计算机应用研究Issue(5)：1546-1548,1553,4.DOI:10.3969/j.issn.1001-3695.2015.05.067
基于时空分布的混合高斯背景建模改进方法
Modified GMMalgorithm based on spatiotemporal distribution
摘要
Abstract
Considering the traditional GMMis sensitive to dynamic environment,has low detection rate for the slow moving tar-get,this paper proposed a modified GMMalgorithm,which used spatial information to compensate time information.It used the random number generation method for sampling the neighborhood to complete background modeling based on pixel spatial dis-tribution during the time distribution based on Gaussian mixture background modeling.Meanwhile,it utilized the foreground de-tection algorithm,which applied pixel’s history statistic information and decision fusion mechanism,to get a more exact judg-ment on static and moving target.Finally,compared with other foreground detection algorithms,it shows that GMM has better robustness and more exact detection for the slow moving target.关键词
背景建模/空间信息/混合高斯模型/动态背景/前景检测方法Key words
background modeling/spatial information/GMM/dynamic background/foreground detection algorithm分类
信息技术与安全科学引用本文复制引用
夏海英,何利平,黄思奇..基于时空分布的混合高斯背景建模改进方法[J].计算机应用研究,2015,(5):1546-1548,1553,4.基金项目
广西自然科学基金资助项目（2013GXNSFBA019278）；广西高校科学预研基金资助项目 （）
