Study on lane boundary detection in night scene

Abstract

Lane boundary detection is the most important component of Driving Assistance System which aims at keeping drivers safe. In this paper, a method combining the edge characteristics with brightness of lane is discussed for traffic scene at night. First images are preprocessed by dual thresholding algorithm in green channel. Then, the edge is detected by a fast method based on single-direction gradient operator. Finally, noises such as headlights of vehicles, reflected lights and street lamps are removed through filter template. Experiment results indicate that the proposed approach is adapted to night condition.