跳到主要內容

臺灣博碩士論文加值系統

(44.200.171.74) 您好!臺灣時間:2022/08/12 07:45
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

我願授權國圖
: 
twitterline
研究生:施皇嘉
研究生(外文):Huang-Chia Shih
論文名稱:利用貝氏信度網路來解釋運動節目
論文名稱(外文):Video Understanding of Sports Programs Using Bayesian Belief Network
指導教授:黃仲陵黃仲陵引用關係
指導教授(外文):Chung-Lin Huang
學位類別:碩士
校院名稱:國立清華大學
系所名稱:電機工程學系
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2002
畢業學年度:90
語文別:英文
論文頁數:60
中文關鍵詞:貝氏網路視訊認知語意
外文關鍵詞:Bayesian NetworkVideo UnderstandingSemantic
相關次數:
  • 被引用被引用:0
  • 點閱點閱:202
  • 評分評分:
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
這份論文我們利用貝氏網路去建構了一個可以用來推演的架構,推演出不易直接觀測到的高階語意特徵,例如,內野或外野鏡頭、近照特寫鏡頭或是遠照俯瞰鏡頭,進而推論出測試視訊的高階特性來做運動節目的語意認知,顛覆了從前只由視訊低階特性做比對的方式;我們並提出一種不需求出運動參數(affine-parameter)的運動物體萃取(moving object extraction)演算法及一個有效的轉場偵測(scene change detection)的方法,來支援我們的低階特徵分析器來做低階特徵的萃取,視我們所要分析的運動節目的不同而建立不同的貝氏網路架構,經由大量資料的訓練來求得當中的各連線所具有的機率分佈,進而提供使用者來認知一段測試視訊的影片特性及種類來達成認知的目的。
  在我們的貝氏網路中大略地畫分成三個階層,由高到低分別是類別層(category layer)、中階語意層(mid-level semantic layer)和低階特徵層(low-level feature layer)。在訓練程序時是由上而下地去取得每一個點的事前機率(prior probability)和每兩點間的條件機率(conditional probability);而在測試程序中,是由下而上,測試視訊先經過我們所設計的各種特徵分析器求得一些特徵值,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語意訊訊及類別資訊。
  這份論文我們所針對的視訊資料是棒球影片,因為棒球影片的鏡頭具有高重覆性的特質,對於用來做認知跟解釋比較有意義,將來它的應用層面可以拓展到其他運動節目,如足球、網球,或是更一般性的影片。

The exploitation of semantic information in computer vision problems can be difficult because of the large difference in representations, levels of knowledge and abstract episodes. Traditional image/video understanding, indexing is formulated in terms of low-level features describing image/video structure and intensity, while high-level knowledge such as common sense and human perceptual knowledge are encoded in abstract, non-geometric representations. In this thesis, we attempt to bridge this gap through the integration of image/video analysis algorithms with multi-level Bayesian Brief Network (BBN), a large semantic network that explicitly links related words in a hierarchical structure. Our problem domain is the understanding of sports programs, as this provides both linguistic information in site information and special efficacy of view. Visual detection algorithms such as scene change detection, moving object segmentation and morphology analysis combined with low—level feature extract algorithms are applied to the video to extract the basic object/background information as the input to the Bayesian Belief Network. Our video understanding system is designated for the baseball game video program, in which the events may be the scenes of pitcher pitching, batter running, or the outfielder catching the ball, etc. Given a video in a specific domain, our system may extract the low-level evidences and then interpret the input video by high-level semantic.

Contents
Chapter 1. Introduction 1
1.1 Motivation 1
1.2 Previous Work 1
1.3 The Proposal of our understanding model 2
1.4 Organization of this thesis 3
Chapter 2. A Framework for Bayesian Belief Network 4
2.1 Introduction Bayesian Belief Network (BBN) 4
2.2 Building up a Bayesian Network 8
Chapter 3. Pre-processing and Feature Extraction 10
3.1 Scene Change Detection 11
3.1.1 One- dimension intensity projection 12
3.1.2 Using Hybrid SAD value detect scene change 12
3.2 Texture Information 15
3.2.1 Gray-Level Co-occurrence Matrix 15
3.2.2 Edge Histogram Descriptor 16
3.3 Color Information 16
3.4 Motion Information 17
3.5 Audio Information 21
3.6 Moving Object Segmentation 21
3.6.1 A Spatial-Temporal Segmentation Method 21
3.6.2 Morphological Filtering 26
Chapter 4. Video Understanding of Sports Programs using 28
Bayesian Network
4.1 Bayesian Belief Network Model 29
4.2 Training Phase 37
4.3 Understanding Phase 38
Chapter 5. Experimentation 39
Chapter 6. Conclusion and Feature works 46
Appendix I. Using Simple Linear Regression to Obtain Displacement
Characteristic Curve 47
References 50

Reference
[1] H. Zhang, A Wang, and Y. Altunbasak, “ Content-based video retrieval and compression, “ IEEE ICIP Santa Barbara, Oct. 1997.
[2] D. Zhong and S. F. Chang, “Spatio-temporal video search using the object-based video representation,” IEEE ICIP Santa Barbara, Oct. 1997.
[3] M. R. Naphade, I. Kozintsev, and T. S. Huang, “A Factor Graph frame work for demantic indexing,” IEEE Trans. on CAS for VT, pp.40-52, Jan. 2002.
[4] N. Vasconcelos and A. Lippman, “Bayesian modeling of video editing and structure: semantic features for video summarization and browsing,” IEEE ICIP, pp. 550-555, Chicago, 1998.
[5] F. V. Jensen, K. G. Olesen, and S. K. Andersen, “An Algebra of Bayesian Belief Universes for Knowledge-Based Systems,” Networks, vol. 20, pp.637-659, 1990.
[6] A. M. Ferman and A, M, Tekalp, “Probabilistic analysis and extraction of video content,” IEEE ICIP Tokyo, Japan, OCT., 1999.
[7] S. F. Chang and H. Sundaram, “Structural and Semantic Analysis of Video,” IEEE ICIP, Vancouver, Sept. 2000.
[8] J. Luo, A. E. Savakis, S. P. Etz, and A. Singhal, “On the application of Bayes Networks to Semantic Understanding of Consumer Photographs,” IEEE ICIP, Sept. Vancouver, Canada, 2000.
[9] A. Ekin, A. M. Tekalp, and R. Mehrotra, “Extraction of Semantic Description of Event using Bayseian Network,” IEEE, ICIP 2001.
[10] B. L. Yeo and B. Liu, “Rapid Scene Analysis on Compressed Video”, IEEE Trans. on Circuit and System for Video Technology, Vol. 5, No. 6, December 1995, pp 533-544.
[11] Chung-Lin Huang and Bing-Yao Liao, “A Robust Scene-Change Detection Method for Video Segmentation”, IEEE Trans. on Circuits and System for Video Technology, Vol. 11, No. 12, Dec. 2001.
[12] M. K. Kim, E. Kim, D. Shim, S. J, G. Kim, “An Efficient Global Motion Characterization Methods for Image Processing Application”, IEEE Trans, on Consumer Electronics, Vol. 43, No. 4, Nov. 1997.
[13] B. S. Manjunath, J. R. Ohm, V.V. Vasudevan, Akio Yamada, “Color and Texture Descriptors”, IEEE Trans. On Circuits and System for Video Tech., Vol. 11, No.6, June 2001.
[14] C. L. Huang, S. H. Jeng, “A model-based hand gesture recognition system”, Machine Vision and Applications, Vol 12, Issue 5, 2001, pp 243-258.
[15] Carl M. Kadie, David Hovel, Eric Horvitz, “MSBNx:A Component-Centric Toolkit for Modeling and Inference with Bayesian Networks”, Microsoft Research Technical Report, 28 July 2001.
[16] Todd K. Moon, “The Expectation-Maximization Algorithm”, IEEE Signal Processing Magazine, Nov 1996, pp 47-60.

QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top