Athlete Movement Technique and Biomechanical Analysis Based on Multimodal Deep Learning and Computer Vision

Precise biomechanical assessment of athletic movements is essential for intelligent sports analysis and wearable sensing applications. This study presents a multimodal deep learning framework that integrates computer vision, RGB video, depth images, and inertial measurement data to achieve markerless motion capture and quantitative biomechanical evaluation. Through spatiotemporal feature alignment and attention-based multimodal fusion, the proposed system accurately estimates joint kinematics, ground reaction forces, torque distribution, and muscle-related motion characteristics while enabling real-time action recognition and technical assessment. Experimental results demonstrate that the framework achieves a keypoint detection accuracy of 89.4%, an F1 score of 92.3% for complex action recognition, and a root mean square error of 4.2◦ in joint angle estimation, providing reliable support for sports performance optimization and injury risk analysis. The proposed multimodal sensing strategy offers an effective solution for integrating visual perception with wearable sensor information and provides valuable methodological insights for intelligent signal acquisition, wireless sensing, and human-centered electromagnetic monitoring systems in next-generation smart engineering applications.