计算机应用研究2012，Vol.29Issue(3)：1188-1190,3.DOI:10.3969/j.issn.1001-3695.2012.03.108
基于自适应邻域的核密度动态目标分割方法
Method for dynamic object segmentation with kernel density estimation based on self-adaption neighborhood
严驰 1唐宁九 1李征 1申红星1
作者信息
- 1. 四川大学计算机学院计算机科学与技术系,成都610064
- 折叠
摘要
Abstract
In classical kernel density estimation, using displacement probability with a small fixed window size to suppress fake target,which caused by moving background. But fixed window size can not adapt to different movement of background. This paper designed and implemented a novel method based on background modeling with kernel density estimation. This method could achieve window size' s adaptive selection. In the same filming scene, it could adapt to more moving background type and suppress many kinds of fake target. Also the method used the technology of image registration. Experiment shows that this method can effectively suppress mostly false detection which caused by moving background.关键词
动态目标分割/核密度估计/图像配准/图像分割Key words
dynamic object segmentation/ kernel density estimation/ image registration/ image segmentation分类
信息技术与安全科学引用本文复制引用
严驰,唐宁九,李征,申红星..基于自适应邻域的核密度动态目标分割方法[J].计算机应用研究,2012,29(3):1188-1190,3.
