近幾年來，為了降低因駕駛者不當駕駛所發生的交通事故以及提高安全性與舒適性，進而在自動化汽車的安全系統應用上有許多新技術發展逐漸被人們重視並且被視為必要性的配備，而車道保持系統則為其一的重要應用。本論文透過網路攝影機擷取道路路面影像，將所得到之影像利用顏色特徵擷取濾波器與頂-帽濾波器偵測出車道線以及降低背景雜訊對車道線所造成的影響。經過影像處理過後所得資訊，再利用最小平方法求得虛擬中心線用來作為代步車所要依循之軌跡，並透過模糊邏輯控制器判別出控制載具所需轉向角度並修正前進之方向。相較於前人所做的研究，此方法不需多餘的感應器來引導車子，並且可透過攝影機擷取不連續或連續的車道線來進行車道保持，本研究透過自行設計的電動代步車驗證所設計之車道保持系統之有效性。

In recent years, many techniques in automobile active safety applications have been developed and regarded as the essential and standard equipments of vehicles. Lane keeping assist system (LKAS) is one of these important applications. In this thesis, we have developed a vision system that utilizes a webcam to capture the image of roads, and use a color extraction filter and a top-hat filter to detect the lane markers on the roads and reduce
the background noise that might cause misclassifications on the lane markers. With the information of the lane markers, we can obtain a virtual centerline by a least-squares method that best fits the central points between two lane markers. The virtual centerline is
regarded as the trajectory for the vehicle to follow and a fuzzy logic controller has been designed to control the vehicle. The advantage of the proposed lane keeping assist
system is that it only requires a camera to capture the road images for recognizing solid or dashed lane markers. The effectiveness of the proposed lane keeping assist system has been validated by experiments on the roads with various curves.

[1] Y. I. Abdel-Aziz and H. M. Karara, “Direct linear transformation into object space
coordinates in close-Range photogrammetry,” in Proc. Symp. on Close-Range
Photogrammetry, pp. 1-18, 1971.
[2] D. H. Ballard and C. M. Brown, Computer Vision. Upper Saddle River, NJ:
Prentic-Hall, 1982.
[3] H. A. Beyer, “Some aspects of the geometric calibration of CCD-camera,” in ISPRS.
FAST Processing of Photogrammetry Data, Interlake, 1987.
[4] T. Bucher, C. Curio, J. Edelbrunner, C. Igel, D. Kastrup, I. Leefken, G. Lorenz, A.
Steinhage, and W. von Seelen, “Image processing and behavior planning for
intelligent vehicles,” IEEE Trans. Industrial Electronics, vol. 50, no. 1, pp. 62-75,
2003.
[5] L. J. Chen, “CCD camera calibration with DLT,” Journal of Computer, no. 3, 1990.
[6] S. B. Choi, “The design of a look-down feedback adaptive controller for the lateral
control of front-wheel-steering autonomous highway vehicles,” IEEE Trans.
Vehicular Technology, vol. 49, pp. 2257-2269, 2000.
[7] R, Chapuis, R. Aufrere, and F. Chausse, “Accurate road following and
reconstruction by computer vision,” IEEE Trans. Intelligent Transportation Systems,
vol. 3, pp. 261-270, 2002.
[8] C. Demonceaux, A. potelle, and D. Kachi-Akkouche, “Obstacle detect in a road
scene based on motion analysis,” IEEE Trans. Vehicular Technology, vol. 53, pp.
1649-1656, 2004.
[9] J. Douret, R. Labayrade, J. laneurit, and R. Chapuis, “A reliable and robust lane
detection system based on the parallel use of three algorithms for driving safety
assistance,” IEICE Trans. INF. & SYST., vol. E89-D, no. 7, 2006.
Ref.-ii
[10] S. G. Foda and A. K. Dawoud, “Highway lane boundary determination for
autonomous navigation,” in Proc. IEEE Pacific Rim Conf. Communications,
Computers and Signal Processing, pp. 698-702, 2001.
[11] J. Guldner, H.-S. Tan, and S. Patwardhan, “Analysis of automatic steering control
for vehicles with look down lateral reference systems,” Veh. Syst. Dynamics, vol. 26,
no. 4, pp. 243-269, 1996.
[12] J. Guldner, H.-S. Tan, and S. Patwardhan, “Study of design directions for lateral
vehicle control,” in Proc. the 36th Conf. Decision and Control, pp. 1732-1737, 1997.
[13] J. P. Gonzalez and U. Ozguner, “Lane detection using histogram-based
segmentation and decision trees,” in Proc. IEEE Intell. Transport. Syst., pp. 346-351,
2000.
[14] R. C. Gonzalez and R. E. Woods, Digital Image Processing. Upper Saddle River, NJ:
Prentice Hall, 2002.
[15] J. Huang and M. Tomizuka, “LTV controller design for vehicle lateral control under
fault in rear sensors,” IEEE/ASME Trans. Mechatronics, vol. 10, pp. 1-7, 2005.
[16] S.-Y. Kim and S.-Y. Oh, “A driver adaptive lane departure warning system based on
image processing and a fuzzy evolutionary technique,” in Proc. IEEE Conf.
Intelligent Vehicles Symposium, pp. 361-365, 2003.
[17] R. Labayrade, S.-S. Ieng, and D. Aubert, “A reliable road lane detector approach
combining two vision-based algorithms,” in Proc. IEEE Conf. Intelligent
Transportation System, pp. 149-156, 2004.
[18] J. Miura, M. Itoh, and Y. Shirai, “Toward vision-based intelligent navigator: Its
concept and prototype,” IEEE Trans. Intelligent Transportation System, vol. 3, no. 2,
pp. 136-146, 2002.
[19] K. Odagiri, K. Kobayashi, K. Watanabe, H. Umino, and N. Numata, “Development
of active contour extraction for autonomous vehicle lane detection at outdoor
environment,” in Proc. Society of Automotive Engineers, no. 2001-01-0807, 2001.
[20] Y. Otsuka, S. Muramatsu, H. Takenaga, Y. Kobayashi, and T. Monj, “Multitype
lane markers recognition using local edge direction,” in Proc. IEEE Intelligent
Vehicles Symp., vol. 2, pp. 604-609, 2002.
[21] K. A. Redmill, “A simple vision system for lane keeping,” in Proc. IEEE Conf.
Intelligent Transportation System, pp. 212-217, 1997.
[22] N. Schleqel, P. Kachroo, J. A. Ball, and J. S. Bay, “Image processing based control
for scaled automated vehicles,” in Proc. IEEE Conf. Intell. Transport. Syst., pp.
1022-1027, 1997.
[23] M. Tsuji, R. Shirato, H. Furusho, and K. Akutagawa, “Estimation of road
configuration and vehicle attitude by lane detection for a lane-keeping system,” in
Proc. Society of Automotive Engineers, no. 2001-01-0799, pp. 45-51, 2001.
[24] T. Taoka, M. Manabe, and M. Fukui, “An efficient curvature lane recognition
algorithm by piecewise linear approach,” in Proc. IEEE 65th Vehicular Technology
Conf., pp. 2530-2534, 2007.
[25] M. Yamamoto, Y. Kagawa, and A. Okuno, “Robust control for automated lane
keeping against lateral disturbance,” in Proc. IEEE International Conf. Intelligent
Transportation Systems, pp. 240-245, 1999.
[26] 吳上立 編譯, “c語言數位影像處理,” 全華科技, 2006.
[27] 鍾國亮, “影像處理與電腦視覺,” 東華書局, 2006.