基於霍夫轉換在參數空間以橢圓形搜尋範圍為基礎之車道線偵測

A Lane Detection Algorithm Based on Elliptical Searching Region in Hough Parameter Space

范修源(H.-Y. Fan)

指導教授 ： 蘇崇彥

國立臺灣師範大學/科技學院/工業教育學系/碩士(2011年)

摘要

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。

關鍵字

霍夫轉換 ； 感興趣的區域 ； 輔助車道偵測系統 ； 變換車道系統

並列摘要

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.

並列關鍵字

Hough Transform(HT) ； Region of Interest(ROI) ； Assistant Lane Detection ； Lane Changing System

參考文獻

[6]瑞馳科技股份有限公司，http://www.tonfada.com/main.php。

[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。

[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 。

[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.