확률적 허프 변환과 HSV 색 공간을 이용한 차선검출및 인식 알고리즘

Abstract

The lane keeping assist system (LKAS) can have errors by various displays on the road. In this paper, we propose the recognition algorithm using color and shape of the lane to overcome this problem. The proposed algorithm is divided into 3 different steps as follows; First, we find white, yellow and blue candidate lanes using HSV color space. Second, we exclude the non-lane from the candidate images using the shape feature of the lane. Third, we use progressive probabilistic Hough transform to determine final lane. The experimental results show that the proposed method has a good performance and low error rate compared to edge-detection methods.