自動化的場景變換偵測一直是重要且熱門的研究題目，因為他是許多影片處理系統的必要前置工作。一般場景變換可分為兩纇，劇變式場景變換以及漸變式場景變換。此外我們還定義了一個特別的場景變換，稱之為快速轉動式場景變換。這是由攝影機快速的轉動所造成。
在這篇論文中，我們建立了一套以學習理論為基礎的場景變換偵測系統。在劇變式變換偵測裡，我們取出色彩以及運動相關的特徵。對於漸變式變換偵測，因為其高度的複雜性，我們加入了光影以及梯度相關的特徵來加強偵測的準確度。在快速轉動式場景變換偵測裡，則以運動以及梯度相關的特徵來訓練。分別將三組不同的特徵參數取出並利用機器學習理論加以訓練，即可得到三個不同的分類器，個別用拿來偵測三種不同的場景變換。
論文最後的實驗結果顯示我們建立的三個子系統偵測率都非常高。在劇變式變換偵測以及漸變式變換偵測子系統的實驗上，我們以美國國家標準局(NIST)於2003所舉辦的影片資料檢索競賽(TRECVID)中使用的影片來測試，並與其他參賽者的系統做比較。由結果可看出，我們的系統可與競賽中最優秀的幾組參賽系統相提並論。這也證明了此篇論文中所提之方法在場景變換偵測上可表現優異。

Video shot transition detection has always been an important and popular research topic because numbers of applications related to video processing, such as key frame extraction, video summarization, require segmenting video into shots as their first step. Basically there are two types of shot transitions: abrupt shot transition (cut) and gradual shot transition including dissolve, wipe and fade. Besides, we also define a special kind of shot transition, called fast-pan, which is mainly caused by fast camera pan action.
In the thesis, we proposed a learning-based shot transition detection system to accomplish this work. For cut detection subsystem, color-based and motion-based features are extracted. In the gradual transition detection subsystem, the luminance-based and edge-based features are added since it is more complicated than cut. Motion-based and gradient-based features are employed in fast-pan detection subsystem. By separately applying these features into a learning machine, we can train three different classifiers to detect cuts, gradual transitions and fast-pan events individually.
Finally the experimental results are shown. Our experimental results give excellent detection accuracy for all the three shot transition subsystems. The performance of the proposed system on the TRECVID 2003 benchmarking videos for cut and gradual shot transition detection is comparable to the best results reported in the competition.

[1] Q. Tian and H.J. Zhang, “Video shot detection and analysis: Content-based approaches,” Visual Information Representation, Communication, and Image Processing, ed. By C. W. Chen and Y. Q. Zhang, pp. 227-253, Marcel Dekker, New York, 1999.
[2] R. Lienhart, “Comparison of automatic shot boundary detection algorithms,” SPIE Proc. Storage and Retrieval for Still Image and Video Databases VII, vol. 3656, pp.290-301, 1999
[3] U. Gargi, R. Kasturi and S.H. Strayer, “Performance characterization of video-shot-change detection methods,” IEEE transactions on circuits and systems for video technology, vol. 10, no. 1, February 2000.
[4] I. Koprinska and S. Carrato, “Temporal video segmentation: A survey,” Signal Processing: Image communication, Vol. 16, pp. 477-500, 2001.
[5] L. Wu, X. Huang, J. Niu, Y. Xia, Z. Feng, Y. Zhou, “FDU at TREC 2002: Filtering, Q&A, Web and Video Tasks,” Proc. TREC 2002, NIST, Maryland, USA, 2002. (Fudan University)
[6] M. J. Pickering, D. Heesch, R. O’Callaghan, S. Ruger and D. Bull, “Video retrieval using global features in keyframes,” Proc. TREC, NIST, Maryland, USA. (Imperial College)
[7] A. Miene, Th. Hermes, G. Ioannidis, R. Fathi, and O. Herzog, “Automatic shot boundary detection and classification of indoor and outdoor scenes,” Proc. TREC 2002, NIST, Maryland, USA, 2002. (University of Bremen)
[8] D. W. Fellner, N. Fuhr and I. Witten (eds.), “Advanced and adaptive shot boundary detection,” Proc. of ECDL WS Generalized Documents, pp. 39-43.
[9] R. Lienhart, C. Kuhmunch, and W. Effelsberg, “On the detection and recognition of television commercials,” Proceedings of the International Conference on Multimedia Computing and Systems, Ottawa, Ontario, Canada, pp. 509-516, June 1997.
[10] R. Zabih, J. Miller and K. Mai, “A feature-based algorithm for detecting and classifying scene breaks,” Proc. ACM Multimedia’95, pp. 189-200, San Francisco, CA, 1993.
[11] J. Canny. “A computational approach to edge detection,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 8, No. 6, pp.34-43, Nov. 1986.
[12] R. Lienhart. “Methods towards automatic video analysis, indexing and retrieval,” Ph.D, thesis, University of Mannheim, June 1998, in German.
[13] S.H. Lai and W.K. Li, “New video shot change detection algorithm based on accurate motion, and illumination estimation,” Proc. SPIE: storage and retrieval for media database, vol. 4676, 2002.
[14] G.M. Quenot, D. Moraru, L. Besacier and P. Mulhem, “CLIPS at TREC-11: Experiments in video retrieval.” Proc. TREC, NIST, Maryland, USA. (CLIPS IMAGE).
[15] P. Bouthemy, M. Gelgon, F. Ganansia, “A unified approach to shot change detection and camera motion characterization,” IEEE transactions on circuits and systems for video technology 9(7), 1999, pp.1030-1044.
[16] L.F. Cheong, H. Guo, “Shot change detection using scene-based constraint,” Multimedia tools and applications 14, 2001, pp.175~186.
[17] B. Yeo, B. Liu, “Rapid scene analysis on compressed video,” IEEE transactions on circuits and systems for video technology 5(6), 1995, pp.533~544.
[18] X. Huang, G. Wei, and V. A. Petrushin, “Shot boundary detection and high-level feature extraction for the TREC video evaluation 2003,” Proc. TRECVID 2003, NIST, Maryland, USA, 2003. (Accenture Technology Labs).
[19] S.W. Lee, Y.M. Kim, and S.W. Choi, “Fast scene change detection using direct feature extraction from MPEG compressed videos,” IEEE transactions on Multimedia, Vol. 2, No. 4, pp. 240-254, Dec. 2000.
[20] J. Meng, Y. Juan, and S.F. Chang, “Scene change detection in a MPEG compressed video sequence.” Proc. SPIE/IS&T Symp. Electronic imaging science and technology: digital video compression: algorithms and technologies, vol. 2419, 1995.
[21] J.H. Kuo, J.L. Wu, “An efficient algorithm for scene change detection and camera motion characterization using the approach of heterogeneous video transcoding on MPEG compressed videos,” Proc. SPIE: storage and retrieval for media database, vol. 4676, 2002, pp. 168~176.
[22] S.C. Pei and Y.Z. Chou, “Efficient MPEG compressed video analysis using macroblock type information,” IEEE Transaction on Multimedia, Vol. 1, No. 4, pp.321-333,1999.
[23] B. Janviwe, E. Bruno, S. Marchand-Maillet, T. Pun, “Information-theoretic framework for the joint temporal partitioning and representation of video data.”
[24] H.J. Zhang, A. Kankanhalli, S.W. Smoliar, “Automatic partitioning of full-motion video,” Multimedia Systems, ACM-Springer 1993, 1(1), 10-28.
[25] B.T. Truong, C. Dorai, S. Venkatesh, “New enhancements to cut, fade, and dissolve detection processes in video segmentation,” ACM Multimedia 2000, pp. 219-227.
[26] M. Cooper, J. Foote, J. Adcock and S. Casi, “Shot boundary detection via similarity analysis,” Proc. TRECVID 2003, NIST, Maryland, USA, 2003. (FX Palo Alto Laboratory)
[27] A. Amir, M. Berg, S.F. Chang, G. Iyengar, C.Y. Lin, A. Natsev, C. Neti, H. Nock, M. Naphade, W. Hsu, J.R. Smith, B. Tseng, Y. Wu, D. Zhang, “IBM Research TRECVID-2003 video retrieval system.” Proc. TRECVID 2003, NIST, Maryland, USA, 2003. (IBM Research).
[28] S. Zhu and K.K. Ma, “A new diamond search algorithm for fast block-matching motion estimation,” IEEE Trans. Image Processing, vol 9, pp. 287-290, Feb. 2000.
[29] Otsu, N., (1979), “A threshold selection method from grey-level histograms,” IEEE Transactions on Systems, Man, and Cybernetics, Vol. SMC-9, No.1,pp. 62-66.
[30] E.M. Voorhees, “Overview of TREC 2003,” Proc. TRECVID 2003, NIST, Maryland, USA, 2003.
[31] http://trec.nist.gov/ .