Eight-Neighborhood Based Background Modeling

Abstract:

In order to solve the Gaussian kernel density-based background modeling, we propose a background modeling method based on an 8-neighborhood pixels sample set. In this method, we use the target pixel and its surrounding 8-neighborhood pixels to analyze whether it is included in the background or in the foreground sample space. Experimental results show that the method can judge the object as the background interference caused by the cyclical movement. By practical verification, the algorithm of the background modeling can full meet the requirements of the target detection algorithm.

• Periodical: Advanced Materials Research (Volumes 532-533)
• Pages: 743-747
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.532-533.743
• Online since: June 2012
• Authors: Yan Lu, Ming Dai, Lei Jiang
• Keywords: Background Modeling, Background Subtraction, Gaussian Kernel Density, Moving Target Detection

References

[1] Elgammal A , Harwood D , Davis L. Non - parametric model for background subtraction. Proceedings of 6th European Conference on Computer Vision. (2000).

DOI: 10.1007/3-540-45053-x_48

[2] Mao Yan-fen, Shi Peng-fei. Gaussian kernel density estimation-based background modeling with noise and shadow suppression. Journal of system simulation. 2005 (In Chinese).

[3] Heikkila M, Pietikainen M. A texture-based method for modeling the background and detecting moving objects. Pattern Analysis and Machine Intelligence. (2006).

DOI: 10.1109/tpami.2006.68

[4] Monnet A, Mittal A, Paragios N, et al. Background modeling and subtraction of dynamic scenes. Proceedings 9th IEEE International conference on computer vision. (2003).

DOI: 10.1109/iccv.2003.1238641

[5] Sun Jian-fen, Chen Ying, Ji Zhi-cheng. Kernel density estimation background model method based on key frame. Optical technique. 2008 (In Chinese).