分鏡偵測(Shot detection)是對數位化影片做處理(索引、註解和儲存)的第一步。分鏡變化(Shot change)，主要可分為兩大類：突然式分鏡變化(abrupt shot change又稱為cut),和漸進式分鏡變化(gradual transition),而漸進式分鏡變化最常見的就是溶解(dissolve)。
在這篇論文中,我們分別提出了兩種方法來偵測突然式分鏡變化和溶解。針對突然式分鏡變化的部分是利用基於直流值影像(DC image)的線性差異來偵測；針對溶解的部分是利用直流值影像將C. W. Su的方法轉換到壓縮領域。

Shot detection is the first step to deal with (index, annotate, store) video. There are two kinds of shot change. One is abrupt shot change (it is also called cut), and the other is gradual shot change. The most popular of gradual shot change is dissolve.
In the thesis, we propose two methods. One is for detecting abrupt shot change and the other is for dissolve. For detecting abrupt shot change, we use the property of “linear difference based on DC image”. For detecting dissolve, we combine the method proposed by C. W. Su with DC image.

1.H.J. Zhang, A. Kankanhalli and S. Smoliar, “Automatic partitioning of video,” Multimedia Systems, 1993, 1(1):10-28.
2.F. Arman, A. Hsu and M-Y Chiu, “Image processing on compressed data for large video databases,” in: Proc. First ACM Intern. Conference on Multimedia, 1993, pp. 267-272.
3.B.-L. Yeo and B. Liu, “A unified approach to temporal segmentation of motion JPEG and MPEG compressed video,” in Proc. 2nd Int. Conf. Multimedia Computing and Systems, 1995, pp. 81–83.
4.S. F. Chang and D. G. Messerschmitt, “Manipulation and compositing of MC-DCT compressed video,” IEEE J. Select. Areas Commun., vol. 13, pp. 1–11, Jan. 1995.
5.W. Fernando and C. Canagarajah and D. Bull, “Sudden scene change detection in MPEG-2 video sequences,” in IEEE International workshop on multimedia signal processing, MMSP’99, Copenhagen Denmark, September 1999.
6.R. Kasturi, R. Jain, Dynamic vision, in Computer Vision: Principles, R. Kasturi and R. Jain,eds.), pp. 469-480, IEEE Computer Society Press, Washington DC, 1991.
7.C. M. Lee and M. C. Ip, “A robust approach for camera break detection in color video sequence,” in Proc. IAPR Workshop Machine Vision Applications, Kawasaki, Japan, 1994, pp. 502–505.
8.Ullas Gargi, Rangachar Kasturi, Susan H. Strayer. “Performance Characterization of Video-Shot-Change Detection Methods,” IEEE Transaction on Circuits and Systems for Video Technology, Vol. 10, No. 1, February 2000.
9.I. K. Sethi and N. Patel, “A statistical approach to scene change detection,” in Proc. IS&T/SPIE Conf. Storage and Retrieval for Image and Video Databases III, vol. SPIE 2420, 1995, pp. 329–338.
10.N. V. Patal and I. K. Sethi, “Video shot detection and characterization for video databases,” Pattern Recognition, 1997, vol. 30, pp. 583–592.
11.H. C. Liu and G. L. Zick, “Automatic determination of scene changes in MPEG compressed video,” in Proc. ISCAS-IEEE Int. Symp. Circuits and Systems, 1995, pp. 764–767.
12.J. Meng, Y. Juan, and S. F. Chang, “Scene change detection in a MPEG compressed video sequence,” in Proc. SPIE/IS&T Symp. Electronic Imaging Science and Technology: Digital Video Compression: Algorithms and Technologies, vol. 2419, 1995.
13.C. W. Su, H. R. Tyan, H. Y. Mark Liao and L. H. Chen, “A motion tolerant dissolve detection algorithm,” to appear in ICME 2002.
14.Sung-Bae Jun, Kyoungro Yoon and Hee-Youn Lee, “Dissolve Transition Detection Algorithm Using Spatio-Temporal Distribution of MPEG Macro-Block Types,” Proceedings of the eighth ACM international conference on Multimedia October 2000.
15.MPEG ORG , http://www.mpeg.org
16.ISO 11172, “Coding of Moving Pictures and Associated Audio --for Digital Storage Media at up to about 1.5 Mbit/s.”