Occlusion Reasoning for Object Detection Under Arbitrary Viewpoint

CVPR 2012 pp. 3146-3153

doi:10.1109/CVPR.2012.6248048 /cvpr/2012/hsiao2012cvpr-occlusion/

Abstract

We present a unified occlusion model for object instance detection under arbitrary viewpoint. Whereas previous approaches primarily modeled local coherency of occlusions or attempted to learn the structure of occlusions from data, we propose to explicitly model occlusions by reasoning about 3D interactions of objects. Our approach accurately represents occlusions under arbitrary viewpoint without requiring additional training data, which can often be difficult to obtain. We validate our model by incorporating occlusion reasoning with the state-of-the-art LINE2D and Gradient Network methods for object instance detection and demonstrate significant improvement in recognizing texture-less objects under severe occlusions.

PDF CVPR Semantic Scholar

Cite

Text

Hsiao and Hebert. "Occlusion Reasoning for Object Detection Under Arbitrary Viewpoint." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2012. doi:10.1109/CVPR.2012.6248048

Markdown

[Hsiao and Hebert. "Occlusion Reasoning for Object Detection Under Arbitrary Viewpoint." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2012.](https://mlanthology.org/cvpr/2012/hsiao2012cvpr-occlusion/) doi:10.1109/CVPR.2012.6248048

BibTeX

@inproceedings{hsiao2012cvpr-occlusion,
  title     = {{Occlusion Reasoning for Object Detection Under Arbitrary Viewpoint}},
  author    = {Hsiao, Edward and Hebert, Martial},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2012},
  pages     = {3146-3153},
  doi       = {10.1109/CVPR.2012.6248048},
  url       = {https://mlanthology.org/cvpr/2012/hsiao2012cvpr-occlusion/}
}