Sticking training and checking integrated system
By using deep learning object detection and Internet of Things technology in the sting training and assessment system, combined with dummy simulation training, the problem that the existing technology cannot effectively judge the sting movement of the soldier is solved, and the identification of soldier movements and the provision of training suggestions is achieved. , realizes data recording and visualization of military training.
Patent Information
- Application Number
- CN202411177973.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-26
- Publication Date
- 2024-11-26
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The existing technology cannot effectively judge the basic movements of soldiers' stabbing, cannot collect wrong movements and give training suggestions, and cannot data-based records and visualize the effects of military training.
Using an integrated system of assassination training and assessment, the first and second cameras are connected to the real-time video stream, combined with deep learning object detection algorithms and Internet of Things technology, the identity and action data of the trainees are identified and recorded, and dummy simulation is used. Training collects strength and location information, and stores and analyzes data through databases to provide training and assessment plan management.
It realizes effective identification of soldiers' movements and collection of wrong movements, provides training suggestions, and data recording and visualizes the effects of military training to fully serve teachers and students.
Smart Images

Figure CN119028020A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of sports training platforms, and in particular to an integrated system for assassination training and assessment. Background Art
[0002] The construction of the thrust assessment system is a new infrastructure centered on the digital construction of the troops. It is based on artificial intelligence analysis systems and Internet of Things perception systems to achieve data interaction, forming an efficient specific personnel training analysis and thrust action assessment service, which provides a strong digital intelligence support for the troops to quickly grasp the training results of soldiers. However, the existing technology cannot effectively judge the basic thrust actions of soldiers, cannot collect erroneous actions and give training suggestions, and cannot record daily military training, digitize the process, and visualize the effects. To address these problems, we propose an integrated system for assassination training and assessment. Summary of the invention
[0003] The main purpose of the present invention is to provide an integrated system for assassination training and assessment, which can effectively solve the problems in the background technology.
[0004] To achieve the above object, the technical solution adopted by the present invention is:
[0005] The integrated assassination training and assessment system provides identification services including the identification object, and has the following features:
[0006] The first camera accesses the real-time video stream via the RTSP protocol, captures the video stream of the identified object, detects the key frames of the video stream, and identifies the identity information of the trainees and assessors;
[0007] Card reader, which identifies the identity information of trainees and assessors by swiping cards;
[0008] The second camera accesses the real-time video stream via the RTSP protocol and detects key frames of personnel training or assessment in the video stream;
[0009] The identification service data front-end collects and calls the identification data of personnel participating in training or assessment, and stores the data in the database through its stab software system;
[0010] The dummy is made of high-strength composite materials, human-like structure, polymer self-healing materials, strong piercing sensation, replaceable modules, high-durability dummy mold, built-in sensor chip, real-time acquisition of sensor data and transmission of evaluation results;
[0011] The key frames in the video stream are detected by using a single-stage deep learning target detection algorithm to detect the target holding a gun and in a ready-to-use gun posture as a trainee. The trainees are tracked frame by frame, and the key actions are detected by top-down human skeleton key points, and 17 key points are detected, including the nose, left and right eyes, left and right ears, left and right shoulders, left and right elbows, left and right wrists, left and right hips, left and right knees, and left and right ankles. For the detected key points, spatial geometry calculations are performed with a human-shaped target as the reference system. Under the default right-handed system, the left foot kicking distance, whether the left arm is straight, whether the left calf is perpendicular to the ground, and whether the body is in an oblique straight line are obtained, and these detection results are fed back in the form of an interface. The database is used to store personnel identity information data, dummy sensor data, action recognition data, and assessment result data.
[0012] Furthermore, the dummy is used as a carrier, and the body parts and strength of the trainees and assessors who stab the dummy are collected through the Internet of Things technology, and the collected data is stored as the basis for subsequent functional data, which records the time of the hit, the location of the hit and the strength information. The information obtained by the dummy is transmitted to the database for storage through a dedicated wireless communication receiver.
[0013] Furthermore, the software system of the identification service data front-end can formulate assessment and training plan management according to personnel, and the plan management includes annual plan, monthly plan, weekly plan and daily plan. After these plans are customized, they are uploaded to the database through the data interface service.
[0014] Furthermore, the database can retrieve the assessment and training plans of the corresponding personnel uploaded to the database through the data interface service. When in the assessment mode, the assessment is executed through the plan management, all the assessment data is uploaded to the database, and the unit assessment statistics or personal assessment statistics are displayed according to the assessment object. Similarly, when in the training mode, the training is executed through the plan management, all the training data is uploaded to the database, and the unit training statistics or personal training statistics are displayed according to the training object. In the training mode, an additional training data model will be displayed for training analysis, and the data will also be stored in the database.
[0015] Furthermore, the data obtained by detecting the key frames in the video stream are first fed back to the identification service data front-end through the dynamic data interface service for assessment data analysis, and then all the data results of the assessment are stored in the database through the data interface service. Similarly, the data obtained by detecting the key frames in the video stream are first fed back to the identification service data front-end through the dynamic data interface service for training data analysis, and then all the data results of the training are stored in the database through the data interface service.
[0016] Furthermore, when the first camera identifies the identity information of the trainees and assessors, it calls the basic data of the personnel for identity recognition through the data interface service and the dynamic data interface service.
[0017] Compared with the prior art, the present invention has the following beneficial effects:
[0018] In the present invention, the integrated system of assassination training and assessment can identify the actions of soldiers, collect wrong actions, give training suggestions, and record daily military training, digitize the process, and visualize the effect. It can provide all-round services to instructors and trainees. BRIEF DESCRIPTION OF THE DRAWINGS
[0019] Figure 1 It is a functional requirement flow chart of the assessment system of the assassination training and assessment integrated system of the present invention;
[0020] Figure 2 It is a training function flow chart of the assassination training and assessment integrated system of the present invention;
[0021] Figure 3 This is a flow chart of the assessment function of the assassination training and assessment integrated system of the present invention;
[0022] Figure 4 It is a functional flow chart of the second camera of the assassination training and assessment integrated system of the present invention;
[0023] Figure 5 This is a functional flow chart of the first camera of the assassination training and assessment integrated system of the present invention;
[0024] Figure 6 It is a dummy function flow chart of the assassination training and assessment integrated system of the present invention;
[0025] Figure 7 The figure is a system overall structure diagram of the assassination training and assessment integrated system of the present invention. DETAILED DESCRIPTION
[0026] In order to make the technical means, creative features, objectives and effects achieved by the present invention easy to understand, the present invention is further explained below in conjunction with specific implementation methods.
[0027] like Figure 1-7As shown, the assassination training and assessment integrated system accesses the real-time video stream through the first camera in the RTSP protocol mode, and shoots the video stream of the identification body, detects the key frames of the video stream, and identifies the identity information of the trainees and assessors. At the same time, the first camera can also identify and enter the identity information of the personnel into the database as the identification data basis for the next training or assessment, or manually upload the basic data of the personnel and the basic data of the model to the database. When entering the system, the personnel can enter the system through the card reader or the first camera for identification. The first entry into the system can be managed by customizing the corresponding plan and stored in the database. When the personnel are in the assessment mode or training mode, the identification service data front-end will call the corresponding plan in the database through the data interface service, and perform assessment or training on the personnel according to the plan, and make data statistics for the corresponding assessment or training objects. In addition, additional training result analysis and display will be made for the training mode, and all data will be stored in the personal file of the database. During the above training or assessment, the second camera will shoot the key frames in the video stream for detection. This The first detection is to use a single-stage deep learning target detection algorithm to detect that the target holding a gun and in a ready-to-use gun posture is determined as a trainee, and the trainee is tracked frame by frame. The key actions are detected by top-down human skeleton key point detection, and 17 key points are detected, including the nose, left and right eyes, left and right ears, left and right shoulders, left and right elbows, left and right wrists, left and right hips, left and right knees, and left and right ankles. For the detected key points, spatial geometric calculations are performed with the human target as the reference system. When the system defaults to a right-handed person, the kicking distance of the left foot, whether the left arm is straight, whether the left calf is perpendicular to the ground, and whether the body is in a straight line are obtained. These detection results are fed back in the form of an interface. At the same time, when the dummy is stabbed, the body parts and strength of the trainees and assessors who stab the dummy are collected through the Internet of Things technology, and the collected data is stored as the basis for subsequent functional data and the statistical output results of the data of this assessment or training object. The time of the hit, the location of the hit and the strength information are recorded. After the assessment or training is completed, all assessment or training information is displayed on the display system of the identification service data front-end for personnel to view the results.
[0028] The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited to the above embodiments. The above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention to be protected. The scope of protection of the present invention is defined by the attached claims and their equivalents.
Claims
1. An integrated assassination training and assessment system, providing identification services including the identification of the identified object. Features have: The first camera accesses the real-time video stream via the RTSP protocol, captures the video stream of the identified object, detects the key frames of the video stream, and identifies the identity information of the trainees and assessors; Card reader, which identifies the identity information of trainees and assessors by swiping cards; The second camera accesses the real-time video stream via the RTSP protocol and detects key frames of personnel training or assessment in the video stream; The identification service data front-end collects and calls the identification data of personnel participating in training or assessment, and stores the data in the database through its stab software system; The dummy is made of high-strength composite materials, human-like structure, polymer self-healing materials, strong piercing sensation, replaceable modules, high-durability dummy mold, built-in sensor chip, real-time acquisition of sensor data and transmission of evaluation results; The key frames in the video stream are detected by using a single-stage deep learning target detection algorithm to detect the target holding a gun and in a ready-to-use gun posture as a trainee. The trainees are tracked frame by frame, and the key actions are detected by top-down human skeleton key points, and 17 key points are detected, including the nose, left and right eyes, left and right ears, left and right shoulders, left and right elbows, left and right wrists, left and right hips, left and right knees, and left and right ankles. For the detected key points, spatial geometry calculations are performed with a human-shaped target as the reference system. Under the default right-handed system, the left foot kicking distance, whether the left arm is straight, whether the left calf is perpendicular to the ground, and whether the body is in an oblique straight line are obtained, and these detection results are fed back in the form of an interface. The database is used to store personnel identity information data, dummy sensor data, action recognition data, and assessment result data.
2. The integrated assassination training and assessment system according to claim 1, Features: The dummy is used as a carrier, and the body parts and strength of the trainees and assessors who stab the dummy are collected through the Internet of Things technology. The collected data is stored as the basis for subsequent functional data, which will record the time of the hit, the location point of the hit and the strength information. The information obtained by the dummy is transmitted to the database for storage through a dedicated wireless communication receiver.
3. The integrated assassination training and assessment system according to claim 1, Features: The software system of the identification service data front-end can formulate a plan management for assessment and training according to the personnel, and the plan management includes annual plan, monthly plan, weekly plan and daily plan. After these plans are customized, they are uploaded to the database through the data interface service.
4. The integrated assassination training and assessment system according to claim 3, Features: The database can retrieve the assessment and training plans of the corresponding personnel uploaded to the database through the data interface service. When in the assessment mode, the assessment is executed through the plan management, all the assessment data is uploaded to the database, and the unit assessment statistics or personal assessment statistics are displayed according to the assessment object. Similarly, when in the training mode, the training is executed through the plan management, all the training data is uploaded to the database, and the unit training statistics or personal training statistics are displayed according to the training object. In the training mode, an additional training data model will be displayed for training analysis, and the data will also be stored in the database.
5. The integrated assassination training and assessment system according to claim 1, Features: The data obtained by detecting the key frames in the video stream are first fed back to the identification service data front-end through the dynamic data interface service for assessment data analysis, and then all the data results of the assessment are stored in the database through the data interface service. Similarly, the data obtained by detecting the key frames in the video stream are first fed back to the identification service data front-end through the dynamic data interface service for training data analysis, and then all the data results of the training are stored in the database through the data interface service.
6. The integrated assassination training and assessment system according to claim 1, Features: When the first camera identifies the identity information of the trainees and assessors, it calls the basic data of the personnel for identity identification through the data interface service and the dynamic data interface service.
Citation Information
Cited By
Training teaching management analysis system and method based on big data
CN119579007A
