近年來，行車安全愈來愈受到人們重視。為了改善行車安全，本論文使用一部架設在車上的相機擷取前方道路影像以偵測道路及行車狀況。本研究所包含的偵測工作有：車道線偵測、多車道位置估計、車道線分類及前車距離估計。
車道線是藉由在影像中搜尋車道線模型中的最佳參數來求得，同時藉由限制車輛的偏轉角度來減少搜尋空間以達到即時偵測的需求，並利用累積邊緣點的方式將車道線分類。多車道位置估計則是利用一限制的公式，不需額外地搜尋就可估計出相鄰車道的位置。相機相對於空間座標系統的傾斜角度和偏轉角度可以由車道線的消失點推論得知，因此前車距離可藉由得到傾斜角估計求出。
實驗結果顯示本研究所提出的方法可以有效地偵側出本車道與相鄰車道的車道線位置，前車距離估計與車道線分類可提供更多有用資訊給駕駛人。在 Pentium 4 2.4GHz 的一般個人電腦上執行車道線偵測、虛實車道線分類、多車道位置估計、與偏離車道警示所需的平均處理時間約為0.027秒。

Recently, people pay much attention on driving safety. To improve the driving safety, we used a camera mounted on the vehicle to capture road scenes for road and driving situation detection. The detection tasks in this study include lane marking detection, multi-lane estimation, lane marking classification, and front-vehicle distance estimation.
The lane markings are detected by searching the optimal parameters of a defined lane model on the images. By restricting the yaw angle of the vehicles, the searching space can be reduced to achieve the real time requirement. The multiple lane estimation method estimates the adjacent lanes based on a restricted formula without any search. The lane markings are classified based on a proposed method of accumulating edge pixels. The tilt and pan angles of camera related to the world coordinate system can be inferred from the vanishing point of lane markings. The distance to a front vehicle is then estimated from the acquired tilt angle.
The experimental results show that the proposed method can detect the current lane markings and adjacent lanes efficiently. The estimated distance and lane marking classification are good enough to provide more information to the drivers. The whole processing time of the proposed system is about 0.027 seconds in average on a 2.4 GHz Pentium-based personal computer.

[1] Aufrère, R., R. Chapuis, and F. Chausse, “A fast and robust vision based road following algorithm,” in Proc. IEEE Intelligent Vehicles Sym., Dearborn, MI, Oct.3-5, 2000, pp.192-197.
[2] Aufrère, R., R. Chapuis, and F. Chausse, “A model-driven approach for real-time road recognition,” Machine Vision and Applications, vol.13, no.2, pp.95-107, 2001.
[3] Bertozzi, M. and A. Broggi, “Real-time lane and obstacle detection on the GOLD system,” in Proc. IEEE Intelligent Vehicles Sym., Tokyo, Japan, Sep.18-20, 1996, pp.213-218.
[4] Bertozzi, M., A. Broggi, and S. Castelluccio, “A real-time oriented system for vehicle detection,” Journal of Systems Architecture, vol.43, pp.317-325, 1997.
[5] Bertozzi, M., A. Broggi, G. Conte, and A. Fascioli, “Obstacle and lane detection on ARGO on autonomous vehicle,” in Proc. IEEE Int’l Conf. Intelligent Transportation Systems, Boston, Nov.10-13, 1997, pp.1010-1015.
[6] Bertozzi, M. and A. Broggi, “GOLD: a parallel real-time stereo vision system for generic obstacle and lane detection,” IEEE Trans. on Image Processing, vol.7, no.1, pp.62-81, Jan. 1998.
[7] Bertozzi, M., A. Broggi, and A. Fascioli, “Stereo inverse perspective mapping: theory and applications,” Image and Vision Computing, vol.16, pp.585-590, 1998.
[8] Bertozzi, M., A. Broggi, G. Conte, and A. Fascioli, “Vision-based automated vehicle guidance: the experience of the ARGO vehicle,” in Tecniche di Intelligenza Artificiale e Pattern Recognition per la Visione Artificiale, Apr.6-7, 1998, pp.35-40.
[9] Bertozzi, M., A. Broggi, G. Conte, and A. Fascioli, “The experience of the ARGO autonomous vehicle,” in Proc. SPIE’98 - Enhanced and Synthetic Vision, Orlando, FL, Apr.13-17, 1998.
[10] Bertozzi, M., A. Broggi, and A. Fascioli, “Experiments using MMX-based processors for real-time image processing on the ARGO vehicle,” in Proc. IEEE Intelligent Vehicles Sym., Stuttgart, Germany, Oct.28-30, 1998, pp.505-510.
[11] Bertozzi, M., A. Broggi, M. Cellario, A.Fascioli, P. Lombardi, and M. Porta, “Artificial vision in road vehicles,” Proc. of the IEEE, vol. 90, no.7, pp. 1258-1271, Jul. 2002.
[12] Bertozzi, M., A. Broggi, A. Fasciolo, and A. Tibaldi, “An evolutionary approach to lane markings detection in road environments,” in Atti del 6 convegno dell’Associazione Italiana per I’Intelligenza Artificiale, Siena, Italy, Sep. 2002, pp.627-736.
[13] Broggi, A., “Parallel and local feature extraction: a real-time approach to road boundary detection,” IEEE Trans. on Image Processing, vol.4, no.2, pp.217-223, 1995.
[14] Broggi, A., “Robust real-time lane and road detection in critical shadow conditions,” in Proc. IEEE Int’l Sym. on Computer Vision, Coral Gables, Florida, Nov.19-21, 1995, pp.353-358.
[15] Broggi, A. and S. Bertè, “Vision-based road detection in automotive systems: a real-time expectation-driven approach,” Journal of Artificial Intelligence Research, vol.3, pp.325-348, Dec.1995.
[16] Broggi A., M. Bertozzi, A. Fascioli, and G. Conte, Automatic Vehicle Guidance: The Experience of The ARGO Autonomous Vehicle, World Scientific, Singapore, 1999.
[17] Broggi, A., M. Bertozzi, A. Fascioli, C. G. L. Bianco, and A. Piazzi, “The ARGO autonomous vehicle’s vision and control systems,” Int. Journal of Intelligent Control and Systems, vol.3, no.4, pp.409-441, 1999.
[18] Broggi, A., M. Bertozzi, and A. Fascioli, “Architectural issues on vision-based automatic vehicle guidance: the experience of the ARGO project,” Real-Time Imaging Journal, vol.6, issue 4, pp.313-324, Aug. 2000.
[19] Canny, J., “A computational approach to edge detection,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol.8, no.6, pp.679-698, Nov. 1986.
[20] Charkari, N. M. and H. Mori, “A new approach for real time moving vehicle detection,” in Proc. IEEE Conf. on Intelligent Robots and Systems, Yokohama, Japan, July 26-30, 1993, pp.273-278.
[21] Chern, M.-Y., and P.-C. Hou, “The lane recognition and vehicle detection at night for a camera-assisted car on highway,” in Proc. IEEE Conf. on Robotics and Automation, Taipei, Taiwan, Sep.14-19, 2003, pp.2110-2115.
[22] Choi, S. Y. and J. M. Lee, “Lane recognition and obstacle detection using moving windows,” Journal of The Institute of Electronics Engineers of Korea, vol.36-S, no.1, pp.93-103, Jan. 1999.
[23] Choi, S. Y. and J. M. Lee, “Optimal moving windows for real-time road image processing,” in Proc. IEEE Int’l Conf. on Robotics and Automation, Seoul, Korea, May 21-26, 2001, pp.1220-1225.
[24] Choi, S. Y., T. S. Jin, and J. M. Lee, “Optimal moving windows for real-time road image processing,” Journal of Robotic systems, vol.20, no.2, pp.65-77, Feb. 2003.
[25] Chu J., L. Ji, L. Guo, Libibing, and R. Wang, ”Study on method of detecting preceding vehicle based on monocular camera,” in Proc. IEEE Intelligent Vehicles Sym., Parma, Italy, June14-17, 2004, pp.750-755.
[26] Gern, A., U. Franke, and P. Levi, “Advanced lane recognition - fusing vision and radar,” in Proc. IEEE Intelligent Vehicles Sym., Dearborn, MI, Oct.3-5, 2000, pp.45-51.
[27] Grimmer, D., S. Lakshmanan, “A deformable template approach to detecting straight edges in radar images,” IEEE Trans. Pattern Anal. Machine Intel, vol.18, no. 4, pp.438-443, Apr. 1996.
[28] Ioannou, P. A., H. Jula, and E. B. Kosmatopoulos, “Collision avoidance analysis for lane changing and merging,” IEEE Trans. Vehicular Technology, vol.49, no. 6, pp.2295-2308, Nov. 2000.
[29] Jung, C. R. and C. R. Kelber, “A robust linear-parabolic model for lane following,” in Proc. of the 17th Brazilian Symp. on Computer Graphics and Image Processing, Oct.17-20, 2004, pp. 72-79.
[30] Kaliyaperumal, K., K. Kluge, and S. Lakshmanan, “An algorithm for detecting roads and obstacles in radar images,” IEEE Trans. Vehicular Technology, vol.50, no. 1, pp.170-182, Jan. 2001.
[31] Kaske, A., R. Husson, and D. Wolf, “Chi-square fitting of deformable templates for lane boundary detection,” in Proc. IAR Annual Meeting ’95, Grenoble, France, Nov. 1995, pp.66-78.
[32] Kaske, A., D. Wolf, and R. Husson, “Lane boundary detection using statistical criteria,” in Int’l Conf. QCAV97-Quality by Artificial Vision, Le Creusot, France, 1997, pp.28-30.
[33] Kluge K., “Extracting road curvature and orientation from image edge points without perceptual grouping into features,” in Proc. IEEE Intelligent Vehicles Sym., Oct.24-26, 1994, pp.109-114.
[34] Kluge K., S. Lakshmanan, “A deformable-template approach to lane detection,” in Proc. IEEE Intelligent Vehicles Sym., Detroit, MI, Sep.25-26, 1995, pp.54-59.
[35] Lee, J.-W., J.-H. Kim, Y.-J. Lee, and K.-S. Lee, ”A study on recognition of lane and movement of vehicles for port AGV vision system,” in Proc. IEEE Conf. on Industrial Electronics, Italy, July 8-11, 2002, pp.463-466.
[36] Liu, H.-J., Real-Time Model-based Lane and Vehicle Detection, Master Thesis, Department of Computer Science and Information Eng., National Central University, Chung-li, Taiwan, 2004.
[37] Malik, J., C. J. Taylor, J. Weber, D. Koller, and Q. T. Luong, A Combined Approach to Stereopsis and Lane-finding, PATH Research Report on Intelligent Transportation System, Univ. of California, Berkeley, July 1997.
[38] McCall, J. C. and M. M. Trivedi, “An integrated, robust approach to lane marking detection and lane tracking,” in Proc. IEEE Intelligent Vehicles Symp., Parma, Italy, June 14-17, 2004, pp. 533-537.
[39] Nedevschi, S., R. Schmidt, T. Graf, R. Danescu, D. Frentiu, T. Marita, F. Oniga, and C. Pocol, “3D lane detection system based on stereo vision,” in Proc. IEEE Int’l Conf. Intelligent Transportation systems Conf., Washington DC, Oct. 3-6, 2004, pp. 161-166.
[40] Park, J. W., Lee J. W., and Jhang K. Y., “A lane-curve detection based on an LCF,” Pattern Recognition Letters, vol.24, no.14, pp. 2301-2313, Oct. 2003.
[41] Shu, Y. and Z. Tan, “Vision based lane detection in autonomous vehicle,” in Proc. of the 5th World Congress on Intelligent Control and Automation, Hangzhou, China, June 15-19, 2004, pp. 5258-5260.
[42] Tseng, D.-C., Monocular Computer Vision Aided Road Vehicle Driving for Safety, U.S. Patent, No. 6765480, July 20, 2004.
[43] Wang, Y., D. Shen, and E. K. Teoh, “Lane detection using Catmull-Rom spline,” in Proc. IEEE Intelligent Vehicles Sym., Stuttgart, Germany, Oct.28-30, 1998, pp.51-57.
[44] Wang, Y., D. Shen, and E. K. Teoh, “Lane detection using spline model,” Pattern Recognition Letters, vol.21, pp.677-689, 2000.
[45] Wang, Y., E. K. Teoh, and D. Shen, “Lane detection and tracking using B-Snake,” Image and Vision Computing, vol.22, no.4, pp.269-280, Apr. 2004.
[46] Wang, Y., E. K. Teoh, and D. Shen, “Lane detection using B-snake,” in Proc. IEEE Information Intelligence and Systems Sym., Bethesda, MD, Oct.31-Nov.3, 1999, pp.438-443.
[47] Camera Calibration Toolbox for Matlab, http://www.vision.caltech.edu/bouguetj/calib_doc/index.html.