3D-2D spatiotemporal registration for sports motion analysis

Computer systems are increasingly being used for sports training. Existing sports training systems either require expensive 3D motion capture systems or do not provide intelligent analysis of userpsilas sports motion. This paper presents a framework for affordable and intelligent sports training systems for general users that require only single camera to record the userpsilas motion. Sports motion analysis is formulated as a 3D-2D spatiotemporal motion registration problem. A novel algorithm is developed to perform spatiotemporal registration of the expertpsilas 3D reference motion and a performerpsilas 2D input video, thereby computing the deviation of the performerpsilas motion from the expertpsilas motion. The algorithm can effectively handle ambiguous situations in a single video such as depth ambiguity of body parts and partial occlusion. Test results show that, despite using only single video, the algorithm can compute 3D posture errors that reflect the performerpsilas actual motion error.