Classifying Sports Gesture Using Event-Based Matching in a Multimedia E-learning System

Computer-based multimedia instructional systems are ideal for e-learning in many domains. For applications such as sport instruction, the central issue is to capture motions accurately and correctly for further processing. A Web-based tennis instruction system is under investigation and being designed and developed. To capture the motion of a tennis swing, the Nintendo Wii Remote is used as the input device. The current focus of the project is the various issues associated with motion-sensing input data: capturing, cleansing, classification and clustering of some basic tennis swings, and the subsequent swing matching and identification which can then be used to index into a multimedia database for instructional purpose. In this work, classification of a tennis swing using event-based matching is presented and illustrated with examples. Results from experiments with 50 people are analyzed. The accuracy and the suitability of the matching algorithms are evaluated and discussed.