Title :
Knowledge-guided visual perception of 3-D human gait from a single image sequence
Author :
Chen, Zen ; Lee, Hsi-Jian
Author_Institution :
Dept. of Comput. Sci. & Inf. Eng., Nat. Chiao Tung Univ., Hsinchu, Taiwan
Abstract :
A computer vision method is presented to determine the 3-D spatial locations of joints or feature points of human body from a film recording the human motion during walking. The proposed method first applies the geometric projection theory to obtain a set of feasible postures from a single image, then it makes use of the given dimensions of the human stick figure, physiological and motion-specific knowledge to constrain the feasible postures in both the single-frame analysis and the multi-frame analysis. Finally a unique gait interpretation is selected by an optimization algorithm. Computer simulations are used to illustrate the ideas presented
Keywords :
biomechanics; computer vision; knowledge based systems; visual perception; 3D human gait; computer vision method; feasible postures; feature points; geometric projection theory; human motion; human stick figure; image sequence; joints; knowledge-guided visual perception; motion-specific knowledge; multi-frame analysis; optimization algorithm; single-frame analysis; walking; Computer simulation; Computer vision; Constraint theory; Humans; Image analysis; Image motion analysis; Joints; Legged locomotion; Motion analysis; Visual perception;
Journal_Title :
Systems, Man and Cybernetics, IEEE Transactions on
