3D human walking modeling

This paper presents a new approach for 3D human walking modeling from monocular image sequences. An efficient feature point selection and tracking approach has been used to compute feature points' trajectories. Peaks and valleys of these trajectories are used to detect key frames-frames where both legs are in contact with the floor. These frames, together with prior knowledge of body kinematics and a motion model, are the basis for the 3D reconstruction of human walking. The legs' configuration at each key frame contributes to tune the amplitude of the motion model. Differently than previous approaches, this tuning process is not performed at every frame, reducing CPU time. In addition, the movement's frequency is defined by the elapsed time between two consecutive key frames, which allows handling walking displacement at different speed. Experimental results with different video sequences are presented.