本研究主要在發展一套自動追蹤的系統，藉由架設在遙控車上的CCD攝影機，將影像經過無線傳輸模組傳給電腦處理後，送出一控制信號來控制遙控車行進方向，以達到自動追蹤的目的。實作方面可分為演算法的實現和電子電路設計兩個部分。
在演算法方面，首先，將所有輪廓點平均放在接近被追蹤物的邊緣，然後利用Adaptive ACM方法所提供的能量方程式和可動態調整搜尋範圍和方向來找出當被追蹤物體移動後輪廓點可能的位置。此時的輪廓受到背景雜訊影響，有可能會得到不屬於被追蹤物體的部分。接著，再利用輪廓點間角度關係和ASM兩種方法，來修正並降低背景雜訊對物體輪廓所造成的影響，以減少追蹤的錯誤率。
在電路設計方面，本研究設計一控制電路，用以接受由電腦送出的控制信號，並連接遙控器，以取代一般遙控器中所用的可變電阻控制遙控車的行進方向。為了能到戶外進行實驗，因此我們也設計了一個dc chopper電路，以提供系統中不同規格需求的直流電源。

The purpose of this research is to develop an automatic tracking system. By using a CCD camera and a wireless transmission module mounted on the remote control car, the images are transmitted to the computer. The computer, then, searches the object contour based on the algorithm developed by ourselves and sends a signal to control the motion of the car.
In algorithm implementation, first, putting contour points equally on the rim of the object, we find out the new position for each contour point whenever the object move by minimizing the energy function, calculating the adjustable contour searching range and direction proposed in Adaptive ACM. At this time, the contour could be interfered with noise and therefore get the part not belong to the object. Next, to reduce the probability of tracking miss, the research uses both of the information of the angle between the contour points and ASM to correct and decrease the influence to the contour produced by noise.
For the control circuit design, we have designed a control circuit to replace the variable resister normally used in remote controller. Also, we have implemented a control circuit to drive the car under the command of the signal from the computer. In order to run the tracking system outdoors, we have also designed a dc chopper circuit to supply the varieties of dc power sources needed in the system.

[1] 顧靜恆, 利用電腦視覺與圖形識別技術在室內環境中作自動車避碰及追蹤人航行之研究, 國立交通大學資訊科學系博士學位論文, 1999.
[2] 陳冠宇, 利用電腦視覺技術做自動車航行之室內環境學習及導航, 國立交通大學資訊科學系博士學位論文, 2000.
[3] M. Kass, A. Witkin and D. Terzopoulos, ”Snake: Active contour models,” International Journal of Computer Vision, vol.1, no.4 pp.321 - 331, 1987.
[4] T. F. Cootes, C. J. Taylor, D. H. Cooper and J. Graham, ”Active shape models-Their training and application,” Computer Vision and Image Understanding, vol.61, no.1, pp.38 - 59, 1995.
[5] 羅欣然, 可動態調整搜尋範圍與方向的ACM結合ASM影像追蹤系統, 國立台灣科技大學電機工程系碩士學位論文, 2004.
[6] Ivins, J.; Porrill, J. ”Active region models for segmenting medical images,” IEEE International Conference on Image Processing, vol.2, pp.227 -231,1994.
[7] D. P. Perrin and C. E. Smith, ”Rethinking classical internal forces for active contour models,” Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, vol.2, pp.II-615 – II-620, 2001.
[8] D. J. Kang, J. Y. Kim and I. S. Kweon, ”A stabilized snake constraint for tracking object boundaries,” IEEE International Symposium on Industrial Electronics, vol.1, pp.672 - 677, 2001.
[9] I. T. Jolliffe, Principal Component Analysis, Springer Verlag, Inc., 1986.
[10] Berhard Flury, Common Principal Components and Related Multivariate Models, John Wiley & Sons, Inc., 1988.
[11] J. E. Jackson, A User s Guide to Principal Components, John Wiley & Sons, Inc., 1991.
[12] Pearaon, K. “On lines and planes of closest fit to systems of points in space.” Philosophical Magazine, vol.2, pp.559 - 572, 1901.
[13] Hotelling, H. ”Analysis of a complex of statistical variables into principal components,” Journal of Educational Psychology, vol.24, pp. 498-520, 1933.
[14] 陳衍亨, 利用人臉影像的三維資訊作身分驗證, 國立交通大學資訊科學研究所碩士論文, 2002.
[15] 陳瑞熙, 高堅志, 鄭明哲, 微電腦介面技術與實作, 碁峰資訊, 1991.
[16] 謝夏玲,李齊雄,微電腦I/O控制與實作, 儒林, 1995.
[17] RASHID M. H., Power Electronics Circuis, Devices, and Applications, 2nd ed., Prentice-Hall International, Inc., 1993.