臺灣博碩士論文加值系統

科技的進步使得多媒體內容的資訊量越來越豐富，造成使用者在眾多的媒體資源中，無法以較有效的方法找到對使用者本身有意義的資訊，因此，如何有效的管理多媒體的內容成為非常重要的課題，本論文使用本體論(Ontology)的知識，建構出一套全新的分鏡本體論(Shot Ontology)描述方法，輔以多媒體搜尋展示系統，藉以解決冗長的籃球影片觀賞時間。我們以影像的色彩為分類特徵，將籃球影片的分鏡類別區分為長分鏡(Long Shot)、及特寫分鏡(Close Up Shot)，並結合了得分板變化的擷取，使得在觀看籃球節目時能夠只針對節目的比賽片段或者特寫片段觀賞，對於時間的節省有著很大的幫助；在分鏡類別的決定方法上，我們利用投票策略(Voting Scheme)統計出畫格中的主要顏色(Dominant Color)，利用有效的膚色偵測方法取出膚色範圍，並以每一個分鏡為單位，取出其中一張畫格(Frame)將分鏡的類別決定，實驗結果證實我們的方法可以有效的將得分事件、長分鏡、以及特寫分鏡偵測出，並且能夠達成影片索引的目的，最後透過我們開發的展示系統，成功的將有興趣的片段展示出來。

Since the mass growing amount of video information has been produced at the present day, how to analysis and to make event mining in video content management issues are become more and more important. In this paper, we reconstructed a novel description based on the shot ontology for the basketball video. Shot ontology is inferred by shot manipulations those included: shot detection, shot type classification, score board detection and motion statistics .The video content management system provided event feature manipulations at multiple levels: signal, structural, or semantic in order to meet user preferences while striking the overall utility of the video. The experiment results showed that our proposed methodologies could correctly detect goal event, long shot, and close up shot and also achieve the purpose of video indexing and weaving what user preferences.

論 文 摘 要 I
ABSTRACT II
致謝 III
目錄 IV
圖目錄 VII
表目錄 IX
第一章 緒論 1
1.1 動機 3
1.2 論文架構 5
第二章 相關研究 (Related Work) 7
2.1 本體論 (Ontology) 7
2.2 視訊檔案格式介紹 11
2.2.1 MPEG-1 11
2.2.2 MPEG-4 12
2.2.3 MPEG-7 12
2.3 影片分析相關研究探討 14
2.3.1 分鏡偵測(Shot boundary detection) 14
2.3.1.1 未壓縮領域下的分鏡偵測方法 15
2.3.1.2 壓縮領域下的分鏡偵測方法 17
2.3.2 自動色彩模型(Automatic Color Modeling) 18
2.3.3 鏡頭分類(Shot Classification) 18
2.3.4 比賽以及中斷時機偵測(Play-Break Detection) 19
2.3.5 慢動作及重播偵測(Slow-Motion Replay Detection ) 19
2.3.6 移動物件切割與追蹤(Moving Object Segmentation and Tracking) 20
2.3.7 影片語意分析(Video Semantic analysis) 20
第三章 分鏡本體論 (Shot Ontology) 22
3.1 籃球本體論 22
3.1.1 應用本體論的內涵 24
3.1.2 事件序列的合併 25
3.2 分鏡本體論的建立 27
3.2.1 分鏡分類 (Shot Classification) 29
3.2.2 動量 (Motion) 31
3.2.3 得分板變化 (Score Board) 31
3.2.4 時間上的關係 (Temporal Relation) 32
3.3 分鏡索引 (Shot Indexing) 34
3.4 分鏡編織 (Shot Weaving) 36
第四章 特徵擷取 (Feature Extraction) 39
4.1 分鏡分類 (Shot Classification) 39
4.1.1 色彩空間 (Color Space) 39
4.1.2 球場顏色 (Court Color) 41
4.1.3 皮膚顏色 (Skin Color) 45
4.1.4 分鏡分類判斷 47
4.1.5 判斷結果探討 49
4.2 得分板偵測 50
4.2.1 得分板變化判斷 53
4.2.2 判斷結果探討 55
4.3 動量偵測 (Motion Detection) 57
第五章 系統實作與評估 59
5.1 系統環境 59
5.2 多媒體內容索引系統介紹 59
5.3 展示平台介紹 62
5.4 實驗結果 64
5.5 討論 65
第六章 結論及未來探討 67
參考文獻 68

[1]林昱璋，「影片中分鏡偵測方法之研究」，國立成功大學工程科學研究所碩士論文，民國九十一年
[2]Ullas Gargi, et.al. “Performance Characterization of Video-Shot-Change Detection Methods” IEEE Transaction on Circuits and Systems for Video Technology, Vol. 10, No. 1, February 2000.
[3]Rainer Lienhart ”Comparison of Automatic Shot Boundary Detection Algorithms” Storage and Retrieval for Still Image and Video Databases VII 1999, Proc. SPIE 3656-29, Jan. 1999
[4]J.R. Bach, et.al “The Virage image search engine: An oprn framework for image management,“ in Proc. SPIE Conf. On Vis. Commun,and Image Proc.
[5]M. Flicker, et.al “Query by Image and Video Content: The QBIC System,” IEEE Computer, Vol.28,No9,pp.23~32, 1995
[6]A.Pentland, et.al “Photobook: Content-based manipulation of image databases,” International Jounal of Computer Vision 1996.
[7]J. R. Smith and S,F, Chang, “Visual SEEK: a fully automated content-base image query system,” Proceeding of ACM International Conference Multimedia, boston, MA, pp.87~98, November. 1996
[8]Blobworld http://elib.cs.berkeley.edu/photos/blobworld/
[9]L. Wang, et.al “Automatic extraction of semantic colors in sports video,” in IEEE International Conference on Acoustic, Speech and Signal Processing (ICASSP’04), Montreal, Canada, May 2004.
[10]Yang Liu, et.al. “Playfield Detection Using Adaptive GMM and Its Application” ICASSP2005, Philadelphia, PA, USA, Mar.19-25,2005
[11]A. Ekin, et.al “Automatic soccer video analysis and summarization,” IEEE Transactions on Image Processing, vol. 12, no. 7, pp. 796–807, July 2003.
[12]A. Ekin, et.al ”Shot Type Classification By Dominant Color for Sports Video Segmentation and Summarization” Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03). 2003 IEEE International Conference on Volume 3, 6-10 April 2003 Page(s):III - 173-6 vol.3
[13]A. Ekin, et.al "Robust dominant color region detection and color-based applications for sports video" Image Processing, 2003. ICIP 2003. Proceedings. 2003 International Conference on Volume 1,14-17 Sept. 2003 Page(s):I - 21-4 vol.1
[14]Hong Lu, Yap-Peng Tan:” Unsupervised clustering of dominant scenes in sports video”. Pattern Recognition Letters 24(15): 2651-2662 (2003)
[15]Hong Lu, Yap-Peng Tan: “An unsupervised approach to dominant video scene clustering”. ISCAS (2) 2003: 680-683
[16]A. Ekin, et.al”Generic Play-Break Event Detection for Summarization and Hierarchical Sports Video Analysis” IEEE International Conference on Multimedia and Expo. (2003)
[17]H. Pan, et.al "Detection of slow motion replay segments in sports video for highlights generation" in IEEE International Conference on Acoustic, Speech and Signal Processing (ICASSP'01),Salt Lake City,Utah,May 2001,vol.3, pp.1649–1652.
[18]V. Kobla, et.al"Detection of slow-motion replays for identifying sports videos,"Proceedings of IEEE Third Workshop on Multimedia Signal Processing, pp.135-140, l999.
[19]V.Mezaris, et.al "Video object segmentation using Bayes-based temporal tracking and trajectory-based region merging" IEEE Trans. Circuits Syst. Video Technol., vol. 14, no. 6, pp. 782-795, Jun.
[20]R. Wang,et.al "A confidence measure based moving object extraction system built for compressed domain" in Proc.IEEE Int. Symp. Circuits and Syst., vol. 5, pp.21-24, May 2000.
[21]V. Mezaris,et.al "Real-Time Compressed-Domain Spatiotemporal Segmentation and Ontologies for Video Indexing and Retrieval" IEEE Trans. on Circuits and Syst. for Video Technol., vol. 14, no. 5, pp. 606-621, May 2004.
[22]V. Mezaris, et.al "Object Segmentation and Ontologies for MPEG-2 Video Indexing and Retrieval," CIVR '04, pp. 573-581, 2004
[23]M.R.Naphade,et.al "A factor graph framework for semantic video indexing," IEEE Trans. on Circuits and Syst. for VideoTechnol., vol. 12, no. 1, pp. 40-52, Jan. 2002.
[24]M.R.Naphade,et.al "Modeling semantic concepts to support query by keywords in video," in Proc. IEEE Int. Conf. on Image Processing ICIP '02, vol. 1, pp. 145-148, Rochester, NY,Sept. 2002.
[25]Min Xu et.al.” Event Detection in Basketball Video Using Multiple Modalities” Information, Communications and Signal Processing, 2003 and the Fourth Pacific Rim Conference on Multimedia. Proceedings of the 2003 Joint Conference of the Fourth International Conference on Volume 3, 15-18 Dec. 2003 Page(s):1526 - 1530 vol.3
[26]Peng Xu et.al "Algorithms and System for High-Level Structure Analysis and Event Detection in Soccer Video" Columbia University, ADVENT – Technical Report #111, June 2001
[27]D.Zhang et.al "Detecting Sound Events in Basketball Video Archive", Technical Report, Columbia University,University,http://www.ee.columbia.edu/~dqzhang/ publication/dqzhang_AudioProcess2001.pdf
[28]Xingquan Zhu et.al "Video data mining: semantic indexing and event detection from the association perspective" Knowledge and Data Engineering, IEEE Transactions on Volume 17,Issue 5,May 2005 Page(s):665-677
[29]Xinghua Sun et.al , “Bayesian network based soccer video event detection and retrieval,” Multispectral Image Processing and Pattern Recognition, Beijing, China, October 2003.
[30]Ashutosh Garg et.al “Boosted Learning in Dynamic Bayesian Networks for Multimodal Speaker Detection,” in Proc. IEEE Vol. 91, No. 9, SEPTEMBER 2003.
[31]V. Mihajlovic et.al“Dynamic Bayesian Networks: A State of the Art,” Computer Science Department, University of Twente, The Netherlands,2001.
[32]L.Xie,et.al "Structure Analysis of Soccer Video with Domain Knowledge and Hidden Markov Models", Pattern Recognition Letters.
[33]L.Xie,et.al "Structure Analysis of Soccer Video with Hidden Markov Models", Proc. Interational Conference on Acoustic, Speech and Signal Processing, (ICASSP-2002), Orlando, FL, USA, May 13-17, 2002.
[34]P.Xu,et.al "Algorithms and Systems for Segmentation and Structure Analysis in Soccer Video", IEEE International Conference on Multimedia and Expo, Tokyo, Japan, Aug. 22-25, 2001.
[35]Chandrasekaran,et.al "What are Ontologies, and Why Do We Need Them?" IEEE Intelligent Systems, vol. 14, no. 1, 1999.
[36]Staab,S.,et.al “Why evaluate ontology technologies? Because it works!”, Intelligent Systems, IEEE, vol. 19, no. 4, pp. 74-81, 2004.
[37]T.R.Gruber.”A translation approach to portable ontologies”.Knowledge cquisition, 5(2):199-220, 1993.
[38]阮明淑，「ontology 應用於知識組織之初探」，佛教圖書館館訊第三十二期，民國九十一年
[39]Barry Smith,”Preprint version of chapter “Ontology”, in L. Floridi (ed.),Blackwell Guide to the Philosophy of Computing and Information, Oxford: Blackwell, 2003, 155–166.
[40]李建中，「本體論為基礎之電子化知識管理模式－以國軍資訊組織導入12207 與J2EE 為例」，國防大學碩士論文，民國九十二年
[41]Forsyth, D.A. and Fleck, M. M., “Automatic Detection of Human Nudes,”International Journal of Computer Vision , 32 , 1, 63-77, August, 1999
[42]Bimbo, A.D., Visual Information Retrieval, Morgan Kaufmann Publishers, Inc., San Francisco, California, 1999.
[43]胡冠宇，「基於膚色之裸體影像偵測之研究」， 國立成功大學碩士論文，民國九十三年
[44]A. Albiol, L. Torres, and E.J. Delp, “Optimum Color Spaces for Skin Detection,”Image Processing, 2001. Proceedings. 2001 International Conference on, IEEE,Thessaloniki Greece, Vol. 1, pp. 122-124, Oct. 2001.
[45]Nicola Guarino,”Formal Ontology and Information Systems,”Proceedings of FOIS’98,Trento,Italy,6-8 June 1998,Amsterdam,IOS Press,3-15.
[46]許正欣，「語意網上自動化建構本體論之研究」，輔仁大學碩士論文，民國九十三年