Lane recognition algorithm using lane shape and color features for vehicle black box

Abstract

The various markings on the road may cause errors of lane detection and recognition in vehicle blackbox images. In this paper, we propose the recognition algorithm using HSV color space and lane shape feature to overcome this problem. We find white and yellow candidate lanes using HSV color space. The lane shape features of the candidate lane are evaluated. Then we use progressive probabilistic Hough(PPH) transform to determine final lane. The experimental results show that the proposed method has a good performance and low error rate than other methods. © 2018 Institute of Electronics and Information Engineers.