Background modeling for dynamic scenes using tensor decomposition

Background modeling is an important topic in video analysis and understanding, while the main difficulty lies in the dynamic scenes. The scenes with limited variation can be effectively described by numerous models, but more precise representation model are needed for complex scenes. In this paper, we propose a background modeling algorithm for dynamic scenes using tensor decomposition. Since video data can be naturally represent as higher-order tensors, the tensor methods can accurately describe the dynamic nature of the nearby pixels, and then background will be estimated by the low-rank representation of tensors. Experimental results show that the proposed method is robust and adaptive in dynamic environments, and furthermore, moving objects can be clearly separated from the complex dynamic background.

[1]  A. Elgammal.  Background Subtraction: Theory and Practice , 2014, Background Subtraction.

[2]  Jing Zhang,et al.  Background segmentation of dynamic scenes based on dual model , 2014, IET Comput. Vis..

[3]  P. Miller,et al.  Regularised region-based Mixture of Gaussians for dynamic background modelling , 2014, 2014 11th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS).

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

[5]  Fan Zhang,et al.  Compact Representation for Dynamic Texture Video Coding Using Tensor Method , 2013, IEEE Transactions on Circuits and Systems for Video Technology.

[6]  Fan Zhang,et al.  Higher-order SVD analysis for crowd density estimation , 2012, Comput. Vis. Image Underst..

[7]  Fan Zhang,et al.  Dynamic Texture Analysis Using Eigenvectors of Gradient Skewness Tensors , 2012, 2012 International Conference on Computer Science and Service System.

[8]  Haitao Liu,et al.  A novel approach for event foreground detection based on PSO parameter optimization and region partition based background modeling , 2011 .

[9]  Nuno Vasconcelos,et al.  Generalized Stauffer–Grimson background subtraction for dynamic scenes , 2011, Machine Vision and Applications.

[10]  Dale Schuurmans,et al.  Real-Time Discriminative Background Subtraction , 2011, IEEE Transactions on Image Processing.

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

[12]  Nuno Vasconcelos,et al.  Background subtraction in highly dynamic scenes , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[13]  Mubarak Shah,et al.  Automatically Tuning Background Subtraction Parameters using Particle Swarm Optimization , 2007, 2007 IEEE International Conference on Multimedia and Expo.

[14]  Weidong Zhang,et al.  A Novel Particle Filter Based Background Subtraction Method , 2006, 2006 International Conference on Computational Intelligence and Security.

[15]  Yaser Sheikh,et al.  Bayesian modeling of dynamic scenes for object detection , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[16]  Larry S. Davis,et al.  Real-time foreground-background segmentation using codebook model , 2005, Real Time Imaging.

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

[18]  Nikos Paragios,et al.  Motion-based background subtraction using adaptive kernel density estimation , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[19]  Stan Sclaroff,et al.  Segmenting foreground objects from a dynamic textured background via a robust Kalman filter , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[20]  Kazuhiko Sumi,et al.  Background subtraction based on cooccurrence of image variations , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[21]  Y. Wu,et al.  Dynamic Textures , 2003, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

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

[23]  H. Kiers.  Towards a standardized notation and terminology in multiway analysis , 2000 .

[24]  Joos Vandewalle,et al.  A Multilinear Singular Value Decomposition , 2000, SIAM J. Matrix Anal. Appl..

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

[26]  Stuart J. Russell,et al.  Image Segmentation in Video Sequences: A Probabilistic Approach , 1997, UAI.

[27]  Johan Håstad,et al.  Tensor Rank is NP-Complete , 1989, ICALP.

[28]  L. Tucker,et al.  Some mathematical notes on three-mode factor analysis , 1966, Psychometrika.

[29]  F. L. Hitchcock.  Multiple Invariants and Generalized Rank of a P‐Way Matrix or Tensor , 1928 .

[30]  F. L. Hitchcock.  The Expression of a Tensor or a Polyadic as a Sum of Products , 1927 .

[31]  S. Venkatesh,et al.  Detection of Dynamic Background Due to Swaying Movements From Motion Features , 2015, IEEE Transactions on Image Processing.

[32]  Fan Zhang,et al.  Gradient skewness tensors and local illumination detection for images , 2013, J. Comput. Appl. Math..

[33]  W. Grimson,et al.  Background Subtraction , 2009, Encyclopedia of Biometrics.