在本篇論文中，我們將提出一些有效率的方法與技術，可利用在運動向量資訊中所萃取的動作特徵，直接在MPEG壓縮領域中搜尋視訊片段。我們之所以對壓縮領域中的動作特徵有興趣的原因如下：第一點，現今大部分的多媒體內容都以壓縮格式存在，因此直接使用壓縮領域中的特徵使我們有機會建立一個有效率且即時的視訊索引及擷取系統。第二點，運動向量的資訊包含在MPEG中，而動作特徵很容易就可以由運動向量資訊中萃取出來，因此我們不需要花費解壓縮時的昂貴運算量。
我們提出一個運動強度頻譜與一個二維的運動向量圖表，利用這兩個工具來萃取動作特徵，並利用萃取出的動作特徵來建立一個可使用範例影片查詢視訊片段的系統。由於科技的發達，多媒體的應用越來越廣泛，人類所能汲取到的資料也越來越多，因此想要找到有興趣的內容也變的越來越困難，利用關鍵字來查詢是最常見且直覺的方法，但有時很難用文字來描述所需要的視訊內容，因此我們透過使用範例影片查詢來解決這個問題。首先，我們由範例查詢影片與視訊片段中萃取出它們所對應的動作特徵，並設計由這些對應的動作特徵來計算影片相似度的方法。接下來，利用動態編制程序的技術和二步驟比對的方法，我們可以在合理的運算量內，由一段影片中找到與範例影片最相似的視訊片段。

最後，經由一個搜尋與範例查詢影片相同或類似之視訊片段的實驗，可以證明我們提出的方法有很不錯的應用價值。

In this thesis, some efficient methods that can explore motion activity features from motion vectors for inquiring video clip on MPEG compressed domain are proposed. The reasons that we are interested in utilizing the compressed-domain motion activity features are as follows. First, much of the multimedia content available today is in compressed form already. Using compressed-domain features directly makes it possible to construct effective video indexing and retrieval systems for real-time applications. Next, motion activity features are easily to be extracted from the existing motion vectors without the need of computation of decompression as well as the delay latency induced.
We analyze and utilize the motion activity features we extracted to build up a system for inquiring video clip by example. With the continuing explosion of multimedia information in today's society, searching for information of interest is becoming increasingly hard. As it is not straightforward to describe video content in keywords, searching video solely on text information has its limitations. We deal with this problem through the technique of query by example. First a matching algorithm is designated to evaluate the similarity between the existing video segment and the query one derived from the information of their corresponding motion activity features. Then, dynamic programming technique is employed to search for the most proximity video segment in the lengthy question video with a reasonable computational cost.

Finally, some applications are given and discussed to demonstrate the potential usage of the proposed techniques.

[1] Nevine AbouGhazaleh, Yousry El Gamal, " Compressed Video Indexing Based on Object's Motion," Proc. SPIE Visual Communications and Image Processing, June 2000.
[2] Roy Wang, Thomas Huang, "Fast Camera Motion Analysis in MPEG domain," Proc. IEEE International Conference on Image Processing, 1999.
[3] Jae-Gon Kim, Hyun Sung Chang, Jinwoong Kim, and Hyung-Myung Kim, "Effieient Camera Motion Characterization for MPEG Video Indexing," Proc. IEEE International Conference on Image Processing, 2000.
[4] H. Zen, T. Hasegawa, S. Ozawa, "Moving Object Detection From MPEG Coded Picture," Proc. IEEE International Conference on Image Processing, 1999.
[5] Y. Nakajima, A.Yoneyama, H.Yanagihara, and M.Sugano, "Moving Object Detection from MPEG Coded Data," Proc. SPIE Visual Communications and Image Processing, 1998.
[6] A.Yoneyama, Y.Nakajima, H.Yanagihara, and M.Sugano, "Moving Object Detection and Identification from MPEG Coded Data," Proc. IEEE International Conference on Image Processing, 1999.
[7] Lorenzo Favalli , Alessandro Mecocci , Fulvio Moschetti," Object Tracking for Retrieval Application in MPEG-2", IEEE Trans. On Circuits and Systems for Video Technology, Apr. 2000.
[8] Emile Sahouria and Avideh Zakhor, "A Trajectory Based Video Indexing System For Street Surveillance", Proc. IEEE International Conference on Image Processing, 1999.
[9] F. Bartolini, V. Cappellini and C, Giani, "Motion Estimation and Tracking for Urban Traffic Monitoring," Proc. IEEE International Conference on Image Processing, 1996.
[10] INTERNATIONAL STANDARD ISO/IEC 11172
[11] ISO/IEC JTC1/SC29/WG11 N4031
[12] ISO/IEC JTC1/SC29/WG11 W4026
[13] Y.-P. Tan, D. D. Saur, S. R. Kulkarni, and P. J. Ramadge, "Rapid Estimation of Camera Motion from Compressed Video with Application to Video Annotation," IEEE Trans. On Circuits and Systems for Video Technology, 1999.
[14] E. Ardizzone, M. La Cascia, A. Avanzato, and A. Bruna, "Video indexing using MPEG motion compensation vectors," Proc. IEEE International Conference on Multimedia Computing and Systems, 1999.
[15] J. Meng, and S.-F. Chang, "CVEPS - a compressed video editing and parsing system," Proc. ACM Multimedia 96, 1996.
[16] A. Divakaran, K. A. Peker, and H. Sun, "Video Indexing using Descriptors of Spatial Distribution of Motion Activity," submitted to IEEE Trans. On Circuits and Systems for Video Technology.
[17] K. A. Peker, A. Divakaran, and T. V. Papathomas, "Automatic Measurement of Intensity of Motion Activity of Video Segments," submitted to IEEE Transactions on Multimedia.
[18] Shih-Fu Change, William Chen, Horace J. Meng, HariSundatam and Di Zhong, "A Fully Automated Content-Based Video Search Engine Supporting Spatiotemoral Queries," IEEE Trans. On Circuits and Systems for Video Technology, 1998.
[19] Y. Deng and B.S. Manjunath, "NeTra-V: toward an object-based video representation", IEEE Trans. On Circuits and Systems for Video Technology, 1998.
[20] Y. Linde, A. Buzo, and R. M. Gray, "An Algorithm for Vector Quantizer Design," IEEE Transactions on Communications, January 1980.