The Robotics Institute

Carnegie Mellon Robotics Institute

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 introduce an approach to accurately detect and segment partially occluded objects in various viewpoints and scales. Our main contribution is a novel framework for combining object-level descriptions (such as position, shape, and color) with pixel-level appearance, boundary, and occlusion reasoning. In training, we exploit a rough 3D object model to learn physically localized part appear- ances. To find and segment objects in an image, we gener- ate proposals based on the appearance and layout of local parts. The proposals are then refined after incorporating object-level information, and overlapping objects compete for pixels to produce a final description and segmentation of objects in the scene. A further contribution is a novel instance penalty, which is handled very efficiently during inference. We experimentally validate our approach on the challenging PASCAL?6 car database.

Notes

Number of pages: 8

Text Reference

Derek Hoiem, Carsten Rother, and John Winn, "3D LayoutCRF for Multi-View Object Class Recognition and Segmentation," IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), June, 2007.

BibTeX Reference

@inproceedings{Hoiem_2007_5827,
   author = "Derek Hoiem and Carsten Rother and John Winn",
   title = "3D LayoutCRF for Multi-View Object Class Recognition and Segmentation",
   booktitle = "IEEE Conf. on Computer Vision and Pattern Recognition (CVPR)",
   month = "June",
   year = "2007",
}

The Robotics Institute

Menu