本研究之目的為從MPEG I/II影片中自動擷取主要畫面(key frames)。本研究之方法分為三個階段：第一階段利用I畫面中取出的DC畫面來做初步的篩選，從連續的I畫面中取出候選者畫面，以及發生片段變化的畫面群。第二階段則從候選者畫面中，利用像素差和Histogram的差異來過濾因亮度改變而重複的畫面。第三階段則利用B畫面中的位移資訊來判斷發生片段變化的位置，以取出真正的主要畫面。
本研究中的測試影片類型包括新聞影片、音樂錄影帶、廣告片、以及教學影片四種。由實驗結果可知，本研究提出之方法不論是在處理速度或是偵測的結果上都有不錯的效果。

This thesis presents a method for detecting key frames from MPEG I/II compressed videos. First, we analyze DC component of DCT coefficients of I frames to extract candidate key frames. Second, removing candidate key frames that differ in luminance only by noting the changes in histogram profiles. Finally, motion information of B frames is used to detect the real shot changing boundaries and extracting the true first (key) frame of the particular scene.
Experiments are conducted using four types of video clips：news, MTVs, commercials, and teaching videos. The results indicate that our method is able to detect key frames accurately in reasonable amount of time.

參考文獻
[1] Adnan M. Alattar, ”Detecting and compressing dissolve regions in video sequences with a DVI multimedia image compression algorithm”, IEEE International Symposium on Circuits and Systems, vol. 1, pp. 13-16, May 1993.
[2] A. Nagasaka & Y. Tanaka, “Automatic video indexing and full-video search for object appearances”, Visual Database System II, pp. 113-127, 1992.
[3] Boon-Lock Yeo & Bede Liu, “A unified approach to temporal segmentation of motion JPEG and MPEG compressed video”, Proceedings of the International Conference on Multimedia Computing and Systems, pp. 81-88, 1995.
[4] Chang-Hsing Lee & Ling-Hwei Chen, “A fast motion estimation algorithm based on the block sum pyramid”, IEEE Transactions on Image Processing, vol. 6, no. 11, pp. 1587-1591, November 1997.
[5] Hain-Ching Liu & Gred Zick, “Automatic determination of scene changes in MPEG compressed video”, IEEE International Symposium on Circuits and Systems, vol. 1, pp. 764-767, 1995.
[6] H. A. Latchman, Ch. Salzmann, D. Gillet & H. Bouzekri, “Information technology enhanced learning in distance and conventional education”, IEEE Transactions on Education, vol. 42, no. 4, pp. 247-254, 1999.
[7] Horace Ho Shing Ip & Siu Lok Chan, “Automatic segmentation and index construction for lecture video”, Journal of Educational Multimedia and Hypermedia, vol. 7, no. 1, pp. 91-104, 1997.
[8] Hyun Mun Kim & Bart Kosko, “Neural fuzzy motion estimation and compensation”, IEEE Transactions on Signal Processing, vol. 45, no. 10, pp. 2515-2532, October 1997.
[9] H. Zhang, A. Kankanhalli & S.W. Smoliar, “Automatic partitioning of full-motion video”, Multimedia Systems, vol. 1, no. 1, pp. 10-28, 1993.
[10]J. Hafner, H. Sawhney, W. Equitz, M. Flickner & W. Niblack, “Efficient color histogram indexing for quadratic form distance functions”, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 17, pp. 729-736, 1995.
[11]Jianhao Meng & Shih-Fu Chang, “CVEPS - a compressed video editing and parsing system”, Proceedings of the Fourth ACM International Conference on Multimedia, pp. 43- 53, 1996.
[12]J. Wei, M. Drew & Z. Li, “Illumination invariant video segmentation by hierarchical robust thresholding”, in Proc. IS&T/SPIE Conf. Storage and Retrieval for Image and Video Databases VI, pp. 188-201, 1997.
[13]Ke Shen & Edward J. Delp, “A fast algorithm for video parsing using MPEG compressed sequences”, IEEE International Conference on Image Processing, vol. 2, pp. 252-255, 1995.
[14]N. Gamaz, X. Huang & S. Panchanathan, ”Scene change detection in MPEG domain”, IEEE Southwest Symposium on Image Analysis and Interpretation, pp. 12 -17, 1998.
[15]Nilesh V. Patel & Ishwar K. Sethi, “Video shot detection and characterization for video databases”, Pattern Recognition, vol. 30, no. 4, pp.583-592, 1997.
[16]O. Fatemi, S. Zhang & S. Panchanathan, “Optical flow based model for scene cut detection”, Canadian Conference on Electrical and Computer Engineering, vol.1, pp. 470-473, 1996.
[17]Renxiang Li, Bing Zeng & Ming L. Liou, “A new three-step search algorithm for block motion estimation”, IEEE Transactions On Circuits and Systems for Video Technology, vol. 4, no. 4, pp. 438-442, August 1994.
[18]Sergio Cesare Brofferio, “A university distance lesson system: experiments, services, and future developments”, IEEE Transactions on Education, vol. 41, no. 1, pp. 17-24, 1998.
[19]Soo-Chang Pei & Yu-Zuong Chou, “Efficient MPEG compressed video analysis using macroblock type information”, IEEE Transactions on Multimedia, vol. 14, pp. 321-333, December 1999.
[20]Tat-Seng Chua & Li-Qun Ruan,”A video retrieval and sequencing system”, ACM Transactions on Information Systems, vol. 13, no. 4, pp. 373-407, October 1995.
[21]U. Gargi, R. Kasturi & S. Strayer, “Performance characterization of video-shot-change detection methods”, IEEE Transactions on Circuits and Systems for Video Technology, vol. 10, no. 1, pp. 1-13, February 2000.
[22]Yun-Teng Roan & Pei-Yin Chen, “A fuzzy search algorithm for the estimation of
motion vectors”, IEEE Transactions On Broadcasting, vol. 46, no. 2, June 2000.
[23]Zane L. Berge, “Computer conferencing and the on-line classroom”, International Journal of Educational Telecommunications, vol. 3, no. 1, pp. 3-21, 1997.
[24]ISO/IEC JTCI CD 11172,“Coding of Moving Pictures and Associated Audio for Digital Storage Media at up to about 1.5Mbits/s”, December 1991.
[25]ISO/IEC Draft International Standard 13818,“Information Technology - Generic Coding of Moving Pictures and Associated Audio”, March 1994.
[26]「Stanford Online」(http://stanford-online.stanford.edu/)
[27] 「BBMPEG」(http://www.members.home.net/beyeler/bbmpeg.html)
[28]陳恆佑、陳景宜、洪政欣(1998)：暨南國際大學在網路影音/網頁同步遠距教學之發展現況。遠距教育，第9期，36頁-40頁。
[29]「暨南大學 – 語音網頁同步遠距教學系統」(http://wsml.csie.ncnu.edu.tw/)