A Subspace Approach to Layer Extraction

Qifa Ke and Takeo Kanade
IEEE International Conference on Computer Vision and Pattern Recognition (CVPR 2001), December, 2001.


Download
  • Adobe portable document format (pdf) (735KB)
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
Representing images with layers has many important applications, such as video compression, motion analysis, and 3D scene analysis. This paper presents an approach to reliably extracting layers from images by taking advantages of the fact that homographies induced by planar patches in the scene form a low dimensional linear subspace. Layers in the input images will be mapped in the subspace, where it is proven that they form well-defined clusters and can be reliably identified by a simple mean-shift based clustering algorithm. Global optimality is achieved since all valid regions are simultaneously taken into account, and noise can be effectively reduced by enforcing the subspace constraint. Good layer descriptions are shown to be extracted in the experimental results.

Notes
Associated Center(s) / Consortia: Vision and Autonomous Systems Center
Number of pages: 8

Text Reference
Qifa Ke and Takeo Kanade, "A Subspace Approach to Layer Extraction," IEEE International Conference on Computer Vision and Pattern Recognition (CVPR 2001), December, 2001.

BibTeX Reference
@inproceedings{Ke_2001_3887,
   author = "Qifa Ke and Takeo Kanade",
   title = "A Subspace Approach to Layer Extraction",
   booktitle = "IEEE International Conference on Computer Vision and Pattern Recognition (CVPR 2001)",
   month = "December",
   year = "2001",
}