Virtual Snakes for Occlusion Analysis

Abstract

We introduce virtual snakes for generating occlusion hypotheses. Initially, snakes are clustered based on their motion to form object hypotheses-a type of motion segmentation. When two snakes intersect, four virtual snakes are generated-a background and a foreground snake for each of the original two. The two foreground virtual snakes are allowed to relax, while the two background virtual snakes move in accordance with their previous motion. The combined energies of the snakes in the two colliding objects are examined after the collision to determine the occlusion relationship, and the inconsistent virtual snakes are deleted. We show that this heuristic can be used to correctly track objects in the presence of strong occlusion.

Cite

Text

Galvin et al. "Virtual Snakes for Occlusion Analysis." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1999. doi:10.1109/CVPR.1999.784647

Markdown

[Galvin et al. "Virtual Snakes for Occlusion Analysis." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1999.](https://mlanthology.org/cvpr/1999/galvin1999cvpr-virtual/) doi:10.1109/CVPR.1999.784647

BibTeX

@inproceedings{galvin1999cvpr-virtual,
  title     = {{Virtual Snakes for Occlusion Analysis}},
  author    = {Galvin, Ben and McCane, Brendan and Novins, Kevin},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {1999},
  pages     = {2294-2299},
  doi       = {10.1109/CVPR.1999.784647},
  url       = {https://mlanthology.org/cvpr/1999/galvin1999cvpr-virtual/}
}