|
|
|
|
RI | Publications | A Robust Subspace Approach to Extracting Layers from Image Sequences
|
|
Text only version of this site
A Robust Subspace Approach to Extracting Layers from Image Sequences
Q. Ke
doctoral dissertation, tech. report CMU-CS-03-173, Computer Science Department, Carnegie Mellon University, August, 2003.
Jump to: Download | Abstract | Notes | Text Reference | BibTeX Reference
| Download [Help] |
Adobe portable document format (pdf) [3211 KB] Compressed postscript (ps.gz) [3244 KB]
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 |
A layer is a 2D sub-image inside which pixels share common appar- ent motion of some 3D scene plane. Representing videos with such layers has many important applications, such as video compression, 3D scene and motion analysis, object detection and tracking, and vehicle naviga- tion. Extracting layers from videos involves solving three subproblems: 1) segment the image into sub-regions (layers); 2) estimate the 2D mo- tion of each layer; and 3) determine the number of layers. These three subproblems are highly intertwined, making the layer extraction problem very challenging. Existing approaches to layer extraction are limited by 1) requiring good initial segmentation, 2) strong assumptions about the scene, 3) unable to fully and simultaneously utilize the spatial and tem- poral constraints in video, and 4) unstable clustering in high dimensional space. This thesis presents a subspace approach to layer extraction which does not have the above limitations. We ¯rst show that the homographies induced by the planar patches in the scene form a linear subspace whose dimension is as low as two or three in many applications. We then for- mulate the layer extraction problem as clustering in such low dimensional subspace. Each layer in the input images will form a well-de¯ned clus- ter in the subspace, and a simple mean shift based clustering algorithm can reliably identify the clusters thus the layers. A proof is presented to show that the subspace approach is guaranteed to increase signi¯cantly the layer discriminability, due to its ability to simultaneously utilize spa- tial and temporal constraints in the video. We present the detailed robust algorithm for layer extraction using subspace, as well as experimental re- sults on a variety of real image sequences.
| Notes |
Number of pages: 171
| Text Reference |
Q. Ke, A Robust Subspace Approach to Extracting Layers from Image Sequences, doctoral dissertation, tech. report CMU-CS-03-173, Computer Science Department, Carnegie Mellon University, August, 2003.
| BibTeX Reference |
@phdthesis{Ke_2003_5109,
author = "Qifa Ke",
title = "A Robust Subspace Approach to Extracting Layers from Image Sequences",
school = "Computer Science Department, Carnegie Mellon University",
month = "August",
year = "2003",
address = "Pittsburgh, PA"
}