A Lane Detection Approach for Driver Assistance

For autonomous vehicles and video-based navigation systems it is necessary to determine position of the ego vehicle relative to the road. One of the principal approaches is to detect lanes using a vision system in the vehicle. In this paper we propose a general method for lane detection that combines steerable filters developed by Freeman and Adelson with Canny edge detection algorithm. The steerable filters used in our paper are based on second derivatives of two-dimensional Gaussians. These filters are useful in many early vision and image processing tasks. The filter results are then processed to eliminate outliers based on the expected road geometry. Our algorithm is able to provide robust and accurate extraction of lane markings under varying lighting and road conditions.