本論文旨在設計並實現視覺伺服系統，以立體視覺即時導引全向移動機器人達成物體追蹤，因此利用兩個影像感測器來模擬人類的雙眼，如此便能計算出目標物在空間中的位置，並以影像處理演算法，建構出即時影像追蹤並結合引導全向移動機器人以達成追蹤控制目的。整個系統主要分成全向移動機器人、影像處理模組、兩顆影像感測器和追蹤控制器部份。其中，影像處理模組部份主要是以可程式邏輯閘陣列(field programmable gate array, FPGA)來完成；影像感測器則是採用CMOS影像感測器；而追蹤控制器部份是以數位訊號處理器為控制核心。在實作上，利用CMOS影像感測器來擷取物體位置，再由FPGA處理相關的影像演算法，並將資訊傳到數位訊號處理器去估測物體在三維空間中的座標，最後分別利用凝視角度增加法(gaining angle of gaze)結合PI控制器與計算轉矩(computed torque)結合PID控制器兩種控制方法來完成引導全向移動機器人的追蹤控制。本論文比較兩種演算法的性能，經過分析與實驗後，以利用計算轉矩結合PID控制器具有較佳之性能。

The objective of this thesis is to design and implement the visual servo system to use the stereo vision to guide an omnidirectional mobile robot for real-time object tracking. The system consists of two image sensors to imitate the human eyes so that the position of the target can be obtained using the image processing algorithms. And also a real-time vision system for an omnidirectional mobile robot is constructed to achieve the tracking control. The system consists of an omnidirectional mobile robot, image processing module, two image sensors, and tracking controller. In this system, the image processing algorithms are implemented on an FPGA device. The CMOS image sensors are used to detecting the position of the object. Besides, the tracking controller is implemented on a digital signal processor. CMOS image sensors capture the images. The FPGA is used to execute the image processing algorithm to estimate the position of the target in 3D space. Finally, the tracking control is done by two control methods, one is gaining of angle gaze with PI controllers and the other is computed torque with PID controllers. The theoretical development is validated through the simulation and experiment. It shows that computed torque with PID controller has superior performance.

[1] 楊志偉，「以視覺伺服為基礎之倒單擺系統平衡控制」，國立成功大學工程科學系碩士論文，民國九十四年。
[2] 翁義清，「全向移動機器人之路徑追蹤控制」，國立成功大學工程科學系碩士論文，民國九十六年。
[3] R. Mori and F. Miyazaki, “GAG Strategy for Ball Tracking and Catching Task,” IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 281-286, 2002.
[4] F. L. Lewis, D. M. Dawson, and C. T. Abdallah, Robot Manipulator Control Theory and Practice, Marcel Dekker Inc., New York, 1993.
[5] D. J. Dailey, F. W. Cathey, and S. Pumrin, “An Algorithm to Estimate Mean Traffic Speed Using Uncalibrated Cameras,” IEEE Transactions on Intelligent Transportation Systems, Vol. 1, No. 2, pp. 98-107, 2000.
[6] A. J. Lipton, H. Fujiyoshi, and R. S. Patil, “Moving Target Classification and Tracking from Real-time Video,” IEEE Workshop on Applications of Computer Vision, pp. 8-14, 1998.
[7] J. A. Leese and C. S. Novak, “An Automated Technique for Obtaining Cloud Motion from Geosynchronous Satellite Data Using Cross Correlation,” Jouranal of Applied Meteorology, pp. 118-132, 1971.
[8] A. Armenti, The Physics of Sport, Springer Verlag, 1992.
[9] P. McLeod, N. Reed, and Z. Dienes, “The Generalized Optic Acceleration Cancellation Theory of Catching,” Journal of Experimental Psychology: Human Perception and Performance, pp. 139-148, 2006.
[10] D. M. Shaffer and M. K. McBeath, “Baseball Outfielders Maintain A Linear Optical Trajectory When Tracking Uncatchable Fly Balls,” Journal of Experimental Psychology: Human Perception and Performance, pp. 335-348, 2002.
[11] 林家民，「以視覺伺服為基礎之物體追蹤系統之設計與實現」，國立成功大學工程科學系碩士論文，民國九十五年。
[12] 徐嘉明，「以視覺伺服為基礎之全向移動機器人追蹤控制」，國立成功大學工程科學系碩士論文，民國九十六年。
[13] 朱立銘，「以視覺伺服為基礎之球與板系統追蹤平衡控制」，國立成功大學工程科學系碩士論文，民國九十八年。
[14] 繆紹綱，「數位影像處理」，普林斯頓國際有限公司，民國九十二年。
[15] L. G. Shapiro and G. C. Stockman, Computer vision, Prentice Hall, Upper Saddle River, NY, 2001.
[16] N. Goncalves and H. Araujo, “Estimation of 3D Motion From Stereo Image-Uncertainty Analysis and Experimental Result,” Proceedings of the intelligent Robots and Systems, Vol. 1, pp. 7-12, 2002.
[17] 蕭天賜，「以數位訊號處理器為基礎之多功能控制平台的研製」，國立成功大學工程科學系碩士論文，民國九十五年。
[18] 張碩，「自動控制」，鼎茂圖書出版股份有限公司，民國九十年。
[19] TM320F2812X Digital Signal Processor Data Manual, Texas Instruments Inc., Apr. 2001.
[20] Cyclone Device Handbook, ALTERA Inc., 2002.
[21] 莊慧仁，「FPGA/CPLD數位電路設計入門與實務應用」，全華科技圖書股份有限公司，民國九十五年。