A Sparse Error Compensation Based Incremental Principal Component Analysis Method for Foreground Detection

Foreground detection is a fundamental task in video processing. Recently, many background subspace estimation based foreground detection methods have been proposed. In this paper, a sparse error compensation based incremental principal component analysis method, which robustly updates background subspace and estimates foreground, is proposed for foreground detection. There are mainly two notable features in our method. First, a sparse error compensation process via a probability sampling procedure is designed for subspace updating, which reduces the interference of undesirable foreground signal. Second, the proposed foreground detection method could operate without an initial background subspace estimation, which enlarges the application scope of our method. Extensive experiments on multiple real video sequences show the superiority of our method.

[1]  Li Song,et al.  Foreground Estimation Based on Linear Regression Model With Fused Sparsity on Outliers , 2013, IEEE Transactions on Circuits and Systems for Video Technology.

[2]  Ming-Hsuan Yang,et al.  Incremental Learning for Robust Visual Tracking , 2008, International Journal of Computer Vision.

[3]  Alex Pentland,et al.  A Bayesian Computer Vision System for Modeling Human Interaction , 1999, ICVS.

[4]  Michael Lindenbaum,et al.  Sequential Karhunen-Loeve basis extraction and its application to images , 1998, Proceedings 1998 International Conference on Image Processing. ICIP98 (Cat. No.98CB36269).

[5]  Lu Wang,et al.  Background Subtraction using Incremental Subspace Learning , 2007, 2007 IEEE International Conference on Image Processing.

[6]  Jun Zhou,et al.  Foreground detection: Combining background subspace learning with object smoothing model , 2013, 2013 IEEE International Conference on Multimedia and Expo (ICME).

[7]  Arvind Ganesh,et al.  Fast Convex Optimization Algorithms for Exact Recovery of a Corrupted Low-Rank Matrix , 2009 .

[8]  Dacheng Tao,et al.  GoDec: Randomized Lowrank & Sparse Matrix Decomposition in Noisy Case , 2011, ICML.

[9]  Yi Ma,et al.  Robust principal component analysis? , 2009, JACM.

[10]  Matthew Brand,et al.  Incremental Singular Value Decomposition of Uncertain Data with Missing Values , 2002, ECCV.

[11]  Stephen P. Boyd,et al.  Distributed Optimization and Statistical Learning via the Alternating Direction Method of Multipliers , 2011, Found. Trends Mach. Learn..

[12]  Laura Balzano,et al.  Incremental gradient on the Grassmannian for online foreground and background separation in subsampled video , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[13]  Namrata Vaswani,et al.  Real-time Robust Principal Components' Pursuit , 2010, 2010 48th Annual Allerton Conference on Communication, Control, and Computing (Allerton).

[14]  G. Sapiro,et al.  A collaborative framework for 3D alignment and classification of heterogeneous subvolumes in cryo-electron tomography. , 2013, Journal of structural biology.

[15]  Ralph R. Martin,et al.  Adding and subtracting eigenspaces with eigenvalue decomposition and singular value decomposition , 2002, Image and Vision Computing.

[16]  Thierry Bouwmans,et al.  Traditional and recent approaches in background modeling for foreground detection: An overview , 2014, Comput. Sci. Rev..

[17]  Namrata Vaswani,et al.  Recursive sparse recovery in large but correlated noise , 2011, 2011 49th Annual Allerton Conference on Communication, Control, and Computing (Allerton).

[18]  Qi Tian,et al.  Statistical modeling of complex backgrounds for foreground object detection , 2004, IEEE Transactions on Image Processing.

[19]  Xiaochun Cao,et al.  Speeding uplow rank matrix recovery for foreground separation in surveillance videos , 2014, 2014 IEEE International Conference on Multimedia and Expo (ICME).

[20]  Zhixun Su,et al.  Linearized Alternating Direction Method with Adaptive Penalty for Low-Rank Representation , 2011, NIPS.