期刊名称：International Journal of Advanced Research in Computer Engineering & Technology (IJARCET)
印刷版ISSN：2278-1323
出版年度：2017
卷号：6
期号：5
页码：773-777
出版社：Shri Pannalal Research Institute of Technolgy
摘要：Background modeling is used in different applications to model the background and to detect the moving objects in the scene in video surveillance. Several of background modeling methods have been proposed to identify foreground objects in a video. In this paper we review the background model methods: parametric and non-parametric methods. Parametric methods building the parameter estimation probability distribution based on the color distribution of images. In non-parametric methods, a kernel function is introduced to model the distribution. In this paper, we address the problem of some representative background modeling. Results shown numerous improvements of this some methods developed to background modeling.
关键词：Subtraction; Optimize; Mixture of Gaussian; Dynamic Adaptation.
