Real-Time Objects Detection Using Layered Codebook Model

Abstract:

In surveillance system,it was challenging to improve real-time in the presence of dynamic background motions.We presented a real-time algorithm for foreground-background segmentation based on codebook model.Pixels were converted from RGB space to YCrCb space,background model used layered model.Firstly we established a basic codebook background model and then got rough background pixels by twice frame difference,and then only trained rough background pixels which have removed foreground pixels.Secondly the foreground was segmented from the background and we updated the background in real-time. The experimental results show that this method can save time of establishment of codebook background model and has small calculation and high accuracy in scenes such as illumination changes,swaying trees and stopped objects should be considered part of the background objects.

• Periodical: Advanced Materials Research (Volumes 694-697)
• Pages: 1937-1944
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.694-697.1937
• Online since: May 2013
• Authors: Dan Yan*, Qiang Yu, Ming Hui Wang
• Keywords: Background Subtraction, Codebook Model, Object Detection, Surveillance System

References

[1] M.Wu and X. Peng."Spatio-temporal context for codebook-based dynamic background subtraction". in International Journal of Electronics and Communications. Vol. 64, 739-747, Aug. (2010)

DOI: 10.1016/j.aeue.2009.05.004

[2] K.Kim T.H. Chalidabhongse,D.Harwood,and L.Davis,"Real-time foreground-background segmentation using codebook model,"Real-Time Imaging,vol. 11 ,2005, pp.172-185.

DOI: 10.1016/j.rti.2004.12.004

[3] K.Toyama,J.Krumm,B.Brumitt,and B.Meyers,"Wall flower: principles and practice of background maintenance,"in Proc.7th IEEE Conf.Computer Vision,1999,vol.x,pp.255-261.

DOI: 10.1109/iccv.1999.791228

[4] J. Gou and C. Hsu."Hierarchical Method for Foreground Detection Using Codebook Model". in IEEE International Conference on Image Processing 2010, Hong Kong.

DOI: 10.1109/icip.2010.5653862

[5] Guo C,Yu J. Steering kernel-based video moving objects detection with local background texture dictionaries. Comput Electr Eng (2012)

DOI: 10.1016/j.compeleceng.2012.09.012

[6] Maddalena L, Petrosino A. A self-organizing approach to background subtraction for visual surveillance applications. IEEE Trans Image Process.2008;17:1168–77.

DOI: 10.1109/tip.2008.924285

[7] Tavakkoli A,NicolescuM, Bebis G, Nicolescu M. Non-parametric statistical background modeling for efficient foreground region detection. Mach Vision Appl 2009;20:395–409.

DOI: 10.1007/s00138-008-0134-2

[8] Q. Tu, Y. Xu and M. Zhou."Box-based Codebook Model for Real-time Objects Detection". in WCICA 2008.

[9] Q.Li,C.Shao,H.Yue and J.Li."Real-time Foreground-background Segmentation Based on Improved Codebook Model ".In CISP2010.

DOI: 10.1109/cisp.2010.5648265

[10] C.Wren, A. Azarbayejani, T. Darrell, and A. Pentland,"Pfinder: Real-time tracking of the human body," IEEE Trans. Pattern Anal. Mach.Intell., vol. 19, no. 7, p.780–785, May 1997.

DOI: 10.1109/34.598236