簡易檢索 / 詳目顯示

研究生: 趙崇淵
Chung-Yuan Chao
論文名稱: 利用動態貝氏網路來解釋足球節目
Semantic Analysis of Soccer Video Programs Using Dynamic Bayesian Networks
指導教授: 黃仲陵
Chung-Lin Huang
口試委員:
學位類別: 碩士
Master
系所名稱: 電機資訊學院 - 電機工程學系
Department of Electrical Engineering
論文出版年: 2004
畢業學年度: 93
語文別: 英文
論文頁數: 51
中文關鍵詞: 動態貝氏網路解釋足球節目
外文關鍵詞: Dynamic, Bayesian Networks, Semantic Analysis, Soccer Video Programs
相關次數: 點閱:2下載:0
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報
  • 由於視訊資料大量數位化,數位資料暴增,但若結合各種最新之壓縮及視訊處理標準,編碼及壓縮的目標不難達成,所以現階段最急於解決的是我們如何在最短的時間內找到最符合我們需求的Content,也就是說,如何快速地、有效率地存取了斛我們所要的數位資料成為一項重要的課題。因此,我的研究主要是去建立一個能夠認知、分類及總結視訊資料的系統,我限定的應用範疇在足球影片的視訊資料,因為運動節目具有高重覆性,高相關性的鏡頭特性,對我在做分析時較有利。
    我的論文方向是利用動態貝氏網路(Dynamic Bayesian Network)的架構,推演出不易直接觀測到的高階語意特徵,例如,射門、角球、十二碼罰球、犯規鏡頭等,進而推論出視訊的高階特性來做來做運動節目的語意認知。也就是動態貝氏網路可以建構起高低特徵的橋梁和結合不同的特徵資訊,進而達到semantic analysis 的目的。測試視訊先經過我們所設計的各種特微分析器求得一些低階的資訊,我們把些資訊視為動態貝氏網路的輸入,籍由在訓練程序所求得的一些機率分佈,向上推演得到我們所要的類別資訊。除了單純考慮一個時間點的貝氏網路外,我也希望利用貝氏網路時間上的相關性(time dependency),也就是動態貝氏網路來判斷視訊的特性,如此可以得到較好的結果。


    Contents Chapter 1. Introduction 1 1.1 Motivation 1 1.2 Previous Work 1 1.3 The proposal of our understanding model 3 1.4 Why soccer? 4 1.5 Organization of this thesis 4 Chapter 2. A Framework for Dynamic Bayesian Network 6 2.1 Bayesian Network 6 2.2 Dynamic Bayesian Network 7 2.3 Building up a Dynamic Bayesian Network 10 Chapter 3. Feature Extraction 12 3.1 Close-up Finding 12 3.2 Panning Motion Identification 16 3.3 Audience Identification 18 3.4 Replay Finding 19 3.5 Parallel Lines Detection for Gate Finding 21 3.6 Board Identification 23 3.7 Referee Identification 24 3.8 Audio 25 3.9 Static camera information 26 Chapter 4. Semantic analysis of Soccer Video Programs Using Dynamic Bayesian Network 28 4.1 Training Phase 29 4.1.1 Quantitative Training 29 4.1.2 Qualitative Training 31 4.2 Dynamic Bayesian Network Model 33 4.3 Temporal Inference Network Model 36 4.3.1 Goal Event Example 37 4.3.2 Card Event Example 40 4.4 Understanding Phase 42 Chapter 5. Experimental Results 43 5.1 Frame-based event detection 43 5.2 Sequence-based event detection 45 Chapter 6. Conclusion and Future work 48 Reference……………………….................................................................................49

    Reference
    [1] Milan Petkovic, Vojkan Mihajlovic, Willem Jonker, S.Djordjevic-Kajan, “Multi-Model Extraction of Highlights from Formula 1 Programs,” in Proceedings IEEE International Conference on Multimedia and Expo/, Lausanne, Switzerland 2002.
    [2] Ashutosh Garg, Vladimir Pavlovic, James M.Rehg, “Boosted Learning in Dynamic Bayesian Networks for Multimodal Speaker Detection,” in Proc. IEEE Vol. 91, No. 9, SEPTEMBER 2003.
    [3] J. Forbes, T. Huang, K. Kanazawa, and S.J. Russell, “The BATmobile: Toward a Bayesian automated taxi,” in Proc. IJCAI, 1995.
    [4] V. Mihajlovic, M. Pekovic, “Dynamic Bayesian Networks: A State of the Art,” Computer Science Department, University of Twente, The Netherlands, 2001.
    [5] Lawrence R. Rabiner, “A Tutorial on Hidden Markov Models and Selected Applications in Speech Recognition,” in Proc. IEEE Vol. 77, No. 2, FEBRUARY 1989.
    [6] Lexing Xie, Shih-Fu Chang, Ajay Divakaran, Huifang Sun, “Structure analysis of soccer video with Hidden Markov Models,” in Proc. IEEE Int. Con. Acoustics, Speech, and Signal Processing (ICASP), 2002.
    [7] Kevin Murphy, 1998 “A Brief Introduction to Graphical Models and Bayesian Network,” http://www.cs.berkeley.edu/~murphyk/Bayes/bayes.html, University of California at Berkeley, 2000.
    [8] Xinghua Sun, Guoying Jin, Mei Huang, Guangyou Xu, “Bayesian network based soccer video event detection and retrieval,” Multispectral Image Processing and Pattern Recognition, Beijing, China, October 2003.
    [9] Ahmet Ekin, A. Murat Tekalp, Rajiv Mehrotra, “Automatic Soccer Video Analysis and Summarization,” IEEE Trans. On Image Processing, Vol. 12, No. 7, July 2003.
    [10] Ahmet Ekin, ”Sports Video Processing for Description, Summarization, and Search,” University of Rochester, New York, 2003.
    [11] Jurgen Assfalg, Marco Bertini, “Semantic annotation of soccer videos: automatic highlights indentification,” Computer Vision and Image Understanding 91(3) 2003.
    [12] Peng Xu, Lexing Xie, Shih-Fu Chang, “Algorithms and System for Segmentation and Structure Analysis in Soccer Video,” in Proc. IEEE Int. Conf. Mult. Expo (ICME), Tokyo, Japan, Aug 2001.
    [13] Kongwah WAN, Joo-Hwee LIM, Changsheng XU, Xinguo YU, “Real-Time Camera Field-view Tracking in Soccer Video,” in Proc. ICASSP, Vol.3, pp 185-188, Hong Kong, 2003.
    [14] D. Yow, B.-L. Yeo, M. Yeung, and B. Liu, “Analysis and presentation of soccer highlights from digital video,” in Proc. Asian Conf. On Comp. Vision (ACCV) 1995.
    [15] W.Zhou, A. Vellaikal, and C.-C.J. Kuo, “Rule-based video classification system for basketball video indexing,” in ACM Mult. Conf., Los, Angeles, USA, November 2000.
    [16] V. Mihajlovic, M. Petkovic, “Automatic Annotation of Formula 1 Races for Content-Based Video Retrieval,” Technical Report, TR-CTIT-01-41, 2001.
    [17] D.Zhong and S.-F. Chang, “Structure analysis of sports video using domain models,” in Proc. IEEE Int. Conf. Mult. Expo (ICME), Tokyo, Japan, Aug. 2001.
    [18] C.G.M. Snoek and M. Worring, “Time interval maximum entropy based event indexing in soccer video,” in Proc. IEEE Int. Conf. Mult. Expo (ICME), Baltimor, USA, July 6-9, 2003.
    [19] Shinichi Takagi, Shinobu Hattori, “Sports video categorizing method using camera motion parameters,” in Proc. IEEE Int. Conf. Mult. Expo (ICME), Baltimor, USA, July 2003.
    [20] David A. Sadlier, Noel O’Connor, Sean Marlow, Noel Murphy, “A combined audio-visual contribution to event detection in field sports broadcast video. Case study: Gaelic Football,” IEEE International Symposium on Signal Processing and Information Technology, Darmstadt, Germany, December 2003.
    [21] Chuan Wu, Yu-Fei Ma, Hong-Jiang Zhang, Yu-Zhuo Zhong, “Events recognition by semantic inference for sports video,” in Proc. IEEE Int. Conf. Mult. Expo (ICME), 2002.
    [22] Hao Pan, Baoxin Li, M.Ibrahim Sezan, “Automatic Detection of Replay Segments in Broadcast Sports Programs by Detection of Logos in Scene Transitions,” in Proc. IEEE Conf. Acoustics, Speech, and Signal Processing (ICASSP 2002).
    [23] H. Pan, P. van Beek, and M.I.Sezan, “Detection of slow-motion replay segments in sports video for highlights generation,” in Proc. IEEE ICASSP 2001,Salt Lake City, UT, May 2002.
    [24] K.N. Plataniotis and A.N. Venetsanopoulos, Color Image Processing and Applications. Berlin, Germany: Springer-Verlag,2000, pp.25-32 and 260-275.

    無法下載圖示 全文公開日期 本全文未授權公開 (校內網路)
    全文公開日期 本全文未授權公開 (校外網路)

    QR CODE