ADAPTIVE GAUSSIAN MIXTURE LEARNING FOR MOVING OBJECT DETECTION

摘要：

Adaptive Gaussian mixture learning has been used for moving object detection in video surveillance applications for years. However, the method suffers from low convergence speed in the learning process, especially in complex environments. This paper proposed a novel method which improves adaptive Gaussian mixture leaning from four aspects including calculating the learning rate of means and variances respectively, employing a default minimal value for variances, selecting the optimal match for new pixel and improving renewal equation of weights. Experimental results show that our algorithm is promising, compared with conventional methods.

关键词： foreground segmentation background subtraction Gaussian mixture object detection video surveillance

作者: Long Zhao Xinhua He

作者单位: National Key Laboratory of Science and Technology on Integrated Control Technology,Beihang Universit National Key Laboratory of Science and Technology on Integrated Control Technology, Beihang Universi

会议类型: 国际会议

会议名称: 2010 3rd IEEE International Conference on Broadband Network & Multimedia Technology(2010年第三届IEEE宽带网络与多媒体国际会议 IC-BNMT 2010)

会议地点: 北京

会议语种:英文

页码: 1176-1180

在线出版日期: 2010-10-26（万方平台首次上网日期，不代表论文的发表时间）