MECSE-5-2006 Smooth Background Maintenance with Markov Random Fields

Background maintenance is a prerequisite for many video processing tasks. The mixture-of-Gaussian (MOG) model is an elegant way to formulate an adaptive statistical description of the background. In this work we incorporate several improvements developed for other background maintenance methods into the MOG model and show that, when properly implemented, the model is competitive with more recent methods. Secondly, most background maintenance algorithms regard the pixels in an image as independent and disregard the fundamental concept of smoothness. We propose to use a Markov random field to cleanly model smoothness of the foreground and background. Experimental results on the Wallflower benchmark show that our algorithm outperforms other background maintenance methods by more than 50%.

[1]  David Suter,et al.  A re-evaluation of mixture of Gaussian background modeling [video signal processing applications] , 2005, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005..

[2]  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..

[3]  M. Cristani,et al.  Multi-level background initialization using Hidden Markov Models , 2003, IWVS '03.

[4]  Nikos Paragios,et al.  Background modeling and subtraction of dynamic scenes , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[5]  Vladimir Kolmogorov,et al.  Multi-camera Scene Reconstruction via Graph Cuts , 2002, ECCV.

[6]  Nikos Paragios,et al.  A MRF-based approach for real-time subway monitoring , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[7]  Vladimir Kolmogorov,et al.  An experimental comparison of min-cut/max- flow algorithms for energy minimization in vision , 2001, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Alex Pentland,et al.  A Bayesian Computer Vision System for Modeling Human Interactions , 1999, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  Andrew Blake,et al.  A Probabilistic Background Model for Tracking , 2000, ECCV.

[10]  Larry S. Davis,et al.  Non-parametric Model for Background Subtraction , 2000, ECCV.

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

[12]  W. Eric L. Grimson,et al.  Adaptive background mixture models for real-time tracking , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[13]  Olga Veksler,et al.  Markov random fields with efficient approximations , 1998, Proceedings. 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No.98CB36231).

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

[15]  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.

[16]  Jitendra Malik,et al.  Robust Multiple Car Tracking with Occlusion Reasoning , 1994, ECCV.

[17]  J. Besag.  On the Statistical Analysis of Dirty Pictures , 1986 .

[18]  Tomaso Poggio,et al.  Computational vision and regularization theory , 1985, Nature.

[19]  Martin D. Levine,et al.  Vision in Man and Machine , 1985 .

[20]  Stan Z. Li,et al.  Markov Random Field Modeling in Image Analysis , 2001, Computer Science Workbench.

[21]  Stuart German,et al.  Stochastic relaxation, Gibbs distributions, and the Bayesian restoration of images , 1988 .