Foreground detection based on low-rank and block-sparse matrix decomposition
- 1 September 2012
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15224880,p. 1225-1228
Abstract
Foreground detection is the first step in video surveillance system to detect moving objects. Principal Components Analysis (PCA) shows a nice framework to separate moving objects from the background but without a mechanism of robust analysis, the moving objects may be absorbed into the background model. This drawback can be solved by recent researches on Robust Principal Component Analysis (RPCA). The background sequence is then modeled by a low rank subspace that can gradually change over time, while the moving foreground objects constitute the correlated sparse outliers. In this paper, we propose to use a RPCA method based on low-rank and block-sparse matrix decomposition to achieve foreground detection. This decomposition enforces the low-rankness of the background and the block-sparsity aspect of the foreground. Experimental results on different datasets show the pertinence of the proposed approach.Keywords
This publication has 10 references indexed in Scilit:
- Recent Advanced Statistical Background Modeling for Foreground Detection - A Systematic SurveyRecent Patents on Computer Science, 2011
- Robust principal component analysis?Journal of the ACM, 2011
- Stable Principal Component Pursuit2010
- Subspace Learning for Background Modeling: A SurveyRecent Patents on Computer Science, 2009
- A fuzzy spatial coherence-based approach to background/foreground separation for moving object detectionNeural Computing and Applications, 2009
- Background Modeling using Mixture of Gaussians for Foreground Detection - A SurveyRecent Patents on Computer Science, 2008
- Bayesian modeling of dynamic scenes for object detectionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2005
- Statistical Modeling of Complex Backgrounds for Foreground Object DetectionIEEE Transactions on Image Processing, 2004
- A Framework for Robust Subspace LearningInternational Journal of Computer Vision, 2003
- Wallflower: principles and practice of background maintenance1999