車道保持(lane keeping)對於交通安全而言，為一重要的要素，且為智慧型車輛研究中一門重要的課題。本研究提出以影像為基礎之智慧型車道保持系統，可防止因駕駛人不專心或是精神不濟導致的偏離車道情況，進而減少交通意外的產生。
本系統中，輸入為道路影像，輸出為方向盤轉角度數，並嘗試以PID控制器，保持車輛行駛在車道中，以減少意外發生的機率。而且，爲了減少影像處理所須的時間，因此在本研究中也使用了幾個減少影像運算量及簡化處理過程的方法，利用較簡單的影像處理法則來得到影像特徵，以減少影像處理的時間，配合影像投影座標轉換與PD和PID控制器，可作即時的車輛動態控制。本研究並考慮了將來使用嵌入式系統，取代電腦來進行影像處理及車輛控制，增加了今後本研究實現在商用車的可能性。
相較於前人之研究而言，本系統不但不需要特別的標的物，可直接使用不連續車道線作為影像特徵外，且可在行駛中經由影像處理得知目前車輛的方向角以及相對於車道的側向位置，並且之後可實踐於嵌入式系統中，以滿足量產商用車的考量，並增進今後的交通安全。

In this work, a control system of lane keeping by utilizing lane markers in the image as the image characteristics and the designed Proportional-Derivative (PD) or Proportional-Integral-Derivative (PID) controllers has been presented. The white lane markers painted on the road were seized as the input image characteristics, and the time needed to handle the input data was decreased by using grayscale transformation, resizing, and Region of Interest (ROI). Then, a PD or PID controller is designed to keep the vehicle driving along the center line of current lane and the steering angle was employed as controller output.
The proposed method in this thesis eliminated special lane marks as the input image characteristics, and was able to detect current vehicle orientation and lateral position in the lane without any special hardware. These advantages improved the current lane keeping system and could reduce the amount of traffic accidents.

[1] A. Ulsoy and H. Peng, Vehicle Control System, The University of Michigan, Intelligent Transportation Systems, pp. 14.4-14.7, 1997.
[2] A. Takagi, S. Muto, and T. Akiyama, “Economic evaluation of advanced cruise-assist highway systems focusing on psychological effects,” Selected Proceedings of the 10th World Conference on Transport Research, pp. 1443-1454, 2005.
[3] M. Yoshida and H. Kamada, “A visual control system using image processing and fuzzy theory,” IEEE Round-table Discussion on Vision-based Vehicle Guidance, pp. 111-128, 1990.
[4] C. Thorpe, M. Hebert, T. Kanade, and S. Shafer, “Towards autonomous driving: the CMU Navlab,” IEEE Expert, vol.6, pp. 31-42, 1991.
[5] T. Hessburg and M. Tomizuka, “Fuzzy logic control for lateral vehicle guidance,” IEEE Control System, vol.2, pp. 55-63, 1994.
[6] D. LeBlanc et al., “CAPC: A road-departure prevention system,” Proceedings of IEEE Conference on Control Application, pp. 61-71, 1996.
[7] R. Yang, C. Huang, and R. Chen, “A vision-based intelligent driver-copilot for vehicle lateral control,” Proceedings of the International Symposium on Advanced Vehicle Control, pp. 389-394, 1998.
[8] J. Jang and C. Sun, “Neuro-fuzzy modeling and control,” Proceedings of the IEEE, vol.83, pp. 378-406, 1995.
[9] L. Wang, Adaptive Fuzzy System and Control, Prentice-Hall International Inc., pp. 65-82, 1994.
[10] K. Redmill, “Simple vision system for lane keeping,” Proceeding of IEEE Conference on Intelligent Transportation System, pp. 212-217, 1997.
[11] M. Aste, M. Rossi, R. Cattoni, and B. Caprile, “Visual routines for real-time monitoring of vehicle behavior,” Machine Vision and Applications, vol.11, pp. 16-23, 1998.
[12] R. Risack, N. Mohler, and W. Enkelmann, “A video–based lane keeping assistant,” Proceedings of the IEEE Intelligent Vehicles Symposium, pp. 356-361, 2000.
[13] S. Lee and W. Kwon, “Robust lane keeping from novel sensor fusion,” Proceeding of the IEEE International Conference on Robotics and Automation, vol.4, pp. 3704-3709, 2001.
[14] X. Zhou and X. Huang, “Multi Lane Line Reconstruction for Highway Application with A Signal View,” Proceedings of the Third International Conference on Image and Graphics IEEE, pp. 35-38, 2004.
[15] S. Suryanarayanan, “Design of simultaneously stabilizing controllers and its application to fault-tolerant lane-keeping controller design for automated vehicles,” IEEE Transactions on Control System Technology, vol.12, pp. 329-339, 2004.
[16] Yeh and Chen, “Vision-based lane and vehicle detection methods on a dual-core DSP platform,” Proceedings of the International Symposium on Advanced Vehicle Control, pp. 685-690, 2006.
[17] T. Gillespie, Fundamentals of Vehicle Dynamics, Society of Automotive Engineers, 1992.
[18] Z. Zalila and F. Coffin, “Transversal control of an autonomous vehicle by a fuzzy supervisor,” Wescon Conference Record, pp. 626-635, 1995.
[19] W. Winsum, K. Brookhuis, and D. Waard, “A comparison of difference ways to approximate time-to-lane crossing (TLC) during car driving,” Accident Analysis and Prevention, vol.32, pp. 47-56, 2000.
[20] N. Matsumoto and M. Tomizuka, “Fuzzy logic control for lateral vehicle guidance,” IEEE Control Systems, pp. 55-63, 1994.