An Improved Background Update Algorithm and Application in Traffic Engineering

Abstract:

The statistical histogram algorithm is one of the common background update algorithms. Considering the statistical histogram algorithm disadvantages of large complex computation, the paper proposes an improved method named fixed window statistical background updating algorithm. The algorithm sets a window which contains N records for each pixel point firstly, every record records value in the permissible range of error and the number of pixel point occurrence, and then counting pixel values for every record through statistical histogram algorithm. When the window is full, the new pixel values will replace the smaller counting, while the pixel which counting larger will be adaptively updated by adaptive background updating formula. The experimental result shows that this method has a high real-time performance and robustness in background updating.

• Periodical: Applied Mechanics and Materials (Volume 620)
• Pages: 228-232
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.620.228
• Online since: August 2014
• Authors: Shi Song Zhu*, Hai Yan Zhang, Cui Yun Zhang, Hong Jin Zhu
• Keywords: Fixed Window Statistical, Real-Time Performance, Robustness, Statistical Histogram, Traffic Video

References

[1] Nicholas A. Mandellos，Iphigenia Keramitsoglou，Chris T. Kiranoudis, A backgro- und subtraction algorithm for detecting and tracking vehicles. Expert Systems with Applications. 38, (2011)1619–1631.

DOI: 10.1016/j.eswa.2010.07.083

[2] Thanarat Horprasert, David Harwood, Larry S. Davis. A Robust Background Subtraction and Shadow Detection, In Proc. Of the 4th ACCV, Vol. 1, (2000)983-988.

[3] Li Guanglun, Shu Weiqun. Real-time Detection of Moving Targets in Video Monitoring System, Computer Engineering, 35 (17), (2009) 217-218.

[4] Gan Ling, Pan Xiaolei. Background Update Method Applied in Moving Vehicle Detection. Computer Engineering, 38(4) (2012): 174-175.

[5] Liu Hao, Zhao Fengmin, Chen Wangda. Moving Target Detection and Tracking Algorithm based on Adaptive Background Update. Journal of Naval Aeronautical Engineering Institute, 27(1) (2012)15-18.

[6] Stauffer C，Grimson W. Adaptive Background Mixture Models for Real-time Tracking, Proceedings of IEEE Conference on Computer, Vision and Pattern Recognition. Fort Collins，Colorado, USA, IEEE, (1999)246-252.

DOI: 10.1109/cvpr.1999.784637

[7] cott J, Pusateri M A, Cornish D. Kalman Filter Based Video Background Estimation[C]/Proc. of Applied Imagery Pattern Recognition Workshop. Washington D. C., USA: IEEE Press, (2009).

DOI: 10.1109/aipr.2009.5466306

[8] Zhao Fake, Shi Yi. The Research in Vehicle Tracking about Background Initialization and Update, Traffic Information and Security, 27(4), (2009) 16-21.

[9] Wang Yong, Tan Yihua, Tian Jinwen. A Segment Algorithm Based on Shadow Elimination and Gaussian Mixture Model, Optoelectronic Component, 35（3）, (2008)21-25.

[10] LEE D S. Effective Gaussian Mixture Learning for Video Background Subtraction, IEEE Transactions on Pattern Analysis and Machine Intelligence, 27(5), (2005)827-832.

DOI: 10.1109/tpami.2005.102

[11] Leone A. and Distante C. Shadow detection for moving objects based on texture analysis, Pattern Recognition (40), No. 4, pp.1222-1233, April (2007).

DOI: 10.1016/j.patcog.2006.09.017

[12] Hao Sixin. The Algorithm Research Based on Moving Vehicle Tracking and Detecting [D]. Shang Hai: East China Normal University, (2009).

[13] FANG Xiao Ying，WANG Xiao. A traffic Abnormity Detection Algorithm based on Vision in the ITS. The Micro Computer and Application, (6), ( 2010) 35-38.

[14] Guo Lin. Research and Simulation on Adaptive Background Update Algorithm in Video Vehicle Detection , Journal of Communication University of China (Natural Science), 20(2), 2013: 69-73.

[15] Zhou Jianqiang, Liu Hua, Zhang Hailong , Li Zhen. An Improved Method on Background Extraction and Update. Journal of Nanjing Normal University (Engineering), 12(4), (2012)67-72.