Geometric Structure of Degeneracy for Multi-body Motion Segmentation

Many techniques have been proposed for segmenting feature point trajectories tracked through a video sequence into independent motions. It has been found, however, that methods that perform very well in simulations perform very poorly for real video sequences. This paper resolves this mystery by analyzing the geometric structure of the degeneracy of the motion model. This leads to a new segmentation algorithm: a multi-stage unsupervised learning scheme first using the degenerate motion model and then using the general 3-D motion model. We demonstrate by simulated and real video experiments that our method is superior to all existing methods in practical situations.

• Type: Conference
• Year: 2004
• Where: ECCV
• Authors: Yasuyuki Sugaya, Ken-ichi Kanatani
• Keywords: Computer Vision, ECCV 2004, Motion Model, Real Video, Video Sequences