Low-Rank Spatio-Temporal Video Segmentation

Alasdair Newson, Mariano Tepper and Guillermo Sapiro

Abstract

Robust Principal Component Analysis (RPCA) has generated a great amount of interest for background/foreground estimation in videos. The central hypothesis in this setting is that a video's background can be well-represented by a low-rank model. However, in the presence of complex lighting conditions this model is only accurate in localised spatio-temporal regions. Following this observation, we propose to model the background with a piecewise low-rank approximation. To achieve this, we introduce the piecewise low-rank segmentation problem. Starting from a carefully designed cost function which assesses the low-rank coherence of two video regions, the segmentation is obtained with an efficient graph-clustering algorithm. We show that this segmentation, when used to establish a local RPCA per segment, leads to improved quantitative and qualitative results for background/foreground estimation in challenging videos.

Session

Poster 2

Files

PDF iconExtended Abstract (PDF, 337K)
PDF iconPaper (PDF, 1560K)

DOI

10.5244/C.29.103
https://dx.doi.org/10.5244/C.29.103

Citation

Alasdair Newson, Mariano Tepper and Guillermo Sapiro. Low-Rank Spatio-Temporal Video Segmentation. In Xianghua Xie, Mark W. Jones, and Gary K. L. Tam, editors, Proceedings of the British Machine Vision Conference (BMVC), pages 103.1-103.12. BMVA Press, September 2015.

Bibtex

@inproceedings{BMVC2015_103,
	title={Low-Rank Spatio-Temporal Video Segmentation},
	author={Alasdair Newson and Mariano Tepper and Guillermo Sapiro},
	year={2015},
	month={September},
	pages={103.1-103.12},
	articleno={103},
	numpages={12},
	booktitle={Proceedings of the British Machine Vision Conference (BMVC)},
	publisher={BMVA Press},
	editor={Xianghua Xie, Mark W. Jones, and Gary K. L. Tam},
	doi={10.5244/C.29.103},
	isbn={1-901725-53-7},
	url={https://dx.doi.org/10.5244/C.29.103}
}