3 结 论

本文提出了一种分级检索MPEG视频的新方法.整个检索过程在压缩域中进行,因不必完全解码,因此所需计算量较小,同时与其他检索算法相比,不用预先提取关键帧,减少了预处理过程,可实时检索.另外,经过多级比较,本方法可保证有较高的检索精度.在第1级检索中改进了原来分析I帧dct_dc_size字段的算法,在第2级检索中使用断层摄影法分析运动矢量的时空分布特性.阈值的自适应问题是我们下一步要进行研究的工作. References:

[1] Zhang HJ, Low CY, Smoliar SW, Wu JH. Video parsing retrieval and browsing: an integrated and content-based solution. In:

Adelson EH, Bergen JR, eds. Proceedings of the 3rd ACM International Conference on Multimedia’95. San Francisco: ACM Press, 1995. 15~24.

[2] Jain AK, Vailaya A, Xiong W. Query by video clip. Multimedia Systems: Special Issue on Video Libraries, 1999,7(5):369~384.

[3] Zhuang YT, Liu XM, Wu Y, Pan YH. A new approach to retrieve video by example video clip. Chinese Journal of Computers,

2000,23(3):300~305 (in Chinese with English Abstract).

[4] Atsuo Y, Tadao I. Survey on content-based retrieval for multimedia databases. IEEE Transactions on Knowledge and Data

Engineering, 1999,11(1):81~93.

[5] Ngo CW, Pong TC, Chin RT. A survey of video parsing and image indexing techniques in compressed domain. In: Vass J, Zhuang

S, eds. Proceedings of the Symposium on Image, Speech, Signal Processing, and Robotics’98. Hong Kong, 1998,1:231~236.

[6] Zhong YZ, Qiao BX, Qi W. General International Coding Standard for Motive Pictures and Audio——MPEG-2. Beijing: Tsinghua

University Press, 1997. 142~319 (in Chinese).

[7] Won CS, Park DK, Yoo S.J. Extracting image features from MPEG-2 compressed stream. In: Ishwar KS, Ramesh J, eds. SPIE

Proceedings of the Storage and Retrieval for Image and Video Databases VI. San Jose, CA: SPIE Press, 1998,3312:426~435.

[8] Liu Y, Wu ZM. A new JPEG image retrieval method in compressed domain. In: Proceedings of the 14th IEEE International

Conference on Application-Specific System, Architectures and Processors. Hague, 2003.

[9] Akutsu A, Tonomura Y. Video tomography: an efficient method for camerawork extraction and motion analysis. In: Wayne N,

Ramesh J, eds. Proceedings of the 4th ACM International Conference on Multimedia’94. San Francisco: ACM Press, 1994. 349~356.

[10] Boreczky JS, Rowe LA. Comparison of video shot boundary detection techniques. In: Sethi K, Jain RC, Ishwar KS, eds.

Proceedings of the SPIE Conference on Storage and Retrieval for Still Images and Video Databases IV. San Jose, CA: SPIE Press, 1996,2664:170~179.

[11] Yeo BL, Liu B. On the extraction of DC sequence from MPEG compressed video. In: Depommier R, Hsu A, eds. Proceedings of

the International Conference on Image Processing’95. Washington, DC: IEEE Press, 1995. 260~263.

附中文参考文献:

[3] 庄越挺,刘小明,吴翌,潘云鹤.通过例子视频进行视频检索的新方法.计算机学报,2000,23(3):300～305.

[6] 钟玉琢,乔秉新,祁卫.运动图象及其伴音通用编码国际标准——MPEG-2.北京:清华大学出版社,1997.142～319.