抄録
In the recent years, motion capture systems are used for robot vision and man-machine interface. Most of those systems need attached markers on human body and several sensors. So makerless motion capture system is needed. In this paper, we propose the technique for posture estimation from monocular image sequences. This technique estimates a posture based on detecting body parts. Body parts (arms, legs, head, torso and so on) are detected without markers using human body structure model. A posture is estimated by constructing detected parts. This technique does not require a manual operation to determine initial posture at the first frame. A markerless motion capture system is realized by using this technique. In the experiment, we confirmed realizability of this technique.
