An Efficient Technique for Motion Recovery Based on Multiple Views

The factorization method is a technique for recovering 3-D shape of an undeformable object without using camera parameters. The technique is extended to an efficient method in this paper for recovering 3-D motion of a deformable object, i.e., a human. The proposed system is composed of three fixed video cameras which take video images of a human motion. Three obtained image sequences are analyzed to yield measurement matrices at individual sampling times, and they are merged into a single measurement matrix to which the factorization is applied and the 3-D human motion is recovered at a time. Experimental results were satisfactory.