A practical method of road detection for intelligent vehicle

• Published in: 2009 IEEE International Conference on Automation and Logistics pp. 980 - 985
• Main Authors: Dezhi Gao, Wei Li, Jianmin Duan, Banggui Zheng
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.08.2009
• Subjects: adaptive double threshold; Change detection algorithms; Convolution; Data mining; Image edge detection; improved SUSAN algorithm; Intelligent vehicles; inverse transformation; Kernel; Lighting; road detection; Road vehicles; Robustness; Vehicle detection
• ISBN: 9781424447947; 1424447941
• ISSN: 2161-8151
• DOI: 10.1109/ICAL.2009.5262562

In the paper, a practical method for road detection is proposed. Many features of vehicle are introduced to detect the preceding vehicles. According to the characteristics of lane marks and vehicles, the improved Sobel operator convolution kernel is introduced in the image preprocessing to enhance the robustness of the algorithm. In order to be feasible to the change of illumination and road conditions, the adaptive double threshold method is introduced to get the binary image, the edges which are needed during detection of lane marks and front vehicles are extracted with Hough Transformation and SUSAN algorithm based on adaptive threshold in different contrast ratio. In order to apply the information to implement the lane departure warming system and forward collision warming system, both distances from host vehicle to left and right lane lines and preceding vehicles are estimated according to the inverse projection. Experiment results indicate that this algorithm is feasible for different road conditions and can realize the detection and tracking of the lane lines and vehicles with robustness and efficiency simultaneously.