在做車道線偵測時，針對感興趣的區域(region of interest, ROI)做定義是為了減少檢測的計算量。在參數空間上一般會習慣將ROI限制成矩形，但矩形的區域容易產生偵測線的躁動。為了解決這個問題，本文中提出了一個橢圓形的ROI在霍夫轉換(Hough Transform, HT)的參數空間中。這麼做不僅提高了車道偵測的精確度，還減少了HT的計算複雜度。

此外本論文還提出了兩種系統。第一個是輔助車道偵測系統，它可用來防止突發事件，如車道線的消失。第二個是變換車道系統，它能有效的警示駕駛者已經偏離車道或正在切換車道。實驗結果證實我們的演算法能夠成功且有效地運用在車道偵測上。

Region of interest (ROI) for the lane detection is a commonly used approach to reduce the computational complexity. However, the traditional ROI in the Hough parameter space is prone to result in vibrated lane markings. To solve this problem, this study presents an elliptic ROI in the Hough parameter space. The proposed ROI not only can increase the accuracy of lane detection but also can further reduce the computational complexity of Hough transform.

Besides, this study also presents two auxiliary systems. One is the assistant lane detection, which is used to solve the problem that one side of lane-markings is disappeared. The other one is the lane changing system, which can be used to warn the driver that the car is going to leave the track. Experimental results show that the proposed algorithm results in more accurate and satisfying lane-marking detection.

[1]車輛中心研發處，「車道偏移警示系統實車搭載功能驗證之探討」，財團法人車輛研究測試中心，2010年9月。
[2]廖永盛, 葉智賢, 謝熹玟，「實現於嵌入式平台之車道辨識演算法」，智慧車輛技術專集，2006年6月。
[3]曾定章，「先進安全車輛的多樣性視覺偵測辨識技術發展」， 中央大學資訊工程系，2010年6月 。
[4]交通部台灣區國道高速公路局，http://www.freeway.gov.tw/Publish.aspx?cnid=516&p=128。
[5]蔡一峰、劉景富，「以DSP晶片實現視覺辨識之車道偏移警示系統」，財團法人車輛研究測試中心，2009年6月。
[6]瑞馳科技股份有限公司，http://www.tonfada.com/main.php。
[7]B.-F Wu, W.-H. Chen, C.-W. Chang, C.-J. Chen and M.-W. Chung, ”A New Vehicle Detection with Distance Estimation for Lane Change Warning Systems,” IEEE Intelligent Vehicles Symposium, June 2007, pp. 698–703.
[8]F. You, R.-B. Wang and R.-H. Zhang, “Based on Digital Image Lane Edge Detection and Tracking under Structure Environment for Autonomous Vehicle,” IEEE International Conference on Automation and Logistics, Aug. 2007, pp.1310-1314.
[9]B. Zheng, B. Tian, J. Duan and D. Gao, “Automatic Detection Technique of Preceding Lane and Vehicle,” Proceedings of the IEEE International Conference on Automation and Logistics Qingdao, Sep. 2008, pp. 1370-1375.
[10]Q. Lin,Y. Han and H. Hahn, “Real-time Lane Departure Detection Based on Extended Edge-linking Algorithm,” Second International Conference on Computer Research and Development, June. 2010, pp.725-730.
[11]J. Wang and X. An, “A Multi-step Curved Lane Detection Algorithm Based on Hyperbola-Pair Model,” IEEE International Conference on Automation and Logistics (ICAL), Aug. 2010, pp132-137.
[12]J. Wang, Y. Wu, Z. Liang and Y. Xi, “Lane Detection Based on Random Hough Transform on Region of Interesting,” IEEE International Conference on Information and Automation (ICIA), Jun. 2010, pp.1735-1740.
[13]C.-Y. Su and G.-H. Fan, “An Effective and Fast Lane Detection Algorithm,” Proceedings of the 4th International Symposium on Advances in Visual Computing, vol. 5359, pp. 942-948, 2008.
[14]范耿豪, “以霍夫轉換為基礎之智慧型快速車道線偵測,” 國立臺灣師範大學 ,碩士論文 ,民國九十八年七月。
[15]N. Otsu, “A Threshold Selection Method from Gray-Level Histogram,” IEEE Tran. On System, Man, and Cybernetics, val. SMC-9, pp. 62-66, 1979.
[16]A. Suzuki, N. Yasui, N. Nakano and M. Kaneko, “Lane Recognition System for Guiding of Autonomous Vehicle,” Intelligent Vehicles 92 Symposium., Jun. 1992, pp.196-201.
[17]R. O. Duda and P. E. Hart, “Use of the Hough Transform to Detect Lines and Curves in Pictures,” CACM(15). , no. 1, January 1972, pp. 11-15.
[18]P. Kultanen, L. Xut and E. Oja, “Randomized Hough Transform(RHT),” 10th International Conference on Pattern Recognition, Jun. 1990, pp.16-21.
[19]S. Du, B. J. van Wyk, C. Tu and X. Zhang, “An Improved Hough Transform Neighborhood Map for Straight Line Segments”, IEEE Transactions On Image Processing , Vol.19 No.3, Mar. 2010.
[20]R. K. Satzoda, S. Sathyanarayana and T. Srikanthan, “Hierarchical Additive Hough Transform for Lane Detection,” IEEE Embedded Systems Letters, vol. 2 no. 2 pp.23-26, Jun. 2010.
[21]R. K. Satzoda, S. Suchitra, and T. Srikanthan, “Parallelizing the Hough transform computation,” IEEE Signal Process. Letters , vol. 15 pp.297–300, 2008.
[22]S. Ben Yacoub and J.-M. Jolion, “Hierarchical line extraction,” IEE Proc. Vis. Image Signal Process., vol. 142, no. 1, pp. 7–14, 1995.
[23]C. Espinosa and M. A. Perkowski, “Hierarchical Hough transform based on pyramidal architecture,” in Proc. 11th Annual International Phoenix Conference Computers and Communications, Scottsdale, AZ., Apr. 1992, pp. 743–750.
[24]J. Princen, J. Illingworth, and J. Kittler, “A hierarchical approach to line extraction,” in Proc. IEEE Computer Society Conference and Computers Vision Pattern Recognition, San Diego, CA, Jun. 1989, pp. 92–97.
[25]B. Fardi, U. Scheunert, H. Cramer, G. Wanielik, “A New Approach for Lane Departure Identification,” IEEE Intelligent Vehicles Symposium, Jun. 2003, pp.100-105.
[26]H.-Y. Fan and C.-Y. Su, “A Lane Detection Algorithm Based on Ellipse Area for Search Region in Hough Space,” ILT 2011 Intelligent Living Technology, May. 2011.