Nighttime lane markings recognition based on Canny detection and Hough transform

Abstract

It is difficult to detect the nighttime lane lines which showed darker and uneven lighted. In order to overcome these problems, a lane recognition method was proposed. Firstly, edge enhancement based on Laplacian was used to enhance the pre-processing image's edges. Then, the edges were detected by Canny based on Otsu algorithm and the straight lines which within the one third at bottom of image were detected by Hough transform. Finally, an inside lane line extraction algorithm was proposed on the basis of slope constraint. Thereby, the aim of marking the inside lane was realized. By experimenting with various lane markers, the proposed algorithm can realize the detection. Moreover, the approach can overcome the influence of uneven light and be able to eliminate the interference from the side lane line, guard rail, etc. Lane line detection is conducive to the vehicle running on its road.