Method and platform for sensing three-dimensional motion data

Abstract

The invention discloses a method and platform for sensing three-dimensional motion data, and relates to the technical field of three-dimensional motion, and the method comprises the steps of 1, data analysis, 2, data analysis and 3, early warning prompt. The method comprises the following steps: synchronously shooting each athlete attached with a mark point through multiple cameras, acquiring motion capture data, analyzing a motion capture index of each athlete in a motion process, judging whether motion capture of each athlete is abnormal or not, if so, carrying out re-monitoring, and if not, judging whether the motion capture of each athlete is abnormal or not. According to the method, the abnormal motion capture data of each abnormal athlete in the motion process is obtained, so that the one-sidedness of local motion analysis is avoided, the precision detection of the motion fluency of the athletes in the motion process is improved, and the training pertinence is improved. According to the method, the abnormal motion capture index of each abnormal athlete in the exercise process is evaluated, and early warning prompt is performed, so that the accuracy of early warning of the exercise risk is improved, and misjudgment of a single index is avoided.

Description

Technical Field

[0001] The present invention relates to the field of three-dimensional motion technology, and in particular to a method and platform for sensing three-dimensional motion data. Background Art

[0002] With the rapid development of modern science and technology, three-dimensional motion data sensing technology has become an indispensable key support in many fields. In the fields of sports and exercise science, accurately acquiring athletes' motion data enables scientific training and sports injury prevention. Three-dimensional motion data sensing mainly relies on mechanical measurement devices. These devices are connected to the measured object through mechanical linkages and directly measure joint angles. However, these devices have problems such as limited measurement range, poor flexibility, and easy interference with the measured object. Therefore, it is necessary to analyze the methods and platforms for sensing three-dimensional motion data.

[0003] Prior art, such as the invention patent application with publication number: CN105229703B, discloses a computer-implemented method for generating a three-dimensional (3D) model. The method includes receiving first and second sets of sensed position data indicating the position of a camera device at or near the time when the camera device was used to respectively acquire first and second images of an image pair, determining a sensed rotation matrix and / or a sensed translation vector for the image pair using the first and second sets of sensed position data, identifying a calculated transformation including the calculated translation vector and the rotation matrix, generating a sensed camera transformation including the sensed rotation matrix and / or the sensed translation vector, and if the sensed camera transformation is associated with a lower error than the calculated camera transformation, using it to generate the 3D model.

[0004] The existing methods and platforms for sensing three-dimensional motion data can meet basic requirements, but there are also some potential defects and challenges, which are specifically reflected in the following aspects: First, the existing technology lacks analysis of the motion capture index of each athlete during exercise, which in turn affects the judgment of whether there is any abnormality in the motion capture of each athlete, affects the one-sidedness of local motion analysis, reduces the accuracy of the detection of the athlete's movement smoothness during exercise, and thus affects the targeted training.

[0005] Second, the existing technology does not pay enough attention to the evaluation of abnormal motion capture indexes of abnormal athletes during exercise, which in turn affects early warning prompts, reduces the accuracy of early warnings of sports risks, leads to misjudgment of a single indicator, affects early warnings of excessive fatigue risks, and thus affects the health protection and competitive level improvement of athletes. Summary of the Invention

[0006] The purpose of the present invention is to provide a method and platform for sensing three-dimensional motion data, which solves the problems existing in the background technology.

[0007] To solve the above technical problems, the present invention adopts the following technical solution: The present invention provides a method for sensing three-dimensional motion data, including step one, data analysis, step two, data analysis and step three, early warning prompt.

[0008] Step 1: Data analysis: Use multiple cameras to synchronously shoot each athlete with attached markers to obtain motion capture data and analyze the motion capture index of each athlete during the exercise.

[0009] Step 2: Data analysis: Based on the obtained motion capture index of each athlete during the exercise, determine whether the motion capture of each athlete is abnormal. If abnormal, re-monitor and obtain the abnormal motion capture data of each abnormal athlete during the exercise.

[0010] Step 3: Early warning: Based on the abnormal motion capture data of each abnormal athlete during the exercise, the abnormal motion capture index of each abnormal athlete during the exercise is evaluated and an early warning is issued.

[0011] Furthermore, the motion capture data specifically includes: optical capture data, inertial capture data and visual capture data.

[0012] Furthermore, the motion capture index of each athlete during the movement is analyzed in a specific analysis method as follows: based on the obtained optical capture data, inertial capture data and visual capture data, the optical capture value A of each athlete during the movement is analyzed. x , inertia capture value R x and visual capture value T x , and then analyze the motion capture index of each athlete during the movement. The specific calculation formula is: x =A x +R x +T x , where x represents the number of each athlete, x=1,2,...,g, and g represents the number of the athlete.

[0013] Furthermore, the specific analysis method of the optical capture value of each athlete during the movement is: based on the obtained optical capture data, wherein the optical capture data includes: the joint trajectory offset value, angular velocity and bending angle of each athlete in each time period during the movement, and extracting the joint trajectory offset value safety interval, angular velocity safety interval and bending angle safety interval of each athlete in each time period during the movement from the database, and comparing the joint trajectory offset value, angular velocity and bending angle of each athlete in each time period during the movement with the joint trajectory offset value safety interval, angular velocity safety interval and bending angle safety interval of each athlete in each time period during the movement; if the joint trajectory offset value of a certain time period of an athlete in the movement is within the joint trajectory offset value safety interval, the angular velocity is within the angular velocity safety interval and the bending angle is within the bending angle safety interval, then the optical capture value of the athlete in this time period during the movement is recorded as 1, otherwise it is recorded as -1, thereby obtaining the optical capture value A of each athlete in the movement. x , where A x The values ​​include 1 and -1.

[0014] Furthermore, the inertia capture value of each athlete during the exercise is specifically analyzed by the following method: based on the obtained inertia capture data, wherein the inertia capture data includes: the cadence and impact peak of each athlete's limbs during the exercise, and extracting the cadence compliance interval and impact peak compliance interval of each athlete's limbs during the exercise from the database, comparing the cadence and impact peak of each athlete's limbs during the exercise with the cadence compliance interval and impact peak compliance interval; if the cadence of an athlete during the exercise is in the cadence compliance interval and the impact peak is in the impact peak compliance interval, then the inertia capture value of the athlete during the exercise is recorded as 1, otherwise, it is recorded as -1, thereby obtaining the inertia capture value R of each athlete during the exercise. x , where R x The values ​​include 1 and -1.

[0015] Furthermore, the visual capture value of each athlete during the movement is specifically analyzed as follows: based on the obtained visual capture data, wherein the visual capture data includes: the visual displacement difference and pixel clarity value of each athlete in each time period during the movement, the visual displacement difference and pixel clarity value of each athlete in each time period during the movement are compared with the visual displacement difference compliance interval and pixel clarity value compliance interval of each athlete in the movement stored in the database; if the visual displacement difference of a certain time period of an athlete in the movement is within the visual displacement difference compliance interval and the pixel clarity value is within the pixel clarity value compliance interval, then the visual capture value of the athlete in the time period during the movement is recorded as 1; otherwise, it is recorded as -1, thereby obtaining the visual capture value H of each athlete in the movement. x , where H x The values ​​include 1 and -1.

[0016] Furthermore, the specific analysis method for determining whether there is an abnormality in the motion capture of each athlete is as follows: based on the obtained motion capture index of each athlete during the exercise, the motion capture index of each athlete during the exercise is compared with the motion capture index compliance interval of the athletes during the exercise stored in the database; if the motion capture index of an athlete during the exercise is not within the motion capture index compliance interval, it indicates that there is an abnormality in the motion capture of the athlete, and then the abnormal athletes during the exercise are obtained, and the abnormal motion capture data of each abnormal athlete during the exercise is obtained.

[0017] Furthermore, the abnormal motion capture data of each abnormal athlete during the exercise process, wherein the abnormal motion capture data includes: the motion deviation value, the power deviation value and the motion timing matching value of each abnormal athlete during the exercise process.

[0018] Furthermore, the abnormal motion capture index of each abnormal athlete in the exercise process is evaluated to provide an early warning prompt. The specific analysis method is: obtaining the motion deviation value compliance interval, power deviation value compliance interval and action timing matching value compliance interval of each abnormal athlete in the exercise process from the database, and importing the abnormal motion capture data into the abnormal motion capture index evaluation model. Get the abnormal motion capture index of each abnormal athlete during the movement, F dp It is represented as the pth abnormal motion capture data of the dth abnormal athlete during the movement, F dp ' represents the safe interval of the pth abnormal motion capture data of the dth abnormal athlete during the movement, p∈[1,3], d represents the number of each abnormal athlete, d=1,2,...,n, n represents the number of abnormal athletes, and p represents the number of abnormal motion capture data.

[0019] When the abnormal motion capture index of each abnormal athlete during exercise is -1, an early warning prompt will be issued, the test will be re-performed, and the data will be sent to the platform.

[0020] The second aspect of the present invention provides a platform for executing the method of sensing three-dimensional motion data, characterized in that it includes: a data analysis module: synchronously shooting each athlete with attached marker points through multiple cameras, obtaining motion capture data, and analyzing the motion capture index of each athlete during the movement.

[0021] Data analysis module: Based on the motion capture index of each athlete during the exercise, it is determined whether there is any abnormality in the motion capture of each athlete. If there is any abnormality, re-monitoring is performed to obtain the abnormal motion capture data of each abnormal athlete during the exercise.

[0022] Early warning prompt module: Based on the abnormal motion capture data of each abnormal athlete during the exercise, the abnormal motion capture index of each abnormal athlete during the exercise is evaluated and early warning prompts are issued.

[0023] The beneficial effects of the present invention are: in step one, data analysis and step two, data analysis: multiple cameras are used to synchronously shoot each athlete with attached markers to obtain motion capture data, analyze the motion capture index of each athlete during the movement, and determine whether there is any abnormality in the motion capture of each athlete. If there is any abnormality, re-monitoring is performed to obtain abnormal motion capture data of each abnormal athlete during the movement, thereby avoiding the one-sidedness of local motion analysis, improving the accuracy of detection of the smoothness of the athletes' movements during the movement, and improving the targeted training.

[0024] In step three, early warning prompts: based on the abnormal motion capture data of each abnormal athlete during the exercise, the abnormal motion capture index of each abnormal athlete during the exercise is evaluated, and early warning prompts are issued to improve the accuracy of early warning of sports risks, avoid misjudgment of a single indicator, and timely warn of excessive fatigue risks, providing dual support for athletes' health protection and improvement of competitive level. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0026] Figure 1The figure is a schematic flow chart of the steps for implementing the method of the present invention.

[0027] Figure 2 This is a schematic diagram of the system structure connection of the present invention. DETAILED DESCRIPTION

[0028] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0029] Reference Figure 1 As shown, the present invention provides a method for sensing three-dimensional motion data, including: step one, data analysis, step two, data analysis and step three, early warning prompt.

[0030] Step 1: Data analysis: Use multiple cameras to synchronously shoot each athlete with attached markers to obtain motion capture data and analyze the motion capture index of each athlete during the exercise.

[0031] In the above embodiment, the motion capture data specifically includes: optical capture data, inertial capture data and visual capture data.

[0032] In the above embodiment, the motion capture index of each athlete during the movement is analyzed by the following specific analysis method: based on the obtained optical capture data, inertial capture data and visual capture data, the optical capture value A of each athlete during the movement is analyzed. x , inertia capture value R x and visual capture value T x , and then analyze the motion capture index of each athlete during the movement. The specific calculation formula is: x =A x +R x +T x , where x represents the number of each athlete, x=1,2,...,g, and g represents the number of the athlete.

[0033] It should be noted that optical capture data uses infrared cameras to capture marker points, accurately recording the three-dimensional coordinates of joints with errors as low as millimeters. Inertial capture data relies on inertial sensors to monitor acceleration and angular velocity in real time, unrestricted by line of sight. Visual capture data uses computer vision algorithms to analyze markerless movements. The fusion of these three types of data can overcome the limitations of individual technologies, such as optical capture's susceptibility to occlusion, inertial capture's cumulative errors, and low visual capture accuracy. For example, in the analysis of complex changes in direction by basketball players, optical data ensures accurate spatial positioning, inertial data assists in capturing rapid changes in movement, and visual data supplements details of markerless parts, allowing the motion capture index to more comprehensively and accurately reflect the actual movement. Therefore, it is necessary to analyze optical, inertial, and visual capture data.

[0034] In the above embodiment, the specific analysis method of the optical capture value of each athlete during the movement is: based on the obtained optical capture data, wherein the optical capture data includes: the joint trajectory offset value, angular velocity and bending angle of each athlete in each time period during the movement, and extracting the joint trajectory offset value safety interval, angular velocity safety interval and bending angle safety interval of each athlete in each time period during the movement from the database, and comparing the joint trajectory offset value, angular velocity and bending angle of each athlete in each time period during the movement with the joint trajectory offset value safety interval, angular velocity safety interval and bending angle safety interval of each athlete in each time period during the movement. If the joint trajectory offset value of a certain time period of an athlete in the movement is within the joint trajectory offset value safety interval, the angular velocity is within the angular velocity safety interval and the bending angle is within the bending angle safety interval, then the optical capture value of the athlete in this time period during the movement is recorded as 1, otherwise it is recorded as -1, thereby obtaining the optical capture value A of each athlete in the movement. x , where A x The values ​​include 1 and -1.

[0035] In the above embodiment, the inertia capture value of each athlete during the exercise is specifically analyzed by the following method: based on the obtained inertia capture data, wherein the inertia capture data includes: the cadence and impact peak of each athlete's limbs during the exercise, and extracting the cadence compliance interval and impact peak compliance interval of each athlete's limbs during the exercise from the database, comparing the cadence and impact peak of each athlete's limbs during the exercise with the cadence compliance interval and impact peak compliance interval; if the cadence of an athlete during the exercise is in the cadence compliance interval and the impact peak is in the impact peak compliance interval, then the inertia capture value of the athlete during the exercise is recorded as 1, otherwise, it is recorded as -1, thereby obtaining the inertia capture value R of each athlete during the exercise. x , where Rx The values ​​include 1 and -1.

[0036] In the above embodiment, the specific analysis method of the visual capture value of each athlete during the movement is as follows: based on the obtained visual capture data, wherein the visual capture data includes: the visual displacement difference and pixel clarity value of each athlete in each time period during the movement, the visual displacement difference and pixel clarity value of each athlete in each time period during the movement are compared with the visual displacement difference compliance interval and pixel clarity value compliance interval of each athlete in the movement stored in the database; if the visual displacement difference of a certain time period of an athlete in the movement is within the visual displacement difference compliance interval and the pixel clarity value is within the pixel clarity value compliance interval, then the visual capture value of the athlete in the time period during the movement is recorded as 1; otherwise, it is recorded as -1, thereby obtaining the visual capture value H of each athlete in the movement. x , where H x The values ​​include 1 and -1.

[0037] Step 2: Data analysis: Based on the obtained motion capture index of each athlete during the exercise, determine whether the motion capture of each athlete is abnormal. If abnormal, re-monitor and obtain the abnormal motion capture data of each abnormal athlete during the exercise.

[0038] In the above embodiment, the specific analysis method for determining whether there is an abnormality in the motion capture of each athlete is as follows: based on the obtained motion capture index of each athlete during the exercise, the motion capture index of each athlete during the exercise is compared with the motion capture index compliance interval of the athletes during the exercise stored in the database. If the motion capture index of an athlete during the exercise is not in the motion capture index compliance interval, it means that there is an abnormality in the motion capture of the athlete, and then the abnormal athletes during the exercise are obtained, and the abnormal motion capture data of each abnormal athlete during the exercise are obtained.

[0039] In the above embodiment, the abnormal motion capture data of each abnormal athlete during the exercise process, wherein the abnormal motion capture data includes: the motion deviation value, the power deviation value and the motion timing matching value of each abnormal athlete during the exercise process.

[0040] It should be noted that the motion deviation value of each abnormal athlete during the exercise process refers to the deviation value between the athlete's actual motion trajectory, joint angle, limb displacement and other spatial parameters and the standard motion model. It is calculated by the three-dimensional coordinates of the infrared marker point. Through spatial positioning, the abnormality of the "shape" of the movement is identified. For example, when a basketball player jumps and shoots, the elbow abduction angle exceeds the standard value by 15°. The motion deviation value directly reflects the spatial position deviation of the joint and provides a morphological basis for the abnormality index. If the motion deviation value of a single joint continues to exceed the standard, it may indicate a deformation of the technical movement, such as excessive internal rotation of the shoulder during a tennis serve, or a decrease in movement control ability due to fatigue. The abnormality index will increase the risk level accordingly.

[0041] It should be noted that the dynamic deviation value of each abnormal athlete during exercise refers to the deviation between the dynamic indicators such as strength, speed, acceleration, and impact force during the movement and the normal state, which is mainly obtained through inertial capture data; the dynamic deviation value can provide early warning of hidden risks. Even if the movement form is not obviously abnormal, if the dynamic parameters are disordered, it will lead to an increase in the abnormal index. For example, when a basketball player changes direction, the horizontal component of the ground reaction force increases abnormally, which may indicate the risk of ACL injury to the knee joint.

[0042] It should be noted that the timing matching value of each abnormal athlete's movement during exercise refers to the matching degree of the time sequence, rhythm and duration of each link of the movement with the standard model, which is calculated by combining visual capture and inertial data.

[0043] Step 3: Early warning: Based on the abnormal motion capture data of each abnormal athlete during the exercise, the abnormal motion capture index of each abnormal athlete during the exercise is evaluated and an early warning is issued.

[0044] In the above embodiment, the abnormal motion capture index of each abnormal athlete during the exercise is evaluated to provide an early warning prompt. The specific analysis method is: obtaining the motion deviation value compliance interval, power deviation value compliance interval and action timing matching value compliance interval of each abnormal athlete during the exercise from the database, and importing the abnormal motion capture data into the abnormal motion capture index evaluation model. Get the abnormal motion capture index of each abnormal athlete during the movement, F dp It is represented as the pth abnormal motion capture data of the dth abnormal athlete during the movement, F dp ' represents the safe interval of the pth abnormal motion capture data of the dth abnormal athlete during the movement, p∈[1,3], d represents the number of each abnormal athlete, d=1,2,...,n, n represents the number of abnormal athletes, and p represents the number of abnormal motion capture data.

[0045] When the abnormal motion capture index of each abnormal athlete during exercise is -1, an early warning prompt will be issued, the test will be re-performed, and the data will be sent to the platform.

[0046] Reference Figure 2 As shown, the present invention provides a platform for a method of sensing three-dimensional motion data, characterized in that it includes: a data analysis module: synchronously shooting each athlete with attached markers through multiple cameras, obtaining motion capture data, and analyzing the motion capture index of each athlete during the movement.

[0047] Data analysis module: Based on the motion capture index of each athlete during the exercise, it is determined whether there is any abnormality in the motion capture of each athlete. If there is any abnormality, re-monitoring is performed to obtain the abnormal motion capture data of each abnormal athlete during the exercise.

[0048] Early warning prompt module: Based on the abnormal motion capture data of each abnormal athlete during the exercise, the abnormal motion capture index of each abnormal athlete during the exercise is evaluated and early warning prompts are issued.

[0049] The above contents are merely examples and explanations of the concept of the present invention. Those skilled in the art may make various modifications or additions to the described specific embodiments or replace them in a similar manner. As long as they do not deviate from the concept of the invention or exceed the scope defined by the present invention, they should all fall within the scope of protection of the present invention.

Claims

1. A method for sensing three-dimensional motion data, characterized in that: include: Step 1: Data analysis: Use multiple cameras to synchronously shoot each athlete with attached markers to obtain motion capture data and analyze the motion capture index of each athlete during the movement; Step 2: Data analysis: Based on the obtained motion capture index of each athlete during the exercise, determine whether the motion capture of each athlete is abnormal. If abnormal, re-monitor and obtain abnormal motion capture data of each abnormal athlete during the exercise; Step 3: Early warning: Based on the abnormal motion capture data of each abnormal athlete during the exercise, the abnormal motion capture index of each abnormal athlete during the exercise is evaluated and an early warning is issued.

2. The method for sensing three-dimensional motion data according to claim 1, wherein: The motion capture data specifically includes: optical capture data, inertial capture data and visual capture data.

3. The method for sensing three-dimensional motion data according to claim 1, wherein: The specific analysis method for analyzing the motion capture index of each athlete during the exercise is as follows: Based on the obtained optical capture data, inertial capture data and visual capture data, the optical capture value A of each athlete during the movement is analyzed. x , inertia capture value R x and visual capture value T x , and then analyze the motion capture index of each athlete during the movement. The specific calculation formula is: x =A x +R x +T x , where x represents the number of each athlete, x=1,2,...,g, and g represents the number of the athlete.

4. The method for sensing three-dimensional motion data according to claim 3, wherein: The specific analysis method of the optically captured values ​​of each athlete during the movement is as follows: Based on the obtained optical capture data, wherein the optical capture data includes: the joint point trajectory offset value, angular velocity and bending angle of each time period of each athlete during the movement process, and the joint point trajectory offset value safety interval, angular velocity safety interval and bending angle safety interval of each athlete in each time period during the movement process are extracted from the database, and the joint point trajectory offset value, angular velocity and bending angle of each athlete in each time period during the movement process are compared with the joint point trajectory offset value safety interval, angular velocity safety interval and bending angle safety interval of each athlete in each time period during the movement process. If the joint point trajectory offset value of a certain time period of an athlete in the movement process is within the joint point trajectory offset value safety interval, the angular velocity is within the angular velocity safety interval and the bending angle is within the bending angle safety interval, then the optical capture value of the athlete in the time period during the movement process is recorded as 1, otherwise it is recorded as -1, thereby obtaining the optical capture value A of each athlete in the movement process. x , where A x The values ​​include 1 and -1.

5. The method for sensing three-dimensional motion data according to claim 3, wherein: The specific analysis method of the inertia capture value of each athlete during the movement is as follows: Based on the obtained inertia capture data, wherein the inertia capture data includes: the cadence and impact peak of each athlete's limbs during the exercise process, and the cadence compliance interval and impact peak compliance interval of each athlete's limbs during the exercise process are extracted from the database, and the cadence and impact peak of each athlete's limbs during the exercise process are compared with the cadence compliance interval and impact peak compliance interval. If the cadence of an athlete during the exercise process is in the cadence compliance interval and the impact peak is in the impact peak compliance interval, the inertia capture value of the athlete during the exercise process is recorded as 1, otherwise, it is recorded as -1, thereby obtaining the inertia capture value R of each athlete during the exercise process. x , where R x The values ​​include 1 and -1.

6. The method for sensing three-dimensional motion data according to claim 3, wherein: The specific analysis method of the visual capture value of each athlete during the movement is as follows: Based on the obtained visual capture data, wherein the visual capture data includes: the visual displacement difference and the pixel clarity value of each time period of each athlete during the movement, the visual displacement difference and the pixel clarity value of each athlete during the movement are compared with the visual displacement difference compliance interval and the pixel clarity value compliance interval of each athlete during the movement stored in the database. If the visual displacement difference of a certain time period of an athlete during the movement is within the visual displacement difference compliance interval and the pixel clarity value is within the pixel clarity value compliance interval, then the visual capture value of the athlete during the movement in the time period is recorded as 1, otherwise, it is recorded as -1, thereby obtaining the visual capture value H of each athlete during the movement. x , where H x The values ​​include 1 and -1.

7. The method for sensing three-dimensional motion data according to claim 1, wherein: The specific analysis method for determining whether the motion capture of each athlete is abnormal is as follows: Based on the obtained motion capture index of each athlete during the exercise, the motion capture index of each athlete during the exercise is compared with the motion capture index compliance interval of the athletes during the exercise stored in the database. If the motion capture index of an athlete during the exercise is not in the motion capture index compliance interval, it means that the motion capture of the athlete is abnormal, and then the abnormal athletes during the exercise are obtained, and the abnormal motion capture data of each abnormal athlete during the exercise is obtained.

8. The method for sensing three-dimensional motion data according to claim 1, wherein: The abnormal motion capture data of each abnormal athlete during the exercise process, wherein the abnormal motion capture data includes: the motion deviation value, power deviation value and action timing matching value of each abnormal athlete during the exercise process.

9. The method for sensing three-dimensional motion data according to claim 1, wherein: The evaluation of abnormal motion capture index of each abnormal athlete during the exercise process and the issuance of early warning prompts are specifically performed by the following analysis method: Obtain the motion deviation value compliance interval, dynamic deviation value compliance interval and action timing matching value compliance interval of each abnormal athlete during the exercise from the database, and import the abnormal motion capture data into the abnormal motion capture index evaluation model. Get the abnormal motion capture index of each abnormal athlete during the movement, F dp It is represented as the pth abnormal motion capture data of the dth abnormal athlete during the movement, F dp ' represents the safe interval of the pth abnormal motion capture data of the dth abnormal athlete during the movement, p∈[1,3], d represents the number of each abnormal athlete, d=1,2,...,n, n represents the number of abnormal athletes, and p represents the number of abnormal motion capture data; When the abnormal motion capture index of each abnormal athlete during exercise is -1, an early warning prompt will be issued, the test will be re-performed, and the data will be sent to the platform.

10. A platform for executing the method for sensing three-dimensional motion data according to any one of claims 1 to 9, characterized in that: include: Data analysis module: Use multiple cameras to synchronously shoot each athlete with attached markers, obtain motion capture data, and analyze the motion capture index of each athlete during the exercise; Data analysis module: Based on the obtained motion capture index of each athlete during the exercise, it is determined whether the motion capture of each athlete is abnormal. If abnormal, re-monitoring is performed to obtain abnormal motion capture data of each abnormal athlete during the exercise; Early warning prompt module: Based on the abnormal motion capture data of each abnormal athlete during the exercise, the abnormal motion capture index of each abnormal athlete during the exercise is evaluated and early warning prompts are issued.

Images