Adaptive Background Subtraction in H.264/AVC Bitstreams based on Macroblock Sizes

In this article, we propose a novel approach to detect moving objects in H.264 compressed bitstreams. More precisely, we describe a multi-modal background subtraction technique that uses the size of macroblocks in order to label them as belonging to the background of the observed scene or not. Here, we integrate an adaptive Gaussian mixture-based scheme to model the background. We evaluate our contribution using the PETS video dataset and a realist synthetic video sequence rendered by a 3-D urban environment simulator. We compare two different background models, and we show that the Gaussian mixture-based is the best and outperforms other techniques that use macro bloc sizes.

[1]  Fatih Murat Porikli,et al.  A Bayesian Approach to Background Modeling , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Workshops.

[2]  P. KaewTrakulPong,et al.  An Improved Adaptive Background Mixture Model for Real-time Tracking with Shadow Detection , 2002 .

[3]  M. Fathy,et al.  Real-time Background Modeling/Subtraction using Two-Layer Codebook Model , 2008 .

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

[5]  Thierry Chateau,et al.  Vehicle trajectories evaluation by static video sensors , 2006, 2006 IEEE Intelligent Transportation Systems Conference.

[6]  Sheng-rong Gong,et al.  Adaptive Shadows Detection Algorithm Based on Gaussian Mixture Model , 2008, 2008 International Symposium on Information Science and Engineering.

[7]  Peter Lambert,et al.  Moving object detection in the H.264/AVC compressed domain for video surveillance applications , 2009, J. Vis. Commun. Image Represent..

[8]  Jan-Olof Eklundh,et al.  Statistical background subtraction for a mobile observer , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[9]  A. Senior,et al.  Performance Evaluation of Surveillance Systems Under Varying Conditions , 2004 .

[10]  Steven Verstockt,et al.  Estimating motion reliability to improve moving object detection in the H.264/AVC domain , 2009, 2009 IEEE International Conference on Multimedia and Expo.

[11]  Zoran Zivkovic,et al.  Improved adaptive Gaussian mixture model for background subtraction , 2004, Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004..

[12]  Ahmet M. Kondoz,et al.  Object tracking in surveillance videos using compressed domain features from scalable bit-streams , 2009, Signal Process. Image Commun..

[13]  Ajay Luthra,et al.  Overview of the H.264/AVC video coding standard , 2003, IEEE Trans. Circuits Syst. Video Technol..

[14]  Wang Xin.  Overview of the H.264 / AVC Video Coding Standard , 2003 .

[15]  Munchurl Kim,et al.  Moving Object Tracking in H.264/AVC Bitstream , 2007, MCAM.

[16]  Peter Lambert,et al.  Improved Background Mixture Models for Video Surveillance Applications , 2007, ACCV.

[17]  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).

[18]  Thierry Chateau,et al.  A benchmark for Background Subtraction Algorithms in monocular vision: A comparative study , 2010, 2010 2nd International Conference on Image Processing Theory, Tools and Applications.

[19]  KimKyungnam,et al.  Real-time foreground-background segmentation using codebook model , 2005 .

[20]  Luis Jiménez,et al.  Real-time moving object segmentation in H.264 compressed domain based on approximate reasoning , 2009, Int. J. Approx. Reason..

[21]  Yi-Ping Hung,et al.  Efficient hierarchical method for background subtraction , 2007, Pattern Recognit..

[22]  Yu Lu,et al.  Real-time spatiotemporal segmentation of video objects in the H.264 compressed domain , 2007, J. Vis. Commun. Image Represent..

[23]  Chandrika Kamath,et al.  Robust techniques for background subtraction in urban traffic video , 2004, IS&T/SPIE Electronic Imaging.