由於監視影片的日漸普及，愈來愈多的應用需要從監視影像中找出感興趣的畫面；然而監視影像龐大的資料量，使得影片資料的搜尋、影像內容的分析變得困難。設計一個簡單、有效率的方法來索引影片資訊，用來分析影片的特徵，將有助於搜尋特殊事件發生的影片片段，進而節省人力及時間。
本篇論文提出利用物體運動量隨時間變化的特性，透過取得監視的物體、分析物體運動量大小與時間的變化，來索引監視影片進而分析事件。我們設計的監視影片摘要系統，首先用[10] 提出的motion intensity spectrum取出可能含物體的影片區段，分析運動向量變化的轉折點(motion-transition points)，並配合背景抽離(Background Subtraction)擷取出正確含有物體的所有影片片段。在取得含有物體的影片片段之後，接著繼續用背景抽離與運動量追蹤(Motion Tracking)的方式擷取及追蹤物體在每張畫面的中的位置及大小資訊，並以物體對映圖(Object Map)的方式紀錄物體分群的資訊。最後，我們可以得到一個以物件為主的運動強度頻譜(Object-based Motion Intensity Spectrum)來描述物體在影片中的運動情形，並經由分析物體運動強度(Motion Intensity)連續變化的情形設計摘要規則，找出含有特殊事件的監視畫面。
實驗結果顯示，我們的方法可找出進入畫面、離開畫面、從連續運動中停下來，及從停止突然開始持續運動等的事件，而這些事件也的確是監視影片中會特別感興趣的監視片段。我們不只提出了一個有效的摘要機制，同時也引進一個以時間軸為主，配合空間資訊進行摘要的概念。透過時間軸與空間資訊的配合，摘要系統的設計將有機會提供更有幫助的知識性摘要。

As the increasing amount of surveillance videos, people are more interested in issues like checking out the specific events. However, the vast amount of video data let video analysis become too complicated. Thus, developing a low-complexity and efficient indexing method is very important.
In this thesis, based on the characteristic that the object motion varies with time, we extract object information from surveillance video sequences. Then, we proposed an object-based motion summary scheme by analyzing the object motion and generating indices with a proposed object-based motion spectrum. In our scheme, we first extract motion-transition points to get initial object segments using the motion intensity spectrum in [10]. By subtracting the motion-transition frames with the background, we can extract the actual object segments. With these object segments, we further utilize the background subtraction along with the motion tracking algorithm to construct and maintain an object map frame-by-frame. We introduce an object-based motion intensity spectrum to denote the variations of object groups. Finally, several event rules are made based on the object-based motion intensity spectrum, and key frames with anomalous events are summarized.
Our experimental results show that the proposed scheme could find out specific events, such as, enter a scene, leave a scene, stop from continuous movement, and move from continuous static, in surveillance videos. We not only propose an effective summary scheme, meanwhile, we also inspire the idea of summarizing spatial location information with temporal relations. Through co-operating the spatial and temporal information, summary schemes can be more powerful and can provide more informative summary indices.

[1] Y. Li, S. Narayanan, and C.-C. Jay Kuo, “Content-based movie analysis and indexing based on audiovisual cues,” IEEE Trans. Circuits Syst. Video Technol., vol. 14, Aug. 2004, pp. 1073–1085.
[2] N. Babaguchi, Y. Kawai, T. Ogura, and T. Kitahashi, “Personalized abstraction of broadcasted American football video by highlight selection,” IEEE Trans. Multimedia, vol. 6, Aug. 2004, pp. 575–586.
[3] Z. Rasheed, Y. Sheikh, and M. Shah, “On the use of computable features for film classification,” IEEE Trans. Circuits Syst. Video Technol., vol. 15, Jan. 2005, pp. 52–64.
[4] K. Shirahama, K. Iwamoto, and K. Uehera, “Video data mining: rhythms in a movie,” in Proc. IEEE Int. Conf. Multimedia and Expo, vol. 2, Jun. 2004, pp. 1463–1466.
[5] M. A. Smith and T. Kanade, “Video skimming and characterization through the combination of image and language understanding techniques,” in Proc. IEEE CVPR, Jun. 1997, pp. 775–781.
[6] A. Yoneyyama, C. H. Yeh, and C.-C. Jay Kuo, “Robust traffic event extraction via content understanding for highway surveillance system,” in Proc. IEEE Int. Conf. Multimedia and Expo, vol. 3, Jun. 2004, pp. 1679–1682.
[7] J. –G. Kim et al., and H. –M. Kim, “Efficient camera motion characterization for MPEG video indexing,” in Proc. IEEE Int. Conf. Multimedia and Expo, vol. 2, Jul. 2000, pp. 1171–1174.
[8] Y. –P. Tan, D. D. Saur, et al., “Rapid estimation of camera motion from compressed video with application to video annotation,” IEEE Trans. Circuits Syst. Video Technol., vol. 10, Feb. 2000, pp. 133–146.
[9] Z. Aghbari, K. Kaneco, and A. Makinouchi “A motion-location based indexing method for retrieving MPEG videos,” in Proc. Int. Wor. Database and Expert Syst. Appl., Aug. 1998, pp.102–107.
[10] C. –Y. Cho, Y. –T. Chuang, P. –C. Chu, S. –Y. Huang, and J. –S. Wang, “Efficient motion-vector-based video search using query by clip,” in Proc. IEEE Int. Conf. Multimedia and Expo, vol. 2, Jun. 2004, pp. 1027–1030.
[11] H. Sundaram, L. Xie, and S.-F. Chang, “A utility framework for the automatic generation of audio-visual skims,” in Proc. ACM Multimedia, Dec. 2002, pp. 189–198.
[12] S. Park and J.K. Aggarwal, “Segmentation and tracking of interacting human body parts under occlusion and shadowing,” in Proc. Int. Wor. Motion and Video Computing, Dec. 2002, pp. 105–111.
[13] C. Kim and J.-N. Hwang, “Object-based video abstraction for video surveillance systems,” IEEE Trans. Circuits Syst. Video Technol., vol. 12, Dec. 2002, pp. 1128–1138.
[14] C. Kim and J.-N. Hwang, “Fast and automatic video object segmentation and tracking for content-based applications,” IEEE Trans. Circuits Syst. Video Technol., vol. 12, Feb. 2002, pp. 122–129.
[15] Y. –H. Jan and D. W. Lin, “Edge-and-motion-based semantic video object extraction and application to scene composition,” IEEE Int. Symposium, Sep. 2004, pp. 340–344.
[16] A. Vassiliou, A. Salway, and D. Pitt, “Formalising stories: sequences of events and state changes,” IEEE Int. Conf. on Multimedia and Expo, Jun. 2004, pp. 587–590.
[17] J. Nam and A. H. Tewfik, “Combined audio and visual streams analysis for video sequence segmentation,” in Proc. IEEE Int. Conf. Acoustics, Speech, and Signal Processing, vol. 4, Apr. 1997, pp. 2665–2668.
[18] Y. Wang, J. Ostermann, and Y. –Q. Zhang, Video processing and communications, Prentice Hall, ISBN 0–13–017547–1, pp. 218–263.