A sports evaluation method and system based on computer vision

Abstract

The present invention discloses a sports evaluation method and system based on computer vision, which belongs to the field of sports intelligent evaluation and includes the following steps: S1, collecting motion images; S2, matching and fusing motion images under multiple perspectives; S3, processing motion video streams; S4, data preprocessing; S5, obtaining the motion trajectories of athletes and targets, and extracting the motion parameters of key parts of athletes; S6, comparing the motion parameters of key parts of athletes with preset data, and outputting evaluation results based on the comparison results, while evaluating the speed changes and route compliance of athletes by analyzing the motion trajectory; S7, encrypting the evaluation results and uploading them to a user interaction interface for display. The above-mentioned sports evaluation method and system based on computer vision can provide athletes with more intuitive and effective training suggestions while improving the accuracy of evaluation, thereby promoting the improvement of competitive level.

Description

Technical Field

[0001] The present invention relates to the technical field of sports intelligent evaluation, and in particular to a sports evaluation method and system based on computer vision. Background Art

[0002] In the early days, physical education, training, and competition relied entirely on manual refereeing and evaluation, a method characterized by low efficiency, strong subjectivity, and significant errors. With technological advancements, infrared technology has been introduced to assist with monitoring and counting. While this has improved some automation, it still lacks accuracy and environmental adaptability, is susceptible to significant environmental interference, and struggles to meet the precision and stability requirements of modern sports.

[0003] Nowadays, intelligent vision technology represented by visual AI is developing rapidly and is widely used in many fields such as campus sports and competitive sports. These technologies not only improve the objectivity and accuracy of evaluation, but also provide scientific training guidance for athletes. However, despite the many advances brought by intelligent vision technology, there are still some technical and data-level defects and deficiencies, as follows: Technical defects and deficiencies

[0004] 1. Limited environmental adaptability: Even advanced visual AI technology can experience reduced recognition accuracy and unstable tracking in extreme weather conditions (such as heavy rain, snow, and dense fog) or complex lighting environments (such as strong backlight and frequently changing stage lighting). This limits its application in outdoor and special venues.

[0005] 2. Occlusion issues remain to be addressed: In multi-player sports, when athletes block each other or objects, intelligent vision systems may struggle to accurately capture and analyze movements, resulting in missing or erroneous data. This issue is particularly prominent in team sports, impacting the accuracy of overall assessments.

[0006] 3. Difficulty identifying high-speed moving objects: Intelligent vision systems may be unable to quickly and accurately track and identify high-speed moving objects in sports such as tennis and racing, hindering game analysis and data collection. This is particularly challenging in keyframe extraction and standard comparison, where system response speed and accuracy pose challenges.

[0007] 4. Hardware limitations: While high-definition camera and sensor technology continues to advance, performance varies significantly across brands and models, potentially leading to inconsistent data quality. Furthermore, factors such as the device's installation location and angle can also affect data integrity and accuracy.

[0008] 5. Uneven data quality: Due to factors such as the accuracy of data collection equipment, environmental factors, and human intervention, the collected data may contain noise, bias, or incompleteness, affecting the accuracy of subsequent analysis and evaluation results. High-quality data is the foundation of model training and application, so improving the quality and consistency of data collection is an urgent issue that needs to be addressed.

[0009] 6. Data labeling difficulties: Sports movements are complex and diverse, and accurately labeling data requires specialized knowledge and a significant amount of manpower. Labeling is costly, inefficient, and can lead to inconsistent labeling, impacting model training effectiveness.

[0010] In summary, although intelligent vision technology has broad application prospects in the field of sports, it still needs to overcome technical challenges such as environmental adaptability, occlusion, and recognition of high-speed moving objects, and solve problems in data security, quality, and labeling. Summary of the Invention

[0011] The purpose of the present invention is to provide a sports evaluation method and system based on computer vision to solve the above technical problems.

[0012] To achieve the above object, the present invention provides a sports evaluation method based on computer vision, comprising the following steps:

[0013] S1. Collect a series of sports images of athletes and targets from multiple perspectives;

[0014] S2, matching and fusing the motion images from multiple perspectives acquired in step S1 to obtain multiple frames of motion images along the motion trajectory, which form a motion video stream;

[0015] S3, using the non-maximum suppression algorithm improved by Soft-NMS to process the motion video stream obtained in step S2 to remove occlusion;

[0016] S4, data preprocessing, and using adaptive illumination compensation algorithm to adjust the brightness and contrast of the motion video stream;

[0017] S5. Use the target detection algorithm in deep learning to identify the athlete and the target, then use algorithms such as Kalman filtering or particle filtering to obtain the motion trajectories of the athlete and the target, and use the OpenPose pose estimation method to extract the motion parameters of the key parts of the athlete;

[0018] S6. Compare the key motion parameters of the athlete with the preset data, and output the evaluation results based on the comparison results. At the same time, analyze the motion trajectory to evaluate whether the athlete's speed changes and route are in compliance;

[0019] S7. The evaluation results are encrypted and uploaded to the user interface for display, and uploaded to the cloud database for storage.

[0020] Preferably, in step S1 , visible light cameras and infrared cameras arranged at multiple angles along the motion path are used to capture motion images.

[0021] Preferably, in step S4, when the illumination intensity is lower than a set threshold, the motion video stream is processed using image enhancement technology, otherwise the background is removed using a background subtraction algorithm.

[0022] Preferably, in step S5, the target detection algorithm in deep learning is the YOLO algorithm or the Faster R-CNN algorithm;

[0023] The key parts of the athlete include the athlete’s trunk connection points, shoulder joints, hip joints, knee joints, ankle joints, and elbow joints;

[0024] Step S5 specifically includes the following steps:

[0025] S51, pre-processing each frame image in the input motion video stream and inputting it into the YOLO network, the YOLO network divides the input image into multiple grids, each grid is responsible for detecting the target in a specific area;

[0026] S52. Inputting image data labeled with the athlete's body parts and key points into the YOLO network for training, so that the YOLO network learns the feature representations of different parts and key parts; when a new image enters, the YOLO network predicts whether there is an object in each grid, and if so, outputs the category and bounding box coordinates of the object;

[0027] S53, decoding the predicted bounding box, removing the bounding boxes with excessive overlap by non-maximum suppression method, and obtaining the final accurate body part detection box;

[0028] S54, initialize the state vector and covariance matrix of the Kalman filter, wherein the state vector includes the position coordinates (x, y) and velocity (v x , v y );

[0029] S55. In each frame, the state of the target in the current frame is predicted based on the state and motion model predicted in the previous frame:

[0030]

[0031] P k|k-1 =AP k-1|k-1 A T +Q;

[0032] Where, represents the state vector predicted at time k based on the state at time k-1; A represents the state transfer matrix; represents the optimal estimated state vector at time k-1; B represents the control input matrix; u k represents the control input at time k; P k|k-1 P represents the covariance matrix predicted at time k based on the state at time k-1; k-1|k-1 represents the covariance matrix of the optimal estimated state at time k-1; Q represents the process noise covariance matrix;

[0033] S56: The detection result obtained by the target detection algorithm is used as the observation value, and the observation value is fused with the predicted value. The predicted result is then corrected using the Kalman gain to obtain the target state estimation of the current frame:

[0034]

[0035] P k|k =(IK k H)P k|k-1 ;

[0036] Where, represents the optimal estimated state vector at time k; K k represents the Kalman gain at time k; Z k represents the observation value at time k; H represents the observation matrix; P k|k represents the covariance matrix of the optimal estimated state at time k; I represents the identity matrix;

[0037] S57, repeat steps S55-S56 to obtain the target's motion trajectory;

[0038] S58, inputting the image containing the athlete after the target detection and trajectory tracking processing into the OpenPose model;

[0039] S59. Use the OpenPose model to extract features from the image, learn the characteristic representation of the human body in the image, predict the position of each key part of the athlete's body, and present the probability distribution of each key part in the image in the form of a heat map;

[0040] S510: Determine the coordinates of the key parts according to the heat map, and extract the motion parameters of the key parts of the athlete by calculating the relative position relationship and angle between the key parts.

[0041] Preferably, in step S6, the preset data is preset standard data or preset historical data, wherein the preset standard data is obtained by training with expert-labeled data using a semi-supervised learning method;

[0042] It specifically includes the following steps:

[0043] S61, comparing the motion parameters of the key parts of the athlete extracted from the extracted motion video with preset data to obtain a comparison result;

[0044] S62. Based on the comparison results of each parameter, conduct a comprehensive evaluation of the athlete's overall performance;

[0045] S63. Generate evaluation results based on the comprehensive evaluation results;

[0046] S64. Calculate the velocity v based on the positions and time intervals of two adjacent points on the motion trajectory:

[0047]

[0048] Where (x1, y1) and (x2, y2) represent the position coordinates of two adjacent points; Δt represents the time interval between (x1, y1) and (x2, y2);

[0049] S65. Assume that the point on the standard route is (x s ,y s ), the point on the athlete's trajectory is (x a ,y a ), the calculation formula for the deviation distance is:

[0050]

[0051] Where d represents the distance from the standard route;

[0052] S67, determine whether the route is compliant: set the maximum allowable deviation distance to d max , if d>d max , the route is considered non-compliant, otherwise it is considered compliant.

[0053] Preferably, in step S7, the athlete's training is guided in real time through voice broadcast.

[0054] Preferably, in step S7, the evaluation results are displayed in the form of charts, animations, or 3D models through virtual reality or augmented reality.

[0055] A sports evaluation system based on computer vision is used to execute a sports evaluation method based on computer vision. The system includes a multi-angle camera module, a data processing module, an analysis and comparison module, a user interaction interface, and a cloud database. The multi-angle camera module is used to capture motion images of athletes and targets from multiple perspectives; the data processing module is used to process the captured motion images to obtain motion trajectories and motion parameters; the analysis and comparison module is used to compare the processed motion parameters with preset data to output evaluation results, and at the same time, evaluate the speed changes and route compliance of athletes by analyzing the motion trajectory; the user interaction interface is used to display the evaluation results; and the cloud database is used to store the evaluation results.

[0056] Preferably, the data processing module includes a graphics processing unit and a programmable gate array, and the graphics processing unit and the programmable gate array are connected via a standard interface.

[0057] Therefore, the present invention adopts the above-mentioned sports evaluation method and system based on computer vision, which has the following beneficial effects:

[0058] 1. Multi-view data acquisition and fusion: (1) Multi-angle camera module: Multiple visible light and infrared cameras are used to capture the athlete's movements from different angles, ensuring the comprehensiveness and accuracy of the data. In particular, in complex environments (such as insufficient light or obstructions), infrared cameras can make up for the shortcomings of visible light cameras and provide a more reliable data source. At the same time, the non-perceptual monitoring method is more flexible in layout; (2) Image matching and fusion technology: Images from different perspectives are accurately matched and fused to generate a continuous and complete motion video stream, which helps to more accurately reconstruct the motion trajectory in three-dimensional space;

[0059] 2. Intelligent target detection and pose estimation: (1) Improved non-maximum suppression algorithm (Soft-NMS): effectively solves the problem of mutual occlusion between targets and improves the accuracy of target detection; (2) Adaptive illumination compensation and background subtraction algorithm: automatically adjusts image quality according to environmental conditions, ensuring high-quality input data under various lighting conditions; (3) Advanced target detection and tracking algorithm: uses deep learning algorithms such as YOLO and Faster R-CNN combined with Kalman filtering or particle filtering to achieve high-precision recognition and stable tracking of athletes and their equipment; (4) OpenPose pose estimation method: accurately extracts the positions of key skeletal points of athletes, providing a solid foundation for subsequent motion analysis;

[0060] 3. Data-driven evaluation mechanism: (1) Comparison between preset standard data and historical data: not only can evaluation be conducted based on standard data marked by industry experts, but also personalized analysis can be conducted based on the athlete's own historical performance, so that athletes can obtain accurate feedback on their movements in a timely manner, thereby improving the quality of training. For example, after a gymnast completes a movement, the system can provide immediate feedback on the center of gravity, speed, and coordination, helping athletes to make timely adjustments and improvements, reduce the risk of injury, improve their competitive level, and make training more scientific and targeted. (2) Real-time feedback and guidance: Evaluation information is conveyed to athletes in real time through voice broadcasts, chart displays, etc., helping them to adjust their training strategies in a timely manner. At the same time, it supports the presentation of results in the form of virtual reality (VR) or augmented reality (AR), which enhances interactivity and fun and reduces interference from human factors.

[0061] 4. Safe and efficient data management: (1) Encrypted transmission and cloud storage: The evaluation results are encrypted and uploaded to the user interface for display, and are simultaneously saved to the cloud database, which not only ensures information security but also facilitates long-term archiving and query; (2) Modular design: The entire system consists of multiple independent but closely coordinated functional modules, which facilitates maintenance and upgrades, and also improves the flexibility and scalability of the system.

[0062] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] Figure 1 The present invention is a flowchart of a sports evaluation method based on computer vision. DETAILED DESCRIPTION

[0064] In order to make the purposes, technical solutions and advantages disclosed in the embodiments of the present invention clearer, the embodiments of the present invention are further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the embodiments of the present invention and are not intended to limit the embodiments of the present invention. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application. Examples of the embodiments are shown in the accompanying drawings, where the same or similar numbers throughout represent the same or similar elements or elements with the same or similar functions.

[0065] It should be noted that the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or are inherent to these processes, methods, products or devices.

[0066] The embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0067] like Figure 1 As shown, a sports evaluation method based on computer vision includes the following steps:

[0068] S1. Collect a series of sports images of athletes and targets from multiple perspectives;

[0069] In step S1 , visible light cameras and infrared cameras arranged at multiple angles along the motion path are used to capture motion images. In bad weather, infrared cameras can be used to assist in imaging.

[0070] S2, matching and fusing the motion images from multiple perspectives acquired in step S1 to ensure data consistency and accuracy, and obtaining multiple frames of motion images along the motion trajectory, which form a motion video stream;

[0071] S3, using the non-maximum suppression algorithm improved by Soft-NMS to process the motion video stream obtained in step S2 to remove occlusion;

[0072] S4, data preprocessing (cleaning, denoising, correction, rotation, flipping, cropping), and using adaptive illumination compensation algorithm to adjust the brightness and contrast of the motion video stream;

[0073] In step S4, when the illumination intensity is lower than the set threshold, the motion video stream is processed using image enhancement technology, otherwise the background is removed using a background subtraction algorithm.

[0074] S5. Use the target detection algorithm in deep learning to identify the athlete and the target, then use algorithms such as Kalman filtering or particle filtering to obtain the motion trajectories of the athlete and the target, and use the OpenPose pose estimation method to extract the motion parameters of the key parts of the athlete;

[0075] In step S5, the target detection algorithm in deep learning is the YOLO algorithm or the Faster R-CNN algorithm. The target detection algorithm in this embodiment is obtained by training data from multiple sports scenes to improve the accuracy and robustness of detection;

[0076] The key parts of the athlete include the athlete’s trunk connection points, shoulder joints, hip joints, knee joints, ankle joints, and elbow joints;

[0077] Step S5 specifically includes the following steps:

[0078] S51, pre-processing each frame image in the input motion video stream and inputting it into the YOLO network, the YOLO network divides the input image into multiple grids, each grid is responsible for detecting the target in a specific area;

[0079] S52. Inputting image data labeled with the athlete's body parts and key points into the YOLO network for training, so that the YOLO network learns the feature representations of different parts and key parts; when a new image enters, the YOLO network predicts whether there is an object in each grid, and if so, outputs the category and bounding box coordinates of the object;

[0080] S53, decoding the predicted bounding box, removing the bounding boxes with excessive overlap by non-maximum suppression method, and obtaining the final accurate body part detection box;

[0081] S54, initialize the state vector and covariance matrix of the Kalman filter, wherein the state vector includes the position coordinates (x, y) and velocity (v x , v y );

[0082] S55. In each frame, the state of the target in the current frame is predicted based on the state and motion model predicted in the previous frame:

[0083]

[0084] P k|k-1 =AP k-1|k-1 A T +Q;

[0085] Where, represents the state vector predicted at time k based on the state at time k-1; A represents the state transfer matrix; represents the optimal estimated state vector at time k-1; B represents the control input matrix; u k represents the control input at time k; P k|k-1 P represents the covariance matrix predicted at time k based on the state at time k-1; k-1|k-1 represents the covariance matrix of the optimal estimated state at time k-1; Q represents the process noise covariance matrix;

[0086] S56: The detection result obtained by the target detection algorithm is used as the observation value, and the observation value is fused with the predicted value. The predicted result is then corrected using the Kalman gain to obtain the target state estimation of the current frame:

[0087]

[0088] P k|k =(IK k H)P k|k-1 ;

[0089] Where, represents the optimal estimated state vector at time k; K krepresents the Kalman gain at time k; Z k represents the observation value at time k; H represents the observation matrix; P k|k represents the covariance matrix of the optimal estimated state at time k; I represents the identity matrix;

[0090] S57, repeat steps S55-S56 to obtain the target's motion trajectory;

[0091] S58, inputting the image containing the athlete after the target detection and trajectory tracking processing into the OpenPose model;

[0092] S59. Use the OpenPose model to extract features from the image, learn the characteristic representation of the human body in the image, predict the position of each key part of the athlete's body, and present the probability distribution of each key part in the image in the form of a heat map;

[0093] S510: Determine the coordinates of the key parts according to the heat map, and extract the motion parameters of the key parts of the athlete by calculating the relative position relationship and angle between the key parts.

[0094] S6. Compare the key motion parameters of the athlete with the preset data, and output the evaluation results based on the comparison results. At the same time, analyze the motion trajectory to evaluate whether the athlete's speed changes and route are in compliance;

[0095] In step S6, the preset data is preset standard data or preset historical data, wherein the preset standard data is obtained by training with expert-labeled data using a semi-supervised learning method, that is, training unlabeled data with a small amount of labeled data to obtain a large amount of labeled data;

[0096] It specifically includes the following steps:

[0097] S61, comparing the motion parameters of the key parts of the athlete extracted from the extracted motion video with preset data to obtain a comparison result;

[0098] S62. Based on the comparison results of each parameter, conduct a comprehensive evaluation of the athlete's overall performance;

[0099] S63. Generate evaluation results based on the comprehensive evaluation results;

[0100] S64. Calculate the velocity v based on the positions and time intervals of two adjacent points on the motion trajectory:

[0101]

[0102] Where (x1, y1) and (x2, y2) represent the position coordinates of two adjacent points; Δt represents the time interval between (x1, y1) and (x2, y2);

[0103] S65. Assume that the point on the standard route is (x s ,y s ), the point on the athlete's trajectory is (x a ,y a ), the calculation formula for the deviation distance is:

[0104]

[0105] Where d represents the distance from the standard route;

[0106] S67, determine whether the route is compliant: set the maximum allowable deviation distance to d max , if d>d max , the route is considered non-compliant, otherwise it is considered compliant.

[0107] In this embodiment, patterns can be learned from empirical values or tracking key areas such as the center of gravity, hip, knee, and ankle in videos of athletes performing 100-meter sprints, standing jumps, triple jumps, marathons, and volleyball. Pixel metrics for these key points can then be determined to determine the optimal range of actual distance for parameters such as angle, angular velocity, support time, support ratio, leg lift angle, foot landing angle, stride length, and calf length. The obtained parameters, such as angle, angular velocity, support time, support ratio, and stride length, are then compared with the actual video, automatically annotating key frames (first push-off, first touchdown; second push-off, second touchdown; third push-off, third touchdown; fourth push-off, fourth touchdown; fifth push-off, fifth touchdown). Comparison results and training recommendations are then provided based on the key frames.

[0108] The specific steps for automatically marking key frames are as follows:

[0109] Step 1: Parameter extraction and calculation: Using target detection algorithms and posture estimation methods, we track key areas such as the center of gravity, hip, knee, and ankle in videos of athletes performing 100-meter sprints, standing jumps, triple jumps, marathons, and volleyball. Based on the pixel coordinates of these key areas, we calculate parameters such as angle, angular velocity, support time, support-to-lift ratio, foot lift angle, foot landing angle, stride length, and calf length.

[0110] The second step is to set the key frame judgment threshold: Based on the rules learned from a large number of motion videos and experience values in the early stage, determine the reasonable range of each parameter at the key frame moment, and use this as the judgment threshold.

[0111] The third step is to traverse the video frames for key frame detection: according to the time sequence of the video, analyze the calculated parameters frame by frame. In each frame, the extracted parameters are compared with the set key frame judgment threshold. For example, for the running project, when detecting the first step, when the detected parameters meet the threshold conditions of the first step push-off (such as the center of gravity moving up quickly, the leg joint angle change meeting the push-off characteristics, etc.), the frame is marked as the first step push-off key frame;

[0112] Step 4: Keyframe Verification and Correction: To avoid misjudgments, verify the initially marked keyframes by analyzing the parameter change trends in the frames before and after the keyframe to ensure that the parameter changes conform to the logic of the key action. For example, after marking the touchdown keyframe for running, check whether the leg joint angles in the subsequent frames change according to the normal running action rules. If not, re-evaluate the accuracy of the keyframe. If a misjudgment is found, correct the keyframe according to the actual situation to ensure the accuracy of the marking;

[0113] Step 5: Annotate and organize: Verified keyframes are annotated and output in a unified format, recording the keyframe's frame number and corresponding action type (e.g., first push-off, second touchdown, etc.). The annotated keyframes are organized into a list or database for subsequent comparison with the preset optimal parameter range, which then provides comparison results and targeted training recommendations.

[0114] S7. The evaluation results are encrypted and uploaded to the user interface for display, and uploaded to the cloud database for storage. The encryption operation is convenient for protecting the privacy of the athletes.

[0115] In step S7, the athlete's training is guided in real time through voice broadcast.

[0116] In step S7, the evaluation results are displayed in the form of charts, animations, or 3D models through virtual reality or augmented reality.

[0117] A computer vision-based sports evaluation system, used to implement a computer vision-based sports evaluation method, includes a multi-angle camera module, a data processing module, an analysis and comparison module, a user interface, and a cloud database. The multi-angle camera module is used to capture motion images of athletes and targets from multiple perspectives; the data processing module is used to process the captured motion images to obtain motion trajectories and motion parameters; the analysis and comparison module is used to compare the processed motion parameters with preset data to output evaluation results, and simultaneously evaluate the athlete's speed changes and route compliance by analyzing the motion trajectory; the user interface is used to display the evaluation results; and the cloud database is used to store the evaluation results. The data processing module includes a graphics processing unit and a programmable gate array. The graphics processing unit and the programmable gate array are connected via a standard interface, enabling seamless integration between different devices and systems. A modular system architecture design is also adopted to facilitate the addition of new functional modules or evaluation items when needed.

[0118] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit the same. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that they can still modify or replace the technical solutions of the present invention with equivalents, and these modifications or equivalent replacements cannot cause the modified technical solutions to deviate from the spirit and scope of the technical solutions of the present invention.

Claims

1. A sports evaluation method based on computer vision, characterized by: The following steps are involved: S1. Collect a series of sports images of athletes and targets from multiple perspectives; S2, matching and fusing the motion images from multiple perspectives acquired in step S1 to obtain multiple frames of motion images along the motion trajectory, which form a motion video stream; S3, using the non-maximum suppression algorithm improved by Soft-NMS to process the motion video stream obtained in step S2 to remove occlusion; S4, data preprocessing, and using adaptive illumination compensation algorithm to adjust the brightness and contrast of the motion video stream; S5. Use the target detection algorithm in deep learning to identify the athlete and the target, then use algorithms such as Kalman filtering or particle filtering to obtain the motion trajectories of the athlete and the target, and use the OpenPose pose estimation method to extract the motion parameters of the key parts of the athlete; S6. Compare the key motion parameters of the athlete with the preset data, and output the evaluation results based on the comparison results. At the same time, analyze the motion trajectory to evaluate whether the athlete's speed changes and route are in compliance; In step S6, the preset data is preset standard data or preset historical data, wherein the preset standard data is obtained by training with expert-labeled data using a semi-supervised learning method; It specifically includes the following steps: S61, comparing the motion parameters of the key parts of the athlete extracted from the extracted motion video with preset data to obtain a comparison result; S62. Based on the comparison results of each parameter, conduct a comprehensive evaluation of the athlete's overall performance; S63. Generate evaluation results based on the comprehensive evaluation results; S64. Calculate the velocity v based on the positions and time intervals of two adjacent points on the motion trajectory: Where (x1, y1) and (x2, y2) represent the position coordinates of two adjacent points; Δt represents the time interval between (x1, y1) and (x2, y2); S65. Assume that the point on the standard route is (x s ,y s ), the point on the athlete's trajectory is (x a ,y a ), the calculation formula for the deviation distance is: Where d represents the distance from the standard route; S67, determine whether the route is compliant: set the maximum allowable deviation distance to d max , if d>d max , the route is considered non-compliant, otherwise it is considered compliant; S7. The evaluation results are encrypted and uploaded to the user interface for display, and uploaded to the cloud database for storage.

2. The computer vision-based sports evaluation method according to claim 1, wherein: In step S1 , motion images are captured using visible light cameras and infrared cameras arranged at multiple angles along a motion path.

3. The computer vision-based sports evaluation method according to claim 1, wherein: In step S4, when the illumination intensity is lower than the set threshold, the motion video stream is processed using image enhancement technology, otherwise the background is removed using a background subtraction algorithm.

4. The computer vision-based sports evaluation method according to claim 1, wherein: In step S5, the target detection algorithm in deep learning is the YOLO algorithm or the Faster R-CNN algorithm; The key parts of the athlete include the athlete’s trunk connection points, shoulder joints, hip joints, knee joints, ankle joints, and elbow joints; Step S5 specifically includes the following steps: S51, pre-processing each frame image in the input motion video stream and inputting it into the YOLO network, the YOLO network divides the input image into multiple grids, each grid is responsible for detecting the target in a specific area; S52. Inputting image data labeled with the athlete's body parts and key points into the YOLO network for training, so that the YOLO network learns the feature representations of different parts and key parts; when a new image enters, the YOLO network predicts whether there is an object in each grid, and if so, outputs the category and bounding box coordinates of the object; S53, decoding the predicted bounding box, removing the bounding boxes with excessive overlap by non-maximum suppression method, and obtaining the final accurate body part detection box; S54, initialize the state vector and covariance matrix of the Kalman filter, wherein the state vector includes the position coordinates (x, y) and velocity (v x , v y ); S55. In each frame, the state of the target in the current frame is predicted based on the state and motion model predicted in the previous frame: P k|k-1 =AP k-1|k-1 From T +Q; Where, represents the state vector predicted at time k based on the state at time k-1; A represents the state transfer matrix; represents the optimal estimated state vector at time k-1; B represents the control input matrix; u k represents the control input at time k; P k|k-1 P represents the covariance matrix predicted at time k based on the state at time k-1; k-1|k-1 represents the covariance matrix of the optimal estimated state at time k-1; Q represents the process noise covariance matrix; S56: The detection result obtained by the target detection algorithm is used as the observation value, and the observation value is fused with the predicted value. The predicted result is then corrected using the Kalman gain to obtain the target state estimation of the current frame: P k|k =(I-K k H)P k|k-1 ; Where, represents the optimal estimated state vector at time k; K k represents the Kalman gain at time k; Z k represents the observation value at time k; H represents the observation matrix; P k|k represents the covariance matrix of the optimal estimated state at time k; I represents the identity matrix; S57, repeat steps S55-S56 to obtain the target's motion trajectory; S58, inputting the image containing the athlete after the target detection and trajectory tracking processing into the OpenPose model; S59. Use the OpenPose model to extract features from the image, learn the characteristic representation of the human body in the image, predict the position of each key part of the athlete's body, and present the probability distribution of each key part in the image in the form of a heat map; S510: Determine the coordinates of the key parts according to the heat map, and extract the motion parameters of the key parts of the athlete by calculating the relative position relationship and angle between the key parts.

5. The computer vision-based sports evaluation method according to claim 1, wherein: In step S7, the athlete's training is guided in real time through voice broadcast.

6. The computer vision-based sports evaluation method according to claim 1, characterized in that: In step S7, the evaluation results are displayed in the form of charts, animations, or 3D models through virtual reality or augmented reality.

7. A sports evaluation system based on computer vision, characterized by: A computer vision-based sports evaluation method for executing any one of claims 1 to 6, comprising a multi-angle camera module, a data processing module, an analysis and comparison module, a user interaction interface, and a cloud database, wherein the multi-angle camera module is used to capture motion images of athletes and targets from multiple perspectives; the data processing module is used to process the captured motion images to obtain motion trajectories and motion parameters; the analysis and comparison module is used to compare the processed motion parameters with preset data to output evaluation results, and at the same time, evaluate the speed changes and route compliance of the athletes by analyzing the motion trajectories; The user interface is used to display the evaluation results; The cloud database is used to store the evaluation results.

8. The computer vision-based sports evaluation system according to claim 7, characterized in that: The data processing module includes a graphics processing unit and a programmable gate array, and the graphics processing unit and the programmable gate array are connected via a standard interface.

Images