Human motion analysis for sports application

Abstract

Nowadays, human motion analysis has been gaining more attention from the researchers in the field of sports science which is used as a tool for athlete to enhance techniques, correction movement error and aid in rehabilitation. Now, with the advance technology and computation power, computer researchers are now able to focus on developing markerless human motion analysis. Our research focuses in tracking the major body if a professional golfer while he/she is performing golf swing activity directly from a broadcast video. However aperture problem still arise when the body movement overlap each other by soley rely on background subtraction. In this paper, we present a combination method of optical flow and template matching to track the head, torso, arms, leg and feet of the golfer. This is to allow each human body parts were able to track overtime in different contour to overcome the aperture problem.