视频检索中镜头分割方法综述

A Survey of Methods for Partitioning Video into Shots in Video Indexing

视频序列的镜头分割亦称镜头变化检测是视频检索中的关键技术之一。镜头变化是指视频序列中场景内容的变化。该文介绍了目前镜头分割的常用方法,包括灰度分割法、边缘分割法、彩色直方图分割法、MPEG视频的分割方法、块匹配镜头分割方法、统计判决镜头分割方法、基于聚类的镜头分割方法、镜头渐变的检测等,指出了研究场景内容的表征方法、特征提取方法、特征的检测尺度以及稳健可靠的实用镜头分割方法是目前主要的研究方向。

Partitioning a video sequence into shots or detecting shot change is one of the key techniques in video indexing.Shot change means scene content change in a video sequence.This article presents most commonly used methods for partitioning video into shots which are grey level -based methods,edge -based methods,color -histogram methods,MPEG methods,block matching methods,statistic decision methods,clustering -based methods and gradual transition detection.In authors' view-point ,the presentation of scene content ,feature extraction,feature measure metrics and robust and practical partitioning methods are the main research directions in the near future.