Skeleton Based Keyframe Detection Framework for Sports Action Analysis: Badminton Smash Case

The analysis of badminton player actions from videos plays a crucial role in improving athletes’ performance and generating statistical insights. complexity speed movements pose unique challenges compared to everyday activities. To analyze actions, we propose skeleton-based keyframe detection framework for action analysis. Keyframe is widely used video summarization visual localization due its computational efficiency memory optimization analyzing all frames video. This segments the complex macro-level activity into micro-level analyzes each individually. Firstly, it extracts skeleton data motion sequence using 3D:VIBE estimation. Then, module explores identifies keyframes activity, including start, ready, strike, end. Finally, posture movement modules identify specific implemented device called CoachBox. proposed evaluated mean absolute error on dataset. average less than 0.168 seconds, striking moment has an only 0.033 seconds. Additionally, coordinate transform method provided convert body coordinates real-world visualization purposes.