A factorization-based approach to articulated motion recovery

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.

[1]  David C. Hogg.  Model-based vision: a program to see a walking person , 1983, Image Vis. Comput..

[2]  Robert J. Holt,et al.  Determining articulated motion from perspective views: a decomposition approach , 1997, Proceedings of 1994 IEEE Workshop on Motion of Non-rigid and Articulated Objects.

[3]  Lucas Paletta,et al.  Euclidean structure recovery through articulated motion , 1997 .

[4]  Takeo Kanade,et al.  A Paraperspective Factorization Method for Shape and Motion Recovery , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  Jitendra Malik,et al.  Tracking people with twists and exponential maps , 1998, Proceedings. 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No.98CB36231).

[6]  Henning Biermann,et al.  Recovering non-rigid 3D shape from image streams , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[7]  Cristian Sminchisescu,et al.  Covariance scaled sampling for monocular 3D body tracking , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[8]  Lorenzo Torresani,et al.  Tracking and modeling non-rigid objects with rank constraints , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[9]  Matthew Brand,et al.  Morphable 3D models from video , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[10]  Thomas S. Huang,et al.  Recovering Articulated Motion with a Hierarchical Factorization Method , 2003, Gesture Workshop.

[11]  A new GPCA algorithm for clustering subspaces by fitting, differentiating and dividing polynomials , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[12]  Mei Han,et al.  Reconstruction of a Scene with Multiple Linearly Moving Objects , 2004, International Journal of Computer Vision.

[13]  Takeo Kanade,et al.  Shape and motion from image streams under orthography: a factorization method , 1992, International Journal of Computer Vision.

[14]  Takeo Kanade,et al.  A Multibody Factorization Method for Independently Moving Objects , 1998, International Journal of Computer Vision.

[15]  Jing Xiao,et al.  A Closed-Form Solution to Non-Rigid Shape and Motion Recovery , 2004, International Journal of Computer Vision.

[16]  Marc Pollefeys,et al.  A Factorization-Based Approach to Articulated Motion Recovery , 2005, CVPR.

[17]  S. Shankar Sastry,et al.  Generalized principal component analysis (GPCA) , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.