Occlusion Reasoning for Object Detection under Arbitrary Viewpoint

Edward Hsiao and Martial Hebert
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June, 2012.


Download
  • Adobe portable document format (pdf) (8MB)
Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.

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 extending the state-of-the-art LINE2D method for object instance detection and demonstrate significant improvement in recognizing texture-less objects under severe occlusions.

Notes
Number of pages: 8

Text Reference
Edward Hsiao and Martial Hebert, "Occlusion Reasoning for Object Detection under Arbitrary Viewpoint," IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June, 2012.

BibTeX Reference
@inproceedings{Hsiao_2012_7085,
   author = "Edward Hsiao and Martial Hebert",
   title = "Occlusion Reasoning for Object Detection under Arbitrary Viewpoint",
   booktitle = "IEEE Conference on Computer Vision and Pattern Recognition (CVPR)",
   month = "June",
   year = "2012",
   number= "CMU-RI-TR-",
}