Abstract des Autors

This paper proposes a motor learning assist system that estimates the proficiency of a trainee in making sports motions on the basis of variability of his/her own 3D motions in trials captured by a single camera. Most existing systems assume that a sequence of human poses must be obtained by multiple calibrated cameras or a marker-based motion capture system. Such systems can be effectively used by professional athletes or broadcast station personnel who specialize in sports, but not by casual sports fans who have no particular athletic skills. We propose a method for evaluating proficiency based on the variance of the 3D motion when it is subjected to repeated trials. It has two important features. First, it requires only a free-position single camera by employed the 3D pose estimation method independent of camera position. It can be used not only by elite athletes but also by casual sports fans. Second, it estimates proficiency only from a trainee's own motion and thus does not require any reference movements. In this paper, the golf swing is used as the target of motor learning. Experiments result shows that variability of 3D motions in trials is inversely proportional to the degree proficiency.