Stochastic approximation for background modelling

Many background modelling approaches are based on mixtures of multivariate Gaussians with diagonal covariance matrices. This often yields good results, but complex backgrounds are not adequately captured, and post-processing techniques are needed. Here we propose the use of mixtures of uniform distributions and multivariate Gaussians with full covariance matrices. These mixtures are able to cope with both dynamic backgrounds and complex patterns of foreground objects. A learning algorithm is derived from the stochastic approximation framework, which has a very reduced computational complexity. Hence, it is suited for real time applications. Experimental results show that our approach outperforms the classic procedure in several benchmark videos.

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

[2]  David J. Fleet,et al.  Performance of optical flow techniques , 1994, International Journal of Computer Vision.

[3]  Jorge S. Marques,et al.  Performance evaluation of object detection algorithms for video surveillance , 2006, IEEE Transactions on Multimedia.

[4]  Ezequiel López-Rubio,et al.  Restoration of images corrupted by Gaussian and uniform impulsive noise , 2010, Pattern Recognit..

[5]  F. Downton.  Stochastic Approximation , 1969, Nature.

[6]  Robert Serfling,et al.  Multivariate spatial U-quantiles: A Bahadur–Kiefer representation, a Theil–Sen estimator for multiple regression, and a robust dispersion estimator , 2008 .

[7]  Paola Mello,et al.  Image analysis and rule-based reasoning for a traffic monitoring system , 1999, Proceedings 199 IEEE/IEEJ/JSAI International Conference on Intelligent Transportation Systems (Cat. No.99TH8383).

[8]  Robert Serfling,et al.  Nonparametric Multivariate Descriptive Measures Based on Spatial Quantiles , 2004 .

[9]  Ezequiel López-Rubio,et al.  Multivariate Student-t self-organizing maps , 2009, Neural Networks.

[10]  É. Moulines,et al.  Convergence of a stochastic approximation version of the EM algorithm , 1999 .

[11]  Larry S. Davis,et al.  W4: Real-Time Surveillance of People and Their Activities , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  Horst Bischof,et al.  Performance evaluation metrics for motion detection and tracking , 2004, ICPR 2004.

[13]  Adrian Hilton,et al.  A survey of advances in vision-based human motion capture and analysis , 2006, Comput. Vis. Image Underst..

[14]  Ferdinand van der Heijden,et al.  Efficient adaptive density estimation per image pixel for the task of background subtraction , 2006, Pattern Recognit. Lett..

[15]  Yongbin Wei,et al.  Noise-constrained least mean squares algorithm , 2001, IEEE Trans. Signal Process..

[16]  Ezequiel López-Rubio.  Probabilistic Self-Organizing Maps for Continuous Data , 2010, IEEE Transactions on Neural Networks.

[17]  Sidney S. Fels,et al.  Evaluation of Background Subtraction Algorithms with Post-Processing , 2008, 2008 IEEE Fifth International Conference on Advanced Video and Signal Based Surveillance.

[18]  H. Kushner,et al.  Stochastic Approximation and Recursive Algorithms and Applications , 2003 .

[19]  Brendan McCane,et al.  Recovering Motion Fields: An Evaluation of Eight Optical Flow Algorithms , 1998, BMVC.

[20]  Olaf Munkelt,et al.  Adaptive Background Estimation and Foreground Detection using Kalman-Filtering , 1995 .

[21]  Alex Pentland,et al.  Pfinder: real-time tracking of the human body , 1996, Proceedings of the Second International Conference on Automatic Face and Gesture Recognition.

[22]  Nizar Bouguila,et al.  A hybrid SEM algorithm for high-dimensional unsupervised learning using a finite generalized Dirichlet mixture , 2006, IEEE Transactions on Image Processing.

[23]  H. Robbins.  A Stochastic Approximation Method , 1951 .

[24]  Domingo López-Rodríguez,et al.  Probabilistic PCA Self-Organizing Maps , 2009, IEEE Transactions on Neural Networks.

[25]  Ludwik Kurz,et al.  A class of robust image processors , 1994, Pattern Recognit..

[26]  Joaquim Salvi,et al.  Motion Segmentation: a Review , 2008, CCIA.

[27]  Chandrika Kamath,et al.  Robust Background Subtraction with Foreground Validation for Urban Traffic Video , 2005, EURASIP J. Adv. Signal Process..

[28]  Ferdinand van der Heijden,et al.  Recursive unsupervised learning of finite mixture models , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[29]  Paulo Villegas,et al.  Perceptually-weighted evaluation criteria for segmentation masks in video sequences , 2004, IEEE Transactions on Image Processing.

[30]  Tieniu Tan,et al.  A survey on visual surveillance of object motion and behaviors , 2004, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[31]  Azriel Rosenfeld,et al.  Tracking Groups of People , 2000, Comput. Vis. Image Underst..

[32]  Max A. Viergever,et al.  Adaptive Stochastic Gradient Descent Optimisation for Image Registration , 2009, International Journal of Computer Vision.

[33]  Laurent Younes,et al.  A Stochastic Algorithm for Feature Selection in Pattern Recognition , 2007, J. Mach. Learn. Res..

[34]  Richard Bowden,et al.  A real time adaptive visual surveillance system for tracking low-resolution colour targets in dynamically changing scenes , 2003, Image Vis. Comput..

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

[36]  Xuelong Li,et al.  Iterative Subspace Analysis Based on Feature Line Distance , 2009, IEEE Trans. Image Process..

[37]  I. Haritaoglu,et al.  Background and foreground modeling using nonparametric kernel density estimation for visual surveillance , 2002 .

[38]  Sanjeev R. Kulkarni,et al.  Noise Conditions for Prespecified Convergence Rates of Stochastic Approximation Algorithms , 1999, IEEE Trans. Inf. Theory.

[39]  Shin Ishii,et al.  On-line EM Algorithm for the Normalized Gaussian Network , 2000, Neural Computation.

[40]  Tiziana D'Orazio,et al.  Moving object segmentation by background subtraction and temporal analysis , 2006, Image Vis. Comput..

[41]  W. Eric L. Grimson,et al.  Using adaptive tracking to classify and monitor activities in a site , 1998, Proceedings. 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No.98CB36231).

[42]  Shigeru Ando,et al.  Image Field Categorization and Edge/Corner Detection from Gradient Covariance , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[43]  Yuan-chin Ivan Chang,et al.  A stochastic approximation view of boosting , 2007, Comput. Stat. Data Anal..

[44]  T. Lai.  Stochastic approximation: invited paper , 2003 .

[45]  Sergio A. Velastin,et al.  Automatic congestion detection system for underground platforms , 2001, Proceedings of 2001 International Symposium on Intelligent Multimedia, Video and Speech Processing. ISIMP 2001 (IEEE Cat. No.01EX489).

[46]  D. Koller,et al.  Towards robust automatic traffic scene analysis in real-time , 1994, Proceedings of 1994 33rd IEEE Conference on Decision and Control.

[47]  Josien P. W. Pluim,et al.  Evaluation of Optimization Methods for Nonrigid Medical Image Registration Using Mutual Information and B-Splines , 2007, IEEE Transactions on Image Processing.

[48]  W. Eric L. Grimson,et al.  Learning Patterns of Activity Using Real-Time Tracking , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[49]  Ezequiel López-Rubio,et al.  Probabilistic self-organizing maps for qualitative data , 2010, Neural Networks.

[50]  Mohan M. Trivedi,et al.  A Survey of Vision-Based Trajectory Learning and Analysis for Surveillance , 2008, IEEE Transactions on Circuits and Systems for Video Technology.

[51]  Peyman Milanfar,et al.  Kernel Regression for Image Processing and Reconstruction , 2007, IEEE Transactions on Image Processing.

[52]  Eric Dubois.  The Structure and Properties of Color Spaces and the Representation of Color Images , 2009, The Structure and Properties of Color Spaces and the Representation of Color Images.

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

[54]  T. List,et al.  Comparison of target detection algorithms using adaptive background models , 2005, 2005 IEEE International Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance.

[55]  P. Rousseeuw,et al.  Breakdown Points of Affine Equivariant Estimators of Multivariate Location and Covariance Matrices , 1991 .

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

[57]  Rama Chellappa,et al.  Stochastic Approximation and Rate-Distortion Analysis for Robust Structure and Motion Estimation , 2003, International Journal of Computer Vision.

[58]  Ying-li Tian,et al.  Robust Salient Motion Detection with Complex Background for Real-Time Video Surveillance , 2005, 2005 Seventh IEEE Workshops on Applications of Computer Vision (WACV/MOTION'05) - Volume 1.

[59]  James E. Black,et al.  A novel method for video tracking performance evaluation , 2003 .