Survey of computer vision-based human motion capture
Yu Guang · Jisuanji gongcheng yu sheji · 2004
Human motion capture is currently one of the most active research topics in the domain of computer vision. It attempts to extract and describe human motion, then track and recognize, from image sequences involving humans. The potential application areas are introduced and a comprehensive survey of the state-of-the-art is gaven, from five major issues: initialization, detection, tracking, pose evaluation and recognition. Finally the research challenges and future directions is briefly discussed.