Multiscale Segmentation by Combining Motion and Intensity Cues

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.

• Type: Conference
• Year: 2005
• Where: CVPR
• Authors: Meirav Galun, Alexander Apartsin, Ronen Basri
• Keywords: Computer Vision, CVPR 2005, Motion Segmentation, Multiscale Method, Real Motion Sequences, Segmentation Method, Translational Motion