基于关键点匹配的视频镜头边界检测  

Video Shot Boundary Detection Based on Key Points Matching

作　　者：厉霞 李旭健[1] 

机构地区：[1]山东科技大学信息科学与工程学院,山东省青岛市266590

出　　处：《曲阜师范大学学报（自然科学版）》2015年第1期69-71,共3页Journal of Qufu Normal University(Natural Science)

基　　金：国家自然科学基金(61170253);山东科技大学"春蕾计划"(2008AZZ055)

摘　　要：镜头边界检测就是找到每个镜头的起始和结束帧,它是视频分析的基础,也是基于内容的视频检索的第一步.因此,其效率和准确度直接关系到整个视频检索的成败.然而,由于摄像头和物体运动的影响,现有的镜头边界检测的准确率较低.为了解决这个问题,论文提出了基于关键点匹配的镜头边界检测方法.该方法通过比较连续两帧关键点匹配的数量,确定镜头边界,并且具有较高的准确率.Shot boundary detection is to find the beginning and the end of each shot,it is the foundation of any video analysis,and it is the first step for content based video retrieval,so its efficiency and accuracy are directly related to the success of the whole video retrieval.However,as the influence of the camera and obj ect motion,the accuracy of the existing shot boundary detection is still low.To solve the problem,this paper proposed the shot boundary detection method based on keyword matching.The method determines the shot boundary by comparing the number of keywords matching between two consecutive frames, which has higher accuracy.

关 键 词：镜头边界检测 SIFT算法 关键点匹配 突变镜头 渐变镜头 

分 类 号：TP37[自动化与计算机技术—计算机系统结构]