A Three-Way Optimization Technique for Noise Robust Moving Object Detection Using Tensor Low-Rank Approximation, l1/2, and TTV Regularizations

The rising demand for surveillance systems naturally necessitates more efficient and noise robust moving object detection (MOD) systems from the captured video streams. Inspired by the challenges in MOD which are yet to be addressed properly, this paper proposes a new MOD scheme using <inline-formula> <tex-math notation="LaTeX">$l_{1/2}$ </tex-math></inline-formula> regularization in the tensor framework. It takes advantage of the special features of tensor singular value decomposition (<inline-formula> <tex-math notation="LaTeX">${t}$ </tex-math></inline-formula>-SVD) along with regularizations using <inline-formula> <tex-math notation="LaTeX">$l_{1/2}$ </tex-math></inline-formula>-norm with half thresholding operation and tensor total variation (TTV) to develop a noise robust MOD system with improved detection accuracy. While <inline-formula> <tex-math notation="LaTeX">${t}$ </tex-math></inline-formula>-SVD exploits the spatio-temporal correlation of the video background, <inline-formula> <tex-math notation="LaTeX">$l_{1/2}$ </tex-math></inline-formula> regularization provides noise robustness besides removing the sparser but discontinuous dynamic elements in the spatio-temporal direction. Moreover, TTV enhances the spatio-temporal continuity and fills up the gaps due to the lingering objects and thereby extracting the foreground precisely. The proposed three-way optimization method is designed to address both static and dynamic background cases of MOD separately with the intention to reduce the misclassifications due to moving/cluttered background. The brilliance of this method is confirmed by the impressive visual quality of the background/foreground separation, noise robustness, reduced computational complexity, and rapid response. The quantitative evaluation discloses the predominance of the proposed method with respect to the state-of-the-art techniques.

[1]  Sudhish N. George,et al.  Simultaneous denoising and moving object detection using low rank approximation , 2019, Future Gener. Comput. Syst..

[2]  Sudhish N. George,et al.  Video Completion and Simultaneous Moving Object Detection for Extreme Surveillance Environments , 2019, IEEE Signal Processing Letters.

[3]  Zemin Zhang,et al.  Exact Tensor Completion Using t-SVD , 2015, IEEE Transactions on Signal Processing.

[4]  Lei Zhang,et al.  Robust Online Matrix Factorization for Dynamic Background Subtraction , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  Marie Louise Groot,et al.  Tensor Regularized Total Variation for Third Harmonic Generation Brain Images , 2017 .

[6]  L. Davis,et al.  Background and foreground modeling using nonparametric kernel density estimation for visual surveillance , 2002, Proc. IEEE.

[7]  Lucia Maddalena,et al.  A Self-Organizing Approach to Background Subtraction for Visual Surveillance Applications , 2008, IEEE Transactions on Image Processing.

[8]  John C. S. Lui,et al.  Online Robust Subspace Tracking from Partial Information , 2011, ArXiv.

[9]  Tao Tao,et al.  Iterative Grassmannian optimization for robust image alignment , 2013, Image Vis. Comput..

[10]  Qinghua Hu,et al.  A Sparse Outliers Iterative Removal Algorithm to Model the Background in the Video Sequences , 2014, ArXiv.

[11]  Jieping Ye,et al.  An efficient ADMM algorithm for multidimensional anisotropic total variation regularization problems , 2013, KDD.

[12]  Sudhish N. George,et al.  Ultrasound image despeckling using low rank matrix approximation approach , 2017, Biomed. Signal Process. Control..

[13]  Luming Zhang,et al.  Online Robust Low-Rank Tensor Learning , 2017, IJCAI.

[14]  Misha Elena Kilmer,et al.  Novel Methods for Multilinear Data Completion and De-noising Based on Tensor-SVD , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

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

[16]  Bin Zhu,et al.  Removal shadow with background subtraction model ViBe algorithm , 2013, 2013 2nd International Symposium on Instrumentation and Measurement, Sensor Network and Automation (IMSNA).

[17]  James M. Rehg,et al.  GOSUS: Grassmannian Online Subspace Updates with Structured-Sparsity , 2013, 2013 IEEE International Conference on Computer Vision.

[18]  Soon Ki Jung,et al.  OR-PCA with MRF for Robust Foreground Detection in Highly Dynamic Backgrounds , 2014, ACCV.

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

[20]  Mircea Nicolescu,et al.  A Novelty Detection Approach for Foreground Region Detection in Videos with Quasi-stationary Backgrounds , 2006, ISVC.

[21]  Namrata Vaswani,et al.  An Online Algorithm for Separating Sparse and Low-Dimensional Signal Sequences From Their Sum , 2013, IEEE Transactions on Signal Processing.

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

[23]  Xiaochun Cao,et al.  Total Variation Regularized RPCA for Irregularly Moving Object Detection Under Dynamic Background , 2016, IEEE Transactions on Cybernetics.

[24]  Rob Fergus,et al.  Fast Image Deconvolution using Hyper-Laplacian Priors , 2009, NIPS.

[25]  Zongben Xu,et al.  Regularization: Convergence of Iterative Half Thresholding Algorithm , 2014 .

[26]  Soon Ki Jung,et al.  Stochastic decomposition into low rank and sparse tensor for robust background subtraction , 2015, ICDP.

[27]  Bin Luo,et al.  Fast Grayscale-Thermal Foreground Detection With Collaborative Low-Rank Decomposition , 2018, IEEE Transactions on Circuits and Systems for Video Technology.

[28]  Zongben Xu,et al.  L1/2 regularization , 2010, Science China Information Sciences.

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

[30]  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.

[31]  Misha Elena Kilmer,et al.  Novel Factorization Strategies for Higher Order Tensors: Implications for Compression and Recovery of Multi-linear Data , 2013, ArXiv.

[32]  Mark E Hallenbeck,et al.  Extracting Roadway Background Image , 2006 .

[33]  Hua Chai,et al.  The L1/2 regularization approach for survival analysis in the accelerated failure time model , 2015, Comput. Biol. Medicine.

[34]  Hejun Wu,et al.  Weighted Low-Rank Decomposition for Robust Grayscale-Thermal Foreground Detection , 2017, IEEE Transactions on Circuits and Systems for Video Technology.

[35]  Zhaojun Wu,et al.  Total variation-regularized weighted nuclear norm minimization for hyperspectral image mixed denoising , 2016, J. Electronic Imaging.

[36]  Guoying Zhao,et al.  Background Subtraction Based on Low-Rank and Structured Sparse Decomposition , 2015, IEEE Transactions on Image Processing.

[37]  Vikas Sindhwani,et al.  Near-separable Non-negative Matrix Factorization with ℓ1 and Bregman Loss Functions , 2013, SDM.

[38]  Lin Zhu,et al.  ${L_{1/2}}$ Norm and Spatial Continuity Regularized Low-Rank Approximation for Moving Object Detection in Dynamic Background , 2018, IEEE Signal Processing Letters.

[39]  Wei Liu,et al.  Tensor Robust Principal Component Analysis: Exact Recovery of Corrupted Low-Rank Tensors via Convex Optimization , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[40]  Liangpei Zhang,et al.  Total-Variation-Regularized Low-Rank Matrix Factorization for Hyperspectral Image Restoration , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[41]  Wensheng Zhang,et al.  The Twist Tensor Nuclear Norm for Video Completion , 2017, IEEE Transactions on Neural Networks and Learning Systems.

[42]  Constantine Caramanis,et al.  Robust PCA via Outlier Pursuit , 2010, IEEE Transactions on Information Theory.

[43]  Aleksandar Lazarevic,et al.  Detection of moving objects using incremental connectivity outlier factor algorithm , 2009, ACM-SE 47.

[44]  Xiaowei Zhou,et al.  Moving Object Detection by Detecting Contiguous Outliers in the Low-Rank Representation , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[45]  Sudhish N. George,et al.  Twist tensor total variation regularized-reweighted nuclear norm based tensor completion for video missing area recovery , 2018, Inf. Sci..

[46]  Dit-Yan Yeung,et al.  Bayesian Robust Matrix Factorization for Image and Video Processing , 2013, 2013 IEEE International Conference on Computer Vision.

[47]  Kentaro Toyama,et al.  Wallflower: principles and practice of background maintenance , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[48]  Steven L. Brunton,et al.  Randomized CP tensor decomposition , 2017, Mach. Learn. Sci. Technol..

[49]  Xin Li,et al.  On a Problem of Weighted Low-Rank Approximation of Matrices , 2015, SIAM J. Matrix Anal. Appl..

[50]  Emmanuel J. Candès,et al.  A Singular Value Thresholding Algorithm for Matrix Completion , 2008, SIAM J. Optim..

[51]  Sudhish N. George,et al.  Moving object detection by low rank approximation and l1-TV regularization on RPCA framework , 2018, J. Vis. Commun. Image Represent..

[52]  Aritra Dutta,et al.  A Batch-Incremental Video Background Estimation Model Using Weighted Low-Rank Approximation of Matrices , 2017, 2017 IEEE International Conference on Computer Vision Workshops (ICCVW).

[53]  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.

[54]  Xi Chen,et al.  Direct Robust Matrix Factorizatoin for Anomaly Detection , 2011, 2011 IEEE 11th International Conference on Data Mining.

[55]  Zongben Xu,et al.  $L_{1/2}$ Regularization: A Thresholding Representation Theory and a Fast Solver , 2012, IEEE Transactions on Neural Networks and Learning Systems.

[56]  Hong Zhang,et al.  Moving Object Detection in Time-Lapse or Motion Trigger Image Sequences Using Low-Rank and Invariant Sparse Decomposition , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[57]  Brendt Wohlberg,et al.  Incremental Principal Component Pursuit for Video Background Modeling , 2015, Journal of Mathematical Imaging and Vision.

[58]  Jian Yu,et al.  $$S_{1/2}$$S1/2 regularization methods and fixed point algorithms for affine rank minimization problems , 2017, Comput. Optim. Appl..

[59]  Wotao Yin,et al.  A Block Coordinate Descent Method for Regularized Multiconvex Optimization with Applications to Nonnegative Tensor Factorization and Completion , 2013, SIAM J. Imaging Sci..

[60]  Hong Zhang,et al.  COROLA: A Sequential Solution to Moving Object Detection Using Low-rank Approximation , 2015, Comput. Vis. Image Underst..

[61]  Gholam Ali Montazer,et al.  Atanassov's intuitionistic fuzzy histon for robust moving object detection , 2017, Int. J. Approx. Reason..

[62]  Chongzhao Han,et al.  A Background Reconstruction for Dynamic Scenes , 2006, 2006 9th International Conference on Information Fusion.

[63]  Wen Gao,et al.  Background Subtraction via generalized fused lasso foreground modeling , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[65]  Aleksandar Lazarevic,et al.  Small moving targets detection using outlier detection algorithms , 2010, Defense + Commercial Sensing.

[66]  Luca Iocchi,et al.  Background modeling in the maritime domain , 2013, Machine Vision and Applications.

[67]  Ce Zhu,et al.  Iterative block tensor singular value thresholding for extraction of lowrank component of image data , 2017, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[68]  Xin Li,et al.  Simultaneous Video Stabilization and Moving Object Detection in Turbulence , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.