臺灣博碩士論文加值系統

由於電影工業的蓬勃發展，每年電影的生產量都以驚人的速度成長，並大量的被數位化以利於流通與保存。但就如一篇論文需要一段簡短的摘要來說明論文主題一般，要想快速了解一部電影的內容，自然也可以透過擷取電影中的精華片段，來達到電影內容摘要的效果。在本篇論文中，我們提出了一個新的自動化電影視訊摘要方法，並透過此一方法擷取出電影的大綱與精華，方便觀眾快速的瀏覽影片內容。
此一方法的流程由前而後可分為5 個步驟:(1)藉由偵測影片中的shot 邊界將影片做正確的切割分段；(2)在每一個shot 中選出一張key-frame 以代表此一shot 的影像內容；(3)利用key-frame 對shot 做視覺上的分類(grouping)；(4)利用對shot transition graph的分析來找出足以呈現劇情重點的shot 片段作為電影摘要；(5)取出影片中的動作要素作為電影摘要。經由前述的5 個步驟，我們可以自動化的完成一部電影的剪輯，並重組成一部有意義的短片以供觀賞。在這篇論文中我們會分別就一部劇情片與一部動作片為例，顯示其摘要結果並做相關之討論。
利用數位化影片適於電腦處理的優勢，我們可以藉由本篇論文所提出的方法，對大量的電影影片做視訊摘要工作，以便省去許多人力上的浪費並提昇工作效率，有助於網路影片販售業者與數位圖書館等方面對影片摘要的大量需求。

1.研究簡介
1.1 關於影片摘要
1.2 影片摘要技術的需求
1.3 影片摘要的問題
1.4 論文架構
2.相關研究
2.1 影片的階層架構
2.2 幾個具代表性的影片摘要方法
2.2.1 HANJALIC AND ZHANG
2.2.2 SMITH AND KANADE
2.2.3 S.PFEIFFER ET AL
3.我們提出的方法
3.1 偵測SHOT 邊界
3.1.1 SHOT 邊界的種類
3.1.2 偵測SHOT 邊界的傳統問題
3.1.3 我們如何偵測SHOT 邊界
3.1.4 三種容易被誤判為SHOT CHANGE 的情況
3.2 KEY-FRAME 的選擇
3.3 SHOT GROUPING
3.4 利用GRAPH ANALYSIS 取出劇情重點
3.5 動作要素的取出
3.6 整個影片摘要的流程
4.實驗結果
4.1 系統介紹
4.2 實驗討論
5.結論
5.1 未來發展的方向
5.2 結論
參考文獻

[1] Jeho Nam; Tewfik, A.H,“Video abstract of video”, IEEE 3rd Workshop on Multimedia Signal Processing, 1999, pp. 117 —122.
[2] Pfeiffer, S.; Lienhart, R.; Fischer, S. and Effelsberg, W., “Abstracting Digital Movies Automatically”, Journal of Visual Communication and Image Representation, Vol. 7, No. 4, Dec, 1996, pp. 345—353.
[3] Zhang, H.J., Kankanhalli, A., and Smoliar, S.W., "Automatic Partitioning of Full-motion Video", Multimedia Systems (1993) Vol. 1, No. 1, pp. 10-28.
[4] Rui, Yong; Huang, Thomas S; Mehrotra, Sharad,“Constructing table-of-content for videos”, Multimedia Systems Vol.7, No. 5, 1999, pp. 359-368.
[5] Hampapur, A., Jain, R., and Weymouth, T., "Digital Video Segmentation", Proc. ACM Multimedia 94, San Francisco, CA, October, 1994, pp. 357-364.
[6] Kasturi, R. and Jain R., "Dynamic Vision", in Computer Vision: Principles, Kasturi R., Jain R., Editors, IEEE Computer Society Press, Washington, 1991.
[7] Arman F, Hsu A, Chiu M-Y (1993) Feature management for large video databases. In: Proc. SPIE Storage and Retrieval for Image and Video Databases.
[8] Yeo B-L (1996) Efficient processing of compressed images and video. Technical report, PhD thesis, Princeton University.
[9] Zabih, R., Miller, J., and Mai, K., "A Feature-Based Algorithm for Detecting and Classifying Scene Breaks", Proc. ACM Multimedia 95, San Francisco, CA, November, 1995, pp. 189-200.
[10] Hanjalic, A.; Hongliang Zhang, "Optimal shot boundary detection based on robust statistical models", IEEE International Conference on Multimedia Computing and Systems, Volume: 2 , 1999, pp. 710 —714.
[11] Swanberg, D., Shu C.F., and Jain, R., "Knowledge Guided Parsing and Retrieval in Video Databases", SPIE Conference on Storage and Retrieval for Image and Video Databases, February, 1993, pp. 173-187.
[12] Hanjalic, A.; HongJiang Zhang, “An integrated scheme for automated video abstraction based on unsupervised cluster-validity analysis”, IEEE Transactions on Circuits and Systems for Video Technology, Vol. 9 No. 8 , Dec. 1999 pp. 1280-1289
[13] Smith, M.A.; Kanade, T., “Video skimming and characterization through the combination of image and language understanding”, Proceedings of the IEEE International Workshop on Content-Based Access of Image and Video Database, 1998, pp. 61 —70.
[14] A. K. Jain, Fundamentals of Digital Image Processing, Information and System Science Series, Prentice Hall, Englewood Cliffs, NJ, 1989.
[15] Rainer Lienhart, “Abstracting home video automatically”, Proceedings of the seventh ACM international conference on Multimedia (Part 2), 1999, pp. 37 —40.
[16] Junzo Kamahara , Yuji Nomura , Kazunori Ueda , Keishi Kandori , Shinji Shimojo , Hideo Miyahara, “A TV News Recommendation System with Automatic Recomposition”, Lecture Notes in Computer Science vol.1554 pp.221-235.
[17] Mark S. Drew, Ze-Nian Li, and Xiang Zhong, “Vidoe Dissolve and Wipe Detection Via Spatio-Temproal Images of Chromatic Histogram Differences”, 2000 International Conference on Image Processing, vol. III, pp.929-932, 2000.
[18] Ba Tu Truong, Chitra Dorai, and Svetha Venkatesh, “Improved Fade and Dissolve Detection for Reliable Video Segmentation”, 2000 International Conference on Image Processing, vol. III, pp.961-964, 2000.
[19] Minerva Yeung, Boon-Lock Yeo, and Bede Liu, “Extracting story units from long programs for video browsing and navigation”, Proceedings of the Third IEEE International Conference on Multimedia Computing and Systems, pp.296 —305, 1996.