臺灣博碩士論文加值系統

由於電腦運算速度的日益提昇，數位化多媒體資料的使用率也跟著大幅增加，以多媒體影片來說，對影片中場景的分類及辨識是一個複雜度較高的問題，但對於影片中事件的偵測而言，這卻是相當重要的一環。
本論文主要是針對棒球比賽的轉播影片，根據影片中顏色的分佈、移動向量以及時空切片圖等資訊，從影片中自動判斷出一些不同的場景。由此方法可有效地辨識出pitching view、outfield view、infield view、running view、touch-base view及audience view。最後觀察這些場景出現的順序，利用有限狀態自動機系統做精彩片段的偵測，在本文中所要偵測的精彩片段為diamond play、high fly ball、nice hit及home run等四種。

第一章、緒論 1
1.1 動機與目的 1
1.2　關於棒球比賽影片中的場景及精彩片段 2
1.3　論文架構 2
第二章、相關研究探討 3
2.1 鏡頭邊界偵測 3
2.2 移動估測 4
2.3 時空切片分析 5
2.4 場景分類（shot classification） 8
2.5 精彩片段偵測（highlight detection） 11
第三章、我們的方法 15
3.1 分類特徵 15
3.1.1 球場顏色特徵 15
3.1.2 動作活動量特徵 17
3.1.2.1移動向量（motion vector） 17
3.1.2.2 motion vector計算 18
3.1.3 時空切片分析 19
3.2 場景分類（shot classification） 21
3.3　精彩片段偵測 32
第四章、實驗結果 37
4.1　系統介紹 37
4.2　實驗討論 38
4.2.1　Shot Classification 38
4.2.2　Highlight Detection 39
第五章、結論與未來方向 41
參考文獻 42

[1] H.J. Zhang, A. Kankanhalli and S.W. Smoliar , “Automatic Partitioning of Full-motion Video”, Journal of Multimedia System , vol. 1, Issue 1, pp. 10-28, June 1993.

[2] Ze-Nian Li and Mark S. Drew, Fundamentals of Multimedia, Prentice Hall, pp. 288-292, 2003.

[3] Alan Hanjalic, “Generic Approach to Highlights Extraction from a Sport Video”, Proceedings of IEEE International Conference on Image Processing, Vol.1, pp. 1-4, Sept. 2003.

[4] Jan Erik Voldhaug, Stian Johansen and Andrew Perkis , “Automatic Football Video Highlights Extraction”, Proceedings of Norsk Symposium, Sept. 2005.

[5] Nguyen Huu Bach, Koichi Shinoda and Sadaoki Furui , “Robust Highlight Extraction Using Mult-stream Hidden Markov Models from Baseball Video”, Proceedings of IEEE International Conference on Image Processing, Vol.3, pp. 173-176 , Sept. 2005.

[6] Chih-Chieh Cheng and Chiou-Ting Hsu , “Fusion of Audio and Motion Information on HMM-based Highlight Extraction for Baseball Games” , IEEE Transactions on Multimedia, Vol. 8, pp. 585-599 , June 2006.

[7] Peng Chang, Mei Han and Yihong Gong, “Extract Highlights from Baseball Game Video with Hidden Markov Models”, Proceedings of International Conference on Image Processing, Vol. 1, pp. 609-612, 2002.

[8] Hung-Chia Shih and Chung-Lin Huang, “Detection of the Highlights in Baseball Video Program”, Proceedings of IEEE International Conference on Multimedia and Expo, Vol. 1, pp. 595-598, June 2004.

[9] Chueh-Wei Chang, Rong Lee and Hui-Ying Kao, “A Baseball Video Scene Classification Method based on Baseball Game Events” , Journal of Information Technology and Applications, Vol.2, No.1, pp.23-31, 2007.

[10] Cheng-Chang Lien, Chiu-Lung Chiang and Chang-Hsing Lee, “Scene based Event Detection for Baseball Videos”, Journal of Visual Communication and Image Representation, Vol. 18, pp. 1-14, 2007.

[11] Chien-Hao Chen and Cheng-Chang Lien, “The Multiresolution and Flooding Based RSST(MFRSST) Image Segmentation Method” , Chung Hua Journal of Science and Engineering, vol. 1, No. 1, pp.9-16 , 2003.

[12] Shou-Ling Peng , “Temporal Slice Analysis of Image Sequences”, Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 283-288, June 1991.

[13] Chong-Wah Ngo, Ting-Chuen Pong and Hong-Jiang Zhang, “On Clustering and Retrieval of Video Shots Through Temporal Slices Analysis”, IEEE Transactions on Multimedia, Vol. 4, Issue 4, pp. 446-458 , Dec. 2002.