Skip to Main Content
This paper addresses the subspace properties and the recovery of articulated motion. We point out that the global motion subspace of an articulated object is a combination of a number of intersecting rigid motion subspaces of the parts. Depending on whether a link of two parts is a joint or an axis, the global motion subspace loses one or two in rank for each link. The rank loss results from the intersection between the rigid motion subspaces of linked parts. Furthermore, the intersection is, in fact, the motion subspace of the link. From these observations, we describe the rank constraint of the global motion subspace of an articulated object; we give an algorithm to recover the image motion of a link, either a joint or an axis; and we propose a novel but simple approach, which is based on subspace clustering, to recover articulated shape and motion from a single-view image sequence.
Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on (Volume:2 )
Date of Conference: 20-25 June 2005