Dynamic Background Discrimination with a Recurrent Network

Discrimination between the moving foreground objects and the complex dynamic background is a challenging task. In this paper, we have proposed a probabilistic graphical model – a recurrent stochastic network, which is able to learn the temporal and the spatial correlation from the video input data and make inference with a generalized belief propagation algorithm. Experiments have shown that the proposed recurrent network can model the dynamic backgrounds containing swaying trees, bushes and moving ocean waves. Very promising segmentation results have been obtained.

[1]  Jake K. Aggarwal,et al.  Human Motion Analysis: A Review , 1999, Comput. Vis. Image Underst..

[2]  Jun Fan,et al.  Online face recognition system for videos based on modified probabilistic neural networks , 2004, 2004 International Conference on Image Processing, 2004. ICIP '04..

[3]  Jake K. Aggarwal,et al.  Human motion analysis: a review , 1997, Proceedings IEEE Nonrigid and Articulated Motion Workshop.

[4]  Zhao Jie-yu.  A recurrent stochastic binary network , 2001 .

[5]  Tai Sing Lee,et al.  Hierarchical Bayesian inference in the visual cortex. , 2003, Journal of the Optical Society of America. A, Optics, image science, and vision.

[6]  William T. Freeman,et al.  Understanding belief propagation and its generalizations , 2003 .

[7]  Christopher K. I. Williams,et al.  Combining Belief Networks and Neural Networks for Scene Segmentation , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  Song-Chun Zhu,et al.  Statistical Modeling and Conceptualization of Visual Patterns , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

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

[10]  Peter Tiño,et al.  Markovian architectural bias of recurrent neural networks , 2004, IEEE Transactions on Neural Networks.

[11]  Michael I. Jordan.  Learning in Graphical Models , 1999, NATO ASI Series.

[12]  Qi Tian,et al.  Foreground object detection from videos containing complex background , 2003, MULTIMEDIA '03.

[13]  Gustavo Deco,et al.  Computational neuroscience of vision , 2002 .

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

[15]  Berthold K. P. Horn,et al.  Determining Optical Flow , 1981, Other Conferences.

[16]  Thomas S. Huang,et al.  A probabilistic framework for segmentation and tracking of multiple non rigid objects for video surveillance , 2004, 2004 International Conference on Image Processing, 2004. ICIP '04..

[17]  Vladimir Pavlovic,et al.  A graphical model framework for coupling MRFs and deformable models , 2004, CVPR 2004.

[18]  Donald Geman,et al.  Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.