Physical exercise evaluation system based on machine vision and implementation method

Abstract

The invention discloses a physical exercise evaluation system based on machine vision and an implementation method, relates to the technical field of intelligent physical exercise visual exercise evaluation, and aims to solve the problems that an existing physical exercise evaluation system based on machine vision has low accuracy and meticulousness of personalized evaluation of athletes and graph acquisition. The problem that the system cannot process and analyze motion data in real time and cannot provide instant feedback exists; according to the system and the implementation method, a data acquisition module, a motion image analysis module and a motion data analysis module are used for analyzing to obtain a motion image accumulation coefficient and a coefficient thereof; the exercise display module is used for displaying and comprehensively analyzing the obtained and calculated word number to obtain an exercise physiological coefficient, matching the exercise physiological coefficient with a preset physiological coefficient weight factor to obtain a body movement exercise proficiency degree and an endurance exercise endurance value, and displaying the exercise proficiency degree and the endurance exercise endurance value; the system meets the evaluation requirements of different types of sports, and finally assists athletes to obtain better scores in a match.

Description

Technical Field

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

[0002] Existing sports evaluation systems based on machine vision use computer vision technology to capture images and video data of athletes in motion through cameras or other sensor devices. The system then analyzes and evaluates the athletes' movements through image processing and pattern recognition algorithms. Such systems can be used in a variety of sports, such as basketball, football, gymnastics, etc., and provide detailed sports evaluation reports by analyzing data such as posture, speed, and trajectory during exercise to help athletes improve their techniques and performance. However, existing sports evaluation systems based on machine vision still have some problems, including problems with personalized evaluation of athletes and low accuracy and detail of collected graphics. There is also the problem that the system cannot process and analyze sports data in real time and provide instant feedback. Summary of the invention

[0003] In order to solve the technical problems raised by the above background technology, the embodiments of the present invention provide a sports evaluation system based on machine vision and an implementation method thereof.

[0004] The purpose of the present invention can be achieved through the following technical solutions: On one hand, the present invention provides a sports evaluation system based on machine vision, including a sports image analysis module and a sports data analysis module; The motion image analysis module is used to analyze the motion image data, collect the multi-directional motion images of the athlete through the mechanical vision camera, obtain the image coordinate systems of different orientations through the mechanical vision cameras of different orientations, construct the three-dimensional space motion coordinate system by the image coordinate systems of different orientations, establish the coordinate points on the limb joints of the athlete to obtain the static limb feature coordinate points of the athlete; the motion image analysis module also obtains the limb feature coordinate points of the athlete during the motion, obtains the change trajectory of the limb feature coordinate points during the motion, and matches the obtained change trajectory with the change trajectory of the motion feature coordinate points of different sports motions preset in the system to obtain the sports type of the athlete; the sports type includes but is not limited to limb motion sports and endurance sports; the motion image analysis module identifies the sports type of the athlete and analyzes to obtain the motion image accumulation coefficient 1 and the motion image accumulation coefficient 2; The motion data analysis module is used to analyze physiological data, and the specific process is as follows: By analyzing the heart rate and blood oxygen information, the heart rate is obtained by wearing physiological monitoring equipment to obtain the heart rate and blood oxygen information of the athlete before and after exercise, and the data is substituted into the curve graph to obtain the heart oxygen curve graph, and the heart rate accumulation coefficient and oxygen accumulation coefficient are obtained by analyzing the heart oxygen curve graph; Analyze the lactic acid concentration, obtain the lactic acid concentration information, and then substitute the obtained lactic acid concentration into the bar chart according to the corresponding time period through the established bar chart, and analyze the bar chart to obtain the lactic acid accumulation coefficient; The body temperature and respiratory rate information are analyzed to obtain the body temperature accumulation coefficient and the respiratory accumulation coefficient.

[0005] As a preferred embodiment of the present invention, it also includes a data acquisition module and a motion display module; The data acquisition module is used to obtain the sports data of the athlete, the sports data including sports image data and sports physiological data, and send the sports physiological data to the sports data analysis module; The motion display module is used to display and comprehensively analyze the number of words obtained by calculation, and obtain the motion physiological coefficient through comprehensive calculation; if the athlete's motion is limb movement, the physiological coefficient is matched with a preset physiological coefficient weight factor one, the motion physiological coefficient is multiplied with the preset physiological coefficient weight factor one, and then the resultant is added with the motion image cumulative coefficient one to obtain the limb movement proficiency; if the athlete's motion is endurance movement, the motion physiological coefficient is matched with a preset physiological coefficient weight factor two; the motion physiological coefficient is multiplied with the preset physiological coefficient weight factor two, and then the resultant is added with the motion image cumulative coefficient two to obtain the endurance endurance value; the limb movement proficiency and the endurance endurance value are both displayed on the display device.

[0006] As a preferred embodiment of the present invention, the motion image analysis module identifies the sports type of the athlete and analyzes to obtain the motion image accumulation coefficient 1 and the motion image accumulation coefficient 2. The specific process is as follows: By analyzing the athlete's movement type, if the athlete's movement type is limb movement, the change trajectory of the motion characteristic coordinate points of the preset limb movement movement is obtained, and the athlete's static limb characteristic coordinate points are proportionally adjusted to the motion characteristic coordinate points of the preset limb movement movement to generate an exclusive motion characteristic coordinate point trajectory of the athlete's limb movement movement; then the athlete's head characteristic coordinate points are captured and overlapped with the athlete's exclusive motion head characteristic coordinate points of the athlete's limb movement movement, and the trajectory of the athlete's other characteristic coordinate points is obtained and compared with the trajectory of the exclusive motion head characteristic coordinate points of the athlete's limb movement movement to obtain the trajectory overlap rate, and then the movement time coefficient is analyzed by decomposing the captured athlete's motion characteristic coordinate point trajectory into several trajectory time intervals.

[0007] As a preferred embodiment of the present invention, the trajectory of the captured athlete's motion characteristic coordinate points is decomposed into a number of trajectory time intervals to analyze the motion time coefficient, specifically: Then, the trajectory of the exclusive motion characteristic coordinate points of the athlete's limb movement is decomposed into several trajectory time intervals, marked as pre-trajectory time intervals; the trajectory time intervals are compared with the corresponding pre-trajectory time intervals one by one to obtain the front required time and the back required time; then the front total required time and the back total required time are summed up by the front required time and the back total required time of several trajectory time intervals; then the front total required time is subtracted from the back total required time to obtain the front and back time excess value, and the front and back time excess value is absolutized to obtain the motion time coefficient, and the motion time coefficient is ≥0; the motion image analysis module obtains the difficulty coefficient of the athlete's limb movement, and substitutes the difficulty coefficient into the XY axis line graph at a fixed ratio, and then calculates the shaded area in the graph, and uses the shaded area value in the graph as the motion image cumulative coefficient one; if the athlete's sport type is endurance sports, a motion analysis is performed to obtain the motion image cumulative coefficient two.

[0008] As a preferred embodiment of the present invention, the lactic acid concentration is analyzed to obtain the lactic acid accumulation coefficient, and the specific process is: By obtaining lactate concentration information and then using the established bar graph, the lactate concentration is substituted into the bar graph according to the corresponding time period, and the highest point of the bar graph is obtained and the highest point value is used as the blood lactate threshold. Then, the difference in lactate concentration before and after exercise and the average lactate concentration of the athlete during exercise are obtained through the bar graph; the lactate clearance rate is obtained from the difference in lactate concentration before and after exercise and the average lactate concentration; the average lactate concentration subtracted from the blood lactate threshold is multiplied by the corresponding preset lactate concentration correction factor, and the lactate clearance rate multiplied by the corresponding preset lactate concentration correction factor is subtracted to obtain the lactate accumulation coefficient.

[0009] As a preferred embodiment of the present invention, the temperature accumulation coefficient and the respiration accumulation coefficient are obtained by analyzing the body temperature and respiration rate information, specifically: By obtaining body temperature information, including the athlete's initial body temperature and the athlete's real-time body temperature, the real-time body temperature is subtracted from the initial body temperature to obtain the real-time body temperature difference, and then by setting the normal exercise temperature difference interval, if the real-time body temperature difference belongs to the normal exercise temperature difference interval, it matches the preset body temperature correction factor one; if the real-time body temperature difference does not belong to the normal exercise temperature difference interval, it matches the preset body temperature correction factor two, and it is set that the body temperature correction factor one is less than the preset body temperature correction factor two; then a number of real-time body temperature differences are multiplied by the preset body temperature correction factors corresponding to the corresponding body temperatures, and the sum is added to obtain the body temperature accumulation coefficient.

[0010] As a preferred embodiment of the present invention, the respiratory accumulation coefficient is obtained by analyzing the respiratory frequency information, specifically: Then, respiratory rate information is obtained, including resting respiratory rate, exercise respiratory rate and respiratory efficiency; the resting respiratory rate and exercise respiratory rate standards are set for cumulative judgment; the respiratory efficiency is calculated by the respiratory exchange ratio RER, and the respiratory exchange ratio RER=carbon dioxide VCO2 produced / oxygen VO2 consumed during exercise; the ventilation efficiency VE / VCO2 slope is also calculated, and the ventilation efficiency VE / VCO2 slope=minute ventilation VE / minute ventilation VE; the comprehensive accumulation standard is set for cumulative judgment; the resting respiratory rate, exercise respiratory rate accumulation, respiratory exchange ratio accumulation and ventilation efficiency accumulation during exercise are respectively averaged to obtain the accumulation of each item, and the total accumulation of each item is weighted to obtain the respiratory accumulation coefficient.

[0011] Another aspect of the present invention provides a method for implementing a sports evaluation system based on machine vision, comprising the following steps: Step 1: Acquire the athlete's sports data, which includes sports image data and sports physiological data; the sports image data is captured by a mechanical vision camera on the athlete's sports action image; the sports physiological data is acquired by the athlete wearing a physiological monitoring device; and the sports image data is sent to a sports image analysis module, and the sports physiological data is sent to a sports data analysis module; Step 2: Collect multi-directional images of the athlete's movements through machine vision cameras. Use machine vision cameras in different directions to obtain image coordinate systems in different directions to construct a three-dimensional space motion coordinate system; capture the athlete's static limb features through machine vision cameras to obtain the athlete's static limb feature coordinate points; Step 3: by obtaining the change trajectory of the limb feature coordinate points during exercise, the obtained change trajectory is matched with the change trajectory of the motion feature coordinate points of different sports movements preset in the system to obtain the athlete's sports type; the sports image analysis module identifies the athlete's sports type and analyzes it to obtain sports image accumulation coefficient 1 and sports image accumulation coefficient 2; Step 4: By acquiring the athlete's physiological data, analyzing the heart rate and blood oxygen information to obtain the heart rate accumulation coefficient and the blood oxygen accumulation coefficient, analyzing the lactate concentration to obtain the lactate accumulation coefficient, and analyzing the body temperature and respiratory rate information to obtain the body temperature accumulation coefficient and the respiratory accumulation coefficient; Step 5: Display the calculated word count to obtain a comprehensive analysis to obtain a sports physiological coefficient, then match the sports physiological coefficient with a preset physiological coefficient weight factor one and a preset physiological coefficient weight factor two, and display the calculated limb movement proficiency and limb movement proficiency.

[0012] Compared with the prior art, the present invention has the following beneficial effects: 1. The present invention uses a multi-directional camera to capture and establish a three-dimensional spatial motion coordinate system through a motion image analysis module, accurately identifies and analyzes the athlete's limb characteristics and motion trajectory, and realizes personalized and real-time sports performance evaluation. The system provides detailed and accurate feedback through dynamic comparison and comprehensive accumulation mechanisms, helping athletes to adjust and optimize training in a timely manner, significantly improving their technical level, and is applicable to a variety of sports events, meeting the evaluation needs of different types of sports, and ultimately helping athletes achieve better results in competitions; 2. The present invention generates detailed cumulative coefficients through comprehensive analysis of physiological data such as heart rate, blood oxygen, lactate concentration, body temperature and respiratory rate through the sports data analysis module, and provides a comprehensive sports performance evaluation; the system can monitor the physiological state of athletes in real time, accurately evaluate endurance sports performance, and help athletes optimize training and competition strategies. Through the dynamic evaluation of the heart oxygen curve, lactate concentration bar graph, body temperature and respiratory rate, athletes can get scientific feedback, improve their own physiological adaptability and sports performance, and effectively improve training efficiency and competitive level. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. The following drawings are not intentionally scaled to the actual size, and the focus is on illustrating the main purpose of the present invention.

[0014] Figure 1 It is a principle block diagram of the present invention; Figure 2 A step diagram of a method for implementing a sports evaluation system based on machine vision of the present invention; Figure 3 A scene graph is collected by the machine vision camera of the present invention; Figure 4 It is a motion image analysis diagram of the present invention; Figure 5 It is the cardio-oxygen curve diagram of the present invention. DETAILED DESCRIPTION

[0015] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work also fall within the scope of protection of the present invention.

[0016] As shown in the present invention and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular, but also include the plural. Generally speaking, the terms "include" and "comprise" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list, and the method or device may also include other steps or elements.

[0017] Although the present invention has made various references to certain modules in the system according to an embodiment of the present invention, any number of different modules can be used and run on a user terminal and / or server. The modules are only illustrative, and different aspects of the system and method can use different modules.

[0018] The present invention uses a flow chart to illustrate the operations performed by the system according to an embodiment of the present invention. It should be understood that the preceding or following operations are not necessarily performed precisely in order. On the contrary, various steps may be processed in reverse order or simultaneously as required. At the same time, other operations may also be added to these processes, or one or more operations may be removed from these processes.

[0019] Below, the exemplary embodiments according to the present invention will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments of the present invention, and it should be understood that the present invention is not limited to the exemplary embodiments described here.

[0020] See also Figure 1 As shown, a sports evaluation system based on machine vision includes a sports data acquisition module, a sports image analysis module, a sports data analysis module and a sports display module; The sports data acquisition module is used to obtain the sports data of athletes, and its sports data includes sports image data and sports physiological data; the sports image data is captured by the mechanical vision camera on the sports action image of the athlete; the sports physiological data is obtained by the athlete wearing physiological monitoring equipment; and the sports image data is sent to the sports image analysis module, and the sports physiological data is sent to the sports data analysis module; See also Figure 3As shown, the motion image analysis module is used to analyze the motion image data, collect the multi-directional motion images of the athletes through the mechanical vision camera, obtain the different directional image coordinate systems through the different directional machine vision cameras, and construct the three-dimensional space motion coordinate system from the different directional image coordinate systems; capture the static limb features of the athletes through the mechanical vision camera, and establish coordinate points on the limb joints of the athletes, and the coordinate points are marked in the different directional image coordinate systems; then, a three-dimensional space motion coordinate system is constructed by the directional image coordinate system, and the coordinate points in the different directional image coordinate systems are marked in the three-dimensional space motion coordinate system to obtain the static limb feature coordinate points of the athletes; it should be noted that: the static limb features of each athlete are different, and the static limb feature coordinate points of each athlete need to be marked; The motion image analysis module obtains the limb feature coordinate points of the athlete during the motion, and then obtains the change trajectory of the limb feature coordinate points during the motion, and matches the obtained change trajectory with the change trajectory of the motion feature coordinate points of different sports movements preset in the system to obtain the athlete's sports type; the sports type includes but is not limited to limb motion sports and endurance sports, wherein limb motion sports include gymnastics, figure skating and dancing, etc., and endurance sports include running, cycling and rowing, etc.; The motion image analysis module identifies the type of motion of the athlete. If the type of motion of the athlete is a limb motion, the changing trajectory of the motion characteristic coordinate points of the preset limb motion in the system is obtained, and then the motion characteristic coordinate points of the preset limb motion are proportionally adjusted by obtaining the static limb characteristic coordinate points of the athlete, and the head characteristic coordinate points are used as fixed moving points, and the fixed moving points are vector-connected with other limb characteristic coordinate points to obtain the proportional characteristics of the static limb characteristic coordinates of the athlete; the motion characteristic coordinate points of the preset limb motion are adjusted according to the proportional characteristics of the static limb characteristic coordinates of the athlete, and the exclusive motion characteristic coordinate point trajectory of the limb motion of the athlete is generated; the characteristic coordinate points of the head of the athlete are captured to overlap with the exclusive motion head characteristic coordinate points of the limb motion of the athlete, and then the trajectory of other characteristic coordinate points of the athlete is obtained and compared with the trajectory of the exclusive motion head characteristic coordinate points of the limb motion of the athlete to obtain the trajectory overlap rate; Then, the trajectory of the captured athlete's motion characteristic coordinate point is decomposed into several trajectory time intervals. Similarly, the trajectory of the exclusive motion characteristic coordinate point of the athlete's limb movement is also decomposed into several trajectory time intervals, which are marked as pre-trajectory time intervals; the trajectory time intervals are compared with the corresponding pre-trajectory time intervals one by one, and whether the motion trajectory in the trajectory time interval is before the motion trajectory in the pre-trajectory time interval or after the motion trajectory in the pre-trajectory time interval is obtained; if the motion trajectory in the trajectory time interval is before the motion trajectory in the pre-trajectory time interval, the time required for the motion trajectory in the trajectory time interval to the exclusive motion characteristic coordinate point trajectory of the motion trajectory in the pre-trajectory time interval is counted, and marked as the front-required time; otherwise, it is marked as the back-required time; then the front-required time and the back-required time of several trajectory time intervals are summed to obtain the front-required time and the back-required time; then the front-required time is subtracted from the back-required time to obtain the front-required time excess, and the front-required time excess is absolutized to obtain the motion time coefficient, and the motion time coefficient is ≥0; See also Figure 4 As shown, the motion image analysis module will obtain the difficulty coefficient of the athlete's limb movement, and substitute the difficulty coefficient into the XY axis line graph at a fixed ratio, draw a line segment with a certain point on the X-axis as the starting point to obtain the difficulty line segment, and then divide the difficulty line segment into three equal line segments, and mark the two points where the three line segments intersect as point one and point two; draw line segments at the starting point of the difficulty line segment, point one, point two and the end point of the difficulty line segment, and the line segments are perpendicular to the difficulty line segment, marked as line segment one, line segment two, line segment three and line segment four; obtain the trajectory overlap rate, multiply it by the preset overlap rate accumulation factor, and substitute it into the XY axis line graph line segment one at a fixed ratio, and the starting point is the difficulty line segment starting point; obtain the front time and the back time, and multiply them by the preset front and back time accumulation factors respectively, and substitute them into the XY axis line graph line segments at a fixed ratio. The first step is to obtain the motion time coefficient and multiply it by the preset motion time factor ratio and substitute it into the fourth line segment in the XY axis line graph, and the starting point is the end point of the difficulty line segment; obtain the motion image analysis graph, and calculate the shaded area in the graph, and use the shaded area value in the graph as the motion image accumulation coefficient one; it should be noted that the difficulty coefficient of the athlete's limb movement, the preset overlap rate accumulation factor, the preset before and after time accumulation factor and the preset motion time factor are all set by relevant personnel according to actual conditions; if the athlete's sport type is endurance sports, the corresponding sports rules are obtained for numerical accumulation, for example: running and cycling, the time, speed and distance used to complete the sport are obtained, and the specific situation of the accumulated value is used as the motion image accumulation coefficient two; The sports data analysis module is used to analyze physiological data by obtaining the athlete's physiological data, which includes but is not limited to heart rate, blood oxygen, lactate concentration, body temperature and respiratory rate information; See also Figure 5As shown, the heart rate and blood oxygen information are analyzed, and the heart rate and blood oxygen information of the athlete before and after exercise are obtained by wearing a physiological monitoring device, and the data is substituted into the curve chart to obtain the heart oxygen curve chart; the heart rate during exercise is averaged according to the data in the chart to obtain the mean heart rate value, and the maximum and minimum heart rate values ​​in the chart and the heart rate value of the athlete at rest are obtained, which are marked as the maximum heart rate value, the minimum heart rate value and the rest heart rate value respectively; then the heart rate after the exercise is obtained and compared with the rest heart rate value to obtain the recovery speed after the exercise, which is marked as the recovery value; the maximum heart rate value minus the minimum heart rate value is calculated. Then multiply it by the corresponding preset heart rate correction factor, and divide it by the recovery value multiplied by the corresponding preset heart rate correction factor, add the mean heart value minus the mean heart value of the historical exercise type and multiply it by the corresponding preset heart rate correction factor to obtain the heart rate accumulation coefficient; then obtain the ratio of the blood oxygen value and the heart rate value at the same time in the figure, and divide the heart rate value by the blood oxygen value, marked as the heart-blood ratio, and then add the heart-blood ratio during the exercise time and multiply it by the preset correction factor to obtain the blood oxygen accumulation coefficient; the corresponding preset heart rate correction factor and the preset correction factor are set by relevant personnel according to actual conditions; Analyze the lactate concentration; obtain the lactate concentration information and then substitute the obtained lactate concentration into the bar chart according to the corresponding time period through the established bar chart, obtain the highest point of the bar chart and use the highest point value as the blood lactate threshold, and then obtain the difference in lactate concentration before and after exercise and the average lactate concentration of the athlete during exercise through the bar chart; obtain the lactate clearance rate from the difference in lactate concentration before and after exercise and the average lactate concentration; multiply the average lactate concentration subtracted from the blood lactate threshold by the corresponding preset lactate concentration correction factor, and subtract the lactate clearance rate multiplied by the corresponding preset lactate concentration correction factor to obtain the lactate accumulation coefficient; the corresponding preset lactate concentration correction factor is set by relevant personnel according to actual conditions; The body temperature and respiratory rate information are analyzed, and the body temperature information is obtained, including the athlete's initial body temperature and the athlete's real-time body temperature. The real-time body temperature is subtracted from the initial body temperature to obtain the real-time body temperature difference, and then the normal exercise temperature difference interval is set. If the real-time body temperature difference belongs to the normal exercise temperature difference interval, the preset body temperature correction factor 1 is matched; if the real-time body temperature difference does not belong to the normal exercise temperature difference interval, the preset body temperature correction factor 2 is matched, and the body temperature correction factor 1 << the preset body temperature correction factor 2 is set; then several real-time body temperature differences are multiplied by the corresponding preset body temperature correction factors of the corresponding body temperatures, and the temperature accumulation coefficient is obtained by adding them; the normal exercise temperature difference interval and the preset body temperature correction factor are set by relevant personnel according to actual conditions; Then, respiratory rate information is obtained, including resting respiratory rate, exercise respiratory rate and respiratory efficiency; the preset resting respiratory rate and exercise respiratory rate standards are used, resting respiratory rate standard: (12-16 times / minute: 10 minutes, 17-20 times / minute: 8 minutes, 21-24 times / minute: 5 minutes and more than 24 times / minute: 2 minutes); exercise respiratory rate standard: (25-30 times / minute: 10 minutes, 31-35 times / minute: 8 minutes, 36-40 times / minute: 5 minutes and more than 40 times / minute: 2 minutes); respiratory efficiency is calculated by respiratory exchange ratio (RER), and respiratory exchange ratio (RER) = carbon dioxide produced (VCO2) / oxygen consumed during exercise (VO2); ventilation efficiency (VE / VCO2 slope) is also calculated, and the calculation Calculate ventilation efficiency (VE / VCO2 slope) = minute ventilation (VE) / minute ventilation (VE); then set comprehensive standards; respiratory exchange ratio (RER): RER < 0.85: 10 points, RER belongs to 0.85-1.0: 8 points, RER> 1.0: 5 points; ventilation efficiency (VE / VCO2 slope): VE / VCO2 < 25: 10 points, VE / VCO2 belongs to 25-30: 8 points, VE / VCO2> 30: 5 points; then calculate the mean of resting respiratory rate, exercise respiratory rate, respiratory exchange ratio and ventilation efficiency during exercise to obtain the mean of each item, and perform weighted calculation on the total mean to obtain the respiratory coefficient; the resting respiratory rate and exercise respiratory rate standards as well as the comprehensive standards are set by relevant personnel according to actual conditions; The sports display module is used to display and comprehensively analyze the number of words obtained by calculation, and obtain the sports physiological coefficient by adding the heart rate cumulative coefficient to the blood oxygen cumulative coefficient plus the lactic acid cumulative coefficient minus the body temperature cumulative coefficient plus the respiration cumulative coefficient; if the athlete's exercise is a limb movement, the physiological coefficient is matched with a preset physiological coefficient weight factor one, and the sports physiological coefficient is multiplied with the preset physiological coefficient weight factor one and then added with the sports image cumulative coefficient one to obtain the limb movement proficiency, and the limb movement proficiency is displayed on the display device; if the athlete's exercise is an endurance exercise, the sports physiological coefficient is matched with a preset physiological coefficient weight factor two; the sports physiological coefficient is multiplied with the preset physiological coefficient weight factor two and then added with the sports image cumulative coefficient two to obtain the endurance exercise endurance value, and the limb movement exercise proficiency and endurance exercise endurance value are displayed on the display device for display; See also Figure 2As shown, a method for implementing a sports evaluation system based on machine vision is implemented based on a sports evaluation system based on machine vision, and the system includes a sports data acquisition module, a sports image analysis module, a sports data analysis module and a sports display module; the sports data acquisition module collects athlete sports data by carrying a machine vision camera, and its sports data includes sports image data and sports physiological data, and then the sports image analysis module obtains different orientation image coordinate systems through different orientation machine vision cameras, and constructs a three-dimensional space action coordinate system from the different orientation image coordinate systems, and then uses the machine vision camera to capture and identify the athlete's static limb features, and distinguish the type of sports, which includes but is not limited to limb action sports and endurance sports; if the type of sports is limb action During exercise, analysis is performed to obtain a motion image accumulation coefficient of one. If the type of sports activity is limb movement, analysis is performed to obtain an endurance sports image accumulation coefficient of two. Then, the sports data analysis module is used to analyze the physiological data, analyze the heart rate information to obtain the heart rate accumulation coefficient, analyze the blood oxygen information to obtain the blood oxygen accumulation coefficient, analyze the lactate concentration information to obtain the lactate accumulation coefficient, analyze the temperature information to obtain the body temperature accumulation coefficient, and analyze the breathing rate information to obtain the breathing accumulation coefficient. Finally, the sports display module is used to analyze the physiological data to obtain the sports physiological coefficient, and then match the sports physiological coefficient with the preset physiological coefficient weight factor one and the preset physiological coefficient weight factor two, and display the calculated limb movement sports proficiency and endurance sports endurance value.

[0021] In addition, those skilled in the art will appreciate that various aspects of the present invention may be illustrated and described by a number of patentable categories or situations, including any new and useful process, machine, product or combination of substances, or any new and useful improvements thereto. Accordingly, various aspects of the present invention may be performed entirely by hardware, entirely by software (including firmware, resident software, microcode, etc.), or by a combination of hardware and software. The above hardware or software may all be referred to as "data blocks", "modules", "engines", "units", "components" or "systems". In addition, various aspects of the present invention may be represented as a computer product located in one or more computer-readable media, which includes computer-readable program code.

[0022] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the invention belongs. It should also be understood that terms such as those defined in common dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant technology and should not be interpreted in an idealized or extremely formal sense, unless explicitly defined as such herein.

[0023] The above is an explanation of the present invention and should not be considered as a limitation thereof. Although several exemplary embodiments of the present invention have been described, it will be readily appreciated by those skilled in the art that many modifications may be made to the exemplary embodiments without departing from the novel teachings and advantages of the present invention. Therefore, all such modifications are intended to be included within the scope of the present invention as defined in the claims. It should be understood that the above is an explanation of the present invention and should not be considered as being limited to the specific embodiments disclosed, and modifications to the disclosed embodiments and other embodiments are intended to be included within the scope of the appended claims. The present invention is defined by the claims and their equivalents.

Claims

1. A sports evaluation system based on machine vision, comprising a sports image analysis module and a sports data analysis module; characterized in that: The motion image analysis module is used to analyze the motion image data, collect the multi-directional motion images of the athlete through the machine vision camera, obtain the image coordinate systems of different directions through the machine vision cameras of different directions, construct the three-dimensional space motion coordinate system from the image coordinate systems of different directions, establish the coordinate points on the limb joints of the athlete to obtain the static limb feature coordinate points of the athlete; The motion image analysis module also obtains the limb feature coordinate points of the athlete during the exercise, obtains the change trajectory of the limb feature coordinate points during the exercise, and matches the obtained change trajectory with the change trajectory of the motion feature coordinate points of different sports movements preset in the system to obtain the athlete's sports type; the sports type includes but is not limited to limb movement sports and endurance sports; the motion image analysis module identifies the athlete's sports type and analyzes it to obtain a motion image accumulation coefficient 1 and a motion image accumulation coefficient 2; The motion data analysis module is used to analyze physiological data, and the specific process is as follows: By analyzing the heart rate and blood oxygen information, the heart rate is obtained by wearing physiological monitoring equipment to obtain the heart rate and blood oxygen information of the athlete before and after exercise, and the data is substituted into the curve graph to obtain the heart oxygen curve graph, and the heart rate accumulation coefficient and oxygen accumulation coefficient are obtained by analyzing the heart oxygen curve graph; Analyze the lactic acid concentration, obtain the lactic acid concentration information, and then substitute the obtained lactic acid concentration into the bar chart according to the corresponding time period through the established bar chart, and analyze the bar chart to obtain the lactic acid accumulation coefficient; The body temperature and respiratory rate information are analyzed to obtain the body temperature accumulation coefficient and the respiratory accumulation coefficient.

2. A sports evaluation system based on machine vision according to claim 1, characterized in that: It also includes a data acquisition module and a motion display module; The data acquisition module is used to obtain the sports data of the athlete, the sports data including sports image data and sports physiological data, and send the sports physiological data to the sports data analysis module; The motion display module is used to display and comprehensively analyze the number of words obtained by calculation, and obtain the motion physiological coefficient through comprehensive calculation; if the athlete's motion is limb movement, the physiological coefficient is matched with a preset physiological coefficient weight factor one, the motion physiological coefficient is multiplied with the preset physiological coefficient weight factor one, and then added with the motion image cumulative coefficient one to obtain the limb movement proficiency; if the athlete's motion is endurance movement, the motion physiological coefficient is matched with a preset physiological coefficient weight factor two; the motion physiological coefficient is multiplied with the preset physiological coefficient weight factor two, and then added with the motion image cumulative coefficient two to obtain the endurance endurance value; the limb movement proficiency and the endurance endurance value are both displayed on the display device.

3. A sports evaluation system based on machine vision according to claim 1, characterized in that: The motion image analysis module identifies the sports type of the athlete and analyzes to obtain motion image accumulation coefficient 1 and motion image accumulation coefficient 2. The specific process is as follows: By analyzing the athlete's movement type, if the athlete's movement type is a limb movement, obtaining the change trajectory of the movement characteristic coordinate points of the preset limb movement movement, proportionally adjusting the obtained athlete's static limb characteristic coordinate points to the movement characteristic coordinate points of the preset limb movement movement, and generating a unique movement characteristic coordinate point trajectory of the athlete's limb movement movement; Then, the characteristic coordinate points of the athlete's head are captured and overlapped with the characteristic coordinate points of the athlete's exclusive head for body movements. The trajectory of the athlete's other characteristic coordinate points is obtained and compared with the trajectory of the characteristic coordinate points of the athlete's exclusive head for body movements to obtain the trajectory overlap rate. Then, the motion time coefficient is analyzed by decomposing the trajectory of the captured athlete's motion characteristic coordinate points into several trajectory time intervals.

4. A sports evaluation system based on machine vision according to claim 3, characterized in that: The capture of the athlete's motion feature coordinate point trajectory is decomposed into a number of trajectory time intervals to analyze the motion time coefficient, specifically: Then, the trajectory of the exclusive motion characteristic coordinate points of the athlete's limb movement is decomposed into several trajectory time intervals, marked as pre-trajectory time intervals; the trajectory time intervals are compared with the corresponding pre-trajectory time intervals one by one to obtain the front required time and the back required time; then the front total required time and the back total required time are summed up by the front required time and the back total required time of several trajectory time intervals; then the front total required time is subtracted from the back total required time to obtain the front and back time excess value, and the front and back time excess value is absolutized to obtain the motion time coefficient, and the motion time coefficient is ≥0; the motion image analysis module obtains the difficulty coefficient of the athlete's limb movement, and substitutes the difficulty coefficient into the XY axis line graph at a fixed ratio, and then calculates the shaded area in the graph, and uses the shaded area value in the graph as the motion image cumulative coefficient one; if the athlete's sport type is endurance sports, a motion analysis is performed to obtain the motion image cumulative coefficient two.

5. A sports evaluation system based on machine vision according to claim 1, characterized in that: The lactic acid concentration is analyzed to obtain the lactic acid accumulation coefficient, and the specific process is as follows: By obtaining lactate concentration information and then using the established bar graph, the lactate concentration is substituted into the bar graph according to the corresponding time period, and the highest point of the bar graph is obtained and the highest point value is used as the blood lactate threshold. Then, the difference in lactate concentration before and after exercise and the average lactate concentration of the athlete during exercise are obtained through the bar graph; the lactate clearance rate is obtained from the difference in lactate concentration before and after exercise and the average lactate concentration; the average lactate concentration subtracted from the blood lactate threshold is multiplied by the corresponding preset lactate concentration correction factor, and the lactate clearance rate multiplied by the corresponding preset lactate concentration correction factor is subtracted to obtain the lactate accumulation coefficient.

6. A sports evaluation system based on machine vision according to claim 5, characterized in that: The body temperature and respiratory rate information are analyzed to obtain the body temperature accumulation coefficient and the respiratory accumulation coefficient, specifically: By obtaining body temperature information, including the athlete's initial body temperature and the athlete's real-time body temperature, the real-time body temperature is subtracted from the initial body temperature to obtain the real-time body temperature difference, and then by setting the normal exercise temperature difference interval, if the real-time body temperature difference belongs to the normal exercise temperature difference interval, the preset body temperature correction factor 1 is matched; If the real-time body temperature difference does not belong to the normal exercise temperature difference range, the preset body temperature correction factor 2 is matched, and the body temperature correction factor 1 is set to be less than the preset body temperature correction factor 2; Then, a number of real-time body temperature differences are multiplied by the preset body temperature correction factors corresponding to the corresponding body temperatures, and the sum is added to obtain the body temperature accumulation coefficient.

7. A sports evaluation system based on machine vision according to claim 6, characterized in that: The respiratory frequency information is analyzed to obtain the respiratory accumulation coefficient, which is specifically: Then, by obtaining the respiratory rate information, which includes the resting respiratory rate, the exercise respiratory rate and the respiratory efficiency, the resting respiratory rate and the exercise respiratory rate standards are set for determination; Respiratory efficiency is calculated by calculating the respiratory exchange ratio RER, and the respiratory exchange ratio RER = carbon dioxide produced VCO2 / oxygen consumed during exercise VO2; it is also calculated by calculating the ventilation efficiency VE / VCO2 slope, and the ventilation efficiency VE / VCO2 slope = minute ventilation VE / minute ventilation VE; then it is judged by setting a comprehensive standard; then the resting respiratory rate, exercise respiratory rate accumulation, respiratory exchange ratio accumulation and ventilation efficiency accumulation during exercise are respectively averaged to obtain the cumulative mean of each item, and the total cumulative mean is weighted to obtain the respiratory accumulation coefficient.

8. A method for implementing a sports evaluation system based on machine vision, characterized in that: A sports evaluation system based on machine vision is applied to implement any one of claims 1 to 7, comprising the following steps: Step 1: Acquire the athlete's sports data, which includes sports image data and sports physiological data; the sports image data is captured by a mechanical vision camera on the athlete's sports action image; the sports physiological data is acquired by the athlete wearing a physiological monitoring device; and the sports image data is sent to a sports image analysis module, and the sports physiological data is sent to a sports data analysis module; Step 2: Collect multi-directional images of the athlete's movements through machine vision cameras. Use machine vision cameras in different directions to obtain image coordinate systems in different directions to construct a three-dimensional space motion coordinate system; capture the athlete's static limb features through machine vision cameras to obtain the athlete's static limb feature coordinate points; Step 3: by obtaining the change trajectory of the limb feature coordinate points during exercise, the obtained change trajectory is matched with the change trajectory of the motion feature coordinate points of different sports movements preset in the system to obtain the athlete's sports type; the sports image analysis module identifies the athlete's sports type and analyzes it to obtain sports image accumulation coefficient 1 and sports image accumulation coefficient 2; Step 4: By acquiring the athlete's physiological data, analyzing the heart rate and blood oxygen information to obtain the heart rate accumulation coefficient and the blood oxygen accumulation coefficient, analyzing the lactate concentration to obtain the lactate accumulation coefficient, and analyzing the body temperature and respiratory rate information to obtain the body temperature accumulation coefficient and the respiratory accumulation coefficient; Step 5: Display the calculated word count to obtain a comprehensive analysis to obtain a sports physiological coefficient, then match the sports physiological coefficient with a preset physiological coefficient weight factor one and a preset physiological coefficient weight factor two, and display the calculated limb movement proficiency and endurance sports endurance value.

Images