Safety assessment alarm system and method for physical education sports

Abstract

The invention discloses a safety assessment alarm system and method for physical education sports, and relates to the technical field of safety alarm, the system comprises a physiological state monitoring module, a sports image acquisition module, a central processing unit and a signal alarm module, the abnormal risk of physical training of the athlete is evaluated from the angle of movement posture and track deviation, and the abnormal condition of physiological parameters of the athlete is combined, so that the training intensity of physical exercise is quantitatively monitored, the personal safety risk degree of the athlete is specifically evaluated, and a safety alarm signal is generated to give an instant alarm. Alarm judgment accuracy is guaranteed through comprehensive data analysis, the probability of misjudgment and false alarm of the system is reduced, physical education professionals are prompted to carry out timely medical safety inspection and management on athletes through safety alarm signals, and balance between improvement of athletic performance and reduction of safety risks is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of safety alarms, and in particular to a safety assessment alarm system and method for physical education teaching movements. Background Art

[0002] Although physical training helps promote physical health and development, it is also accompanied by certain risks. Among them, sports injuries are the most common risk. High-intensity training, incorrect posture and technique, lack of proper warm-up and cooling, etc. can all lead to sports injuries. Therefore, safety management is crucial in physical education teaching and training. Through the safety assessment alarm system, potential safety risks can be discovered and handled in a timely manner to prevent accidents. However, the existing physical education and exercise process has the problem of difficulty in quantifying and monitoring the intensity of sports training, and the limitation of safety monitoring. Due to individual differences, athletes have different tolerances. Therefore, a unified training model will cause different personal safety risks for different athletes. There are limitations in physiological monitoring through sports bracelets. Since sports training itself will cause certain differences between athletes' physiological parameters and standard ranges, such as increased heart rate, single monitoring of physiological parameters may cause system false alarms. There are also limitations in motion monitoring through high-definition images. Due to the lack of self-motivation of athletes, the training movements may be deliberately deformed, resulting in the defect of system misjudgment and false alarm. In view of the above technical defects, a solution is now proposed. Summary of the invention

[0003] The purpose of the present invention is to solve the defects of the prior art that it is difficult to quantify and monitor the training intensity of sports, the monitoring judgment has limitations, and the problem of system false alarms caused by single monitoring of physiological parameters or movement postures. The present invention monitors the physiological parameters of athletes and collects movement images, evaluates the abnormal risks of athletes in physical training from the perspective of movement posture and trajectory deviation, and combines the abnormal conditions of athletes' physiological parameters to quantify and monitor the training intensity of sports, specifically evaluate the degree of personal safety risk of athletes, generate safety alarm signals for immediate alarms, ensure the accuracy of alarm judgments through comprehensive data analysis, reduce the probability of system misjudgment and false alarms, and prompt sports teaching professionals to conduct timely medical safety inspections and management of athletes through safety alarm signals to ensure the personal safety of athletes.

[0004] In order to achieve the above object, the present invention adopts the following technical solutions: A safety assessment alarm method for physical education teaching movement, comprising the following steps: Step 1: Monitor the athlete's physiological parameters and collect sports images: Set the student ID to mark the athlete, and the athlete logs into the athlete port by entering the student ID. The athlete port includes a smart bracelet, which monitors the athlete's physiological parameters and collects the athlete's sports images through high-definition camera equipment; Step 2: Perform preliminary processing on the athlete's physiological parameters: set the standard range of the physiological parameters, compare and obtain the abnormal evaluation coefficient of the physiological parameters, so as to determine the abnormal physiological parameters and output the corresponding abnormal risk level; Step 3: Perform image analysis on the athlete's motion images: construct motion posture vectors by performing posture marking on the motion images, collect and record the athlete's standard action videos, extract standard posture vectors, and then compare the motion posture vectors with the standard posture vectors to evaluate the degree of deviation of the motion posture; then, perform time series analysis on the motion posture vectors to evaluate the degree of deviation of the motion trajectory; thus, comprehensively evaluate and output the level of abnormal risk of the athlete's physical training; Step 4: Comprehensively assess the personal safety risk level of athletes: By combining the abnormal risk level of physiological parameters with the abnormal risk level of physical training, comprehensively assess the personal safety risk level of athletes; Step 5: Generate a safety alarm signal and issue a corresponding signal alarm: Generate a corresponding safety alarm signal based on the athlete's personal safety risk level, transmit the athlete's safety risk in the form of a signal to the physical education teacher's terminal and present it visually.

[0005] Furthermore, the specific process of preliminary processing of the athlete's physiological parameters is as follows: The number of marked physiological parameters is N0, any physiological parameter is marked as i, the value of the marked physiological parameter i is φi, and the standard interval of the physiological parameter i is set to [Xi, Yi], where Xi is the lowest threshold value of the physiological parameter i, and Yi is the highest threshold value of the physiological parameter i; By comprehensively comparing the value φi of the physiological parameter i with its standard interval [Xi, Yi], the abnormal evaluation coefficient EXCi of the physiological parameter i is obtained; Then, the abnormal risk degree of the abnormal physiological parameters is determined: an evaluation interval of the abnormal evaluation coefficient EXCi is set, and the level of the abnormal risk degree of the physiological parameter i is evaluated by comparing the intervals.

[0006] Furthermore, the specific process of image analysis of athletes' sports images is as follows: Mark the posture of the athlete through the sports image, construct the sports posture vector, and compare it with the standard posture vector to obtain the sports posture deviation coefficient; Through the time series analysis of the motion posture vector, the degree of change of the athlete's motion trajectory during training is analyzed to obtain the motion trajectory deviation coefficient; By combining the sports posture deviation coefficient and the sports trajectory deviation coefficient, the abnormal evaluation coefficient EXCp of the athlete's physical training is output; Set the video frame period Tz, extract video frames according to the video frame period Tz through the standard action video, so as to obtain n0 standard action pictures, and then extract the three-dimensional coordinate data through the standard action pictures to obtain the standard posture vector B(t); The athlete's motion posture features D(t)=CNN_d(W(t)) are obtained through the athlete's motion images based on the convolutional neural network; where t is the target time node corresponding to the video frame period Tz, and W(t) refers to the three-dimensional coordinate data of the athlete's characteristic joints.

[0007] Furthermore, the specific process of evaluating the degree of deviation of the movement posture is as follows: Through the athlete's motion image, posture marking is performed, the characteristic points of human joints and their coordinates are identified, the motion posture vector is constructed, and it is compared with the standard posture vector to obtain the motion posture deviation coefficient; Mark any motion posture vector of the motion image as D(t), and mark the standard posture vector of the video frame corresponding to the target time node t as B(t); Then the motion posture vector D(t) includes the actual three-dimensional coordinates of m0 limb feature points, and the standard posture vector B(t) includes the reference three-dimensional coordinates of m0 limb feature points; Set the posture comparison function Fzt(D(t), B(t)), substitute the motion posture vector D(t) and the standard posture vector B(t) into the posture comparison function Fzt(D(t), B(t)), and obtain the motion posture deviation coefficient ZSPC.

[0008] Furthermore, the specific process of evaluating the degree of motion trajectory deviation is as follows: Through the time series analysis of the motion posture vector, the degree of change of the athlete's motion trajectory during training is analyzed to obtain the motion trajectory deviation coefficient; The motion posture vector D(t) includes the actual three-dimensional coordinates of m0 limb feature points; Mark any limb feature point as d, the actual three-dimensional coordinates of the limb feature point d are (Xd, Yd, Zd), set the video frame period Tz to track the motion trajectory of the limb feature point d, and obtain m1 actual three-dimensional coordinates of the limb feature point d through m1 video frame periods Tz; The motion trajectory matrix Vd of the limb feature point d is constructed through m1 actual three-dimensional coordinates of the limb feature point d, and the regression curve function LR of the limb feature point is obtained through the motion trajectory matrix Vd analysis; Then, the motion trajectory vector Gv of the athlete is obtained through the motion trajectory matrix of the m0 limb feature points of the motion posture vector D(t), and the regression curve function of the m0 limb feature points is obtained through the motion trajectory vector Gv of the athlete; The motion trajectory vector Gv is substituted into the regression curve function in time sequence to compare and evaluate the trajectory deviation between the actual three-dimensional coordinates and the regression curve, and the motion trajectory deviation coefficient GJPC is obtained.

[0009] Furthermore, the specific process of assessing the abnormal risk level of physical training is as follows: By combining the sports posture deviation coefficient ZSPC and the sports trajectory deviation coefficient GJPC, the abnormal evaluation coefficient EXCp of the athlete's physical training is output; An evaluation interval of the abnormal evaluation coefficient EXCp of physical training is set, and the level of abnormal risk degree of physical training is evaluated through interval comparison.

[0010] Furthermore, the specific process of comprehensively assessing the personal safety risk level of athletes is as follows: By combining the abnormal evaluation coefficients EXCi of N0 physiological parameters with the abnormal evaluation coefficients EXCp of physical training, a personal safety risk index AQFX is generated; Set the evaluation interval of the personal safety risk index AQFX, evaluate the personal safety risk level of athletes through interval comparison, and generate a safety alarm signal of the corresponding level.

[0011] A physical education sports safety assessment alarm system includes a physiological state monitoring module, a motion image acquisition module, a central processing unit and a signal alarm module, wherein the physiological state monitoring module, the motion image acquisition module, the central processing unit and the signal alarm module are connected in communication, and the system applies the above-mentioned physical education sports safety assessment alarm method; The physiological status monitoring module is used to collect the athlete's physiological parameters; The sports image acquisition module is used to acquire sports images of athletes; The central processing unit is used to perform preliminary processing on the athlete's physiological parameters and to perform image analysis on the athlete's sports images, thereby comprehensively assessing the athlete's personal safety risk level; The signal alarm module is used to generate a safety alarm signal and make a corresponding signal alarm.

[0012] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are: The present invention monitors the physiological parameters of athletes and collects sports images, evaluates the abnormal risks of athletes in physical training from the perspective of sports posture and trajectory deviation, and combines the abnormal conditions of athletes' physiological parameters to quantitatively monitor the training intensity of sports, specifically evaluate the degree of personal safety risk of athletes, generate safety alarm signals for immediate alarms, ensure the accuracy of alarm judgments through comprehensive data analysis, reduce the probability of system misjudgment and false alarms, prompt sports teaching professionals to conduct timely medical safety examinations and management of athletes through safety alarm signals, and adjust the training intensity accordingly according to the physical condition of the athlete, so as to achieve a balance between improving sports performance and reducing safety risks, and finally realize adaptive sports training courses and dynamic adjustment of intensity under the premise of ensuring the personal safety of athletes. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 A schematic diagram showing the steps of the overall process of the present invention is shown; Figure 2 A connection diagram of the system modules of the present invention is shown. DETAILED DESCRIPTION

[0014] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. 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 creative work are within the scope of protection of the present invention.

[0015] Embodiment 1: like Figure 1-Figure 2 As shown, a safety assessment alarm method for physical education teaching movement includes the following steps: S1, monitoring the physiological parameters of athletes and collecting sports images: setting student numbers to mark athletes, athletes log in to the athlete port by entering their student numbers, the athlete port includes a smart bracelet, the smart bracelet is used to monitor the physiological parameters of athletes, and high-definition camera equipment is used to collect sports images of athletes during physical education teaching and exercise; wherein the physiological parameters include heart rate, blood pressure, respiratory rate and blood oxygen concentration; the student number is the athlete's unique identity code during school; S2, preliminary processing of the athlete's physiological parameters: setting standard intervals for the physiological parameters, comparing and obtaining abnormal evaluation coefficients of the physiological parameters, thereby determining abnormal physiological parameters and outputting corresponding abnormal risk levels; S2-1, the number of marked physiological parameters is N0, any physiological parameter is marked as i, the value of the marked physiological parameter i is φi, and the standard interval of the physiological parameter i is set to [Xi, Yi], where Xi is the lowest threshold value of the physiological parameter i, and Yi is the highest threshold value of the physiological parameter i; When the value φi of the physiological parameter i is within the standard interval [Xi, Yi], the physiological parameter i is judged to be in a normal state; conversely, when the value φi of the physiological parameter i is not within the standard interval [Xi, Yi], the physiological parameter i is judged to be in an abnormal state, and the higher the degree to which the value φi of the physiological parameter i deviates from the standard interval [Xi, Yi], the higher the degree of abnormality of the physiological parameter i is judged to be; S2-2, by comprehensively comparing the value φi of the physiological parameter i with its standard interval [Xi, Yi], obtain the abnormal evaluation coefficient EXCi of the physiological parameter i: , where e is a preset conversion constant and the preset e is 2.7; when the physiological parameter i is in a normal state, the abnormal evaluation coefficient EXCi is between (0, 1]; when the physiological parameter i is in an abnormal state, the abnormal evaluation coefficient EXCi is greater than 1, and the physiological parameter i is marked as an abnormal physiological parameter, and the higher the abnormality of the physiological parameter i, the greater the abnormal evaluation coefficient EXCi; S2-3, determine the abnormal risk level of abnormal physiological parameters: Setting an evaluation interval of the abnormal evaluation coefficient EXCi, and evaluating the level of abnormal risk of the physiological parameter i by comparing the intervals; There are U evaluation intervals of the preset abnormal evaluation coefficient EXCi, and any evaluation interval is marked as Qu. When the abnormal evaluation coefficient EXCi is in the evaluation interval Qu, the abnormal risk level of the physiological parameter i is determined to be Au level, and the level Au of the abnormal risk level of the physiological parameter i is output; S3, image analysis of the athlete's motion images: constructing motion posture vectors by posture marking of the motion images, and collecting and recording the athlete's standard action videos to extract standard posture vectors, and then comparing the motion posture vectors with the standard posture vectors to evaluate the degree of deviation of the motion posture; and then evaluating the degree of deviation of the motion trajectory by performing time series analysis on the motion posture vectors; thereby comprehensively evaluating and outputting the level of abnormal risk of the athlete's physical training; In the actual application process, the standard action video of the athlete is stored under the supervision and judgment of the physical education teacher, and the standard action video of the athlete is recorded into the system, and the standard action video is called by the central processor for image analysis: the video frame period Tz is set, and the video frame is extracted according to the video frame period Tz through the standard action video, so as to obtain n0 standard action pictures, and then the three-dimensional coordinate data is extracted through the standard action picture to obtain the standard posture vector; It should be noted that, by configuring multiple image feature convolution layers, multiple pooling layers and at least one feature splicing layer through the existing convolutional neural network, the image feature convolution layer is used to perform image feature convolution on the video frame of the motion image, and the pooling layer is used to extract data from the features obtained after each convolution, and then the next image feature convolution is performed, so as to obtain the athlete's motion posture feature D(t)=CNN_d(W(t)); wherein t is the target time node corresponding to the video frame period Tz, and W(t) refers to the three-dimensional coordinate data of the athlete's characteristic joints; The specific process of image analysis of athletes' sports images is as follows: S3-1, through the athlete's motion image, posture marking, constructing the motion posture vector, and comparing it with the standard posture vector, obtaining the motion posture deviation coefficient, evaluating the consistency and repeatability of the athlete's movements, capturing and analyzing the coordinate position of the athlete's limb joints and other data, identifying incorrect or unstable postures, which may lead to sports injuries, and revealing whether the athlete has maintained the correct training method. The greater the deviation, the higher the risk of injury; The specific process of evaluating the degree of deviation in sports posture is as follows: Through the athlete's motion image, posture marking is performed, the characteristic points of human joints and their coordinates are identified, the motion posture vector is constructed, and it is compared with the standard posture vector to obtain the motion posture deviation coefficient; Mark any motion posture vector of the motion image as D(t), and mark the standard posture vector of the video frame corresponding to the target time node t as B(t); Then the motion posture vector D(t) includes the actual three-dimensional coordinates of m0 limb feature points, and the standard posture vector B(t) includes the reference three-dimensional coordinates of m0 limb feature points; Set the posture comparison function Fzt(D(t), B(t)), substitute the motion posture vector D(t) and the standard posture vector B(t) into the posture comparison function Fzt(D(t), B(t)), and obtain the motion posture deviation coefficient ZSPC: ; The actual three-dimensional coordinates are marked as (Xd, Yd, Zd), and the reference three-dimensional coordinates are marked as (Xb, Yb, Zb). It refers to the coordinate deviation between any set of actual three-dimensional coordinates and the reference three-dimensional coordinates. ; Refers to the coordinate deviation between the actual three-dimensional coordinates of group m0 and the reference three-dimensional coordinates The average value of Refers to the coordinate deviation between the actual three-dimensional coordinates of group m0 and the reference three-dimensional coordinates The standard deviation of When the coordinate deviation between the actual three-dimensional coordinates and the reference three-dimensional coordinates The higher the average value and the larger the standard deviation, the higher the sports posture deviation coefficient ZSPC is, and the greater the degree of sports posture deviation is, indicating that the overall level of coordinate deviation between the actual three-dimensional coordinates and the reference three-dimensional coordinates is high and the degree of difference is large, indicating that the athlete has abnormal movement deformation, indicating that the sports posture is incorrect or unstable; S3-2, through the time series analysis of the motion posture vector, analyze the degree of change of the athlete's motion trajectory during training, obtain the motion trajectory deviation coefficient, evaluate the smoothness and safety of the athlete's movement process, determine whether the posture changes due to fatigue, so as to evaluate when to rest or adjust the training intensity, and evaluate the subsequent posture instability, poor exercise state and lack of endurance that may be caused by long-term exercise training; The specific process of evaluating the degree of motion trajectory deviation is as follows: Through the time series analysis of the motion posture vector, the degree of change of the athlete's motion trajectory during training is analyzed to obtain the motion trajectory deviation coefficient; The motion posture vector D(t) includes the actual three-dimensional coordinates of m0 limb feature points; Mark any limb feature point as d, the actual three-dimensional coordinates of the limb feature point d are (Xd, Yd, Zd), set the video frame period Tz to track the motion trajectory of the limb feature point d, and obtain m1 actual three-dimensional coordinates of the limb feature point d through m1 video frame periods Tz; The motion trajectory matrix Vd of the limb feature point d is constructed through the m1 actual three-dimensional coordinates of the limb feature point d: ; Then, the athlete's motion trajectory vector Gv is obtained through the motion trajectory matrix of the m0 limb feature points of the motion posture vector D(t): ; The regression curve function LR of the limb feature points is obtained by analyzing the motion trajectory matrix Vd: ; The regression curve vector R(t) is obtained by marking Xr, Yr and Zr as the lateral quantity, longitudinal quantity and vertical vector of any point of the regression curve in sequence; α1, α2 and α3 are the weight factor coefficients of the lateral quantity Xr, longitudinal quantity Yr and vertical vector Zr of the point of the regression curve, and α1, α2 and α3 are all preset to be greater than 0, εt is the adjustment variable of the limb feature point d, and the adjustment variable is preset and obtained after a large amount of data fitting curve calculation and , is the discrete variance value of the limb feature point, which is calculated by taking the average of the square of the distance between the discrete actual three-dimensional coordinates and the fitted regression curve; Then, the regression curve function of m0 limb feature points is obtained through the athlete's motion trajectory vector Gv, and the motion trajectory vector Gv is substituted into the regression curve function in time sequence to compare and evaluate the trajectory deviation between the actual three-dimensional coordinates and the regression curve, and obtain the motion trajectory deviation coefficient GJPC: ; in, It refers to the coordinate deviation between any set of actual three-dimensional coordinates and the regression curve coordinates. ; Refers to the coordinate deviation between the actual three-dimensional coordinates of group m0 and the coordinates of the regression curve The average value of Refers to the coordinate deviation between the actual three-dimensional coordinates of group m0 and the coordinates of the regression curve The standard deviation of When the coordinate deviation between the actual three-dimensional coordinates and the regression curve coordinates The higher the average value and the larger the standard deviation, the larger the motion trajectory deviation coefficient GJPC is, and the greater the degree of motion trajectory deviation is, indicating that the overall level of coordinate deviation between the actual three-dimensional coordinates and the regression curve coordinates is high and the degree of difference is large, indicating that there is a change in posture due to fatigue, resulting in poor subsequent posture and insufficient endurance in the movement; The regression curve function LR refers to the regression curve generated by the athlete performing repeated movements within a certain time range during movement training, and fitting the generated regression curve for the limb feature points. For example, during running training, the athlete's movements are divided into several regression cycle action segments according to the motion trajectory matrix, and the limb feature points in the action segments are similarly subjected to regression cycles, such as elbow joints, knee joints, etc. However, the human body cannot be completely overlapped during repeated training. Therefore, the motion trajectories of the limb feature points are approximately the same but not completely consistent. The discrete limb feature point coordinates are fitted with regression curves through the existing mathematical model to obtain the motion trajectory reference curves of several repeated movements. When the athlete has abnormal conditions such as fatigue and lack of endurance, the subsequent movement amplitudes will be greatly different, resulting in deviations between the limb feature points and their corresponding running reference curves. The risk level of the motion trajectory is determined by setting a deviation threshold. When the deviation exceeds the threshold and the higher the deviation, the higher the risk level of the motion trajectory. S3-3, outputting the abnormal evaluation coefficient EXCp of the athlete's physical training by combining the sports posture deviation coefficient and the sports trajectory deviation coefficient; The specific process for assessing the abnormal risk level of physical training is: By combining the sports posture deviation coefficient ZSPC and the sports trajectory deviation coefficient GJPC, the abnormal evaluation coefficient EXCp of the athlete's physical training is output: ; Among them, ω1 and ω2 are weight factor coefficients of the movement posture deviation coefficient ZSPC and the movement trajectory deviation coefficient GJPC, respectively, and ω1 and ω2 are both greater than 0; when the movement posture deviation coefficient ZSPC and the movement trajectory deviation coefficient GJPC are higher, the abnormal evaluation coefficient EXCp of the physical training is higher, and the abnormal risk degree of the physical training is higher; Setting an evaluation interval of the abnormal evaluation coefficient EXCp of physical training, and evaluating the level of abnormal risk of physical training by comparing the intervals; There are H evaluation intervals of the preset abnormal evaluation coefficient EXCp, and any evaluation interval is marked as Qh. When the abnormal evaluation coefficient EXCp is in the evaluation interval Qh, the abnormal risk level of the physical training is determined to be Bh level, and the level Bh of the abnormal risk level of the physical training is output; S4, Comprehensively assess the personal safety risk level of athletes: By combining the abnormal risk level of physiological parameters with the abnormal risk level of physical training, comprehensively assess the personal safety risk level of athletes. The specific process is as follows: By combining the abnormal evaluation coefficients EXCi of N0 physiological parameters with the abnormal evaluation coefficients EXCp of physical training, the personal safety risk index AQFX is generated: ; When the abnormal evaluation coefficient EXCi of physiological parameters and the abnormal evaluation coefficient EXCp of physical training are higher, the personal safety risk index AQFX is higher, indicating that the abnormal degree of physiological parameters and physical training is higher, and the comprehensive evaluation of the personal safety risk of athletes is higher; Set the evaluation interval of the personal safety risk index AQFX, evaluate the personal safety risk level of athletes through interval comparison, and generate a safety alarm signal of the corresponding level; The assessment range of the preset personal safety risk index AQF is , mark any evaluation interval as , when the personal safety risk index AQF is in the evaluation interval When , the athlete's personal safety risk level is determined to be Level, Output Level 1 safety alarm signal; S5, generating a safety alarm signal and performing a corresponding signal alarm: generating a corresponding safety alarm signal according to the athlete's personal safety risk level, transmitting the athlete's safety risk in the form of a signal to the physical education teacher's terminal and performing a visual presentation; The visualized content includes the athlete's student number, abnormal physiological parameters, abnormal sports images and personal safety risk level of the athlete, so as to prompt sports teaching professionals to conduct timely medical safety examinations and management of athletes, and adjust the training intensity according to the athlete's physical condition, and conduct corresponding sports training courses under the premise of ensuring the athlete's personal safety, so as to achieve a balance between improving sports performance and reducing safety risks; A physical education sports safety assessment alarm system includes a physiological state monitoring module, a motion image acquisition module, a central processing unit and a signal alarm module, wherein the physiological state monitoring module, the motion image acquisition module, the central processing unit and the signal alarm module are connected in communication, and the system applies the above-mentioned physical education sports safety assessment alarm method; The physiological status monitoring module is used to collect the athlete's physiological parameters; The sports image acquisition module is used to acquire sports images of athletes; The central processing unit is used to perform preliminary processing on the athlete's physiological parameters and to perform image analysis on the athlete's sports images, thereby comprehensively assessing the athlete's personal safety risk level; The signal alarm module is used to generate a safety alarm signal and make a corresponding signal alarm.

[0016] In summary, the present invention monitors the physiological parameters of athletes and collects sports images, evaluates the abnormal risks of athletes in physical training from the perspective of sports posture and trajectory deviation, and combines the abnormal conditions of athletes' physiological parameters to quantitatively monitor the training intensity of sports, comprehensively evaluate the degree of personal safety risk of athletes, generate safety alarm signals for immediate alarm, ensure the accuracy of alarm judgment through comprehensive data evaluation, reduce the probability of system misjudgment and false alarm, prompt sports teaching professionals to conduct timely medical safety examinations and management of athletes through safety alarm signals, and adjust the training intensity accordingly according to the physical condition of the athlete, so as to achieve a balance between improving sports performance and reducing safety risks, and finally realize adaptive sports training courses and dynamic adjustment of intensity under the premise of ensuring the personal safety of athletes.

[0017] The size of the interval and threshold is set to facilitate comparison. The size of the threshold depends on the amount of sample data and the number of bases set by technical personnel in this field for each group of sample data; as long as it does not affect the proportional relationship between the parameter and the quantized value.

[0018] The above formulas are all dimensionless and numerical calculations. The formula is a formula obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formula are set by technicians in this field according to actual conditions. The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A safety assessment alarm method for physical education teaching, characterized in that: The following steps are involved: Step 1: Monitor the athlete's physiological parameters and collect sports images: Set the student ID to mark the athlete, and the athlete logs into the athlete port by entering the student ID. The athlete port includes a smart bracelet, which monitors the athlete's physiological parameters and collects the athlete's sports images through high-definition camera equipment; Step 2: Perform preliminary processing on the athlete's physiological parameters: set the standard range of the physiological parameters, compare and obtain the abnormal evaluation coefficient of the physiological parameters, so as to determine the abnormal physiological parameters and output the corresponding abnormal risk level; Step 3: Perform image analysis on the athlete's motion images: construct motion posture vectors by performing posture marking on the motion images, collect and record the athlete's standard action videos, extract standard posture vectors, and then compare the motion posture vectors with the standard posture vectors to evaluate the degree of deviation of the motion posture; then, perform time series analysis on the motion posture vectors to evaluate the degree of deviation of the motion trajectory; thus, comprehensively evaluate and output the level of abnormal risk of the athlete's physical training; Step 4: Comprehensively assess the personal safety risk level of athletes: By combining the abnormal risk level of physiological parameters with the abnormal risk level of physical training, comprehensively assess the personal safety risk level of athletes; Step 5: Generate a safety alarm signal and issue a corresponding signal alarm: Generate a corresponding safety alarm signal based on the athlete's personal safety risk level, transmit the athlete's safety risk in the form of a signal to the physical education teacher's terminal and present it visually.

2. A safety assessment alarm method for physical education teaching according to claim 1, characterized in that: The specific process of preliminary processing of athletes' physiological parameters is as follows: The number of marked physiological parameters is N0, any physiological parameter is marked as i, the value of the marked physiological parameter i is φi, and the standard interval of the physiological parameter i is set to [Xi, Yi], where Xi is the lowest threshold value of the physiological parameter i, and Yi is the highest threshold value of the physiological parameter i; By comprehensively comparing the value φi of the physiological parameter i with its standard interval [Xi, Yi], the abnormal evaluation coefficient EXCi of the physiological parameter i is obtained; Then, the abnormal risk level of the abnormal physiological parameters is determined: an evaluation interval of the abnormal evaluation coefficient EXCi is set, and the level of the abnormal risk level of the physiological parameter i is evaluated by comparing the intervals.

3. A safety assessment alarm method for physical education teaching according to claim 2, characterized in that: The specific process of image analysis of athletes' sports images is as follows: Mark the posture of the athlete through the sports image, construct the sports posture vector, and compare it with the standard posture vector to obtain the sports posture deviation coefficient; Through the time series analysis of the motion posture vector, the degree of change of the athlete's motion trajectory during training is analyzed to obtain the motion trajectory deviation coefficient; By combining the sports posture deviation coefficient and the sports trajectory deviation coefficient, the abnormal evaluation coefficient EXCp of the athlete's physical training is output; Set the video frame period Tz, extract video frames according to the video frame period Tz through the standard action video, so as to obtain n0 standard action pictures, and then extract the three-dimensional coordinate data through the standard action pictures to obtain the standard posture vector B(t); The athlete's motion posture features D(t)=CNN_d(W(t)) are obtained through the athlete's motion images based on the convolutional neural network; where t is the target time node corresponding to the video frame period Tz, and W(t) refers to the three-dimensional coordinate data of the athlete's characteristic joints.

4. A safety assessment alarm method for physical education teaching according to claim 3, characterized in that: The specific process of evaluating the degree of deviation in sports posture is as follows: Through the athlete's motion image, posture marking is performed, the characteristic points of human joints and their coordinates are identified, the motion posture vector is constructed, and it is compared with the standard posture vector to obtain the motion posture deviation coefficient; Mark any motion posture vector of the motion image as D(t), and mark the standard posture vector of the video frame corresponding to the target time node t as B(t); Then the motion posture vector D(t) includes the actual three-dimensional coordinates of m0 limb feature points, and the standard posture vector B(t) includes the reference three-dimensional coordinates of m0 limb feature points; Set the posture comparison function Fzt(D(t), B(t)), substitute the motion posture vector D(t) and the standard posture vector B(t) into the posture comparison function Fzt(D(t), B(t)), and obtain the motion posture deviation coefficient ZSPC.

5. A safety assessment alarm method for physical education teaching according to claim 4, characterized in that: The specific process of evaluating the degree of motion trajectory deviation is as follows: Through the time series analysis of the motion posture vector, the degree of change of the athlete's motion trajectory during training is analyzed to obtain the motion trajectory deviation coefficient; The motion posture vector D(t) includes the actual three-dimensional coordinates of m0 limb feature points; Mark any limb feature point as d, the actual three-dimensional coordinates of the limb feature point d are (Xd, Yd, Zd), set the video frame period Tz to track the motion trajectory of the limb feature point d, and obtain m1 actual three-dimensional coordinates of the limb feature point d through m1 video frame periods Tz; The motion trajectory matrix Vd of the limb feature point d is constructed through m1 actual three-dimensional coordinates of the limb feature point d, and the regression curve function LR of the limb feature point is obtained through the motion trajectory matrix Vd analysis; Then, the motion trajectory vector Gv of the athlete is obtained through the motion trajectory matrix of the m0 limb feature points of the motion posture vector D(t), and the regression curve function of the m0 limb feature points is obtained through the motion trajectory vector Gv of the athlete; The motion trajectory vector Gv is substituted into the regression curve function in time sequence to compare and evaluate the trajectory deviation between the actual three-dimensional coordinates and the regression curve, and the motion trajectory deviation coefficient GJPC is obtained.

6. A safety assessment alarm method for physical education teaching according to claim 5, characterized in that: The specific process for assessing the abnormal risk level of physical training is: By combining the sports posture deviation coefficient ZSPC and the sports trajectory deviation coefficient GJPC, the abnormal evaluation coefficient EXCp of the athlete's physical training is output; An evaluation interval of the abnormal evaluation coefficient EXCp of physical training is set, and the level of abnormal risk degree of physical training is evaluated through interval comparison.

7. A physical education sports safety assessment alarm method according to claim 6, characterized in that: The specific process of comprehensively assessing the personal safety risk level of athletes is as follows: By combining the abnormal evaluation coefficients EXCi of N0 physiological parameters with the abnormal evaluation coefficients EXCp of physical training, a personal safety risk index AQFX is generated; Set the evaluation interval of the personal safety risk index AQFX, evaluate the personal safety risk level of athletes through interval comparison, and generate a safety alarm signal of the corresponding level.

8. A safety assessment alarm system for physical education teaching, characterized by: The system comprises a physiological state monitoring module, a motion image acquisition module, a central processing unit and a signal alarm module, wherein the physiological state monitoring module, the motion image acquisition module, the central processing unit and the signal alarm module are communicatively connected with each other, and the system applies a safety assessment alarm method for physical education sports as described in any one of claims 1 to 7 above; The physiological status monitoring module is used to collect the athlete's physiological parameters; The sports image acquisition module is used to acquire sports images of athletes; The central processing unit is used to perform preliminary processing on the athlete's physiological parameters and to perform image analysis on the athlete's sports images, thereby comprehensively assessing the athlete's personal safety risk level; The signal alarm module is used to generate a safety alarm signal and make a corresponding signal alarm.

Images