一种基于视频聚类的关键帧提取方法  

An Approach of Key Frame Extraction Based on Video Clustering

作　　者：朱映映[1] 周洞汝[1] 

机构地区：[1]武汉大学计算机学院,武汉430072

出　　处：《计算机工程》2004年第4期12-13,121,共3页Computer Engineering

基　　金：国家自然科学基金资助项目(60173045)

摘　　要：关键帧提取技术是视频分析和基于内容的视频检索的基础。关键帧的使用大大减少了视频索引的数据量,同时也为视频摘要和检索提供了一个组织框架。该文简单介绍了目前的关键帧提取技术,提出了一种基于聚类利用颜色直方图提取关键帧的方法来克服其它方法的不足。实验证明该方法计算量小,可以较好地代表视频内容。Key frame extraction is one of fundamental processes in video analysis and content-based video retrieval. Key frame can dramatically reduce the data of the video indexing, and provides a framework for video abstraction and retrieval. This paper briefly discusses the existing approaches. To overcome the shortcomings of the existing approaches, it presents a new approach for key frame extraction based on clustering. Experimental results show that the approach is computationally simple and able to adapt to the visual content.

关 键 词：关键帧提取 视频聚类 镜头 颜色直方图 

分 类 号：TP37[自动化与计算机技术—计算机系统结构]