一种基于颜色特征的视频镜头边界检测方法  

A Shot Boundary Detection Method Based on Color Features

作　　者：王丽红[1] 张桂芸[1] 贾花萍[1,2] 

机构地区：[1]天津师范大学计算机与信息工程学院,天津300387 [2]渭南师范学院,陕西渭南714000

出　　处：《计算机工程与科学》2008年第10期33-34,42,共3页Computer Engineering & Science

基　　金：天津市教委资助项目(20071328);天津师范大学大博士基金资助项目(52LX17)

摘　　要：视频镜头的边界检测是视频分析与检索的最基本环节之一。通常进行镜头边界检测时,需要设定阈值来判断特征差异是否足够引起镜头边界出现,但阈值的选取往往因视频内容不同而需重新设定。针对这一问题,本文提出了基于颜色特征进行的镜头边界检测方法。实验结果验证了该方法的有效性。Video shot boundary detection is one of the most basic steps of video analysis and retrieval. Generally, a threshold is set to compare with the changes between frame pairs. Once the change is beyond the threshold,a shot boundary is declared. However the threshold usually depends on the video content. Different video styles may require to reset a new threshold. To solve this problem,we propose a shot boundary detection method based on color features. Experimental results are given to demonstrate the effectiveness and practicality of the method.

关 键 词：颜色特征 镜头边界 检测 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]