Incremental Tracking of Human Actions from Multiple Views

This paper proposes a new method for model-based tracking of a human body in 3D motion from multiple views. The tracking is performed by estimating the pose increment of the body parts from multiple image sequences after establishing of tting an articulated model to the human body at the initial frame. The pose increment can be obtained from solving a system of linear equations. This calculation does not depend on the number of view points. Experiments verify that the proposed method can avoid occlusion and visual degenerate from a particular view point, and track a human body in complicated motion.