Road Background Generation and Update Method Based on Segment Statistics

Abstract:

A road background generation and update method that is based on segment statistics is put forward. It is to generate background by image segmentation and statistic of the gray average in each gray segment interval. It realizes background update with the measurement features of adopting the gray average in each segment and the standard deviation, detects and eliminates the stationary vehicles in the background through complexity comparison of the edge. The experiment shows that the generated background has good quality, and can accurately detect and update the area of stationary vehicles in the background.

• Periodical: Applied Mechanics and Materials (Volumes 157-158)
• Pages: 489-493
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.157-158.489
• Online since: February 2012
• Authors: Jing Li, Huai Yu Liu, Liu Rong Hong
• Keywords: Background Generation, Background Update, Edge Detection, Moving Target Detection, Segment Statistics

References

[1] MEYER D, DENZLER J, and NIEMANNH, Model based extraction of articulated objects in image sequences for gait analysis, In: Proc IEEE International Conference on Image Processing, Santa Barbara, California , pp.78-81, (1997).

DOI: 10.1109/icip.1997.631988

[2] LIPTON A J, FUJIYOSHIH, and PATLRS, Moving target classification and tracking from real-time video", Proc of WACV, 98, pp.8-14, (1998).

[3] JAIN R, Difference and accumulative difference pictures in dymamic scene analysis, Image and Vision Computing, vol. 2, no 2, pp.99-108, (1984).

DOI: 10.1016/0262-8856(84)90004-0

[4] CHEN B S, LEI Y Q, Indoor and outdoor people detection and shadow suppression by exploiting HSV color information, The Fourth International Conference on Computer and Information Technology. Washington, DC, USA: IEEE Computer Society, pp.137-142, (2004).

DOI: 10.1109/cit.2004.1357186

[5] WANG Xiao-mei, WANG Yang-li, and NIU Ping-hong, Gait detection and recognition based on adaptive background model, Application Research of Computers, vol. 11, pp.258-260, (2006).

[6] LI Ming-hui, SU Hong-ye, and DONG Li-da, Rapid background extraction and update algorithm, Computer Engineering, vol. 11, pp.258-260, (2006).

[7] LI Qing-wu, CAI Yan-mei, XU Li-zhong, Background update algorithm based on blocks classification for intelligent video surveillance, CAAI Transactions on Intelligent Systems, vol. 5, no. 3, pp.272-276, (2010).