Articulated Structure from Motion by Factorization
- 27 July 2005
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2, 1110
- https://doi.org/10.1109/cvpr.2005.75
Abstract
Multibody affine structure from motion (SFM) methods commonly assume independent motion between objects such that the 'measurement matrix' has rank 4k. When multiple views are available, each object is then independently calibrated to a metric co-ordinate frame. However, articulated motion results in a further decrease in rank - a fact that we exploit to detect articulated objects and determine their degrees of freedom using simple linear methods. Furthermore, these objects cannot be recovered and calibrated independently since this violates articulation constraints. We show that articulation constraints can be imposed during factorization and self-calibration to recover consistent 3D structure and motion, from which link lengths and joint angles can be computed. The stability of the method is evaluated using synthetic data for comparison with ground truth and results are also presented for real image sequences.Keywords
This publication has 15 references indexed in Scilit:
- Morphable 3D models from videoPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Degeneracies, dependencies and their implications in multi-body and multi-sequence factorizationsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Kinematic jump processes for monocular 3D human trackingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Synchronizing Image Sequences of Non-Rigid ObjectsPublished by British Machine Vision Association and Society for Pattern Recognition ,2003
- A step towards sequence-to-sequence alignmentPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Recovering non-rigid 3D shape from image streamsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Reconstruction of articulated objects from point correspondences in a single uncalibrated imagePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- The Development and Comparison of Robust Methods for Estimating the Fundamental MatrixInternational Journal of Computer Vision, 1997
- Active tracking of foveated feature clusters using affine structureInternational Journal of Computer Vision, 1996
- Shape and motion from image streams under orthography: a factorization methodInternational Journal of Computer Vision, 1992