Human body posture evaluation method and system for daily training of public security

Abstract

The invention provides a human body posture evaluation method and system for daily training of public security, and the system comprises a data obtaining system for obtaining data, a data processing system for data processing, a historical database for improving the evaluation precision, and an evaluation system for evaluating the human body posture. The comprehensive processing unit is quicker and more accurate in attitude analysis, meanwhile, environment variable and personal information variable data are added, the data accuracy is further improved, it is avoided that due to the temperature, some errors occur in the training process of trainees, the evaluation result is affected, and meanwhile the evaluation accuracy is improved. The personal information variable data is the body data of the trainee, whether the body data of the trainee will affect the training posture or not is judged according to the change of the body data of the trainee, the accuracy of the evaluation result is effectively improved, some errors occurring in the training process of the trainee can be guided more conveniently, and the training efficiency is improved. Therefore, the posture of the trainee during training is improved, and the training effect is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of human motion analysis, and in particular to a human posture assessment method and system for daily police training. Background Art

[0002] Human posture assessment is a technology used to analyze and evaluate human posture and body structure. It can help people understand whether their posture is correct, whether there is a bad posture, and how to improve their posture.

[0003] Generally speaking, the need for human posture assessment is mostly during training, such as athlete training, public security training, etc.

[0004] Among them, in public security training, whether the human body posture is standard determines the accuracy of the training results, that is, public security personnel can improve their professional skills according to the training and ensure that their professional skills can be effectively exerted. Incorrect training posture not only easily causes damage to the body of the training personnel, but also makes it impossible to improve themselves, resulting in a decline in their professional skills. Therefore, the evaluation of training posture is particularly important. Posture evaluation can effectively point out some problems in the training process and help personnel improve themselves.

[0005] Traditional training posture assessment is mostly performed through head-mounted devices, and is mostly judged based on human heart rate, training time and training distance. Although this method is simple and convenient, it is unable to intuitively obtain the behavioral trajectory of key points of human posture, that is, it can only assess the intensity and efficiency of human training, but cannot perform posture assessment on the behavior of key points of the human body, and cannot provide good post-training guidance. Therefore, the present invention proposes a human posture assessment method and system for daily public security training. Summary of the invention

[0006] The purpose of the present invention is to solve the shortcomings of the prior art and to provide a human body posture assessment method and system for daily police training.

[0007] In order to achieve the above-mentioned object, the present invention adopts the following technical scheme: a human posture assessment system for daily police training, comprising a data acquisition system for acquiring data, a data processing system for data processing, a historical database for improving the assessment accuracy, and an assessment system for assessing human posture;

[0008] The data acquisition system includes a monitoring unit, a data uploading unit, a timing unit, a distance sensor and a temperature sensor. The monitoring unit includes a monitoring camera. The monitoring range of the monitoring camera covers the entire training ground. The timing unit is used to record the training time. The distance sensor is used to record the training distance. The temperature sensor is used to record the surrounding temperature data.

[0009] The data processing system includes a data receiving unit, a data classification unit, a data processing unit, a data uploading unit and a data retrieval unit, wherein the data retrieval unit is used to retrieve data from a historical database;

[0010] Historical database, including video recording storage unit, log unit, data overwriting unit, data sorting unit and personal information data unit;

[0011] The evaluation system includes a comprehensive processing unit, a similarity matching unit, a data comparison unit, an evaluation report generation unit and a data uploading unit.

[0012] Preferably, the monitoring range of the monitoring camera in the monitoring unit is 5 square meters and an ultra-clear camera is used. The number of monitoring cameras is: Where n is the number of cameras, s is the area of ​​the training ground, and the cameras are numbered, such as camera 1 ,Camera 2 ....Camera n.

[0013] Preferably, the specific processing steps of the data processing system are as follows: when the data receiving unit receives the data uploaded by the monitoring unit, the timing unit, the distance sensor and the temperature sensor, it first classifies the data. After the classification is completed, the monitoring data of each adjacent camera in the monitoring unit are arranged together, and the data uploaded by the monitoring camera is classified according to the number and time. The time classification depends on the data uploaded by the timing unit. Then, the relevant historical data is retrieved from the historical database through the data retrieval unit, and the data is classified with the data received in real time.

[0014] Preferably, the specific retrieval steps of the data retrieval unit are as follows: the data retrieval unit accesses the historical database and retrieves relevant training data from the historical database, that is, first retrieves personal physical fitness data, evaluation reports, and training record data according to the personal information data unit. The training record data includes the relevant monitoring video data, time data, training distance data and surrounding temperature data of the person during training. The log unit records the retrieval record and retrieval time during the data retrieval process.

[0015] Preferably, in the historical database, when the historical database receives updated data uploaded from the evaluation system, it will automatically overwrite duplicate data through the data overwriting unit and record the overwriting date of the overwritten data, that is, overwrite data similar to the evaluation results and related training data. The data sorting unit is used to sort the recorded data, which only records the covering time and does not record related data.

[0016] Preferably, in the evaluation system, the comprehensive processing unit includes a video processing unit, a posture estimation algorithm software, a visualization unit and a posture analysis unit. The video processing unit is used for processing monitoring video, frame extraction and image enhancement. The posture estimation algorithm software includes a YLOL deep learning algorithm for human body detection and a machine learning model for tracking the positions of key points of the human body. The visualization unit is used for visualization of result analysis, which is convenient for intuitive viewing and assists in generating evaluation reports. The posture analysis unit is used to analyze the joint angles and body balance of the human body.

[0017] Preferably, the specific evaluation process of the evaluation system is as follows: first, the frame number of the monitoring video is extracted by the video processing unit in the comprehensive processing unit, that is, each frame of the image is extracted from the video, and the image is enhanced, that is, the noise and contrast are enhanced. Then, the position of the human body is quickly located in the video frame according to the posture estimation algorithm software, and the key points of the human body are tracked in real time. The behavior trajectory of the key points is generated by the visualization unit, and a visualized key point behavior trajectory view is generated. Then, the posture of the human body during training is analyzed according to the posture analysis unit. After the analysis is completed, the environmental data and personal information data are input into the evaluation report production unit to generate the entire evaluation report, thereby completing the evaluation of the posture analysis.

[0018] Preferably, during the evaluation process of the evaluation system, the environmental data is the temperature data during training, and the personal information data is the physical examination data of the trainees.

[0019] A human body posture assessment method for daily police training, the specific assessment method of the human body posture assessment system for daily police training is as follows:

[0020] S1. Data acquisition: First, relevant data of personnel training is acquired through the monitoring unit, timing unit, distance sensor and temperature sensor;

[0021] S2, data processing: perform relevant classification processing on the data obtained in step S1, and retrieve the units in the relevant historical database and upload them to the evaluation unit synchronously;

[0022] S3, data comparison: the evaluation unit first compares the data, and the data types to be compared include time data, temperature data, and distance data;

[0023] S4, posture evaluation: the monitoring video uploaded by the monitoring unit is processed by the comprehensive processing unit and a human posture-related trajectory diagram is generated. Then, the posture analysis unit analyzes the human posture change. After inputting the compared time data, temperature data and distance data, the evaluation report generation unit generates a related report. Finally, the data is uploaded to the historical database.

[0024] S5. Determination of report results: retrieve the current training report and the previous training report of the trainee, match the data of the two reports, and when the matching similarity is lower than 95%, arrange the trainee to train again in the same training environment, re-collect data, repeat steps S1-S4, record the second evaluation report, and compare the results of the three reports respectively. If the similarity of the evaluation reports of the two training results is higher than 95%, record the first evaluation report; if the similarity of the evaluation report of the second training result and the historical report data is higher than 95%, record the second evaluation report, and then upload the two report data synchronously, and the error report is recorded synchronously as the error report.

[0025] Compared with the prior art, the advantages and positive effects of the present invention are:

[0026] In the posture evaluation of the training personnel, the present invention adds a comprehensive processing unit, and extracts the frame number of the monitoring video through the video processing unit in the comprehensive processing unit, that is, extracts each frame of image from the video, performs image enhancement processing on the image, that is, removes noise and enhances the contrast, then quickly locates the position of the human body in the video frame according to the posture estimation algorithm software, and tracks the key points of the human body in real time, generates the behavior trajectory of the key points by using the visualization unit, generates a visualized key point behavior trajectory view, and then analyzes the posture of the human body during training according to the posture analysis unit. After the analysis is completed, the environmental data and personal information data are input into the evaluation report production unit to generate the entire evaluation report. Table, completes the evaluation of posture analysis. Compared with traditional posture analysis, the comprehensive processing unit in the present invention is faster and more accurate in posture analysis. At the same time, environmental variables and personal information variable data are added to further improve the accuracy of the data, avoiding the evaluation results affected by some mistakes made by trainees during training due to temperature reasons. At the same time, the personal information variable data, that is, the body data of the trainees, is used to judge whether it will affect the training posture according to the changes in the body data of the trainees, which effectively improves the accuracy of the evaluation results. At the same time, it is more convenient to guide some mistakes made by trainees during training, thereby improving the posture of trainees during training and improving the training effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 A system diagram of a human posture assessment method and system for daily police training according to the present invention;

[0028] Figure 2 A flow chart of a human posture assessment method and system for daily police training according to the present invention;

[0029] Figure 3The present invention is a human posture assessment method for daily police training and a module diagram of a comprehensive processing unit in the system. DETAILED DESCRIPTION

[0030] 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.

[0031] Example 1

[0032] like Figure 1 as well as Figure 3 As shown, the present invention provides a technical solution: a human posture assessment system for daily public security training, comprising a data acquisition system for acquiring data, a data processing system for data processing, a historical database for improving assessment accuracy, and an assessment system for assessing human posture;

[0033] The data acquisition system includes a monitoring unit, a data uploading unit, a timing unit, a distance sensor and a temperature sensor. The monitoring unit includes a monitoring camera. The monitoring range of the monitoring camera covers the entire training ground. The timing unit is used to record the training time. The distance sensor is used to record the training distance. The temperature sensor is used to record the surrounding temperature data.

[0034] The data processing system includes a data receiving unit, a data classification unit, a data processing unit, a data uploading unit and a data retrieval unit, wherein the data retrieval unit is used to retrieve data from a historical database;

[0035] Historical database, including video recording storage unit, log unit, data overwriting unit, data sorting unit and personal information data unit;

[0036] The evaluation system includes a comprehensive processing unit, a similarity matching unit, a data comparison unit, an evaluation report generation unit and a data uploading unit.

[0037] The monitoring range of the monitoring camera in the monitoring unit is 5 square meters and an ultra-clear camera is used. The number of monitoring cameras is: Where n is the number of cameras, s is the area of ​​the training ground, and the cameras are numbered, such as camera 1 ,Camera 2....camera n, the number of cameras required can be calculated according to the area of ​​the training ground, which can ensure that the cameras can record the training videos of the trainees without blind spots. Numbering the cameras will facilitate the subsequent video processing. According to the number, when processing the video, the time for the trainees to move from the monitoring range of one camera to the monitoring range of the adjacent camera can be calculated according to the timing unit. At this time, the duplicate data of the monitoring camera can be removed according to this time difference, which not only ensures the integrity of the data, but also reduces the volume of data, facilitating the operation of the system.

[0038] Among them, the specific processing steps of the data processing system are as follows: when the data receiving unit receives the data uploaded by the monitoring unit, timing unit, distance sensor and temperature sensor, it first classifies it. After the classification is completed, the monitoring data of each adjacent camera in the monitoring unit are arranged together, and the data uploaded by the monitoring camera is classified according to the number and time. The time classification depends on the data uploaded by the timing unit. Then, the data retrieval unit retrieves the relevant historical data from the historical database, and classifies the data with the real-time received data. By classifying the cameras according to the number and time, it is not only convenient for subsequent data processing, but also can find the training data of a certain time period in a targeted manner, and evaluate the single training data, making the evaluation more diversified and targeted.

[0039] Among them, the specific retrieval steps of the data retrieval unit are as follows: the data retrieval unit accesses the historical database and retrieves relevant training data from the historical database, that is, first retrieves personal physical fitness data, evaluation reports, and training record data according to the personal information data unit. The training record data includes the relevant monitoring video data, time data, training distance data of the person during training, and the surrounding temperature data during training. The log unit records the retrieval record and retrieval time during the data retrieval process. The personal information data and temperature data are important variables that affect the training posture. Changes in temperature affect the mentality and other physical reactions of the trainees. The personal information data represents changes in the trainees' own body functions, which will also affect the training posture.

[0040] Among them, in the historical database, when the historical database receives updated data uploaded from the evaluation system, it will automatically overwrite the duplicate data through the data overwriting unit, and record the overwriting date of the overwritten data, that is, overwrite the evaluation results and data similar to the relevant training data. The data sorting unit is used to sort the recorded data. This data only records the covering time and does not record related data. By overwriting duplicate data and only performing record processing, the storage capacity of the historical database is effectively reduced, ensuring that it can store data for a longer time.

[0041] In the evaluation system, the comprehensive processing unit includes a video processing unit, a posture estimation algorithm software, a visualization unit and a posture analysis unit. The video processing unit is used for processing surveillance videos, frame extraction and image enhancement. The posture estimation algorithm software includes a YLOL deep learning algorithm for human body detection and a machine learning model for tracking the positions of key points of the human body. The visualization unit is used for visualization of result analysis, which is convenient for intuitive viewing and assists in generating evaluation reports. The posture analysis unit is used to analyze the joint angles and body balance of the human body.

[0042] Preferably, the specific evaluation process of the evaluation system is as follows: first, the frame number of the monitoring video is extracted by the video processing unit in the comprehensive processing unit, that is, each frame of the image is extracted from the video, and the image is enhanced, that is, the noise and contrast are enhanced. Then, the position of the human body is quickly located in the video frame according to the posture estimation algorithm software, and the key points of the human body are tracked in real time. The behavior trajectory of the key points is generated by the visualization unit, and a visualized key point behavior trajectory view is generated. Then, the posture of the human body during training is analyzed according to the posture analysis unit. After the analysis is completed, the environmental data and personal information data are input into the evaluation report production unit to generate the entire evaluation report, and the evaluation of the posture analysis is completed. By generating a real-time behavior trajectory view of the key points of the human body during the training process, the training results can be better evaluated, and better guidance can be given for the human body posture.

[0043] Among them, during the evaluation process of the evaluation system, the environmental data, i.e., the temperature data during training, and the personal information data, i.e., the physical examination data of the trainees, are added, which further improves the accuracy of the data and avoids the evaluation results being affected by some mistakes made by the trainees during the training process due to temperature reasons. At the same time, the personal information variable data, i.e., the body data of the trainees, is used to judge whether it will affect the training posture according to the changes in the body data of the trainees, which effectively improves the accuracy of the evaluation results and makes it more convenient to guide some mistakes made by the trainees during the training process, thereby improving the posture of the trainees during training and improving the training effect.

[0044] Example 2

[0045] like Figure 2 As shown, a human posture assessment method for daily police training, the specific assessment method of the human posture assessment system for daily police training is as follows:

[0046] S1. Data acquisition: First, relevant data of personnel training is acquired through the monitoring unit, timing unit, distance sensor and temperature sensor. Specifically, the monitoring unit records the training video of human training, and the timing unit can record the training time of the trainee, which includes not only the overall training time, but also the time passing each monitoring camera and the training time of one-way training. The distance sensor is used to record the training distance, and the temperature sensor records the change of the surrounding temperature during the training process;

[0047] S2, data processing: perform relevant classification processing on the data obtained in step S1, and retrieve the units in the relevant historical database, and upload them to the evaluation unit synchronously. Specifically, when the data receiving unit receives the data uploaded by the monitoring unit, the timing unit, the distance sensor and the temperature sensor, it first classifies them. After the classification is completed, the monitoring data of each adjacent camera in the monitoring unit are arranged together, and the data uploaded by the monitoring camera is classified according to the number and time. The time classification depends on the data uploaded by the timing unit. Then, the relevant historical data is retrieved from the historical database through the data retrieval unit. The data retrieval unit is connected to the historical database and retrieves relevant training data from the historical database, that is, first retrieve personal physical fitness data, evaluation reports, and training record data according to the personal information data unit. The training record data includes the relevant monitoring video data, time data, training distance data and surrounding temperature data of the person during training. The log unit records the retrieval record and retrieval time during the data retrieval process, and then classifies the data with the real-time received data;

[0048] S3. Data comparison: the evaluation unit first compares the data. The data types to be compared include time data, temperature data, and distance data. The time comparison includes the comparison of unidirectional training time and the comparison of overall training time. The temperature data comparison is the comparison of temperature changes during the training process. The distance data comparison is the comparison of training distance and historical training distance.

[0049] S4, posture evaluation: extract the number of frames of the surveillance video through the video processing unit in the comprehensive processing unit, that is, extract each frame of the image from the video, perform image enhancement processing on the image, that is, remove noise and enhance the contrast, then quickly locate the position of the human body in the video frame according to the posture estimation algorithm software, and track the key points of the human body in real time, use the visualization unit to generate the behavior trajectory of the key points, generate a visualized key point behavior trajectory view, and then analyze the posture of the human body during training according to the posture analysis unit. After the analysis is completed, the environmental data and personal information data are input into the evaluation report production unit to generate the entire evaluation report, and the evaluation of the posture analysis is completed;

[0050] S5. Determination of report results: retrieve the current training report and the previous training report of the trainee, match the data of the two reports, and when the matching similarity is lower than 95%, arrange the trainee to train again in the same training environment, re-collect data, repeat steps S1-S4, record the second evaluation report, and compare the results of the three reports respectively. If the similarity of the evaluation reports of the two training results is higher than 95%, record the first evaluation report; if the similarity of the evaluation report of the second training result and the historical report data is higher than 95%, record the second evaluation report, and then upload the two report data synchronously, and the error report is recorded synchronously as the error report.

[0051] In step S5, due to the changes in temperature data and human body function data, the evaluation results will be affected to a certain extent. Therefore, when there is an obvious error in the evaluation result, the error here is that the training evaluation result is lower than the historical evaluation result. If there is an evaluation result that is better than the historical evaluation result, there is no need to repeat the training.

[0052] The above description is only a preferred embodiment of the present invention and does not limit the present invention in other forms. Any technician familiar with the profession may use the technical content disclosed above to change or modify it into an equivalent embodiment with equivalent changes and apply it to other fields. However, any simple modification, equivalent change and modification made to the above embodiment based on the technical essence of the present invention without departing from the content of the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A human posture assessment system for daily police training, characterized in that: including a data acquisition system for acquiring data, a data processing system for processing data, a historical database for improving the accuracy of evaluation, and an evaluation system for evaluating human posture; The data acquisition system includes a monitoring unit, a data uploading unit, a timing unit, a distance sensor and a temperature sensor. The monitoring unit includes a monitoring camera. The monitoring range of the monitoring camera covers the entire training ground. The timing unit is used to record the training time. The distance sensor is used to record the training distance. The temperature sensor is used to record the surrounding temperature data. The data processing system includes a data receiving unit, a data classification unit, a data processing unit, a data uploading unit and a data retrieval unit, wherein the data retrieval unit is used to retrieve data from a historical database; Historical database, including video recording storage unit, log unit, data overwriting unit, data sorting unit and personal information data unit; The evaluation system includes a comprehensive processing unit, a similarity matching unit, a data comparison unit, an evaluation report generation unit and a data uploading unit.

2. The human body posture assessment system for daily police training according to claim 1 is characterized in that: The monitoring range of the monitoring camera in the monitoring unit is 5 square meters and an ultra-clear camera is used. The number of monitoring cameras is: Where n is the number of cameras, s is the area of ​​the training ground, and the cameras are numbered, such as camera 1, camera 2,...camera n.

3. A human posture assessment system for daily police training according to claim 2, characterized in that: The specific processing steps of the data processing system are as follows: when the data receiving unit receives the data uploaded by the monitoring unit, the timing unit, the distance sensor and the temperature sensor, it first classifies it. After the classification is completed, the monitoring data of each adjacent camera in the monitoring unit are arranged together, and the data uploaded by the monitoring camera is classified according to the number and time. The time classification depends on the data uploaded by the timing unit. Then, the relevant historical data is retrieved from the historical database through the data retrieval unit, and the data is classified with the data received in real time.

4. The human body posture assessment system for daily police training according to claim 3 is characterized in that: The specific retrieval steps of the data retrieval unit are as follows: the data retrieval unit accesses the historical database and retrieves relevant training data from the historical database, that is, first retrieves personal physical fitness data, evaluation reports, and training record data based on the personal information data unit. The training record data includes the relevant monitoring video data, time data, training distance data, and surrounding temperature data of the person during training. The log unit records the retrieval record and retrieval time during the data retrieval process.

5. The human body posture assessment system for daily police training according to claim 4 is characterized in that: In the historical database, when the historical database receives updated data uploaded from the evaluation system, the duplicate data will be automatically overwritten by the data overwriting unit, and the overwriting date of the overwritten data will be recorded, that is, the evaluation results and data similar to the relevant training data will be overwritten. The data sorting unit is used to sort the recorded data, which only records the covering time and does not record the relevant data.

6. The human body posture assessment system for daily police training according to claim 5, characterized in that: In the evaluation system, the comprehensive processing unit includes a video processing unit, a posture estimation algorithm software, a visualization unit and a posture analysis unit. The video processing unit is used for processing surveillance video, frame extraction and image enhancement. The posture estimation algorithm software includes a YLOL deep learning algorithm for human body detection and a machine learning model for tracking the positions of key points of the human body. The visualization unit is used for visualization of result analysis, which is convenient for intuitive viewing and assists in generating evaluation reports. The posture analysis unit is used to analyze the joint angles and body balance of the human body.

7. A human posture assessment system for daily police training according to claim 6, characterized in that: The specific evaluation process of the evaluation system is as follows: first, the frame number of the monitoring video is extracted by the video processing unit in the comprehensive processing unit, that is, each frame of the image is extracted from the video, and the image is enhanced, that is, the noise and contrast are enhanced. Then, the position of the human body is quickly located in the video frame according to the posture estimation algorithm software, and the key points of the human body are tracked in real time. The behavior trajectory of the key points is generated by the visualization unit, and a visualized key point behavior trajectory view is generated. Then, the posture of the human body during training is analyzed according to the posture analysis unit. After the analysis is completed, the environmental data and personal information data are input into the evaluation report production unit to generate the entire evaluation report, and the evaluation of the posture analysis is completed.

8. The human body posture assessment system for daily police training according to claim 7 is characterized in that: During the evaluation process of the evaluation system, the environmental data refers to the temperature data during training, and the personal information data refers to the physical examination data of the trainees.

9. A human posture assessment method for daily police training, according to a human posture assessment system for daily police training according to any one of claims 1 to 8, characterized in that: The specific evaluation method of the human posture evaluation system used for daily public security training is as follows: S1. Data acquisition: First, relevant data of personnel training is acquired through the monitoring unit, timing unit, distance sensor and temperature sensor; S2, data processing: perform relevant classification processing on the data obtained in step S1, and retrieve the units in the relevant historical database and upload them to the evaluation unit synchronously; S3, data comparison: the evaluation unit first compares the data, and the data types to be compared include time data, temperature data, and distance data; S4, posture evaluation: the monitoring video uploaded by the monitoring unit is processed by the comprehensive processing unit and a human posture-related trajectory diagram is generated. Then, the posture analysis unit analyzes the human posture change. After inputting the compared time data, temperature data and distance data, the evaluation report generation unit generates a related report. Finally, the data is uploaded to the historical database. S5. Determination of report results: retrieve the current training report and the previous training report of the trainee, match the data of the two reports, and when the matching similarity is lower than 95%, arrange the trainee to train again in the same training environment, re-collect data, repeat steps S1-S4, record the second evaluation report, and compare the results of the three reports respectively. If the similarity of the evaluation reports of the two training results is higher than 95%, record the first evaluation report; if the similarity of the evaluation report of the second training result and the historical report data is higher than 95%, record the second evaluation report, and then upload the two report data synchronously, and the error report is recorded synchronously as the error report.

Images