Background scene modeling for PTZ cameras using RBM

Background subtraction is primarily used as feature extraction and modeling in video analysis. Pan-tilt-zoom cameras, with their adjuvant capacity to capture the videos, add complexities to background model. Conventional techniques for background subtraction rely on the background model to extract the foreground object. In this work, we investigated restricted Boltzmann machine (RBM) to model the structure of the scene from videos captured by PTZ cameras. The generative modeling paradigm of RBM gives an extensive and non-parametric background learning framework. Experimentation results demonstrate the manifest ability of modeling structure of various scenes using RBM.

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

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

[3]  Yoshua Bengio,et al.  Understanding the difficulty of training deep feedforward neural networks , 2010, AISTATS.

[4]  Brian C. Lovell,et al.  Improved Foreground Detection via Block-Based Classifier Cascade With Probabilistic Decision Integration , 2013, IEEE Transactions on Circuits and Systems for Video Technology.

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

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

[7]  Lucia Maddalena,et al.  A Self-Organizing Approach to Background Subtraction for Visual Surveillance Applications , 2008, IEEE Transactions on Image Processing.

[8]  Guillaume-Alexandre Bilodeau,et al.  Adaptive Fuzzy Particle Filter Tracker for a PTZ Camera in an IP Surveillance System , 2011, IEEE Transactions on Instrumentation and Measurement.

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

[10]  Borko Furht,et al.  Neural Network Approach to Background Modeling for Video Object Segmentation , 2007, IEEE Transactions on Neural Networks.

[11]  Benjamin Höferlin,et al.  Evaluation of background subtraction techniques for video surveillance , 2011, CVPR 2011.

[12]  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.

[13]  Moongu Jeon,et al.  A New Framework for Background Subtraction Using Multiple Cues , 2012, ACCV.

[14]  Marc Van Droogenbroeck,et al.  ViBE: A powerful random technique to estimate the background in video sequences , 2009, 2009 IEEE International Conference on Acoustics, Speech and Signal Processing.

[15]  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).

[16]  Ahmed M. Elgammal,et al.  Online Moving Camera Background Subtraction , 2012, ECCV.

[17]  Ho Gi Jung,et al.  Background Compensation for Pan-Tilt-Zoom Cameras Using 1-D Feature Matching and Outlier Rejection , 2011, IEEE Transactions on Circuits and Systems for Video Technology.

[18]  Lucia Maddalena,et al.  Neural Moving Object Detection by Pan-Tilt-Zoom Cameras , 2012, WIRN.

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