%0 Journal Article
%T Scene change detection in video stream based on Bhattacharyya distance<br>基于巴氏距离的视频流场景变化检测
%A SHEN Bi-chuan
%A MAO Qi-jian
%A LV Yi
%A <br>沈壁川
%A 毛期俭
%A 吕翊
%J 重庆邮电大学学报(自然科学版)
%D 2009
%I 
%X This paper studies statistics based scene change detection in the video streaming scenario, and three scene fea-ture metrics including histogram distance, chi-square distance, and Bhattacharyya distance have been investigated. With the unique characteristics of triangular inequality and non-singularity, Bhattacharyya distance has been proposed as a viable scene change metrics. It outperforms much better than the other two in that it calculates and maximizes the feature vector distance between muhi-modal clusters in a hyper-sphere space. The experiments are conducted and the precision recall sta-tistics are compared, and the results support our analysis.
%K scene change detection
%K feature vector distance
%K Bhattacharyya distance
%K Chi-square distance<br>场景变化检测
%K 特征向量距离
%K 巴氏距离
%K 卡方距离
%U http://www.alljournals.cn/get_abstract_url.aspx?pcid=01BA20E8BA813E1908F3698710BBFEFEE816345F465FEBA5&cid=96E6E851B5104576C2DD9FC1FBCB69EF&jid=5C2694A2E5629ECD6B59D7B28C6937AD&aid=FFE5AEDC8F8B09D780A539DFFB4AA5C6&yid=DE12191FBD62783C&vid=659D3B06EBF534A7&iid=CA4FD0336C81A37A&sid=CB423C9A71560A74&eid=B9704B40A4225A24&journal_id=1673-825X&journal_name=重庆邮电大学学报(自然科学版)&referenced_num=1&reference_num=11