臺灣博碩士論文加值系統

近年來，影像和視訊資料快速地充斥在多媒體資訊網路上。對於多媒體資訊而言，特別是視訊資料，具有最多樣的資訊、最豐富的內容及最多可能的應用。因此，發展以視訊內容為主的分析技術是相當急迫且需要的。
對於視訊資料的組織和索引而言，自動化場景切割是一向不可或缺的工作。一般而言，場景片段通常被視為組成視訊資料的基本單位，因此場景邊界偵測是提供我們做視訊摘要、檢索、瀏覽和甚至更高階視訊切割的基礎。而場景切割的最主要工作是將真實場景變換和同一個場景內的正常變化區分出來。
本篇論文主要的目地大致分成兩部分：我們先詳細的規劃及分析場景變換偵測的問題以便完整偵測及分類場景變換的型態。然後我們提出一套適合各種場景變換的視訊編輯模組並且去分析其測量後的統計特性。
從模擬結果顯示，本論文所提出的方法不只能夠偵測各種場景變換並且能夠將它們詳盡的分類出來。

Recently, image and video collections are increasing rapidly in the multimedia information network. For the multimedia information, especially for video data, it has the most variety information, the most possible applications and most complex content. Therefore, the techniques of content-based video analysis are critical issues to be developed.
Automatic video scene shot partitioning is a prerequisite procedure for organizing and indexing video source. Because the scene shots are generally considered as the elementary units to constitute a video, therefore, shot boundaries detection is the basis for providing the ground of video abstraction, retrieving, browsing and even high-level video segmentation. The main problem of shot detection is the ability to distinguish the real scene changes and normal variation that happen in a shot.
The objective of this paper is twofold. We first formulate the problem of shot-boundary detection in detail and identify the issues that need to be considered in order to robust detect and classify the different shot change types. Then we proposed the video-editing model for various types of shot boundaries and analysis the statistical property of the measuring features.
Simulations results show that the proposed method not only detect various shot changes but also classify the types of shot boundary.

Abstract i
摘要 ii
致謝 iii
Content iv
List of Figures vi
List of Tables viii
Chapter 1 Introduction 1
1.1 Motivation 1
1.2 Organization of the thesis 5
Chapter 2 Related Researches of Scene Change Detection Techniques 6
2.1 Uncompressed Domain 6
2.1.1 Intensity Template Matching 6
2.1.2 Histogram-Based Techniques 7
2.1.3 Block-Based Techniques 9
2.1.4 Twin-Comparison Techniques 10
2.2 Compressed Domain 11
2.2.1 DCT Coefficients 11
2.2.2 Motion Information 12
Chapter 3 Problem Formulation 13
3.1 The Characteristic of Shot Boundary 13
3.2 The Feature of Shot Boundary 13
3.3 Summary 16
Chapter 4 System of the Model-Based Video Scene Change Detection 18
4.1 The Overview of Proposed Algorithm 18
4.2 Previous Approach 19
4.2.1 Motion Fields Classification 19
4.3 Motion Estimation and Compensation 19
4.3.1 An Improved Three-Steps Search Block-Matching Algorithm 19
4.4 Video Editing Models for Various Scene Change Types 23
4.4.1 Abrupt Scene Change Model 24
4.4.2 Gradual Transition Models 27
4.4.2.1 Fade-in 27
4.4.2.2 Fade-out 30
4.4.2.3 Dissolve 33
4.4.2.4 Wipe 37
4.5 Implementation Issues 44
Chapter 5 Experiment Results and Analysis 47
5.1 Models Verification 51
5.2 Performance of Video Sequence Detection 63
Chapter 6 Conclusion and Future Works 74
6.1. Conclusions 74
6.2. Future Works 75
References 76

[1] W.A.C. Faernando, C.N. Canagarajah and D.R. Bull, “ Scene change detection algorithms for content-based video indexing and retrieval ”, Electronics & Communication Engineering Journal, Volume: 13 Issue: 3, pp 117-126, Jun 2001.
[2] S.W. Smoliar, and Hong Jiang Zhang, “ Content based video indexing and retrieval ”, Multimedia, IEEE, Volume: 1 Issue: 2, pp 62-72, Summer 1994.
[3] S. Jeannin and A. Divakaran, “ MPEG-7 visual motion descriptors ”, IEEE Transactions on Circuits and Systems for Video Technology, Volume: 11 Issue: 6, pp720-724, Jun 2001.
[4] U. Gargi, R. Kasturi and S.H.Strayer, “ Performance Characterization of Video Shot Change Detection Methods ”, IEEE Transaction on Circuits and Systems for Video Technology, Vol. 10, No. 1, pp 1-13, February 2000.
[5] G. Boccignone, M. De Santo and G. Percannella, “ Automated Threshold Selection for the Detection of Dissolves in MPEG Videos ”, IEEE International Conference on Multimedia and Expo (ICME), Volume 3, pp1535-1538, July 2000.
[6] R. Zabih, J. Miller and K. Mai, “ A Feature-Based Algorithm for Detecting and Classifying Scene Breaks ”, Proc. ACM Multimedia 95, San Francisco, CA, pp. 189-200, Nov. 1995.
[7] A. Hampapur, R. C. Jain and T. Weymouth, “ Model-Based Digital Video Segmentation ”, Multimedia Tools and Applications, Vol.1, No. 1, pp 9-46, Mar.1995.
[8] A. Nagasaka and Y. Tanaka, “ Automatic videos indexing and full-video search for object appearance ”, IFIP: Visual Database Systems II, pp 113-127, 1992.
[9] H. J. Zhang, A. Kankanhalli, and S. Smoliar. ” Automatic Partitioning of Full Motion Video ”, ACM Multimedia Systems, Vol. 1, No. 1, pp.10-28, 1993.
[10] Y. Tonomura, “ Video handling based on structured information for hypermedia systems ”, International Conference on Multimedia Information Systems ’91, pp.333-334 November 1991.
[11] R. Kasturi and R. Jain, “ Dynamic vision “, in Computer Vision：Principles, pp. 469-480, IEEE Comput. Soc., Los Alamitos, CA, 1990.
[12] H. J. Zhang, A. Kankanhalli and S. Smoliar, “ Automatic Partitioning of Full-Motion Video ”, ACM Multimedia Systems, Vol. 1, No. 1, pp.10-28, 1993.
[13] H.B. Lu, Y.J. Zhang and Y.R. Yao,” Robust gradual scene change detection”, International Conference on Image Processing Proceedings 1999, Vol. 3, 304 —308, 1999.
[14] Chung-Lin Huang; Bing-Yao Liao;” A robust scene-change detection method for video segmentation “, IEEE Transactions on Circuits and Systems for Video Technology, Vol. 11 Issue: 12, pp 1281-1288, Dec 2001.
[15] B.L. Yeo and B. Liu,” On the extraction of DC sequence from MPEG compressed video ”, International Conference on Image Processing, Volume: 2, pp 23-26, Oct 1995.
[16] Hain-Ching Liu and G.L. Zick, ” Scene adaptive MPEG encoding algorithm using the P-picture-based analysis”, Proceedings of the Third IEEE International Conference on Multimedia Computing and Systems, pp 17-23, Jun 1996.
[17] W.A.C. Faernando, C.N. Canagarajah and D.R. Bull, ” Scene change detection algorithms for content-based video indexing and retrieval ”, Electronics & Communication Engineering Journal, Volume: 13 Issue: 3, pp 117-126, Jun 2001.
[18] U. Gargi, R. Kasturi and S.H. Strayer, ” Performance Characterization of Video-Shot-Change Detection Methods ”, IEEE Transaction on Circuits and Systems for Video Technology, Volume. 10, No. 1, pp 1-13, February 2000.
[19] R. Dugad, K. Ratakonda and N. Ahuja, “ Robust video shot change detection ”, IEEE Multimedia Signal Processing, p376 —381, Dec.1998.
[20] Xu Donglai, C. Bailey and R. Sotudeh, ” An improved three-step search block-matching algorithm for low bit-rate video coding applications ”, International Symposium on Signals, Systems, and Electronics, ISSSE 98, pp 178 —181, Oct 1998.