Adding context to traditional player analysis through machine learning

Engineering of Sport 15 - Proceedings from the 15th International Conference on the Engineering of Sport (ISEA 2024)

Performance analysis within sports is a pivotal element in the feedback process that coaches rely on. This process involves analysts processing numerous videos involving a specific athlete competing against various opponents and transforming these data-rich inputs into meaningful insights about the athlete's performance. In this paper we investigate the use of object detection models and how they can be implemented in Taekwondo to track player locations, this is combined with traditional analysis of using coding software such as SportsCode, Nacsport and Dartfish to produce a heatmap of common events during a bout such as kicks and punches.