Lane Detection Method Based on Recursive Binary Fitting ^†

This paper introduces a method of lane detection based on recursive binary fitting method of the lane detection: First use canny edge detection algorithm to detect the edges on the basis of gray images, and then scan the edge image from the left to the right and from the bottom to the top, we can extract the inner side of the lane edge of the interested region and dilate the lane by connecting some breakup, and on this basis and through the connected domain filtering, to remove the one that does not conform to the characteristics of binary image of lane. At last, we can get the lane by the recursive binary fitting method. The results show that the algorithm has good robustness and real-time performance.