environmental coefficient is: ; in, is the number of environmental parameters detected, For the The detected value of the environmental parameter, For the Suitable standard values ​​of environmental parameters, For the The correlation coefficient of each parameter can be set according to the importance of each parameter to the training. For example, air quality may have a greater impact on the health of athletes, so a higher correlation coefficient can be assigned. In addition, the Internet of Things technology can be used to interconnect sensors and make environmental monitoring more intelligent and automated. For example, when the air quality sensor detects that the concentration of harmful gases exceeds the standard, the system can automatically start the ventilation equipment to improve the air quality.

[0071] In some embodiments, the method for overall judging the training environment status according to the overall deviation of each environmental parameter value includes: calculating the environmental coefficient of the athlete's training environment by the following formula: : in, is the number of environmental parameters detected, is the index of the environment parameter item and , For the The detected value of the environmental parameter, For the Suitable standard values ​​of environmental parameters, For the Suitable reference values ​​for environmental parameters, For the Correlation coefficient of item parameters; According to the environmental coefficient of the athlete's training environment Analyze the status of the training environment.

[0072] It should be noted that the method of making an overall judgment on the training environment status based on the overall deviation of the values ​​of various environmental parameters is to calculate the environmental coefficient of the athlete's training environment. The environmental coefficient here is a comprehensive indicator used to quantitatively evaluate the overall quality of the training environment. By comparing the deviation between the actual detection value of the environmental parameter and the appropriate standard value, and combining the correlation coefficient of each parameter, a value reflecting the state of the training environment can be obtained. This value can help coaches and managers quickly understand whether the training environment is suitable and take corresponding measures.

[0073] Specifically, the environmental factor The calculation formula is in, is the number of environmental parameters detected, For the The detected value of the environmental parameter, For the Suitable standard values ​​of environmental parameters, For the The correlation coefficient of each parameter. For example, if the temperature of the training venue is detected to be 28 degrees Celsius, while the suitable standard value is 22 degrees Celsius, and the humidity is 70%, while the suitable standard value is 50%, the deviation values ​​of temperature and humidity can be calculated, and the environmental coefficient can be calculated based on their correlation coefficients. The correlation coefficient can be set according to the degree of influence of each parameter on the performance and health of the athlete, which is usually determined through expert evaluation or experimental research.

[0074] Preferably, in order to more accurately evaluate the training environment status, a dynamic adjustment mechanism can be introduced to adjust the appropriate standard value and the correlation coefficient in real time according to the different stages of training and the feedback of athletes. For example, in the early stage of training, athletes may have poor adaptability to the environment, so the range of the appropriate standard value can be appropriately relaxed; as the training progresses, the standard value requirements can be gradually increased to simulate the competition environment.

[0075] Furthermore, we can use big data analysis technology to collect a large amount of training environment data and athlete performance data, and use data mining algorithms to find the potential relationship between environmental parameters and athlete performance, so as to optimize the setting of the correlation coefficient. For example, through analysis, it is found that when the air quality index exceeds a certain value, the athlete's endurance performance decreases significantly, so the correlation coefficient of the air quality parameter can be improved.

[0076] In some embodiments, the environmental coefficient of the athlete's training environment Methods for analyzing the state of the training environment include: The environmental factor of the athlete training environment Environmental coefficient thresholds for athlete training environments By comparison, if the environmental coefficient of the athlete's training environment Greater than or equal to the environmental coefficient threshold of the athlete's training environment , then the overall training environment of the athlete is unqualified and an early warning is issued immediately.

[0077] It should be noted that according to the environmental coefficient of the athlete's training environment The method of analyzing the training environment status is to use the environmental coefficient Compared with the preset environmental coefficient threshold The environmental coefficient threshold here is a standard value used to judge whether the training environment is qualified. Greater than or equal to the environmental factor threshold , it indicates that the overall training environment is unqualified and an early warning needs to be issued immediately so that measures can be taken to improve environmental conditions.

[0078] Specifically, the environmental coefficient threshold The setting of the environmental coefficient should be based on the research results of sports science and human physiology, as well as the performance data of athletes under different environmental conditions. For example, for indoor swimming training, the environmental coefficient threshold may be set based on factors such as water temperature, water quality, and indoor air circulation. If the water temperature is below the appropriate range or the air quality is poor, the environmental coefficient May exceed the threshold .

[0079] More specifically, in practical applications, the environmental coefficient threshold can be a fixed value or a range that is dynamically adjusted according to the training program and the athlete's state. For example, during high-intensity training, stricter environmental standards are required, so the environmental coefficient threshold can be increased accordingly.

[0080] Preferably, in order to improve the accuracy and timeliness of environmental assessment, a real-time monitoring system can be used, which can continuously collect environmental parameters and calculate environmental coefficients in real time. When the environmental factor Approaching or exceeding the threshold When the air quality in an indoor training venue deteriorates, the system will not only issue an alarm, but also indicate which pollutants are exceeding the standard and recommend improvement measures.

[0081] Furthermore, intelligent control systems can be used to The system automatically adjusts environmental parameters according to changes in the environment, such as automatically adjusting the air conditioning system to maintain appropriate temperature and humidity, or starting air purification equipment to improve air quality. This automated environmental management can ensure that athletes are always in the best training environment, thereby improving training effectiveness and safety.

[0082] The above-mentioned various embodiments of the present invention have the following beneficial effects: First, by numbering the athletes and collecting the changes of their motion data over time, it is possible to accurately track and analyze the movements of each athlete, and provide basic data support for subsequent abnormal detection and quality assessment. Secondly, in step S2, by comparing the real-time motion speed and amplitude of the athlete with the set standard threshold, the abnormal movement can be quickly identified, and an early warning can be issued in time to avoid potential sports injury risks. Further, the analysis of potential abnormalities, the construction of a function of the change of motion speed and amplitude over time, and the calculation of the potential abnormality coefficient can more carefully evaluate the stability of the athlete's movements and discover potential problems that may affect performance in advance.

[0083] In addition, the collection and analysis of the action quality parameters in step S4, by constructing a function of the action quality parameters changing over time and calculating the action quality coefficient, can quantitatively evaluate the athlete's action quality, provide scientific training suggestions for coaches, and help improve the athlete's technical level. At the same time, the collection and analysis of the real-time parameters of the training environment in step S5 can ensure that the athlete trains in a suitable environment. By calculating the environmental coefficient and making an overall judgment, it is possible to timely discover and adjust the training environment factors that do not meet the requirements, and ensure the training effect and the safety of the athlete. These comprehensive monitoring and evaluation methods together constitute a comprehensive and systematic sports training motion capture method, which provides a strong technical support for improving the scientificity and effectiveness of sports training.

[0084] Furthermore, the storage medium of the embodiment of the present application stores program instructions that can implement all the above methods, wherein the program instructions can be stored in the above storage medium in the form of a software product, including several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) or a processor to execute all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, or terminal devices such as a computer, a server, a mobile phone, and a tablet.

[0085] The above descriptions are only some preferred embodiments of the present invention and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present invention is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above inventive concept. For example, the above features are replaced with (but not limited to) technical features with similar functions disclosed in the embodiments of the present invention.

Claims

1. A motion capture method based on sports training, characterized in that: The method comprises the following steps: Step S1, numbering all athletes participating in sports training, the numbers are: 1, 2, ..., n; Step S2, collecting the changes of the motion data of all athletes over time, and analyzing whether the athlete's motion is abnormal according to the changes of the real-time motion data of each athlete over time; Step S3: If the athlete's action is abnormal or potentially abnormal, an early warning is immediately issued; if the athlete's action is not abnormal or potentially abnormal, the process proceeds to step S4; Step S4, collecting the data of the variation of the movement quality parameters of all athletes over time, and analyzing the movement quality state of each athlete according to the data of the variation of the movement quality parameters of each athlete over time; Step S5: collect the real-time parameters of the training environment of all athletes, and analyze the training environment status of the athletes according to the real-time parameters of the training environment of the athletes. If the training environment of the athletes does not meet the requirements, an early warning is immediately issued.

2. A motion capture method based on sports training according to claim 1, characterized in that: The specific method in step S2 includes: Obtain the real-time movement speed and movement range of the ith athlete; compare the real-time movement speed and movement range of the ith athlete with the set standard threshold. If any movement parameter exceeds the standard threshold range, it means that the movement of the ith athlete is abnormal, and an early warning is issued immediately. Otherwise, further analyze whether there is potential abnormality in the movement of the ith athlete.

3. A motion capture method based on sports training according to claim 2, characterized in that: The specific process of further analyzing whether the i-th athlete's action has potential abnormalities includes: Get the i-th athlete in the set time period The internal action speed changes over time data, construct the action speed change function of the i-th athlete over time ； in, is the amplitude, is the angular frequency, is the initial phase, is the time variable within the set time period; Get the i-th athlete in the set time period The internal movement amplitude changes over time data, and the movement amplitude change function of the i-th athlete is constructed ； in, is the amplitude, is the angular frequency, is the initial phase, is the time variable within the set time period; The potential abnormal coefficient of the action of the i-th athlete is calculated by the following formula : In the formula, For function right The derivative of For function right The derivative of To find the maximum value of a function, To find the minimum function, is the standard reference value of the action speed, It is the standard reference value of the range of motion; The potential abnormal coefficient of the action of the i-th athlete The preset threshold value of the potential abnormal coefficient of the action of the i-th athlete For comparison, if the potential abnormal coefficient of the action of the i-th athlete is Greater than or equal to the preset threshold of the potential abnormal coefficient of the action of the i-th athlete , it means that the action of the i-th athlete is potentially abnormal, and an early warning is issued immediately. Otherwise, go to step S4.

4. The motion capture method based on sports training according to claim 1, characterized in that: The specific method of step S4 includes: Get the i-th athlete's The quality parameters of the action are within the set time period The data changes over time in the same box, and constructs the i-th athlete’s The function of the quality parameter of each action changing with time; The action quality coefficient of the i-th athlete is calculated by the following formula : ； In the formula, is the function of the j-th action quality parameter of the i-th athlete changing with time, is the standard function of the j-th action quality parameter of the ith athlete changing with time, is the weight coefficient corresponding to the j-th action quality parameter, is the time variable within the set time period, To set the initial detection time point within the time period, To end the detection time point within the set time period; according to the action quality coefficient of the i-th athlete Determine the quality level of the i-th athlete's movements.

5. A motion capture method based on sports training according to claim 4, characterized in that: The action quality coefficient of the i-th athlete The specific process of judging the action quality level of the i-th athlete includes: Get the number of athletes in the same event as the i-th athlete , calculate the difference coefficient of the ith athlete according to the following formula: : The i-th athlete's difference coefficient Difference coefficient with the i-th athlete The preset threshold is compared. If the difference coefficient of the i-th athlete Greater than or equal to the i-th athlete's difference coefficient The preset threshold indicates that the action quality level of the i-th athlete is lower than the expected level, and it is recommended to strengthen targeted training, among which, is the movement quality coefficient of the zth athlete in the same event as the ith athlete.

6. The motion capture method based on sports training according to claim 1, characterized in that: The specific method of step S5 includes: Obtain various parameter values ​​of the athlete's training environment; Compare the values ​​of various environmental parameters with the set appropriate thresholds respectively: if there are environmental parameter items that exceed the set appropriate threshold range, the athlete's training environment is judged to be unqualified and an early warning is issued immediately; otherwise, the training environment status is judged as a whole based on the overall deviation of the values ​​of various environmental parameters.

7. A motion capture method based on sports training according to claim 6, characterized in that: The method for overall judging the training environment state according to the overall deviation of each environmental parameter value includes: calculating the environmental coefficient of the athlete's training environment by the following formula: : ； in, is the number of environmental parameters detected, is the index of the environment parameter item and , For the The detected value of the environmental parameter, For the Suitable standard values ​​of environmental parameters, For the Suitable reference values ​​for environmental parameters, For the Correlation coefficient of item parameters; According to the environmental coefficient of the athlete's training environment Analyze the status of the training environment.

8. The motion capture method based on sports training according to claim 7, characterized in that: The environmental coefficient according to the athlete's training environment Methods for analyzing the state of the training environment include: The environmental factor of the athlete's training environment Environmental coefficient thresholds for athlete training environments By comparison, if the environmental coefficient of the athlete's training environment Greater than or equal to the environmental coefficient threshold of the athlete's training environment , then the overall training environment of the athlete is unqualified and an early warning is issued immediately.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the motion capture method based on sports training as described in any one of claims 1-8 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: The computer program is executed by a processor to implement a motion capture method based on sports training as described in any one of claims 1 to 8.

Images