由於多媒體和網際網路的快速成長，大量的多媒體資料已經造成使用與查詢上的負擔，為了能在大量的數位影片中針對視訊內容查詢出特定影片段落，需要建立視訊資料庫，並將視訊內容分隔成一個個場景(Shot)以建立此特徵資料庫，在針對每個場景去找代表畫面(key frame)來做特徵比對。本論文提出一個結合多個描述子的方法來減少假警報的發生和增加精確度。在突然式的場景變換演算法部分，我們使用3個複雜度低的描述子和一個MPEG-7的標準描述子來偵測快速的場景變換。在漸進式的場景變換偵測演算法部分，類似上面的方法，我們也使用兩個低複雜度的描述子來偵測緩慢的場景變換，實驗結果顯示提出的演算法是有效的，並且在精確度上勝過以往提出的演算法。

　　Due to the rapidly growing multimedia content available on the internet it is highly desirable to index multimedia data automatically and to provide content based search and retrieval functionalities. For this, we divide the sequence into several shots by scene change detection algorithm. For each shot, we look for key frames to reach characteristic comparing. In general, we divide the sequence by single descriptor, but the disadvantage is to result in false alarm easily. so we proposes a new method that combining multiple descriptors to reduce numbers of false alarm and increase the precision. In the algorithm for abrupt scene change, three low-complexity descriptors and one standard descriptor of MPEG-7 are used for abrupt scene change detection. In the algorithm for gradual scene change, we use similar skills that to determine scene change detection(two low-complexity descriptors are used). Experimental results show that the proposed algorithms are effective and outperform the previous approaches.

[1] A. M. Alattar. Detecting fade regions in uncompressed video sequences. In Proceedings of 1997 IEEE International Conference on Acoustics Speech and Signal Processing, pages 3025-3028, 1997.

[2] A. M. Alattar. Wipe Scene Change Detector for Segmenting Uncompressed Video Sequences. In Proc. IEEE Int. Sym. Circuits and Systems, Vol. 4, pp. 249-252, 1998.

[3] A. M. Alattar, "Wipe scene change detector for use with video compressed algorithms and MPEG-7", IEEE Trans. on Consumer Electronics, Vol. 44, No.1, February 1998

[4] B. Yeo and B.Liu, "Rapid scene analysis on compressed video," IEEE Trans. on Circuits and Syst. for Video Tech. , 1995.

[5] C.-L. Huang and B.-Y. Liao, "A robust scene change detection method for video segmentation", IEEE Trans. on Circuits and Systems for Video Technology, Vol. 11, No. 12, pp. 1281-1288, Dec. 2001.

[6] C.N. Canagarajah W.A.C.Fernando and D.R.Bull,"Wipe scene change detection in video sequences," in ICIP-99, IEEE, Ed., 1999.

[7] Fernando, WAC, Canagarajah, C.N., Bull, D.R., "Automatic Detection of Fade-in and Fade-out in Video

[8] R. Kasturi and R. Jain, Dynamic vision, in Computer Vision: Principles (R. Kasturi and R. Jain, Eds.), pp. 469-480, IEEE Computer Society Press, Washington, DC, 1991.

[9] Gong, Y.H, "An Accurate and Robust Method for Detecting Video Shot Boundaries", , IEEE International Conference on Multimedia Systems, Florence, Italy, June, 1999.

[10] Han, K.J., Tewfik, A.H.,Eigen-Image Based Video Segmentation And Indexing,ICIP(B), pp. 538-541. BibRef

[11] Hai bin Lu, Zhongfei Zhang, Y. R. Yao: Robust Gradual Scene Change Detection. ICIP (3) 1999: 304-308

[12] H.J. Zhang, A. Kankanhalli, S.W. Smoliar: "Au-tomatic Partitioning of Full-motion Video" Multi-media Systems 1993, Vol.1, No.1, pp. 10-28

[13] Ho Young Lee and Yeong Ho Ha, "Spatial Color Descriptor for Image Retrieval and Video Segmentation," accepted by IEEE Transactions on Multimedia in 2002 and to be appeared in 2003.

[14] J. W. Jang and I. K. Oh, Performance Evaluation of Scene Change Detection Algorithms, Proceedings of the Fifth Asia-Pacific Conference on Communications and Fourth Optoelectronics and Communications Conference (APCC/OECC 99?), vol.2, pp. 841-844, Oct. 1999.

[15] Lu H. B., Zhang Y. J., Yao Y. R. "Robust Gradual Scene Change Detection", Proceeding of International Conference on Image Processing, 2: 304-308, 1999.
[16] M. A. Smith and T. Kanade, "Video skimming and characterization through the combination of image and language understanding techniques," in Proceedings of CVPR'97, (Puerto Rico), pp. 775-781, 1997

[17] Ramin Zabih, Justin Miller, and Kevin Mai: Video Browsing Using Edges and Motion. CVPR 1996: 439-446

[18] Rakesh Dugad, K. Ratakonda, and N. Ahuja (1998) Robust Video Shot Change Detection. In: IEEE Workshop on Multimedia Signal Processing, Redondo Beach, California, pp. 376-381

[19] R. Dugad, K. Ratakonda, and N. Ahuja. Robust video shot change detection. IEEEWorkshop on Multimedia Signal Processing, Dec 1998

[20] R.M. Ford, C. Robson, D. Temple, and M. Gerlach, Metrics for Scene Change Detection in Digital Video Sequences, ACM Multimedia Systems Journal in January 2000.

[21] Shiuh-Sheng Yu, Jinn-Rong Liou, and Wen-Chin Chen,"Computational Similarity Based on Chromatic Barycenter Algorithm" IEEE Transactions on Consumer Electronics, Vol.42, No.2,MAY 1996, pp. 216-220

[22] S. Satoh. News video analysis based on identical shot detection. In Proc. 2002 IEEE Intl. Conf. On Multi

[23] W. A. C. Fernando, C. N. Canagarajah, D. R. Bull,"A unified approach to scene change detection in uncompressed and compressed video," IEEE Transactions on Consumer Electronics, Vol. 46, No.3, pp. 769-779, Aug. 2000.

[24] Yu H., Wolf W. "A Multi-resolution Video Segmentation Scheme for Wipe Transition Identification", Proceedings of ICASSP, pp. 2965-2968, 1998.

[25] Zabith, R., Miller, J., and Mai, K., "Feature-Based Algorithms for Detecting and Classifying Scene Breaks", ACM International Conference on Multimedia, pp. 189-200, California, USA, 1993.