一种分级检索MPEG视频的方法

1000-9825/2003/14(03)0675 ©2003 Journal of Software 软 件 学 报 Vol.14, No.3 一种分级检索MPEG视频的方法

刘 阳, 许松涛, 吴志美+

(中国科学院 软件研究所,北京 100080)

A Hierarchical Retrieval Method for MPEG Video

LIU Yang, XU Song-Tao, WU Zhi-Mei+

(Institute of Software, The Chinese Academy of Sciences, Beijing 100080, China)

+ Corresponding author: Phn: 86-10-62645407, Fax: 86-10-62645410, E-mail: wzm@

Received 2002-02-06; Accepted 2002-05-21

Liu Y, Xu ST, Wu ZM. A hierarchical retrieval method for MPEG video. Journal of Software, 2003,14(3): 675~681.

Abstract: Video retrieval is a current hot research area. Most of the past algorithms are done in pixel domain, which need many decode calculations. What is more, the same matching algorithm is used to all the video clips in the same way, which wasts many unnecessary calculations. A new hierarchical retrieval method based on example video for MPEG video is proposed: firstly the dct_dc_size field in I frames is used to locate the suspected videos quickly, then the retrieval result scope can be further reduced by analyzing the spatiotemporal distribution of motion vector in B frames using tomography method, at last DC images precise matching analysis is used to validate the retrieval result. The experimental results show that this method needs a few calculations and has higher precision ratio.

Key words: video retrieval; MPEG; hierarchical; dct_dc_size; spatiotemporal analysis; DC image

摘　　要: 视频检索是当前的一个研究热点.以前的检索方法大多在像素域中进行,需要较大的解码运算量;且不加区分地对所有视频片断采用统一的匹配算法,浪费了许多不必要的计算.提出了一种基于样本的分级检索MPEG视频的新方法:首先用I帧的dct_dc_size字段快速粗检,然后用断层摄影(tomography)法分析B帧运动矢量的时空分布特性以进一步缩小结果集,最后用DC图像的精确匹配方法验证检索结果.试验结果表明,本方法所需计算量较小,且可保证较高的检索精度.

关键词: 视频检索;MPEG;分级;dct_dc_size;时空分析;DC图像

中图法分类号: TP391 文献标识码: A

随着多媒体技术的应用和计算技术的发展,有越来越多的学者投入到视频检索的研究中,并提出了有效的检索方法[1~3].视频检索不同于字符检索,在很大程度上也不同于图像检索,因为图像检索只需分析单幅图像的 　Supported by the National Grand Fundamental Research 973 Program of China under Grant No.G1998030407 (国家重点基础研究发展规划(973)); the Foundation of Beijing Science Committee of China under Grant No.H011710010123 (北京科委基金)

第一作者简介: 刘阳(1975－),男,山东莱芜人,博士生,主要研究领域为视频分析,多媒体通信.