本論文的主要目的是研究以視覺伺服為基礎之物體追蹤系統，系統是以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，並以機電系統帶動一雷射瞄準器，使其指向目標物所在位置，藉此證明追蹤之效果。整個系統主要分為機械結構、馬達致動器、影像處理模組、影像感測器和馬達位置控制器。其中，影像處理模組與馬達位置控制器是以德州儀器(Texas Instruments, TI)所生產的數位訊號處理器(digital signal processor, DSP) TMS320C6416為核心來實現;影像感測器是採用原相科技(PixArt Technologies)所生產的CMOS黑白影像感測器PAS109B。在偵測移動物體的方法中，本論文採用廣受歡迎的運動能量法(motion energy methods)，然而這個方法容易因為攝影機的震動或是背景亮度的改變而產生誤差，為了解決這個問題，本論文嘗試以訊息理論中的最大熵定理(maximum entropy theorem)，找出適當的臨界值，利用此一臨界值消除背景亮度改變所造成的影響。經過分析及驗證後，本論文證實了演算法的可行性，並完成了以視覺伺服為基礎之物
體追蹤系統。

The objective of this thesis is to develop a tracking system based on visual servo control. The system consists of two image sensors to imitate the human eyes so that the position of the target object can be obtained. The mechatronic system drives a laser pointer to indicate the position of the target object, and it will help us to evaluate the performance of the designed tracking system. The system consists of a mechanism, two motor actuators, an image processing module, image sensors, and a motor position controller. In this system, the image processing module and the motor position controller is implemented by a digital signal processor (TMS320C6416). The image sensor is a mono CMOS camera (PAS109B) from PixArt Technologies. The motion energy method is used for detecting the moving object. However, this method easily causes errors from the vibration of camera and the variation of the light source. In order to overcome this drawback, a proper threshold value is determined by the maximum entropy theorem from information theory. The influence of the variation of the light source is attenuated by using the chosen threshold. The system is developed and proven to function well through simulation and experiments.

[1]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.
[2]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.
[3]D. S. Jang, G. Y. Kim, and H. I. Choi, “Model-based tracking of moving object,” Pattern Recognition, Vol. 30, No. 6, pp. 999-1008, 1997.
[4]B. Lucas and T. Kanade, “An iterative image registration technique with an application to stereo vision,” Proceedings of the DARAP Image Understanding Workshop, pp. 121-130, 1981.
[5]T. Pun, “Entropic thresholding: A new approach,” Computer Graphics Image Process, Vol. 16, pp. 210-239, 1981.
[6]J. N. Kapur, P. K. Sahoo, and A. K. C. Wong, ”A new method for gray-level picture thresholding using the entropy of the histogram,” Computer Vision Graphics Image Process, Vol. 29, pp. 273-285, 1985.
[7]L. G. Shapiro and G. C. Stockman, Computer Vision, Prentice Hall, Upper Saddle River, NY, 2001.
[8]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。
[9]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。
[10]N. Goncalves and H. Araujo, “Estimation of 3D motion from stereo image-uncertainty analysis and experimental results,” Proceedings of the intelligent Robots and Systems, Vol. 1, pp. 7-12, 2002.
[11]TMS320C6416 DSK Technical Reference, Spectrum Digital Inc., 2004.
[12]吳賢財，「德州儀器C6000 DSP入門實務」，滄海，民國九十二年。
[13]王逸如、陳信宏，「數位信號處理的新利器 TMS320C6X」，全華，民國九十一年。
[14]S. Hutchinson, G.D. Hage and P.I. Corke, “A Tutorial on Visual Servo Control,” IEEE Trans. on Robotics and Automation, No. 5, pp. 651–670 , 1996.
[15]林傳生，「MATLAB 之使用與應用」，儒林，民國九十三年。
[16]籃振銘，「以灰階色彩及邊界強度的濾除法設計二維的影像追蹤系統」，國立成功大學工程科學系碩士論文，民國九十三年。
[17]陳寬益，「即時視覺伺服追蹤系統之設計與實現」，國立成功大學機械工程學系碩士論文，民國九十一年。