Partially-Sparse Restricted Boltzmann Machine for Background Modeling and Subtraction

Restricted Boltzmann Machine (RBM) has been successfully applied to unsupervised learning and intensity modeling of images. In this paper, we cast background subtraction as an image recovery and foreground residual estimation problem within the RBM hierarchy. We propose a partially-sparse RBM (PS-RBM) framework which models the image as the integration of the trained RBM weights where the weights are learnt from partially sparse and controlled redundancy network structure. The PS-RBM helps provide accurate background modeling even in dynamic and noisy environments. Experiments also validate the effectiveness of the proposed method on a comprehensive benchmark database.

[1]  Tapani Raiko,et al.  Enhanced Gradient and Adaptive Learning Rate for Training Restricted Boltzmann Machines , 2011, ICML.

[2]  Geoffrey E. Hinton.  A Practical Guide to Training Restricted Boltzmann Machines , 2012, Neural Networks: Tricks of the Trade.

[3]  Volkan Cevher,et al.  Compressive Sensing for Background Subtraction , 2008, ECCV.

[4]  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.

[5]  Geoffrey E. Hinton.  Training Products of Experts by Minimizing Contrastive Divergence , 2002, Neural Computation.

[6]  Xiaogang Wang,et al.  Background Subtraction via Robust Dictionary Learning , 2011, EURASIP J. Image Video Process..

[7]  Atsushi Shimada,et al.  Evaluation report of integrated background modeling based on spatio-temporal features , 2012, 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops.

[8]  Lucia Maddalena,et al.  The SOBS algorithm: What are the limits? , 2012, 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops.

[9]  Thomas S. Huang,et al.  Robust estimation of foreground in surveillance videos by sparse error estimation , 2008, 2008 19th International Conference on Pattern Recognition.

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

[11]  Geoffrey E. Hinton,et al.  Restricted Boltzmann machines for collaborative filtering , 2007, ICML '07.

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

[13]  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).

[14]  Honglak Lee,et al.  Sparse deep belief net model for visual area V2 , 2007, NIPS.

[15]  Geoffrey E. Hinton,et al.  Robust Boltzmann Machines for recognition and denoising , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[16]  Tao Xiang,et al.  Background Subtraction with Dirichlet Processes , 2012, ECCV.

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

[18]  Ruimin Shen,et al.  Sparse Group Restricted Boltzmann Machines , 2010, AAAI.