本論文旨在設計並實現視覺伺服系統，建構出以視覺為基礎之擊球控制系統。其中利用影像感測器模擬人的眼睛，如此便能計算出目標物在空間中的位置，並將此資訊回授給擊球控制器產生擊球控制命令，進而驅動擊球機構達到擊球目的。整個系統主要分成擊球機構、影像處理模組、影像感測器、數位訊號處理器與擊球控制器。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互補性金屬氧化矽感應器(complementary metal-oxide silicon, CMOS)影像感測器；而擊球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，由FPGA處理相關的影像演算法，再將資訊傳到數位訊號處理器估測出物體在二維空間中的位置與速度，並由擊球控制器依球的位置及速度決定擊球板擊球時間與擊球角度命令，最後透過PID控制器進行馬達控制。經過驗證與分析後，本論文證實了演算法的可行性，並完成了以視覺為基礎之擊球控制系統。

The objective of this thesis is to design and implement a vision-based ball-hitting control system. The system uses an image sensor to imitate the human eyes to obtain the position of the target in the space, and the spatial information is used to calculate the control command, and to achieve the purpose of ball hitting by driving the hitting mechanism. The system consists of the ball-hitting mechanism, image processing module, one image sensor, digital signal processor (DSP) and ball-hitting controller. In this system, the image processing is implemented on a field programmable gate array (FPGA).A complementary metal-oxide silicon (CMOS) image sensor is used to acquire the image data. The ball-hitting controller is implemented on a DSP. According to the position and velocity of the ball, the ball-hitting controller determines the hitting time and hitting angle. Finally, the PID controller is used to control the motor to drive the hitting mechanism. This thesis shows the effectiveness of the control algorithm through the simulation and experimental results.

[1] J. Hill and W. T. Park, “Real Time Control of a Robot with a Mobile Camera,” Proceedings of 9th ISIR, Washington, D. C., pp. 233-246, 1979.
[2] S. Hutchinson, G. D. Hager, and P. I. Corke, “A Tutorial on Visual Servo Control,” IEEE Transactions on Robotics and Automation, Vol. 12, No. 5, pp. 651-670, 1996.
[3] S. Rovetta and R. Zunino, “A Multiprocessor-Oriented Visual Tracking System,” IEEE Transactions on Industrial Electronics, Vol. 46, No. 4, pp. 842-850, 1999.
[4] C. T. Huitzil and M. A. Estrada, “Real-Time Image Processing with a Compact FPGA-Based Systolic Architecture,” Real-Time Imaging, Vol. 10, No. 3, pp. 177-187, 2004.
[5] J. Batlle, J. Marti, P. Ridao, and J. Amat, “A New FPGA/DSP-Based Parallel Architecture for Real-Time Image Processing,” Real-Time Imaging, Vol. 8, No. 5, pp. 345-356, 2002.
[6] D. R. Lee, S. H. Jin, P. C. Thien, and J. W. Jeon, “FPGA Based Connected Component Labeling,” Proceedings of IEEE International Conference on Control, Automation and Systems, pp. 2313-2317, 2007.
[7] M. Buhler, D. E. Koditschek, and P. J. Kindlmann, “Planning and Control of Robotic Juggling and Catching Tasks,” International Journal of Robotics Research, Vol. 13, No. 2, pp. 101-118, 1994.
[8] A. A. Rizzi and D. E. Koditschek, “Progress in Spatial Robot Juggling,” IEEE International Conference on Robotics and Automation, Vol. 1, pp. 775-780, 1992.
[9] R. Mori, F. Takagi, and F. Miyazaki, “Development of Intelligent Robot System Realizing Human Skill,” IEEE International Conference on Robotics and Automation, pp. 1280-1285, 2006.
[10] 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。
[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] 蔡任右，「以視覺為基礎之複雜背景下物體追蹤控制系統之設計與實現」，國立成功大學工程科學系碩士論文，民國九十八年。
[14] 張居強，「以視覺伺服為基礎之舉球控制系統之研製」，國立成功大學工程科學系碩士論文，民國九十八年。
[15] 簡彰億，「以DSP為基礎於複雜背景中之視覺引導全像機器人之研製」，國立成功大學工程科學系碩士論文，民國九十九年。
[16] 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。
[17] O. Faugeras, Three-Dimensional Computer Vision: A Geometric Viewpoint, Massachusetts Institute of Technology, Cambridge, 1993.
[18] Y. Ma, S. Soatto, J. Kosecka, and S. S. Sastry, An Invitation to 3-D Vision: From Images to Geometric Models, Springer, NY, 2004.
[19] R. Hartley and A. Zisserman, Multiple View Geometry in Computer Vision, Cambridge University, Cambridge, 2003.
[20] S. H. Friedberg, A. J. Insel, and L. E. Spence, Linear Algebra, Pearson Education, NJ, 2003.
[21] K. M. Walker, Applied Mechanics, Prentice Hall, 1999.
[22] B. C. Kuo, Automatic Control Systems, Prentice Hall International Editions, Upper Saddle River, NJ, 1997.
[23] 廖顯慶，「利用倒階設計方法於球與板系統的追蹤平衡控制」，國立成功大學工程科學研究所碩士論文，民國九十五年。
[24] 張碩，「自動控制」，鼎茂圖書出版股份有限公司，民國九十年。
[25] 吳信成，「X-Y平台之即時運動控制系統的設計與實現」，國立成功大學工程科學系碩士論文，民國九十五年。
[26] The -Bus Specification Version 2.1, Philips Semiconductors, 2000.
[27] IC61LV5128 512K 8 High-Speed CMOS Static RAM, ISSI Inc., 2000.