We present a multiscale method for motion segmentation. Our method begins with local, ambiguous optical flow measurements. It uses a process of aggregation to resolve the ambiguities and reach reliable estimates of the motion. In addition, as the aggregation process proceeds and larger aggregates are identified it employs a progressively more complex model to describe the motion. In particular, we proceed by recovering translational motion at fine levels, through affine transformation at intermediate levels, to 3D motion (described by a fundamental matrix) at the coarsest levels. Finally, the method is integrated with a segmentation method that uses intensity cues. We further demonstrate the utility of the method on both random dot and real motion sequences.
Multiscale segmentation by combining motion and intensity cues
2005-01-01
851409 byte
Conference paper
Electronic Resource
English
Segmentation using multiscale cues
IEEE | 2004
|Segmentation Using Multiscale Cues
British Library Conference Proceedings | 2004
|Incorporating non-motion cues into 3D motion segmentation
British Library Online Contents | 2007
|Incorporating Non-motion Cues into 3D Motion Segmentation
British Library Conference Proceedings | 2006
|