Fast robust foreground-background segmentation based on variable rate codebook method in Bayesian framework for detecting objects of interest

In this paper, a reliable pixel-based foreground-background segmentation technique for detecting object(s) of interest (OOI) from video sequence captured by a fixed camera is proposed. OOIs, used for further tracking or positioning applications, should be detected accurately from those moving (or still) objects even under variable illumination and the corresponding background model need to update quickly. To cope with fast change of the scene, we present an adaptive variable rate codebook update algorithm based on the cache mechanism, which adjusts the time thresholds according to the number of current effective samples in codebook. Then Bayes rule is employed to make the final decision based on prebuilt OOIs' color model and the background model deduced from the codebook. The experiment results have proven the given method's effectiveness.

[1]  M. Sreeraj,et al.  Hybrid Background Subtraction in video using Bi-level CodeBook model , 2014, The Fifth International Conference on the Applications of Digital Information and Web Technologies (ICADIWT 2014).

[2]  Subhash Challa,et al.  Combining background subtraction and temporal persistency in pedestrian detection from static videos , 2013, 2013 IEEE International Conference on Image Processing.

[3]  Hélène Laurent,et al.  Review and evaluation of commonly-implemented background subtraction algorithms , 2008, 2008 19th International Conference on Pattern Recognition.

[4]  N. Armanfard,et al.  A non-parametric pixel-based background modeling for dynamic scenes , 2009, 2009 International Conference on Advances in Computational Tools for Engineering Applications.

[5]  Hubert Konik,et al.  CAMSHIFT improvement on multi-hue and multi-object tracking , 2011, Proceedings of the 2011 International Conference on Electrical Engineering and Informatics.

[6]  Shahrizat Shaik Mohamed,et al.  Background modelling and background subtraction performance for object detection , 2010, 2010 6th International Colloquium on Signal Processing & its Applications.

[7]  J. Chambers,et al.  A robust technique for person-background segmentation in video sequences based on the codebook method of background subtraction and head tracking , 2010 .

[8]  Hubert Konik,et al.  CAMSHIFT improvement on multi-hue object and multi-object tracking , 2011, 3rd European Workshop on Visual Information Processing.

[9]  Gihun Song,et al.  Edge-segment-based Background Modeling: Non-parametric online background update , 2013, 2013 10th IEEE International Conference on Advanced Video and Signal Based Surveillance.

[10]  Shengping Zhang,et al.  Spatial-temporal nonparametric background subtraction in dynamic scenes , 2009, 2009 IEEE International Conference on Multimedia and Expo.

[11]  Manoranjan Paul,et al.  On Stable Dynamic Background Generation Technique Using Gaussian Mixture Models for Robust Object Detection , 2008, 2008 IEEE Fifth International Conference on Advanced Video and Signal Based Surveillance.

[12]  Xiaobo Zhou,et al.  Red Blood Cell Tracking Using Optical Flow Methods , 2014, IEEE Journal of Biomedical and Health Informatics.

[13]  Anni Cai,et al.  Hierarchical codebook background model using haar-like features , 2012, 2012 3rd IEEE International Conference on Network Infrastructure and Digital Content.

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

[15]  Ming Zhu,et al.  Adaptive Non-parametric Foreground Subtraction Using Rotation-invariant Local Frequency Pattern , 2012, 2012 Fourth International Conference on Multimedia Information Networking and Security.

[16]  Yueting Zhuang,et al.  Segmenting Layers in Automated Visual Surveillance , 2005, 2005 IEEE International Conference on Multimedia and Expo.