臺灣博碩士論文加值系統

Shot 通常是被使用在分析(analyze)及索引(index)影片(video)的一種方法。而其目的就是把一個影片，讀進來後經由一些判斷方法，能夠將影片分段，一個影片現在可能是在拍一個地方，等下又去拍了別的地方，一個影片的某幾個frame區間是在拍同一個地方。我們要分析一個影片，知道裡面的內容，可能有某一段是在拍風景的，某段是在拍動作比較多的，某個區間可能是在演講的‧‧‧ 等等，然而在shot change時，時常會因為Flashlight的發生而產生誤判，也就是明明是the same shot卻誤判為shot change。
本論文的目標主要著重在Flashlight的偵測，而我們用一個簡單的方法以及兩個門檻值並結合現行常用的SVM來做分類，經由我們提供的演算法可以蠻準確的判別影片中是否有Flashlight(閃光)，然而在Cut的預測中仍有多重的問題，我們會去分析這些問題以期望能改善之，使我們的演算法能更powerful。

第一章 緒論------1
1.1 研究動機------1
1.2 flashing lights 對 shot boundary detection 的影響------2
1.3論文架構------3
第二章 相關文獻------4
2.1 相關名詞------4
2.2 shot boundary 的種類------5
2.3 現行常用的Flashlight偵測方法------10
2.3.1 使用Cut Model 與 Flashlight Model 來偵測 shot boundary------10
2.3.2 利用flashlight的特性來偵測flashlight------17
2.3.3 利用edge的方式來偵測flashlight------19
2.3.4 其他偵測flashlight的方法------21
第三章 我們的方法------22
3.1 特徵抽取------23
3.1.1 Color feature------23
3.1.2 Edge feature------29
3.2 SVM 基本概念介紹------35
3.3 演算法流程------42
第四章 實驗結果------48
4.1 實驗數據------48
4.2 結果討論------61
第五章 結論------71
第六章 參考文獻------74

[01] F. Arman, A. Hsu, and M.Y. Chiu, "Image processing on compressed data for large video databases", Proceedings of 1st ACM International Conference on Multimedia, Anaheim,CA, pp.267-272, 1993.
[02] Dong Zhang, Wei Qi, Hong Jiang Zhang, "A New Shot Boundary Detection Algorithm" , Lecture Notes In Computer Science; Vol.2195,pp.63-70, Springer-Verlag London, UK ublisher ,2001
[03] H. J. Zhang, A. Kankanhalli, S. W. Smoliar, "Automatic Partitioning of Full-motion Video", ACM Multimedia System, Vol. 1, No.1, pp. 10-28, 1993.
[04] Ba Tu Truong and Svetha Venkatesh, "DETERMINING DRAMATIC INTENSIFICATION VIA FLASHING LIGHTS IN MOVIES", International Conference on Multimedia and Expo,2001 IEEE
[05] Geng Yuliang; Xu De , "A SOLUTION TO ILLUMINATION VARIATION PROBLEM IN SHOT DETECTION", TENCON 2004. 2004 IEEE Region 10 Conference Volume B, 21-24 Nov. 2004 Page(s):81 - 84 Vol. 2
[06] Wei Jyh Heng, King N. Ngan, "High accuracy flashlight scene determination for shot boundary detection", 2003 Elsevier Science B.V. All rights reserved.
[07] A. Jacobs, A. Miene, G. T. Ioannidis, and O. Herzog , "Automatic shot boundary detection combining color, edge, and motion features of adjacent frames", In TRECVID 2004 Workshop Notebook Papers, pp. 197--206, Gaithersburg, Maryland, USA, National Institute of Standards and Technology, nov 2004.
[08] Ming Luo, Daniel DeMenthon, and David Doermann. "Shot boundary detection using pixel-to-neighbor image differences in video". In TREC Video Retrieval Evaluation Online Proceedings: TRECVID 2004, 2004.
[09] Nunnapus Benjamas, Nagul Cooharojananone, Chuleerat Jaruskulchai, "Flashlight detection in Indoor Sport Videos for highlight Generation", ECTI-CON, pp. 534-537, May 12-13, 2005
[10] Tong Lin, Hong-Jiang Zhang, Qing-Yun Shi, "Video Scene Extraction by Force Competition", IEEE International Conference on Multimedia and Expo,pp.490-497,Tokyo,Japan,August, 2001.
[11] Y.C. Lai., "Scene Segmentation using Mosaic Technique", Master thesis, Fu Jen Catholic University, 2004.
[12] Xia Wan, and C.-C. Jay Kuo, "A new approach to image retrieval with hierarchical color clustering", IEEE Transactions on Circuits and Systems for Video Technology, Vol. 8, No.5, pp.628-643, September 1998.
[13] C.S. Li, et al. "Vision and Cognition ", Yuan Liou Publishing, Taipei, Taiwan, 1999.
[14] Ramesh Jain, Rangachar Kasturi, Brian G. Schunck, "Machine Vision", pp.169-173.
[15] 劉彥秀，2003，『最小二乘模型與影像套合之後續探討』，國立成 功大學測量工程學系碩士論文，第23-29頁。
[16] Chih-Jen Lin, "A Practical Guide to Support Vector Machines", August 28, 2004
[17] Chang, C.-C. and C.-J. Lin (2006). LIBSVM(2.82): a library for
support vector machines. Software available at
http://www.csie.ntu.edu.tw/~cjlin/libsvm.