Standing long jump evaluation system and method based on visual motion capture

Abstract

The invention discloses a standing long jump evaluation system and method based on visual motion capture, and relates to the technical field of multi-point coordinate data evaluation.Multi-point coordinate data of an athlete is captured through the evaluation system, the position of the athlete in the air is recognized, the tolerance range is adjusted according to a dynamic adjustment algorithm, and the track of the athlete is analyzed through multi-dimensional data; according to multipoint coordinate data and historical data of the athlete, an intelligent correction algorithm is used for predicting and correcting an abnormal track, and according to a current track analysis result, a tolerance range after dynamic adjustment and an air position of the athlete, subsequent analysis parameters are adjusted in real time and then evaluation is carried out. The system can intelligently optimize the analysis process according to different camera shooting angles, athlete postures and environmental factors, errors caused by the environmental factors can be remarkably reduced through flexible adjustment of the tolerance range under irregular environmental conditions, it is ensured that the captured motion trails accurately reflect real actions of athletes, and therefore the evaluation precision is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of multi-point coordinate data evaluation, and particularly relates to a standing long jump evaluation system and method based on visual motion capture. BACKGROUND

[0002] Standing long jump is a common sports test item, especially in school sports, athlete training and physical fitness testing, and has a wide range of applications. However, the traditional test method is easily affected by manual measurement errors, and lacks detailed analysis of the multi-point coordinate data of athletes. In order to improve the accuracy and efficiency of the test, standing long jump evaluation systems based on visual motion capture have gradually developed in recent years.

[0003] The prior art has the following disadvantages: In the traditional standing long jump evaluation method based on visual motion capture, changes in camera angles and environmental factors (such as changes in lighting and background interference) often result in inaccurate capture of movement trajectories, affecting the accuracy of the final evaluation results. In addition, the traditional system usually relies on pre-set standards and fixed tolerance ranges, lacks flexibility, and cannot make intelligent adjustments according to individual differences of different athletes or real-time environmental conditions, which may cause misjudgment or missed judgment.

[0004] Based on this, the present application proposes a standing long jump evaluation system and method based on visual motion capture, which can intelligently optimize the analysis process according to different camera angles, athlete postures and environmental factors. The flexible adjustment of the tolerance range under irregular environmental conditions can significantly reduce errors caused by environmental factors, ensuring that the captured movement trajectories accurately reflect the real actions of athletes, thereby improving the accuracy of the evaluation. SUMMARY

[0005] The purpose of the present application is to provide a standing long jump evaluation system and method based on visual motion capture to solve the problems in the background art.

[0006] In order to achieve the above-mentioned purpose, the present application provides the following technical solution: a standing long jump evaluation method based on visual motion capture, the evaluation method comprising the following steps: The evaluation system captures the multi-point coordinate data of the athlete and identifies the position of the athlete in the air, and adjusts the tolerance range according to a dynamic adjustment algorithm; Analyze the athlete's trajectory through multi-dimensional data analysis, predict and correct abnormal trajectories using intelligent correction algorithms based on the athlete's multi-point coordinate data and historical data; According to the current trajectory analysis result, the dynamically adjusted tolerance range and the athlete's position in the air, the subsequent analysis parameters are adjusted in real time and the evaluation is carried out.

[0007] In a preferred embodiment, adjusting the tolerance range according to the dynamic adjustment algorithm includes the following steps: Calculate the initial tolerance value of each data point based on the average error value of all trajectory points in the historical data; Based on the current environment's light intensity and the current angle between the camera and the athlete's trajectory, the initial tolerance value of the data point is dynamically adjusted to obtain a dynamically adjusted tolerance value.

[0008] In a preferred embodiment, the initial tolerance value calculation formula is: ,in: For the The initial tolerance value for data points, is the adjustment coefficient, is the average error value of all trajectory points in the historical data; The calculation expression of the tolerance value after dynamic adjustment is: ,in, For the The tolerance value after dynamic adjustment of data points, For the The initial tolerance value for data points, is the environmental impact coefficient, is the environmental sensitivity coefficient, Illumination is the current environmental illumination intensity, and Angle is the angle between the current camera and the athlete's trajectory.

[0009] In a preferred embodiment, the evaluation is performed after adjusting subsequent analysis parameters in real time based on the current trajectory analysis results, the dynamically adjusted tolerance range, and the athlete's aerial position, including the following steps: According to the position of the athlete in the air, the changes in his posture and center of gravity are calculated in real time to estimate the athlete's position in the air; Dynamically feeds back the athlete's performance based on current trajectory analysis and tolerance range, updating the athlete's technical assessment at every moment and providing real-time feedback via the display; By analyzing the athlete's movement pattern, the future movement trajectory is predicted, and the analysis parameters, including speed weighting and acceleration tolerance, are dynamically adjusted according to the athlete's predicted trend.

[0010] In a preferred embodiment, the evaluation method further comprises the following steps: Calculate the error value of the coordinate point. If the error value of the coordinate point exceeds the set error threshold, the coordinate point is judged as an outlier and removed from the trajectory. Interpolation is used to fill in the missing coordinate point data.

[0011] In a preferred embodiment, the error value of the coordinate point is calculated using the expression: wherein: is the actual captured coordinate point, is the estimated ideal coordinate point, is the error value of the coordinate point.

[0012] In a preferred embodiment, the missing coordinate point data is filled in using an interpolation method, and the linear interpolation expression is: wherein, is the coordinate value of the two adjacent time points, is the corresponding time point, is the time point that needs to be interpolated, is the coordinate value obtained after interpolation.

[0013] In a preferred embodiment, the evaluation system captures the multi-point coordinate data of the athlete and identifies the position of the athlete in the air, including the following steps: establishing a mathematical model based on perspective transformation to correct the coordinate deviation caused by angle change; obtaining the calibrated coordinates by real-time detection of the position information of the athlete and compensation according to the movement of the athlete in space; repositioning the data of each time point through angle correction to obtain the rotated coordinates through the rotation matrix.

[0014] In a preferred embodiment, the calibrated coordinates are obtained by real-time detection of the position information of the athlete and compensation according to the movement of the athlete in space, and the expression is: wherein: is the actual three-dimensional coordinate of the athlete, is the calibrated coordinate, is the position offset of the athlete relative to the camera.

[0015] The application also provides a standing long jump evaluation system based on visual motion capture, including a tolerance adjustment module, a trajectory analysis module, and an evaluation module; The tolerance adjustment module captures the multi-point coordinate data of the athlete and identifies the position of the athlete in the air, dynamically adjusts the tolerance range according to the historical data, the multi-point coordinate data of the athlete, and the current sports environment; The trajectory analysis module analyzes the trajectory of the athlete through multi-dimensional data analysis, and uses intelligent correction algorithm to predict and correct abnormal trajectory according to the multi-point coordinate data of the athlete and the historical data; The evaluation module adjusts the subsequent analysis parameters in real time according to the current trajectory analysis result, the dynamically adjusted tolerance range, and the position of the athlete in the air, and then performs evaluation.

[0016] In the above technical solution, the application provides technical effects and advantages: The application captures the multi-point coordinate data of the athlete through the evaluation system, identifies the position of the athlete in the air, adjusts the tolerance range according to the dynamic adjustment algorithm, analyzes the trajectory of the athlete through multi-dimensional data, predicts and corrects the abnormal trajectory according to the multi-point coordinate data and historical data of the athlete, and uses the intelligent correction algorithm, adjusts the subsequent analysis parameters in real time according to the current trajectory analysis result, the tolerance range after dynamic adjustment, and the position of the athlete in the air, and then performs evaluation. The system can intelligently optimize the analysis process according to different camera angles, athlete postures and environmental factors. Under irregular environmental conditions (such as different camera angles or changes in light), the flexible adjustment of the tolerance range can significantly reduce errors caused by environmental factors, ensure that the captured movement trajectory accurately reflects the real action of the athlete, thereby improving the accuracy of the evaluation, and can optimize the analysis process according to real-time data, avoiding errors caused by improper camera angle adjustment in traditional static methods. BRIEF DESCRIPTION OF DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments described in the present application, and other drawings can also be obtained by those skilled in the art based on these drawings.

[0018] Figure 1 The flowchart of the evaluation method of the present application.

[0019] Figure 2 The timing diagram of the evaluation method of the present application. DETAILED DESCRIPTION

[0020] In order to make the purpose, technical scheme and advantages of the embodiments of the present application more clear, the technical scheme in the embodiments of the present application will be described clearly and completely below in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0021] Embodiment 1: Please refer to Figure 1 and Figure 2 The standing long jump evaluation method based on visual motion capture described in this embodiment includes the following steps: The evaluation system captures the multi-point coordinate data of the athlete, identifies the position of the athlete in the air, and adjusts the tolerance range according to the dynamic adjustment algorithm. The trajectory of the athlete is analyzed through multidimensional data analysis, the multi-point coordinate data and historical data of the athlete are used to predict and correct abnormal trajectories by using intelligent correction algorithms, and the subsequent analysis parameters are adjusted in real time according to the current trajectory analysis results, the dynamically adjusted tolerance range and the position of the athlete in the air. According to the current trajectory analysis results, the dynamically adjusted tolerance range and the position of the athlete in the air, the subsequent analysis parameters are adjusted in real time for evaluation.

[0022] The application captures multi-point coordinate data of athletes through an evaluation system, identifies the position of athletes in the air, adjusts the tolerance range according to a dynamic adjustment algorithm, analyzes the trajectory of athletes through multidimensional data analysis, uses intelligent correction algorithms to predict and correct abnormal trajectories according to multi-point coordinate data and historical data of athletes, and adjusts subsequent analysis parameters in real time according to the current trajectory analysis results, the dynamically adjusted tolerance range and the position of the athlete in the air. The system can intelligently optimize the analysis process according to different camera angles, athlete postures and environmental factors. In irregular environmental conditions (such as different camera angles or changes in lighting), the flexible adjustment of the tolerance range can significantly reduce errors caused by environmental factors, ensuring that the captured movement trajectory accurately reflects the real action of the athlete, thereby improving the accuracy of the evaluation. The analysis process can be optimized according to real-time data to avoid errors caused by improper camera angle adjustment in traditional static methods.

[0023] In the standing long jump evaluation method based on visual motion capture, analyzing the movement trajectory during the jump is a crucial step. Accurate trajectory analysis not only helps to accurately measure the jump distance, but also provides in-depth analysis for athletes on technical improvement. However, the trajectory data during the jump is affected by many factors, especially the change of camera angle and the inconsistency of multi-point coordinate data of athletes, which may cause certain errors or irregularities in the captured trajectory data. In order to ensure accurate capture of the athlete's path in a dynamic environment, the system needs to intelligently adjust the tolerance range in trajectory analysis and make appropriate adjustments for irregular multi-point coordinate data.

[0024] Before the system starts analyzing the jump trajectory, it first needs to capture the multi-point coordinate data of the athlete through high-precision cameras and sensors. The key multi-point coordinate data of standing long jump includes take-off, air posture, landing and landing, etc. The movement trajectory of each link needs to be accurately captured. In this process, the position, angle, resolution of the camera and the relative position between the athlete and the camera will affect the accuracy of the capture. Therefore, the camera system needs to adapt to different sports environments and can handle the deviation caused by the change of camera angle.

[0025] After the multi-point coordinate data capture system successfully captures the athlete's multi-point coordinate data, it performs trajectory recognition and data preprocessing. This stage uses algorithms to identify each key position of the athlete in mid-air (such as the take-off point, highest point, and landing point). However, due to individual differences in the athlete's multi-point coordinate data and the potential for sudden speed changes and directional adjustments during movement, the time intervals and spatial positions between trajectory points may be uneven. Therefore, the system must perform data filtering and smoothing to eliminate outliers or noise data and ensure the continuity and rationality of the trajectory.

[0026] When analyzing the trajectory, the system needs to set a tolerance range to identify and filter out abnormal data points caused by environmental factors or inconsistent multi-point coordinate data of athletes. For example, in some special cases, the multi-point coordinate data of an athlete's jump may be irregular, such as a short take-off or an overly hasty landing, which will cause the trajectory to perform unstable. At this time, the system needs to dynamically adjust the tolerance range based on historical data, the characteristics of the athlete's multi-point coordinate data, and the current sports environment, allowing a certain deviation within a reasonable range to avoid misjudgment. The setting of the tolerance range not only takes into account the individual differences of athletes, but also needs to be flexibly adjusted in combination with the actual conditions of the test site, such as changes in the camera's shooting angle, changes in lighting conditions, etc.

[0027] During trajectory analysis, the system doesn't just focus on the athlete's positional changes in space; it also considers factors such as time, velocity, and acceleration. For example, an athlete's takeoff is often accompanied by significant velocity changes, and mid-air posture stability and changes in center of gravity can also affect jumping performance. Therefore, the system comprehensively evaluates the athlete's trajectory through multi-dimensional data analysis. For cases where multi-point coordinate data is irregular or deviates significantly from the standard trajectory, the system automatically adjusts the analysis model, appropriately relaxing the trajectory linearity requirements to improve the robustness of the analysis.

[0028] In some extreme cases (such as an athlete's take-off angle being too steep or their landing being irregular), the system may encounter trajectory points that are difficult to accurately capture. In these cases, the system needs to use intelligent correction algorithms to predict and correct abnormal trajectories based on the athlete's known multi-point coordinate data patterns and historical data. For example, if the trajectory at a certain moment deviates significantly from the normal trajectory, the system will use interpolation or fitting algorithms to fill in the missing trajectory data to ensure data continuity and accuracy. In addition, based on big data analysis, the system can also identify the athlete's potential movement trends and make predictive adjustments to avoid deviations in the overall evaluation results due to anomalies in individual data points.

[0029] Finally, to ensure the continuous accuracy of the system, the standing long jump evaluation system based on visual motion capture needs to have dynamic feedback and real-time optimization functions. The system will adjust the parameters of subsequent analysis in real time based on the current trajectory analysis results, dynamic adjustment of the tolerance range, and the athlete's in-flight position, and then perform evaluation. For example, the system may adjust the take-off and landing threshold values in real time during the test according to the athlete's real-time performance, so that the test results are more accurate and personalized in each evaluation. This real-time optimization mechanism can ensure that the system always maintains high accuracy and robustness when facing different athletes and different environmental conditions.

[0030] Through the above steps, the standing long jump evaluation system based on visual motion capture can effectively deal with the challenges brought by changes in camera angles and inconsistencies in athlete multi-point coordinate data. By dynamically adjusting the tolerance range in trajectory analysis, the system can ensure accurate capture of the athlete's jump trajectory even in the case of irregular multi-point coordinate data. This flexible and intelligent adjustment mechanism not only improves the evaluation accuracy of the system, but also provides more scientific and efficient long jump performance evaluation according to the individualized multi-point coordinate data of different athletes and the changing environmental factors.

[0031] In Example 2, before the system begins to analyze the jump trajectory, it first needs to capture the athlete's multi-point coordinate data through high-precision cameras and sensors. Key multi-point coordinate data for standing long jump includes take-off, in-flight posture, landing, and landing, and the motion trajectory of each link needs to be accurately captured. During this process, the position, angle, resolution of the camera, and the relative position between the athlete and the camera will affect the accuracy of the capture. Therefore, the camera system needs to adapt to different sports environments and be able to handle the deviations caused by changes in camera angles.

[0032] In the standing long jump evaluation method based on visual motion capture, the system first needs high-precision cameras and sensors to capture the athlete's key multi-point coordinate data, including take-off, in-flight posture, landing, and landing, before starting to analyze the jump trajectory. To deal with errors caused by changes in camera angles and environments, the system needs to adapt to different sports environments and perform accurate angle and position compensation. The following are the key steps in this process: To compensate for the deviations caused by changes in camera angles, the system first needs to calibrate the camera and dynamically adjust the relative position between the athlete and the camera. The system uses a mathematical model based on perspective transformation to correct the coordinate deviations caused by changes in angle. The perspective transformation formula is: where: is the three-dimensional coordinate point in the physical space, is the two-dimensional coordinate point in the image coordinate system, is the focal length of the camera, is the coordinate of the image center. Through perspective transformation, the system can calibrate the captured multi-point coordinate data according to the focal length and position of the camera, eliminating the deviation caused by the change of viewing angle.

[0033] In order to adapt to the relative position between the athlete and the camera, the system needs to detect the position information of the athlete in real time and compensate according to its movement in space. The coordinates can be adjusted through a three-dimensional space conversion formula: where: is the actual three-dimensional coordinate of the athlete, is the calibrated coordinate, is the position offset of the athlete relative to the camera. By adjusting the relative position between the athlete and the camera, the system can continuously update the real-time coordinates of the athlete in dynamic testing, improving the accuracy of the data.

[0034] In a complex sports environment, the angle of the camera and the movement of the athlete may cause the captured data to be unstable. In order to cope with such changes, the system repositions the data at each time point through angle correction. Dynamic angle adjustment is performed using a rotation matrix: where: is the rotation matrix, representing the rotation angle along the x, y, z axes, is the original coordinate, is the coordinate after rotation. Through the rotation matrix, the system can adjust and correct the coordinate deviation caused by the change of camera angle in real time, ensuring accurate capture of the athlete's movement trajectory under different environmental conditions. Through the above steps, the system can compensate for errors caused by changes in camera angle, athlete position and inconsistent movements in dynamic environments, ensuring the accuracy and consistency of multi-point coordinate data, providing reliable data support for subsequent trajectory analysis and jump evaluation.

[0035] After the multi-point coordinate data capture system successfully obtains the multi-point coordinate data of the athlete, the system will perform trajectory recognition and data preprocessing. The task of this stage is to identify each key position of the athlete in the air (such as the take-off point, the highest point, the landing point, etc.) through algorithms. However, due to individual differences in the athlete's multi-point coordinate data, sudden changes in speed, direction adjustment, etc. may occur during the movement, resulting in uneven time intervals or spatial positions between trajectory points. Therefore, the system must perform data filtering and smoothing to eliminate abnormal points or noise data, ensuring the continuity and reasonableness of the trajectory.

[0036] After successfully capturing the multi-point coordinate data of the athlete using the multi-point coordinate data capture system, trajectory recognition and data preprocessing are crucial steps. To ensure the continuity and reasonableness of the trajectory, the system needs to perform data filtering and smoothing to remove abnormal points or noise data. Here is the detailed process of the current step: First, the system needs to identify and remove abnormal values caused by device errors, environmental factors, or sudden changes in athlete movements. By setting reasonable thresholds (such as the range of speed and acceleration changes), it can detect abnormal data points that do not conform to the normal trajectory and remove them. The formula for anomaly detection is: where: is the actual captured coordinate point, is the estimated ideal coordinate point, is the error value of the coordinate point. If the error value of the coordinate point exceeds the set error threshold, it is considered an abnormal point and is removed from the trajectory.

[0037] For normal data points in the trajectory, the system needs to smooth them to eliminate small-scale random noise. Low-pass filters or moving average methods can be used to smooth the trajectory. The smoothed trajectory can more accurately reflect the athlete's movement trajectory while avoiding errors caused by local fluctuations. Using low-pass filters or moving average methods to smooth the trajectory is a prior art, and this application will not be repeated.

[0038] During the movement, some data points may be missing due to device or athlete movement characteristics. To maintain the integrity of the trajectory, the system can use interpolation methods (such as linear interpolation, spline interpolation, etc.) to fill in the missing coordinate point data. The linear interpolation formula is: where, is the coordinate value of the known adjacent two time points, is the corresponding time point, is the time point that needs to be interpolated, is the coordinate value obtained after interpolation.

[0039] To further reduce noise, the system can also smooth the acceleration and speed data to ensure that the athlete's movement trajectory is physically reasonable. Low-pass filtering can be used to smooth the acceleration data, or Gaussian filtering can be used to smooth the speed data. This solution is a prior art, and this application will not be repeated.

[0040] Through these steps, the system can delete noise data, smooth the trajectory, fill in missing data, and further ensure the continuity and reasonableness of the movement trajectory, providing a stable and accurate data foundation for subsequent trajectory recognition and evaluation.

[0041] When analyzing the trajectory, the system needs to set a tolerance range to identify and filter out abnormal data points caused by environmental factors or inconsistent multi-point coordinate data of athletes. For example, in some special cases, the multi-point coordinate data of an athlete's jump may be irregular, such as a short take-off or an overly hasty landing, which will cause the trajectory to perform unstable. At this time, the system needs to dynamically adjust the tolerance range based on historical data, the characteristics of the athlete's multi-point coordinate data, and the current sports environment, allowing a certain deviation within a reasonable range to avoid misjudgment. The setting of the tolerance range not only takes into account the individual differences of athletes, but also needs to be flexibly adjusted in combination with the actual conditions of the test site, such as changes in the camera's shooting angle, changes in lighting conditions, etc.

[0042] When analyzing an athlete's jump trajectory, the system needs to set a tolerance range to identify and filter out anomalous data points caused by environmental factors or inconsistent coordinate data across multiple points. By flexibly adjusting the tolerance range, the system can adapt to different environments and individual athlete differences, reducing the risk of misjudgment. The following are the key steps for setting the tolerance range.

[0043] Because each athlete's movement pattern is different, the fluctuation range of the trajectory will also vary. Therefore, the system needs to set an initial tolerance value to adapt to the individual differences of different athletes. For example, for athletes with weak jumping power, the trajectory fluctuation may be larger, while for professional athletes, the trajectory is more stable. To this end, the initial tolerance value can be adjusted according to the athlete's movement characteristics. The initial tolerance value calculation formula is: ,in: For the The initial tolerance value for data points, The adjustment coefficient is usually set at 0.8~1.0, and is dynamically estimated based on the athlete's historical data. is the average error value of all trajectory points in the historical data.

[0044] Environmental factors such as camera angle and lighting conditions can affect the accuracy of multi-point coordinate data. Therefore, the system needs to dynamically adjust the tolerance range based on the current environmental conditions. For example, in the case of poor lighting or an unfavorable camera angle, the capture of data points may have errors. The system should allow for a certain deviation. The calculation expression for the dynamically adjusted tolerance value is: ,in, For the The tolerance value after dynamic adjustment of data points, For the The initial tolerance value for data points, is the environmental impact coefficient, which is calculated in real time based on environmental data. where Sensitivity is the environmental sensitivity coefficient, Illumination is the current environmental light intensity, and Angle is the current camera angle with the athlete's trajectory. This formula indicates that when the light is insufficient or the camera angle deviates from the standard angle, the system will automatically increase the tolerance range, allowing for certain deviations.

[0045] Through the above steps, the system can dynamically adjust the tolerance range based on the athlete's historical data, individual differences, and environmental factors, thus processing abnormal data within a reasonable range. The flexible adjustment of the tolerance range not only improves the robustness of the system, but also avoids misjudgments and omissions caused by inconsistent data or environmental influences, providing accurate evaluation basis for jump trajectory analysis.

[0046] During the trajectory analysis process, the system not only focuses on the spatial position changes of the athlete, but also considers factors such as time dimension, speed change, and acceleration. For example, the athlete's takeoff moment is often accompanied by a large speed change, and the stability of the air posture and the change of the center of gravity may also affect the jump performance. Therefore, the system will conduct comprehensive evaluation on the athlete's trajectory through multi-dimensional data analysis.

[0047] Time calibration of trajectory data: The system first sorts the multi-point coordinate data according to the timestamp to ensure the time sequence relationship of the trajectory data is clear and accurately records the athlete's position at each time point. Time dimension analysis can help the system distinguish the influence of different movement stages (takeoff, air, landing) on the movement trajectory. Time calibration formula: where: and are the timestamps of the current and previous data points, is the time interval between adjacent data points. Time correlation of speed and acceleration: The system needs to calculate the change of speed and acceleration over time to identify the athlete's acceleration, deceleration, or uniform motion during the jump. Speed reflects the athlete's position change per unit time and is an important indicator for evaluating the power at the takeoff moment. The system calculates the speed by calculating the spatial distance and time interval between adjacent trajectory points. Speed calculation formula: where: is the speed at time , , and , are the coordinate points at the current and previous times, is the time interval between adjacent trajectory points. The change of speed reflects the athlete's takeoff process, the stability of the air posture, and the speed decay during the landing phase. The system needs to analyze these changes through consecutive speed values. Speed change formula: where: is the velocity at the moment, and are the current and previous moment velocities, respectively.

[0048] Acceleration is a key physical quantity that reflects the dynamic changes of the athlete, especially during the jump. The acceleration is larger at the take-off, smaller or close to zero in the air, and increases again at landing. The acceleration calculation formula is: where: is the acceleration at the moment, and are the velocities at the moment and the previous moment, is the time interval. The change in acceleration can help the system identify the speed increase at the take-off instant, the stability of the posture in the air, and the impact force at landing. The acceleration change formula is: where: is the acceleration change at the moment, and are the current and previous moment accelerations, respectively.

[0049] The system will comprehensively evaluate the athlete's performance at different stages by combining the velocity and acceleration changes. For example, during the take-off phase, the system focuses on the increase in acceleration and the sudden rise in speed; during the air phase, the system focuses on the stability of the speed and the maintenance of the center of gravity; and during the landing phase, the system evaluates the stability of the landing action and the impact force by analyzing the change in acceleration.

[0050] After completing the above analysis, the system can give the final result of the jump by calculating the total distance of the athlete's jump, flight time, and other indicators. At the same time, the system can also provide suggestions for technical improvement based on the action analysis results to help athletes improve their jumping skills.

[0051] During the test process, the system can give real-time data such as the athlete's speed and acceleration to help the athlete understand their performance and make adjustments based on feedback. If the environmental conditions or the athlete's performance change during the test process, the system will dynamically adjust the analysis parameters, such as the tolerance range and smoothing coefficient, to ensure the stability and accuracy of the data analysis.

[0052] By comprehensively analyzing the time dimension, speed change, acceleration, and dynamically adjusting the analysis parameters, the system can comprehensively evaluate the athlete's jump trajectory. This multi-dimensional data analysis can help the system accurately identify key actions during the jump and give targeted technical suggestions to improve the athlete's long jump performance and technical level.

[0053] In some extreme cases (such as an athlete's takeoff angle being too large, landing irregularly, etc.), the system may encounter trajectory points that are difficult to accurately capture. At this time, the system needs to use intelligent correction algorithms to predict and correct abnormal trajectories based on the known multi-point coordinate data patterns and historical data of the athlete. For example, if the trajectory at a certain moment deviates significantly from the normal trajectory, the system can fill in the missing trajectory data through interpolation or fitting algorithms, ensuring the continuity and accuracy of the data. In addition, based on big data analysis, the system can also identify the athlete's potential movement trends and make predictive adjustments to avoid deviations in overall evaluation results caused by individual data points.

[0054] The system can use curve fitting methods (such as least squares or polynomial fitting) to fit the athlete's trajectory, thereby obtaining a smooth trajectory model and then predicting and correcting abnormal points. The least squares fitting formula is: where: is the fitted trajectory point, is the actual data point, is the weighting coefficient, representing the weight of the fitting. In some complex trajectory changes, the system can use high-order polynomials for trajectory fitting to obtain more accurate trajectory predictions. The polynomial fitting formula is: where: is the fitted polynomial trajectory function, is the coefficient of the polynomial, calculated by least squares.

[0055] The system can analyze the athlete's historical data to identify potential movement trends and predict trajectory changes under different environmental conditions. This helps to correct trajectory deviations caused by abnormal data points. The potential trend analysis formula is: where: is the time moment of the movement trend, and are the amplitude and mean of the trend, is the frequency of the trend, is the phase angle.

[0056] Based on the predicted trend, the system can use predictive correction methods to correct the trajectory when the preliminary data of the trajectory is abnormal, avoiding relying solely on abnormal points for adjustment. The predictive adjustment formula is: where: is the corrected trajectory point, is the trajectory point at the previous moment, is the correction value obtained through trend analysis.

[0057] Through the above steps, the system can intelligently identify abnormal trajectory points, fill in missing data, correct trajectories through interpolation or fitting algorithms, and predict potential movement trends of athletes based on big data analysis. The system not only corrects trajectory deviations caused by extreme situations, but also ensures data continuity and accuracy, thereby providing a reliable data foundation for subsequent jump evaluation.

[0058] Finally, to ensure the continuous accuracy of the system, the standing long jump evaluation system based on visual motion capture needs to have dynamic feedback and real-time optimization functions. The system will adjust the parameters of subsequent analysis in real time based on the current trajectory analysis results, dynamically adjusted tolerance range, and the athlete's in-flight position, and then perform evaluation. For example, the system may adjust the take-off and landing threshold values in real time during the test based on the athlete's real-time performance, making the test results more accurate and personalized in each evaluation. This real-time optimization mechanism can ensure that the system maintains high accuracy and robustness when facing different athletes and different environmental conditions.

[0059] To ensure that the standing long jump evaluation system based on visual motion capture can continuously provide accurate analysis results, the system needs to have dynamic feedback and real-time optimization functions. Based on the current trajectory analysis results, dynamically adjusted tolerance range, and the athlete's in-flight position, the system can adjust the parameters of subsequent analysis in real time, thereby more accurately evaluating the athlete's performance.

[0060] The system will calculate the athlete's posture and center of gravity changes in real time based on their in-flight position to further optimize the evaluation results. For example, the changes in in-flight trajectory and posture after take-off will affect the stability of the jump and the results. The athlete's in-flight position estimation formula is: where: is the coordinate of the in-flight position at time t, is the initial position of the take-off point, is the velocity component at the moment of take-off, is the acceleration component, which is usually constant or small during the in-flight phase. Based on the athlete's in-flight trajectory, the system can optimize the tolerance range and parameter settings in real time to help identify changes in the athlete's in-flight posture and center of gravity.

[0061] During the evaluation process, the system will dynamically feedback the athlete's performance based on the current trajectory analysis and tolerance range. The system will update the athlete's technical evaluation at each moment and provide real-time guidance through the display screen or other feedback mechanisms. The real-time feedback formula is: where: is the real-time feedback result, which is usually a weighted combination of velocity, acceleration, and error, is the moment speed, For the moment The acceleration of is the trajectory error at the current moment, is the feedback weight coefficient.

[0062] Based on real-time feedback, the system can automatically adjust subsequent analysis parameters, such as tolerance range and trajectory fitting algorithm, according to the current analysis results to ensure the accuracy and stability of subsequent evaluations. Based on historical data and real-time feedback, the system can predict the athlete's potential performance trends and optimize parameter settings during the evaluation process. By analyzing the athlete's movement patterns, the system can adjust the tolerance range, predict future movement trajectories, and optimize the data analysis process. Trend prediction formula: ,in: For the moment The predicted trajectory trend, and are the mean and standard deviation of the trend, is the frequency of the trend, is the phase angle.

[0063] Based on the athlete's predicted performance, the system dynamically adjusts analysis parameters, such as speed weighting and acceleration tolerance, to ensure the evaluation model adapts to future trajectory performance. Once all parameters are adjusted, the system generates the final long jump evaluation results, comprehensively considering multiple factors such as trajectory analysis, speed, acceleration, and posture to produce a final performance and technical evaluation report. Based on the final evaluation results, the system generates a detailed report including jump performance, movement evaluation, and technical improvement suggestions to help athletes further improve their skills.

[0064] If the system predicts that the athlete's acceleration changes significantly (for example, during the take-off or landing phase), the acceleration tolerance can be increased to avoid misjudgment. Acceleration tolerance adjustment formula: ,in: is the adjusted acceleration tolerance. is the adjustment coefficient, which indicates the flexibility of tolerance. is the predicted acceleration.

[0065] Through dynamic feedback and real-time optimization, the system continuously adjusts parameters and optimizes data analysis during the long jump assessment based on athlete performance and environmental factors. This adaptive capability not only improves assessment accuracy but also enables the system to better adapt to different athletes' movement patterns and real-time conditions, ensuring the reliability and accuracy of assessment results.

[0066] Embodiment 3: The standing long jump evaluation system based on visual motion capture, comprising a tolerance adjustment module, a trajectory analysis module and an evaluation module. The tolerance adjustment module: capture the multi-point coordinate data of the athlete, identify the position of the athlete in the air, dynamically adjust the tolerance range according to the historical data, the multi-point coordinate data of the athlete and the current sports environment, and send the identified position of the athlete in the air to the evaluation module, and send the multi-point coordinate data to the trajectory analysis module. The trajectory analysis module: analyze the trajectory of the athlete through multi-dimensional data analysis, use intelligent correction algorithm, predict and correct abnormal trajectory according to the multi-point coordinate data of the athlete and historical data, and send the trajectory analysis result to the evaluation module. The evaluation module: according to the current trajectory analysis result, the dynamically adjusted tolerance range and the position of the athlete in the air, adjust the subsequent analysis parameters in real time and then evaluate.

[0067] It should be understood that the term "and / or" herein only describes the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B, which can represent the three cases of A alone, A and B together, and B alone, where A and B can be singular or plural. In addition, the character " / " herein generally represents an "or" relationship between the front and rear associated objects, but it can also represent an "and / or" relationship, which can be understood in the context before and after.

[0068] It should be understood that in various embodiments of the present application, the size of the sequence number of the above-mentioned processes does not mean the order of execution, and the execution order of the processes should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0069] Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application. Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the above-described system, device and unit can refer to the corresponding process in the foregoing method embodiments, which will not be described here.

[0070] The above merely provides the specific implementation of the present application, but the protection scope of the present application is not limited to this. Any person skilled in the art can easily think of the changes or replacements within the technical range disclosed by the present application, which should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A standing long jump assessment method based on visual motion capture, characterized by: The evaluation method comprises the following steps: The evaluation system captures the athlete's multi-point coordinate data, identifies the athlete's position in the air, and adjusts the tolerance range based on a dynamic adjustment algorithm; Analyze athlete trajectories through multi-dimensional data, and use intelligent correction algorithms to predict and correct abnormal trajectories based on the athlete's multi-point coordinate data and historical data; Based on the current trajectory analysis results, the dynamically adjusted tolerance range, and the athlete's aerial position, subsequent analysis parameters are adjusted in real time before evaluation.

2. The standing long jump evaluation method based on visual motion capture according to claim 1, characterized in that: Adjusting the tolerance range according to a dynamic adjustment algorithm includes the following steps: Calculate the initial tolerance value of each data point based on the average error value of all trajectory points in the historical data; The initial tolerance value of the data point is dynamically adjusted based on the current environment's light intensity and the current angle between the camera and the athlete's trajectory to obtain a dynamically adjusted tolerance value.

3. The standing long jump evaluation method based on visual motion capture according to claim 2, characterized in that: The initial tolerance value is calculated as: ,in: For the The initial tolerance value for data points, is the adjustment coefficient, is the average error value of all trajectory points in the historical data; The calculation expression of the tolerance value after dynamic adjustment is: ,in, For the The tolerance value after dynamic adjustment of data points, For the The initial tolerance value for data points, is the environmental impact coefficient, is the environmental sensitivity coefficient, Illumination is the current environmental illumination intensity, and Angle is the angle between the current camera and the athlete's trajectory.

4. The standing long jump evaluation method based on visual motion capture according to claim 3, characterized in that: Based on the current trajectory analysis results, the dynamically adjusted tolerance range, and the athlete's aerial position, subsequent analysis parameters are adjusted in real time and then evaluated. The following steps are included: According to the position of the athlete in the air, the changes in his posture and center of gravity are calculated in real time to estimate the athlete's position in the air; Dynamically feeds back the athlete's performance based on current trajectory analysis and tolerance range, updating the athlete's technical assessment at every moment and providing real-time feedback via the display; By analyzing the athlete's movement pattern, the future movement trajectory is predicted, and the analysis parameters, including speed weighting and acceleration tolerance, are dynamically adjusted according to the athlete's predicted trend.

5. The standing long jump evaluation method based on visual motion capture according to claim 4, characterized in that: The evaluation method further comprises the following steps: Calculate the error value of the coordinate point. If the error value of the coordinate point exceeds the set error threshold, the coordinate point is judged as an outlier and removed from the trajectory. Interpolation is used to fill in the missing coordinate point data.

6. The standing long jump evaluation method based on visual motion capture according to claim 5, characterized in that: Calculate the error value of the coordinate point, the expression is: ,in: is the actual captured coordinate point, is the estimated ideal coordinate point, is the error value of the coordinate point.

7. The standing long jump evaluation method based on visual motion capture according to claim 6, characterized in that: Use interpolation to fill in the missing coordinate point data. The linear interpolation expression is: ,in, are the coordinate values ​​of two adjacent known time points, For the corresponding time point, is the time point that needs to be interpolated, is the coordinate value obtained after interpolation.

8. The standing long jump evaluation method based on visual motion capture according to claim 7, characterized in that: The evaluation system captures the athlete's multi-point coordinate data and identifies the athlete's position in the air, including the following steps: Establish a mathematical model based on perspective transformation to correct coordinate deviation caused by angle changes; By detecting the athlete's position information in real time and compensating according to their movement in space, calibrated coordinates are obtained; The data at each time point are repositioned through angle correction, and the rotated coordinates are obtained through the rotation matrix.

9. The standing long jump evaluation method based on visual motion capture according to claim 8, characterized in that: By detecting the athlete's position information in real time and compensating according to their movement in space, the calibrated coordinates are obtained. The expression is: ,in: is the actual three-dimensional coordinate of the athlete, are the calibrated coordinates, is the position offset of the player relative to the camera.

10. The standing long jump evaluation system based on visual motion capture according to claim 9, used to implement the evaluation method according to any one of claims 19, characterized in that: Includes tolerance adjustment module, trajectory analysis module and evaluation module; Tolerance adjustment module: Captures the multi-point coordinate data of athletes and identifies their positions in the air. It dynamically adjusts the tolerance range based on historical data, the multi-point coordinate data of athletes, and the current sports environment. Trajectory Analysis Module: Analyzes the athlete's trajectory through multi-dimensional data analysis and uses intelligent correction algorithms to predict and correct abnormal trajectories based on the athlete's multi-point coordinate data and historical data; Evaluation Module: Based on the current trajectory analysis results, the dynamically adjusted tolerance range, and the athlete's aerial position, subsequent analysis parameters are adjusted in real time before evaluation.

Images