ML Anthology

Occlusion Boundary Detection and Figure/ground Assignment from Optical Flow

Patrik Sundberg, Thomas Brox, Michael Maire, Pablo Arbeláez, Jitendra Malik
CVPR 2011 pp. 2233-2240
doi:10.1109/CVPR.2011.5995364 /cvpr/2011/sundberg2011cvpr-occlusion/

Abstract

In this work, we propose a contour and region detector for video data that exploits motion cues and distinguishes occlusion boundaries from internal boundaries based on optical flow. This detector outperforms the state-of-the-art on the benchmark of Stein and Hebert, improving average precision from .58 to .72. Moreover, the optical flow on and near occlusion boundaries allows us to assign a depth ordering to the adjacent regions. To evaluate performance on this edge-based figure/ground labeling task, we introduce a new video dataset that we believe will support further research in the field by allowing quantitative comparison of computational models for occlusion boundary detection, depth ordering and segmentation in video sequences.

CVPR Semantic Scholar

Cite

Text

Sundberg et al. "Occlusion Boundary Detection and Figure/ground Assignment from Optical Flow." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2011. doi:10.1109/CVPR.2011.5995364

Markdown

[Sundberg et al. "Occlusion Boundary Detection and Figure/ground Assignment from Optical Flow." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2011.](https://mlanthology.org/cvpr/2011/sundberg2011cvpr-occlusion/) doi:10.1109/CVPR.2011.5995364

BibTeX

@inproceedings{sundberg2011cvpr-occlusion,
  title     = {{Occlusion Boundary Detection and Figure/ground Assignment from Optical Flow}},
  author    = {Sundberg, Patrik and Brox, Thomas and Maire, Michael and Arbeláez, Pablo and Malik, Jitendra},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2011},
  pages     = {2233-2240},
  doi       = {10.1109/CVPR.2011.5995364},
  url       = {https://mlanthology.org/cvpr/2011/sundberg2011cvpr-occlusion/}
}