DBN model-based golf swing reconstruction using Kinect data

Abstract

The last decade has witnessed an explosion of interest in golf, and the number of golf players has increased significantly. Therefore, how to train a golfer to make a proper and accurate golf swing has attracted extensive research attentions. Among these researches the most important step is swing capture and reconstruction. Thus far, restricted to the development of present depth imaging devices, of which the most famous one is Kinect, the initial captured swing movement may not be acceptable enough due to occlusions and mixing up of body parts. To restore motion information from self-occlusion and reconstruct 3D golf swing from low resolution depth data, a dynamic Bayesian network (DBN) model based golf swing reconstruction algorithm is proposed to increase the capture accuracy which integrates the spatial relationship among joints and their movement dynamics. Experimental results have proved that the proposed algorithm can achieve comparable reconstruction accuracy to the commercial optical motion caption (OMocap) system and better performance than state of art modification algorithms using depth information.