臺灣博碩士論文加值系統

在視訊中擷取正在移動的物件，許多方法都針對物件本身來做處理，也就是前景的部份，這些方法通常綜合了空間上的分割法﹝如Canny邊緣判定法，分水嶺法等﹞和時間上的分割法﹝如運動預估法，改變偵測法等﹞。在這篇論文中，我們以改變偵測法為基礎，不同的是，我們不只以連續兩個視框的差異性做為分割時的參考，且利用了背景資訊的更新，來產生比前景可靠的背影記錄，再從背影記錄與視框的差異性獲得移動物件，最後應用型態學上的運算，消除camera產生的雜訊並使得物件更加平滑完整。實驗結果顯示我們提出的方法確實能自動且快速產生品質較佳的視訊物件。

The main subject is to extract out the moving object in video. There are many methods focus the object itself to process, the foreground part. These methods often are combined with spatial segmentation (Canny edge detection, the Watershed algorithm) and temporal segmentation (Motion estimation, change detection). In this thesis, our approach is based on change detection; unlike traditional change detection approach, we not only utilize the frame difference to be our reference resources of segmentation, but we use the up-to-date background information to generate a background record which is more reliable than the foreground one. Then, we use the difference between the background record and frames to obtain the initial moving object. At least, we use the morphological operations to remove noise from camera and get a new object with more smooth and complement. The experiment results show our approach indeed can make the VOPs with good quality fast and automatically.

CONTENTS
ABSTRACT(CHINESE) i
ABSTRACT(ENGLISH) ii
ACKNOWLEDGEMENTS iii
CONTENTS iv
LIST OF FIGURES vi
LIST OF TABLES viii
1. Introduction 1
1.1 Motivation 1
1.2 Known Problems 3
1.3 Organization of This Thesis 4
2. Overview of Color Image Quantization 6
2.1 Mathematical Morphology 6
2.1.1 Morphological Operations 7
2.1.2 Extension to Gray-Scale Images 8
2.1.3 Conditional Dilation----------------------------------------------------10
2.2 Spatial-domain segmentation 12
2.2.1 Edge detection-----------------------------------------------------------12
2.2.2 Canny edge detector----------------------------------------------------15
2.2.3 Watershed segmentation-----------------------------------------------16
2.3 Temporal-domain segmentation 19
2.3.1 Change detection--------------------------------------------------------19
2.3.2 Global motion estimation and compensation------------------------20
3. Proposed Segmentation Algorithm 24
3.1 Introduction 24
3.2 Segmentation Algorithm 25
3.2.1 Frame Difference 26
3.2.2 Update Background Buffer 28
3.2.3 Background Difference 30
3.2.4 Object Recognition 30
3.2.5 Post Processing----------------------------------------------------------34
4. Experience result 37
4.1 Time Cost 37
4.2 The Quality Performance 41
4.3 Discussion 48
5. Conclusions and Future Work 49
References 51

References
[1] Information Technique — Coding of Moving Pictures and Associated Audio for Digital Storage Media at up to About 1.5 m bits/s, ISO/IEC 11 172, 1993.
[2] Information Technique — Generic Coding of Moving pictures and associated Audio Information, ISO/IEC 13 818, 1994.
[3] MPEG-4 Video Verification Model version 15.0, ISO/IEC JTC1/SC29/WG11 N3093, 1999.
[4] H. M. Hang, “Multimedia Communications,” Class Lecture Notes, Spring 2000.
[5] R. Mech and M. Wollborn, “A noise robust method for 2D shape estimation of moving objects in video sequences considering a moving camera,” Signal Processing, vol. 66, pp. 203-217, Apr.1998.
[6] J. M. Gauch, “Image segmentation and analysis via multiscale gradient watershed hierarchies,” IEEE Trans. Image Processing, vol. 8, pp. 69-79, Jan. 1999.
[7] K. Haris, S. N. Efstratiadis, N. Maglaveras, and A. K. Katsaggelos, “Hybrid image segmentation using watersheds and fast region merging,” IEEE Trans. Image Processing, vol. 2, pp. 1684-1699, Dec. 1998.
[8] Hai Gao, Wan-Chi Siu, Chao-Huan Hou, “Improved techniques for automatic image segmentation,” IEEE Trans. on Circuit and System for Video Technology, vol. 11, pp. 1273-1280, Dec. 2001.
[9] F. Meyer and S. Beucher, “Morphological segmentation,” J. Vis. Commun. Image Rep., vol. 1, no. 1, pp. 21-46, Sept. 1990.
[10] Shao-Yi Chien, Shyh-Yih Ma, and Liang-Gee Chen, Fellow, IEEE, “Efficient Moving Object Segmentation Algorithm Using Background Registration Technique,” IEEE Trans. on Circuit and System for Video Technology, vol. 12, pp. 577-586, July 2002.
[11] Canny, J., “A Computational Approach to Edge Detection,“ IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. PAMI-8, 1986.
[12] Luc Vincent and Pierre Soille, “Watershed in Digital Spaces: An Efficient Algorithm Based on Immersion Simulations,” IEEE Trans. Pattern Anal. Machine Intell., vol. 13, no. 6, pp. 583-598, June 1991.
[13] Luis Salgado, Narciso Garcia, Jose M. Menendez, and Enrique RenDon, “Efficient Image Segmentation for Region-Based Motion Estimation and Compensation,” IEEE Trans. Circuit Syst. Video Technol., vol. 10, no. 7, pp. 1029-1038, Oct. 2000.
[14] J. G. Choi, M. Kim, M. H. Lee, and C. Ahn, “Automatic segmentation based on spatio-temporal information,” ISO/IEC JTC1/SC29/WG11 MPEG97/m2091, Bristol, U.K., 1997.
[15] M. Kim, J. G. Choi, D. Kim, H. Lee, M. H. Lee, C. Ahn, and Y. Ho,“A VOP generation tool: Automatic segmentation of moving objects in image sequences based on spatio-temporal information,” IEEE Trans. Circuits Syst. Video Technol., vol. 9, pp. 1216—1226, Dec. 1999.
[16] N. Paragios and G. Tziritas, “Adaptive detection and localization of moving objects in image sequences,” Signal Processing: Image Commun., vol. 14, pp. 277—296, Feb. 1999.
[17] Ullas Gargi, Rangachar Kasturi, and Susan H. Strayer, “Performance Characterization of Video-Shot-Change Detection Methods,” IEEE Trans. Circuit Syst. Video Technol., vol. 10, no. 1, pp. 1-13, Feb. 2000.
[18] Frederic Dufaux and Janusz Konrad, “Efficient, Robust, and Fast Global Motion Estimation for Video Coding,“ IEEE Trans. Image Proc., vol. 9, no. 3, pp. 497-501, March 2000
[19] A. Neri, S. Colonnese, G. Russo, P. Talone, “Automatic Moving Object and Background Separation,” Signal Processing, vol. 66, issue 2, pp. 219-232, April 1998.
[20] Q. Wei, H. J. Zhang, and Y. Z. Zhong, “A Pre-analysis Method for Robust Global Motion Estimation,” Proc. IEEE Int. Conf. Image Processing (ICIP’ 99), vol. 2, pp. 625-628, 1999.
[21] F. Moscheni, F. Dufaux, and M. Kunt, “A New Two-stage Global/Local Motion Estimation Based on a Background/Foreground Segmentation,” IEEE Proc. ICASSP’95, Detroit, MI, pp. 2261-2264, May 1995.
[22] D. Adolph and R. Buschmann, “1.15 Mbit/s Coding of Video Signals Including Global Motion Compensation,” Signal Processing: Image Communication, vol. COM-38, no. 9, pp. 259-274, June 1991.
[23] Matheron, G., Random Sets and Integral Geometry, John Wily, New York, 1975.
[24] Serra, J., editor, Image Analysis and Mathematical Morphology, Academic Press, 1983.
[25] T. Meier and K. N. Ngan, “Automatic segmentation of movinf objects for video object plane generation,” IEEE Trans. Circuit Syst. Video Technol., vol. 8, pp. 525-538, Sept. 1998.
[26] H. Nicolas and C. Labit, “Global motion identification for image sequence analysis and coding,” in Proc. IEEE Int. Conf. Acoustics, speech and Signal Processing, 1991, pp. 2825-2828.
[27] A. Smolic, T. Sikora, and J.-R. Ohm, “Long-term global motion estimation and its application for sprite coding, content description and segmentation,” IEEE Trans. Circuits Syst. Video Technol., vol. 9, pp. 1227-1242, Dec. 1999.
[28] N. MUkawa and H. Kuroda, “Uncovered background prediction in inter-frame coding,” IEEE Trans. Commun., vol. COM-33, pp. 1227-1231, Nov. 1985
[29] D. Hepper, “Efficiency analysis and application of uncovered background prediction in a low bit rate image coder,” IEEE Transactions Commun., vol. 38, pp. 1578-1584, Sept. 1990.
[30] Gonzalez, R.C., Woods, R.E., 2002. Digital Image Processing, second ed. Prentice Hall, Upper Saddle River, New Jersey, USA.