Recent Advances in Computer Vision and Machine Learning for Athletic Performance in Jump Events

The application of machine learning and computer vision in athletics facilitates analytical tools for the triple jump and long jump, allowing for the monitoring of speed, posture, and the phases of take-off and landing. Prior research has focused on sports biomechanics; however, this work integrates computer vision and machine learning techniques for triple and long jump events. This study examines how sophisticated technology may transform conventional analytical methods concerning precision and efficiency in evaluating athletes' techniques. The investigation indicates that neural networks, RNNs, and CNNs surpassed traditional methods. This study examines the issues associated with advanced algorithms, including accuracy degradation with varying jumps, expenses related to video capture systems, and the ethical implications of contemporary technology. This work investigates computer vision and machine learning to improve athlete performance via comprehensive feedback, encompassing data acquisition through wearables and computer vision systems. This research facilitates the creation of prediction models for performance analysis and addresses dataset restrictions using machine learning approaches, including transfer learning. It examines AI-driven feedback mechanisms to enhance training efficiency. The research demonstrated that approach velocity directly affects leap distance. The categorization and forecasting of leaps using these techniques help coaches assess skills and adjust training regimens.