A sparse tensor optimization approach for background subtraction from compressive measurements

Background subtraction from compressive measurements (BSCM) is a fundamental and critical task in video surveillance. Existing methods have limitations for incorporating the structural information and exhibit degraded performance in dynamic background, shadow and complex natural scenes. To address this issue, we propose a new Tucker decomposition-based sparse tensor optimization problem, which makes full use of the spatio-temporal features embedded in the video. The l0-norm in the objective function is used to constrain the sparseness of the spatio-temporal structure of video foreground, which enhances the spatio-temporal continuity and improves the accuracy of foreground detection. The orthogonality constraints on factor matrices in low-rank Tucker decomposition are used to characterize the spatio-temporal correlation of video background, which enhances low-rank characterization and makes better background estimation. Optimality analysis in terms of Karush-Kuhn-Tucker (KKT) conditions is addressed for the proposed sparse tensor optimization problem and a hard-threshing based alternating direction method of multipliers (HT-ADMM) is designed. Comprehensive experiments are conducted on real-world video datasets to demonstrate the effectiveness and superiority of our approach for BSCM.

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

[2]  Zhaosong Lu,et al.  Optimization over Sparse Symmetric Sets via a Nonmonotone Projected Gradient Method , 2015, 1509.08581.

[3]  Richard G. Baraniuk,et al.  An Architecture for Compressive Imaging , 2006, 2006 International Conference on Image Processing.

[4]  Loong Fah Cheong,et al.  Block-Sparse RPCA for Salient Motion Detection , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  Changsheng Xu,et al.  Mining Semantic Context Information for Intelligent Video Surveillance of Traffic Scenes , 2013, IEEE Transactions on Industrial Informatics.

[6]  Wotao Yin,et al.  Parallel Multi-Block ADMM with o(1 / k) Convergence , 2013, Journal of Scientific Computing.

[7]  Hong Jiang,et al.  Surveillance Video Analysis Using Compressive Sensing With Low Latency , 2014, Bell Labs Tech. J..

[8]  Emmanuel J. Candès,et al.  Robust uncertainty principles: exact signal reconstruction from highly incomplete frequency information , 2004, IEEE Transactions on Information Theory.

[9]  Emmanuel J. Candès,et al.  Decoding by linear programming , 2005, IEEE Transactions on Information Theory.

[10]  Thierry Bouwmans,et al.  Incremental and Multi-feature Tensor Subspace Learning Applied for Background Modeling and Subtraction , 2014, ICIAR.

[11]  Thierry Bouwmans,et al.  Robust PCA via Principal Component Pursuit: A review for a comparative evaluation in video surveillance , 2014, Comput. Vis. Image Underst..

[12]  Yuan Xie,et al.  Moving Object Detection Using Tensor-Based Low-Rank and Saliently Fused-Sparse Decomposition , 2017, IEEE Transactions on Image Processing.

[13]  Soon Ki Jung,et al.  Background–Foreground Modeling Based on Spatiotemporal Sparse Subspace Clustering , 2017, IEEE Transactions on Image Processing.

[14]  Richard G. Baraniuk,et al.  A new compressive imaging camera architecture using optical-domain compression , 2006, Electronic Imaging.

[15]  Soon Ki Jung,et al.  Online Stochastic Tensor Decomposition for Background Subtraction in Multispectral Video Sequences , 2015, 2015 IEEE International Conference on Computer Vision Workshop (ICCVW).

[16]  Wei Liu,et al.  Tensor Robust Principal Component Analysis with a New Tensor Nuclear Norm , 2018, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[17]  Hong Zhang,et al.  Moving Object Detection Under Discontinuous Change in Illumination Using Tensor Low-Rank and Invariant Sparse Decomposition , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[18]  Aswin C. Sankaranarayanan,et al.  SpaRCS: Recovering low-rank and sparse matrices from compressive measurements , 2011, NIPS.

[19]  Narendra Ahuja,et al.  Robust Visual Tracking Via Consistent Low-Rank Sparse Learning , 2014, International Journal of Computer Vision.

[20]  Tamara G. Kolda,et al.  Tensor Decompositions and Applications , 2009, SIAM Rev..

[21]  Lixia Chen,et al.  Background subtraction with Kronecker-basis-representation based tensor sparsity and $$l_{1,1,2}$$ l 1 , 1 , 2020, Multidimens. Syst. Signal Process..

[22]  Emmanuel J. Candès,et al.  Exact Matrix Completion via Convex Optimization , 2009, Found. Comput. Math..

[23]  Naihua Xiu,et al.  Global and Quadratic Convergence of Newton Hard-Thresholding Pursuit , 2019, J. Mach. Learn. Res..

[24]  Laith Mohammad Abualigah,et al.  Hybrid clustering analysis using improved krill herd algorithm , 2018, Applied Intelligence.

[25]  Donald Goldfarb,et al.  Robust Low-Rank Tensor Recovery: Models and Algorithms , 2013, SIAM J. Matrix Anal. Appl..

[26]  Dong Liang,et al.  Tensor RPCA by Bayesian CP Factorization with Complex Noise , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[27]  Xiaoyu Li,et al.  An ${\ell}_{0}$ -Norm Minimization for Energy-Efficient Timetabling in Subway Systems , 2019, IEEE Access.

[28]  Simon Foucart,et al.  Hard Thresholding Pursuit: An Algorithm for Compressive Sensing , 2011, SIAM J. Numer. Anal..

[29]  Volkan Cevher,et al.  Compressive Sensing for Background Subtraction , 2008, ECCV.

[30]  Robert E. Mahony,et al.  Optimization Algorithms on Matrix Manifolds , 2007 .

[31]  Andrzej Cichocki,et al.  Nonnegative Matrix and Tensor Factorization T , 2007 .

[32]  Eero P. Simoncelli,et al.  Image quality assessment: from error visibility to structural similarity , 2004, IEEE Transactions on Image Processing.

[33]  Stephen P. Boyd,et al.  Convex Optimization , 2004, Algorithms and Theory of Computation Handbook.

[34]  Andrzej Cichocki,et al.  Total Variation Regularized Tensor RPCA for Background Subtraction From Compressive Measurements , 2015, IEEE Transactions on Image Processing.

[35]  Massimo Piccardi,et al.  Background subtraction techniques: a review , 2004, 2004 IEEE International Conference on Systems, Man and Cybernetics (IEEE Cat. No.04CH37583).

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

[37]  Antoine Vacavant,et al.  A comprehensive review of background subtraction algorithms evaluated with synthetic and real videos , 2014, Comput. Vis. Image Underst..

[38]  Tamara G. Kolda,et al.  Efficient MATLAB Computations with Sparse and Factored Tensors , 2007, SIAM J. Sci. Comput..

[39]  Wotao Yin,et al.  Global Convergence of ADMM in Nonconvex Nonsmooth Optimization , 2015, Journal of Scientific Computing.

[40]  Laith Mohammad Abualigah,et al.  Feature Selection and Enhanced Krill Herd Algorithm for Text Document Clustering , 2018, Studies in Computational Intelligence.

[41]  Fatih Murat Porikli,et al.  Changedetection.net: A new change detection benchmark dataset , 2012, 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops.

[42]  Stephen J. Wright,et al.  Sparse reconstruction by separable approximation , 2009, IEEE Trans. Signal Process..

[43]  Joos Vandewalle,et al.  On the Best Rank-1 and Rank-(R1 , R2, ... , RN) Approximation of Higher-Order Tensors , 2000, SIAM J. Matrix Anal. Appl..

[44]  Hong Jiang,et al.  Surveillance Video Processing Using Compressive Sensing , 2012, ArXiv.