A Taekwondo kicking video capture and scoring system based on deeplabcut

Abstract

The invention claims protection of a Taekwondo kick motion video capture and scoring system based on DeepLabCut, which belongs to the technical field of motion capture. It specifically includes: the video acquisition module, which is used to obtain the video of the athlete's lateral kick action in the XYZ three-dimensional system, and uses three mobile phones to shoot video from the three directions of X, Y, and Z; the video processing module uses DeepLabCut software to process the acquired video Processing, converting the acquired video data into quantifiable specific parameters such as dynamics and kinematics; the data analysis module combines the obtained data with the parameters and threshold parameters in the established standard action database Carry out separate comparisons and analyze the movement quality through relevant algorithms; the result output module outputs the various data results obtained by the data analysis unit to complete the accurate evaluation of kicking movements. The central processing unit module is used to receive and send various instructions, and coordinate the work of the above modules.

Description

technical field [0001] The invention belongs to the field of motion posture capture, and in particular relates to the technology of Taekwondo kick motion video capture and scoring system. Background technique [0002] Accurately tracking body movement during behavior is an important aspect of exercise science. However, researchers usually need to spend a lot of time and energy to mark each frame; some studies need to place markers on predetermined points on the subject's body, but the markers may interfere with the behavior of the research target, and suitable motion Types are very limited. DeepLabCut is an open source toolkit that can automatically track and label moving biological body parts, which can quickly and easily perform high-precision motion tracking on any animal. Any researcher can download any video from the web and digitally tag specific body parts in dozens of frames of footage. This tool will automatically learn how to pick out the same or similar feature...

AI Technical Summary

Problems solved by technology

[0005] Existing technology for motion capture has a long reaction time and requires a series of cumbersome processing and analysis of the acquired data. Researchers either need to spend time and effort to mark each frame, and the processing and reaction time cannot be synchronized, which cannot be realized. real time

Some studies require placing markers at predetermined points on the subject’s body, such as pasting or tying motion-sensing aids to body parts related to the form of movement through Velcro or straps, and markers may interfere with the movement of the subject. Behavior that is detrimental to athletic training and generally only suitable for limited types of sports

Images