Multiscale Segmentation by Combining Motion and Intensity Cues

Abstract

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. 1.

Cite

Text

Galun et al. "Multiscale Segmentation by Combining Motion and Intensity Cues." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2005. doi:10.1109/CVPR.2005.244

Markdown

[Galun et al. "Multiscale Segmentation by Combining Motion and Intensity Cues." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2005.](https://mlanthology.org/cvpr/2005/galun2005cvpr-multiscale/) doi:10.1109/CVPR.2005.244

BibTeX

@inproceedings{galun2005cvpr-multiscale,
  title     = {{Multiscale Segmentation by Combining Motion and Intensity Cues}},
  author    = {Galun, Meirav and Apartsin, Alexander and Basri, Ronen},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2005},
  pages     = {256-263},
  doi       = {10.1109/CVPR.2005.244},
  url       = {https://mlanthology.org/cvpr/2005/galun2005cvpr-multiscale/}
}