本論文主要研究目的在於建構多相機視覺追蹤系統，利用兩顆相機模擬人類雙眼，以移動目標物的顏色資訊進行視覺追蹤。整個系統結構可分為全景遙攝機構，影像處理模組以及馬達控制模組，藉由多相機影像處理演算法得知物體於空間中的位置，並以數位訊號處理器實現馬達控制器，帶動全景搖攝機構追隨空間中的移動目標物，使目標物維持在相機的視野中。由於利用目標物的色彩資訊作為目標物判斷的依據，使該視覺追蹤系統在背景的選擇上更具彈性，能夠在更為複雜的背景中擷取到目標物。在本論文中，將以質點拋體作為追蹤的目標，並引進卡門濾波器對拋體軌跡進行軌跡預測，使追蹤過程更趨流暢。此外，也利用質點拋體運動學對拋體進行落點預測。本論文藉由模擬與實作驗證了演算法的可行性，完成以目標物色彩資訊為基礎之視覺伺服追蹤系統。

The objective of the thesis is to develop a multi-camera visual servo system by using two image sensors to imitate human eyes, and to track a moving object based on the color information of the object. The system consists of three parts: a pan and tilt mechanism, image processing module and motor control module. The position of the target object in the space is determined by using the image processing algorithms based on the color detection. The position controller on the motor control module controls the pan and tilt mechanism to track and keep the target object in the field of view of two cameras. Use of color detection allows more flexibility in choosing the background and makes the visual servo system able to work in a more complicated circumstance. In this thesis, tracking of a flying object is considered. The Kalman filter is used for predicting the flying trajectory to improve the performance of tracking control. Moreover, estimation of the point of fall is studied by the projectile physics. The effectiveness of the algorithms is verified through simulation and experimental studies. The experimental results show that the designed color-based visual servo system performs well in real-time.

[1] J. L. Barron, D. J. Fleet and S. S. Beachemin, “Performance of Optical Flow Techniques,” International Journal of Computer Vision, pp. 43-77, 1994.
[2] K. P. Horn and G. Schunk, “Determine Optical Flow,” Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge.
[3] D. Lucas and T. Kanade, “An Iterative Image Registration Technique with an Application to Stereo Vision,’’ Computer Science Department, pp.674-679, 1981
[4] D. Murray and A. Basu, “Motion Tracking with an Active Camera,” IEEE Transactions on Pattern Analysis and Machine Intelligent, Vol. 16, No. 5. May 1944.
[5] A. J. Lipton, H. Fujiyoshi and R. S. Patil, “Moving Target Classification and Tracking from Real-Time Video,” The Robotics Institution, Carnegie Mellon University, 1998
[6] P. Perez, C. Hue, J. Vermaak and M. Gangnet, “Color-Based Probabilistic Tracking,” ECCV 2002, LNCS 2002, Vol. 10, pp. 661-675, 2002.
[7] V. Vezhnevets, V. Sazonov and A. Andreeva, “A Survey on Pixel-Based Skin Color Detection Techniques,” Graphics and Media Laboratory, 2003
[8] K. Deguchi, H. Sakural and S. Ushida, “A Goal Oriented Just-In-Time Visual Servoing for Ball Catching Robot Arm,” IEEE International Conference on Intelligent Robots and Systems, pp. 22-26, 2008.
[9] U. Frese, B. Bauml, S. Haidacher, G. Schreiber, I. Schaefer, M. Hahnle, “Off-the-Shelf Vision for a Robotic Ball Catcher,” Proceedings of IEEE International Conference on Intelligent Robots and Systems. pp. 1623-1629, 2001.
[10] 林家民，｢以視覺伺服為基礎之物體追蹤系統系統之設計與實現｣，國立成功大學工程科學系碩士論文，民國九十五年七月。
[11] 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，民國九十六年七月。
[12] 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，民國九十八年七月。
[13] 蔡任右，｢以視覺伺服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，民國九十八年七月。
[14] 顏忠逸，｢即時物體追蹤之立體視覺導引全向移動機器人之研製｣，國立成功大學工程科學系碩士論文，民國九十八年七月。
[15] 簡彰億，｢以DSP為基礎於複雜背景中之視覺引導全向移動機器人之研製｣，國立成功大學工程科學系碩士論文，民國九十九年七月。
[16] 鄭文勝，｢利用順滑模態控制之球與球系統穩定化｣，國立成功大學工程科學系碩士論文，民國一○○年七月。
[17] 林柏瑋，｢以視覺為基礎之擊球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，民國九十九年七月。
[18] E. Trucco and A. Verri, Introductory Techniques for 3D Computer Vision. Prentic Hall, Upper Saddle River, New Jersey, 2008
[19] Color – space Wikipedia, the free encyclopedia web site,
http://en.wikipedia.org/wiki/Color_space
[20] G. Welch and G. Bishop, “An Introduction to the Kalman Filter,” Department of Computer Science, University of North Carolina at Chapel Hill, 2006.
[21] 1/2.5-Inch 5Mp CMOS Digital Image sensor MT9P001 datasheet.
[22] Texas Instrument TMS320DM6437 Digital Media Processor datasheet.
[23] Texas Instrument TMS320F2812 Digital Signal Processor datasheet.
[24] Altera Cyclone FPGA EP1C12Q240C8 datasheet.
[25] 陳奕隆，｢單輪車系統平衡控制之設計與實現｣，國立成功大學工程科學系碩士論文，民國九十九年七月。
[26] 洪介仁，｢車與桿倒單擺系統之平衡控制｣，國立成功大學工程科學系碩士論文，民國九十二年七月。