A Novel Recursive Bayesian Learning Method for Video Segmentation

摘要：

This work presents a novel Bayesian learning method for dynamic video segmentation. In the algorithm, each frame pixel is represented as layered normal distributions and the recursive Bayesian estimation is used to update the background parameters to obtain a robust background model. In the segmentation, foreground is separated by simple background subtraction method firstly. And then, a local texture correlation method is introduced to remove vacancies in the separated foreground to achieve better segmentation result. Experimental results on two typical video clips are used to show the proposed method can outperform traditional methods in both segmentation result and converging speed.

关键词： Recursive Bayesian learning Gaussian Mixture Model video segmentation background subtraction

作者: Qingsong Zhu Zhan Song

作者单位: Shenzhen Institutes of Advanced Technology,Chinese Academy of Sciences,Shenzhen,China The Chinese University of Hong Kong,Hong Kong,China

会议类型: 国际会议

会议名称: 2010 IEEE信息与自动化国际会议(ICIA 2010)

会议地点: 哈尔滨

会议语种:英文

页码: 1-4

在线出版日期: 2010-06-20（万方平台首次上网日期，不代表论文的发表时间）