近年來自主式移動機器人的發展蓬勃，廣泛地應用在服務機器人和保全機器人等等。視覺影像追蹤也是研究發展的熱門課題，應用在安全監控系統，居家防護系統等等。
視覺影像追蹤大多使用固定式攝影機，一旦目標離開鏡頭就無法再進行追蹤，本論文使用PTZ(Pan/tilt/zoom)攝影機發展影像追蹤系統，攝影機的鏡頭將隨著動態目標轉動，擴大追蹤的範圍。此外，追蹤系統並與自主移動機器人搭配，令自主移動機器人跟隨目標移動並且保持距離。
本論文使用基於貝葉斯定理（Bayes’ theorem）的背景建模方法達到動態物體的偵測。當偵測到動態物體之後，再使用粒子濾波器（Particle filter）以顏色分佈做為特徵，估測動態目標的中心點。計算出動態目標和自主移動機器人相對角度後，自主移動機器人據此跟隨在動態物標後，自主移動機器人在跟隨動態目標的過程中配合智慧型避障控制器，利用八顆超音波偵測器偵測障礙物的距離，避免自主移動機器人碰撞到其他障礙物。追蹤結果的中心和實際目標的中心的準確度高於80%，實驗結果證明本架構可以使機器人達到即時追蹤目標的效果。

In recent years, autonomous mobile robot has become an important and popular research topic. It is widely used in service robot and security robot, etc. Visual tracking is also a popular topic of research and development. It is applied in security monitoring system and home care system, etc.
The conventional visual tracking system applies the fixed camera as the sensor. The drawback is once the target out of the sensing area, the system won’t be able to track the target. This research adopt PTZ (Pan/ tilt/zoom) CCD camera to develop a dynamic tracking system which the camera can be rotated according to the orientation of the moving target, and expand the area of tracking in real-time. Furthermore, the proposed tracking methodologies command the autonomous mobile robot to follow the moving object and keep in the line of sight.
This thesis detects the moving object based on the Bayes' theorem background modeling method and applies color based Particle filter to track the centroid of moving object. The visual tracking system calculates the relative angle of moving object and the autonomous mobile robot. According to this angle, the autonomous mobile robot tracks the moving object. This thesis uses eight ultrasonic sensors to detect distance of obstacles. Autonomous mobile robot with intelligent obstacle avoidance controller follows, tracks moving object and avoids hitting the other obstacles. The accuracy of center point of tracking results and the real target are more than 80%. The experiments proved that this approach can achieve real-time tracking system.

[1]G. A. Bekey, Autonomous Robots From Biological Inspiration to Implementation and Control. London, England: The MIT Press, 2005.
[2]I. R. N. Roland Siegwart, Introduction to Autonomous Mobile Robots: Massachusetts Institute of Technology, 2004.
[3]H. R. E. J. Borenstein, L. Feng, D. Wehe, "Mobile Robot Positioning & Sensors and Techniques," Invited paper for the Journal of Robotic Systems vol. 14, 1996.
[4]劉修廷、吳明川, "PTZ 攝影機應用於人物偵測與追蹤之研究," presented at the 2008 數位科技與創新管理研討會, 台北, 2008.
[5]F. Kobayashi, Masumoto, D. Kojima, F., "Sensor Selection based on Fuzzy Inference for Sensor Fusion," in Fuzzy Systems, 2004. Proceedings. 2004 IEEE International Conference on, 2004, pp. 305-310 vol.1.
[6]W. C. Xiang Xiang, Du Zeng, "Intelligent Target Tracking and Shooting System with Mean Shift," in Parallel and Distributed Processing with Applications, 2008. ISPA '08. International Symposium on, 2008, pp. 417-421.
[7]W. Y. Liu Guocheng, "An Algorithm of Visual Target Tracking on Monocular Camera based on Particle Filter," in Control Conference, 2008. CCC 2008. 27th Chinese, 2008, pp. 472-476.
[8]X. D. Chi-Yi Tsai, Kai-Tai Song, Hendrik Van Brussel Marnix Nuttin, "Visual State Estimation using Self-tuning Kalman Filter and Echo State Network," in Robotics and Automation, 2008. ICRA 2008. IEEE International Conference on, 2008, pp. 917-922.
[9]M. S. Arulampalam, et al., "A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking," Signal Processing, IEEE Transactions on, vol. 50, pp. 174-188, 2002.
[10]J. H. Liu, "Reconnaissance System for Intelligent Autonomous Mobile Robot," 自動化及控制研究所, 國立臺灣科技大學 台北, 2009.
[11]G. S. Li, Hongbo, "Study of Technology on Path Planning for Mobile Robots," in Control and Decision Conference, 2008. CCDC 2008. Chinese, 2008, pp. 3295-3300.
[12]L. C. Linan Zu, Zuojun Liu,Peng Yang, "Research on Path Planning Method of Multi Mobile Robot in Dynamic Environment," in Intelligent Control and Automation, 2008. WCICA 2008. 7th World Congress on, 2008, pp. 8286-8291.
[13]H. S. L. H. X. Zenga, "Research on Path Planning for the Mobile Intelligent Robot," in Computer Science and Information Engineering, 2009 WRI World Congress on, 2009, pp. 121-124.
[14]T. T. Weiming Hu, Liang Wang S. Maybank, "A Survey on Visual Surveillance of Object Motion and Behaviors," Systems, Man, and Cybernetics, Part C: Applications and Reviews, IEEE Transactions on, vol. 34, pp. 334-352, 2004.
[15]W. W. Dongpyo Hong, "A Background Subtraction for a Vision-based user Interface," in Information, Communications and Signal Processing, 2003 and the Fourth Pacific Rim Conference on Multimedia. Proceedings of the 2003 Joint Conference of the Fourth International Conference on, 2003, pp. 263-267 Vol.1.
[16]M. Piccardi, "Background Subtraction Techniques: a Review," in Systems, Man and Cybernetics, 2004 IEEE International Conference on, 2004, pp. 3099-3104 vol.4.
[17]A. J. F. Lipton, H. Patil R. S., "Moving Target Classification and Tracking from Real-time Video," in Applications of Computer Vision, 1998. WACV '98. Proceedings., Fourth IEEE Workshop on, 1998, pp. 8-14.
[18]S. R. Deqing Sun, J.P. Lewis, Michael J. Black, "Learning Optical Flow," presented at the The 10th European Conference on Computer Vision 2008.
[19]J. L. Barron, Fleet, D. J.Beauchemin, S. S. Burkitt T. A., "Performance of Optical Flow Techniques," in Computer Vision and Pattern Recognition, 1992. Proceedings CVPR '92., 1992 IEEE Computer Society Conference on, 1992, pp. 236-242.
[20]B. D. Coifman B , Mclauchlan P Malik J., "A Real-time Computer Vision System for Vehicle Tracking and Traffic Surveillance," Tansportation Research Part C, vol. 6(4), pp. 271-288, 1998.
[21]O. J. M. S. Alper Yilmaz, "Object Tracking: A Survey," ACM Computing Surveys, vol. 38, December 2006.
[22]F. G. Meyer, "Region-based Tracking using Affine Motion Models in Long Image Sequences," CVGIP: Image Understanding archive, vol. 60, pp. 119-140, September 1994.
[23]H. Z.-Q. H. Chong-Zhao, "A Survey of Visual Tracking," Acta Automatica Sinica, vol. 32, 2006.
[24]T. Y. X. M. Z. Qiu, "Robust Vehicle Tracking based on Scale Invariant Feature Transform," in Information and Automation, 2008. ICIA 2008. International Conference on, 2008, pp. 86-90.
[25]A. K. Z. Jain, Yu Dubuisson-Jolly ,Marie-Pierre, "Deformable Template Models: A Review," Signal Processing, vol. 71, pp. 109-129, 1998.
[26]J. A. K. Yu Zhong, Dubuisson-Jolly M. P., "Object Tracking using Deformable Templates," Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol. 22, pp. 544-549, 2000.
[27]J. Canny, "A Computational Approach to Edge Detection," Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol. PAMI-8, pp. 679-698, 1986.
[28]M. S. C. Harris, "A Combined Corner and Edge Detector," presented at the Proceedings of the 4th Alvey Vision Conference, 1988.
[29]M. H. Muyun Weng, "Image Feature Detection and Matching Based on SUSAN Method," in Innovative Computing, Information and Control, 2006. ICICIC '06. First International Conference on, 2006, pp. 322-325.
[30]S. M. S. J. M. Brady, "SUSAN - A New Approach to Low Level Image Processing," International Journal of Computer Vision vol. 23, pp. 45-78, 1997.
[31]W. H. Liang, Ju, "A Robust Blob Detection and Delineation Method," in Education Technology and Training, 2008. and 2008 International Workshop on Geoscience and Remote Sensing. ETT and GRS 2008. International Workshop on, 2008, pp. 827-830.
[32]孫振東、吳怡憬, "植基於多維色彩質心空間特徵之影像檢索系統," presented at the 全國計算機會議, 2005.
[33]C. Ivancsits, "Visual navigation system for small unmanned aerial vehicles," 自動化及控制研究所, 國立臺灣科技大學, 台北, 2010.
[34]M. S. Arulampalam M.S. , Gordon N. Clapp T. , "A Tutorial on Particle Filters for Online Nonlinear/Non-Gaussian Bayesian Tracking," Signal Processing, IEEE Transactions on, vol. 50, pp. 174-188, 2002.
[35]L. Pei-Hua, "A Novel Color Based Particle Filter Algorithm for Object Tracking," Chinese Journal of Computers, vol. 32, Dec. 2009.