Abstract
We present a novel approach to improving subspace clustering by exploiting the spatial constraints. The new method encourages the sparse solution to be consistent with the spatial geometry of the tracked points, by embedding weights into the sparse formulation. By doing so, we are able to correct sparse representations in a principled manner without introducing much additional computational cost. We discuss alternative ways to treat the missing and corrupted data using the latest theory in robust lasso regression and suggest numerical algorithms so solve the proposed formulation. The experiments on the benchmark Johns Hopkins 155 dataset demonstrate that exploiting spatial constraints significantly improves motion segmentation.
Original language | English |
---|---|
Title of host publication | 2012 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2012 |
Pages | 550-557 |
Number of pages | 8 |
DOIs | |
Publication status | Published - 1 Oct 2012 |
Externally published | Yes |
Event | IEEE Conference on Computer Vision and Pattern Recognition 2012 - Providence, United States of America Duration: 16 Jun 2012 → 21 Jun 2012 https://ieeexplore.ieee.org/xpl/conhome/6235193/proceeding (Proceedings) |
Publication series
Name | Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition |
---|---|
ISSN (Print) | 1063-6919 |
Conference
Conference | IEEE Conference on Computer Vision and Pattern Recognition 2012 |
---|---|
Abbreviated title | CVPR 2012 |
Country/Territory | United States of America |
City | Providence |
Period | 16/06/12 → 21/06/12 |
Internet address |