${L_{1/2}}$ Norm and Spatial Continuity Regularized Low-Rank Approximation for Moving Object Detection in Dynamic Background
- 1 January 2018
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 25 (1) , 15-19
Abstract
Low-rank modeling-based moving object detection approaches proposed so far use fixed l1-norm penalty to capture the sparse nature of foreground in video, and thus, hardly adapt readily to the statistical variability of underlying foreground pixels in dynamic background. Additionally, they ignore the spatial continuity prior among the neighbor foreground pixels. Consequently, they cannot offer a satisfactory performance in practical dynamic background. In this letter, we present a unified regularization framework, namely l1/2-norm and spatial continuity regularized low-rank approximation (SCLR-l1/2), to solve this problem. First, in order to promote accuracy, we introduce an l1/2 constraint into the framework. Second, to guarantee the continuity among the neighbor foreground pixels, we introduce a spatial continuity regularization term, motivated by total variation. Finally, we generalize our framework to the lq-norm penalized case (SCLR-lq). By adjusting the shrinkage parameter q, the framework gets better flexibility to choose a reasonable sparse domain. To deal with the present constrained minimization problem, the augmented Lagrange multiplier method is employed and extended with the help of the alternating direction minimizing strategy. Experimental results show that the proposed method outperforms some state-of-the-art algorithms especially for the cases with dynamic backgrounds.Keywords
This publication has 42 references indexed in Scilit:
- A Benchmark Dataset for Outdoor Foreground/Background Extraction2013
- Fast image deconvolution using closed-form thresholding formulas of regularizationJournal of Visual Communication and Image Representation, 2013
- $L_{1/2}$ Regularization: A Thresholding Representation Theory and a Fast SolverIEEE Transactions on Neural Networks and Learning Systems, 2012
- Robust principal component analysis?Journal of the ACM, 2011
- A survey on vision-based human action recognitionImage and Vision Computing, 2010
- L 1/2 regularizationScience China Information Sciences, 2010
- Object trackingACM Computing Surveys, 2006
- A survey of advances in vision-based human motion capture and analysisComputer Vision and Image Understanding, 2006
- Real-time foreground–background segmentation using codebook modelReal-Time Imaging, 2005
- Affine Invariant Flows in the Beltrami FrameworkJournal of Mathematical Imaging and Vision, 2004