Key points are not available for this paper at this time.
The possibilities of an AI gym tracker helping fitness to optimize their training and avoid potential accidents through AI pose analysis are significant. This paper presents a new approach that skillfully combines Mediapipe and OpenCV features to accurately calculate the pose. The well-known computer vision library OpenCV provides a large number of methods for analyzing pictures and videos, while 33 Points for Human Pose Estimation assesses human circumstances using pre-trained models. This approach provides an AI positioning algorithm that comes about by combining the advantages of both methods. User video is initially captured by the system, which uses MediaPipe to analyze it before detecting vital landmarks of the normal human body. The angles between these identified landmarks are then calculated using OpenCV, enabling a comprehensive conditional analysis. The user receives immediate feedback on corrective exercises. Notably, the system performs very well in pose recognition in different lighting conditions and without obstructions or background interference. Our AI Gym Tracker technology can help fitness enthusiasts improve in any way and through it, reducing damage from training.
Gowrish et al. (Tue,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: