在本論文中，我們建立了一個在複雜環境下仍具有高度可靠性的即時視覺追蹤系統。本追蹤系統的架構主要可分為三大部分，第一部份是以移動邊緣法(Moving Edges)為基礎的目標偵測法則，其目的是偵測出現在攝影機視野中的移動目標，並取得目標初始位置。第二部份則是目標資訊擷取機制，結合第一部份之目標偵測法則和吸引式蛇型輪廓模型(Attractable Snake Model)，本系統能自動取得目標外型輪廓及目標顏色、亮度資訊，並將這三種資訊整合於第三部分的目標追蹤法則，利用輪廓比對法(Contour Matching)及亮度、顏色樣版比對法(Template Matching)來持續追蹤目標的位置，以增進此系統的強健性及適用性。另外，在硬體架構方面，本系統建立在一低價的商業化雙軸相機平台上，並利用個人電腦及其RS232通訊埠來控制平台上的步進馬達，以達成視覺伺服追蹤的目的。最後，我們將此系統應用於一般物體追蹤及頭部追蹤，並做了包括目標變形、目標受到暫時遮蔽、目標通過低對比環境、相似目標干擾等數個實驗來驗證此追蹤系統的強健性及效能，並獲得良好的成果。

　　This thesis develops a highly reliable real-time visual tracking system capable of tracking a moving target in cluttered environment. In this thesis, the proposed visual tracking system is classified into three components – the target detector, the target information extractor, and the target tracker. The first component is a target detector that can detect any moving object in the image using the “moving edges” technique. Then, by integrating the information from the target detector and the attractable snake model, the second component is a target information extractor that can automatically extract target’s contour, illumination and color information that are necessary for target tracking. Finally, the third component adopts a hybrid matching method that enables the system to continuously track the target with great robustness and adaptability. Notably, this new hybrid matching method incorporates the template matching method and a modified contour matching method.

　　Moreover, the visual tracking system presented in this thesis is established on a low-cost commercial camera platform, which can be controlled by a personal computer through RS232 serial port. At last, several experiments including object tracking and human head tracking are conducted to verify the robustness of the tracking system.

[1] S. Birchfield, “An Elliptical Head Tracker,” 31st Asilomar Conference on Signals, Systems, and Computers, Nov. 1997.
[2] S. Birchfield, “Elliptical Head Tracking Using Intensity Gradient and Color Histograms,” IEEE Conference On Computer Vision and Pattern Recognition, July 1998.
[3] L. D. Cohen, “On Active Contour Models and Balloons,” CVGIP:Image Understanding, Vol.53, No.2, pp.211-218, March 1991.
[4] V. Caselles, R. Kimmel and G. Sapiro, “Geodesic Active Contours,” International Journal of Computer Vision, Vol.22, pp.61-79, 1997.
[5] T. M. Chen, R. C. Luo and T. H. Hsiao, “Visual Tracking Using Adaptive Color Histogram Model,” Proceedings of IEEE 25th Annual Conference, Vol.3, pp. 1336-1341, Dec. 1999.
[6] C. H. Chuang and W. N. Lie, “Fast and Accurate Active Contours for Object Boundary Segmentation,” IEEE Asia-Pacific Conference on Circuits and Systems, Dec. 2000.
[7] Y. S. Chen, Y. P. Hung and C. S. Fuh, “A Fast Block Matching Algorithm Based on the Winner-Update Strategy,” Proceedings of the 4th Asian Conference on Computer Vision, Vol. 2, pp. 977-982, Jan. 2000.
[8] H.D. Cheng, X.H. Jiang, Ying Sun and Jingli Wang, “ Color Image Segmentation: Advances and Prospects,” Pattern Recognition, Vol. 34, Issue 12, pp. 2259-2281, Dec. 2001.
[9] F. Cen and F. Qi, “Tracking Non-rigid Objects in Clutter Background with Geometric Active Contours,” Electronics Letters, Vol. 38, No.12, June 2002.
[10] P.Y. Chen, “A Robust Visual Servo System for Tracking an Arbitrary Shaped Object by a New Active Contour Method,” Master Thesis, Dept. of Electrical Engineering, National Taiwan University, 2003.
[11] C. J. Chen, “Motion Detection and Estimation of a Real-Time Visual Servo Tracking System,” Master Thesis, Dept. of Mechanical Engineering, National Cheng-Kung University, 2003.
[12] C. H. Chuang, “Object Segmentation, Registration, and Tracking based on Contour Detection,” Ph.D. Thesis, Dept. of Electrical Engineering, National Chung Cheng University, 2003.
[13] S. Hutchinson, G. D. Hager and P. I. Corke, “A Tutorial on Visual Servo Control,” IEEE Trans. On Robotics and Automation, Vol. 12, No. 5, pp. 651-670, 1996.
[14] C. Gentile, O. Camps and M. Sznaier, “Segmentation for Robust Tracking in the Presence of Severe Occlusion,” IEEE Transactions on Image Processing, Vol. 13, No.2, 2004.
[15] J. Hu, T. M. Su, C. C. Cheng, W. H. Liu and T. I. Wu, “A Self-calibrated Speaker Tracking System Using Both Audio and Video Data,” Proceedings of IEEE 2002 International Conference on Control Applications, Sep. 2002.
[16] F. Huang and J. Su, “Face Contour Detection Using Geometric Active Contours,” IEEE Proceedings on 4th World Congress on Intelligent Control and Automation, June 2002.
[17] J. Haddadnia, M. Ahmadi and K. Faez, “An Efficient Method for Recognition of Human Faces Using Higher Orders Pseudo Zernike Moment Invariant,” Proceedings of Fifth IEEE International Conference on Automatic Face and Gesture Recognition, pp. 315-320, 2002.
[18] C. M. Huang, S. C. Wang, L. C. Fu, P. Y. Chen and Y. S. Cheng, “A Robust Visual Tracking of an Arbitrary-Shaped Object by a New Active Contour Method for a Virtual Reality Application,” IEEE Conference Proceedings on Networking, Sensing and Control, Mar. 2004.
[19] L. Ji and H. Yan, “An Attractable Snake Model for Contour Extraction in MRI Images,” Proceedings of the 20th Annual International Conference of the IEEE , Vol.2, pp.609-612, Oct. 1998.
[20] L. Ji and H. Yan, “Attractable Snakes Based on the Greedy Algorithm for Contour Extraction,” Pattern Recognition, Vol. 35, pp. 791-806, April 2002.
[21] J. H. Jean and R.Y. Wu, “Adaptive Visual Tracking of Moving Objects Modeled with Unknown Parameterized Shape Contour,” IEEE International Conference on Networking, Sensing and Control, Vol.1, pp.76 – 81, Mar. 2004.
[22] M. Kass, A. Witkin and D. Terzopoulos, “Snake: Active Contour Models,” International Journal of Computer Vision, Vol. 1, pp. 321-331, 1987.
[23] H. Kondo and S.B.A. Rahman, “Human-Face Recognition Using Neural Network with Mosaic Pattern,” IEEE International Conference on Systems, Man, and Cybernetics, Vol.6, pp. 831-834, 1999.
[24] W. Kim and J. J. Lee, “Visual Tracking using Snake Based on Target’s Contour Information,” Proceedings of IEEE International Symposium on Industrial Electronics, Vol. 1, June 2001.
[25] K.M. Lam and Hong Yan, “Fast Greedy Algorithm for Active Contours,” Electronics Letters, Vol.30, No.1, pp.21-23, Jan. 1994.
[26] A. J. Lipton, H. Fujiyoshi and R. S. Patil, “ Moving Target Classification and Tracking from Real-Time Video,” Proceedings of the DARPA Image Understanding Workshop, 1998
[27] A. J. Lipton, H. Fujiyoshi and R. S. Patil, “Moving Target Classification and Tracking from Real-Time Video,” Proceeding of the Fourth IEEE Workshop on Application of Computer Vision, pp. 8-14, 1998.
[28] D. Liu and L. C. Fu, “Target Tracking in an Environment of Nearly Stationary and Biased Clutter,” IEEE Int. Conf. on Intelligent Robots and Systems, Vol. 3, pp. 1358-1363, 2001.
[29] D. Murry and A. Basu, “Motion Tracking with an Active Camera,” IEEE Trans. on Pattern Analysis and Machine Intelligence, vol.16, no.5, pp.449-459, May 1994.
[30] R. A. McLaughlin and M. D. Alder, “Recognition of Infra Red Images of Aircraft Rotated in Three Dimensions,” Proceedings of the Third Australian and New Zealand Conference on Intelligent Information Systems, pp. 82-87, 1995.
[31] S. Marouani, A. Huertas and G. Medioni, “Model-Based Aircraft Recognition in Perspective Aerial Imagery,” Proceedings of International Symposium on Computer Vision, pp. 371-376, Nov. 1995.
[32] A.R. Mirhosseini and H. Yan, “An Optimally Fast Greedy Algorithm for Active Contours,” Proceedings of IEEE Int. Symposium Circuit and Systems, Vol. 2, pp. 1189~1192, June 1997.
[33] N. Paragios and R. Deriche, “Geodesic Active Contours and Level Sets for the Detection and Tracking of Moving Objects,” IEEE Trans. on Pattern Analysis and Machine Intelligence, Vol. 22,No.3, Mar. 2000.
[34] Y. T. Tsai, “Video Object Segmentation and Tracking Based on Background Construction,” Master Thesis, Dept. of Electrical and Control Engineering, National Chiao-Tung University, 2002.
[35] D.J. Williams and M. Shah, “A Fast Algorithm for Active Contours and Curvature Estimation,” CVGIP: Image Understanding, Vol. 55, No. 1, pp. 14-26, Jan. 1992.
[36] G. Xu, E. Segana and S. Tsuji, “Robust Active Contours with Insensitive Parameters,” Pattern Recognition, Vol.27, pp. 879-884, 1994.
[37] C. Xu and J. L. Prince, “Gradient Vector Flow: A New External Force for Snake,” IEEE. Proceedings Conference on Computer Vision and Pattern Recognition, pp. 66-71, 1997.
[38] C. Xu and J. L.Prince, “Snakes, Shapes, and Gradient Vector Flow,” IEEE Trans. On Image Processing, Vol. 7, No. 3, pp. 359369, 1998.
[39] C. Xu, A. Yezzi Jr. and J. L. Prince, “On the Relationship between Parametric and Geometric Active Contours,” IEEE Conference on Signals, Systems and Computers, Nov. 2000.
[40] N. Xu and N. Ahuja, “Object Contour Tracking Using Graph Cuts Based Active Contours,” International Conference on Image Processing. Vol. 3, June 2002.
[41] N. Xu, R. Bansal and N. Ahuja, “Object Segmentation Using Graph Cuts Based Active Contours,” IEEE Conference Proceedings on Computer Vision and Pattern Recognition, Vol. 2, June 2003.
[42] Q. Zang and R. Klette, “Robust Background Subtraction and Maintenance,” Proceedings of the 17th International Conference on Pattern Recognition, Vol.2, pp.90-93, Aug. 2004.
[43] Z. Zhang, “A Flexible New Technique for Camera Calibration,” Technical Report MSR-TR-98-71, Update on Microsoft Corporation, pp.1-21, 1998.

[44] W. Forstner, R.M. Haralick and B. Radig, “Robust Computer Vision,” Wichmann,1992.
[45] D. Forsyth and J. Ponce, ”Computer Vision- A Modern Approach,” Prentice Hall, 2003.
[46] R.C. Gonzalez, and R. E. Woods, “Digital Image Processing,” 2nd Edition, Prentice Hall, 2002.