Research on moving object detection based on improved mixture Gaussian model

被引:21
作者
Chen, Xiaorong [1 ]
Xi, Chuanli [1 ]
Cao, Jianghui [1 ]
机构
[1] Univ Shanghai Sci & Technol, Sch Opt Elect & Comp Engn, Shanghai Key Lab Modern Opt Syst, Shanghai 200093, Peoples R China
来源
OPTIK | 2015年 / 126卷 / 20期
基金
中国国家自然科学基金;
关键词
Gaussian mixture model; Object detection; Parameter estimation;
D O I
10.1016/j.ijleo.2015.05.122
中图分类号
O43 [光学];
学科分类号
070207 ; 0803 ;
摘要
For the deficiency of the mixture Gaussian model (GMM), an improved GMM algorithm is proposed, which can be applied to moving object detection. Combined with codebook detection algorithm, the GMM model is initialized by video images pixels statistical mean and variance, and updated model using parameters confidence interval. The experiment results indicate that the proposed update model can detect moving objects in complex background effectively and has good robustness. (C) 2015 Elsevier GmbH. All rights reserved.
引用
收藏
页码:2256 / 2259
页数:4
相关论文
共 7 条
[1]  
[Anonymous], PATTERN RECOGNITION
[2]  
Chen D., 2010, P 2010 IEEE INT C RO
[3]   Real-time foreground-background segmentation using codebook model [J].
Kim, K ;
Chalidabhongse, TH ;
Harwood, D ;
Davis, L .
REAL-TIME IMAGING, 2005, 11 (03) :172-185
[4]  
Lucas BD., 1981, P DARPA IM UND WORKS
[5]   Real-time image tracking for automatic traffic monitoring and enforcement applications [J].
Tai, JC ;
Tseng, ST ;
Lin, CP ;
Song, KT .
IMAGE AND VISION COMPUTING, 2004, 22 (06) :485-501
[6]  
Tu Q., 2008, P 7 WORLD C INT CONT
[7]  
Xie F.Y., 2008, VISUAL C DIGITAL IMA, P450