Robust Road Lane Detection for High Speed Driving of Autonomous Vehicles

With the Hough transform and region of interest, how to improve the processing time of high-speed driving is being actively investigated. This study proposes a road lane detection algorithm based on expressway driving videos through a computer vision-based image processing system without using sensors. The proposed method detects straight lines that are estimated to be lanes using the Hough transform. When lanes are detected from actual images, the scope of left and right lanes is limited to reduce computational load. Extensive simulation results are given to show the effects of Hough transform method for high speed driving and region of interest for processing time on actual expressways.