Causal Video Object Segmentation from Persistence of Occlusions

Brian Taylor, Vasiliy Karasev, Stefano Soatto

CVPR 2015

doi:10.1109/CVPR.2015.7299055 /cvpr/2015/taylor2015cvpr-causal/

Abstract

Occlusion relations inform the partition of the image domain into ``objects'' but are difficult to determine from a single image or short-baseline video. We show how long-term occlusion relations can be robustly inferred from video, and used within a convex optimization framework to segment the image domain into regions. We highlight the challenges in determining these occluder/occluded relations and ensuring regions remain temporally consistent, propose strategies to overcome them, and introduce an efficient numerical scheme to perform the partition directly on the pixel grid, without the need for superpixelization or other preprocessing steps.

PDF CVPR Semantic Scholar

Cite

Text

Taylor et al. "Causal Video Object Segmentation from Persistence of Occlusions." Conference on Computer Vision and Pattern Recognition, 2015. doi:10.1109/CVPR.2015.7299055

Markdown

[Taylor et al. "Causal Video Object Segmentation from Persistence of Occlusions." Conference on Computer Vision and Pattern Recognition, 2015.](https://mlanthology.org/cvpr/2015/taylor2015cvpr-causal/) doi:10.1109/CVPR.2015.7299055

BibTeX

@inproceedings{taylor2015cvpr-causal,
  title     = {{Causal Video Object Segmentation from Persistence of Occlusions}},
  author    = {Taylor, Brian and Karasev, Vasiliy and Soatto, Stefano},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2015},
  doi       = {10.1109/CVPR.2015.7299055},
  url       = {https://mlanthology.org/cvpr/2015/taylor2015cvpr-causal/}
}