A novel curve lane detection based on Improved River Flow and RANSA

Abstract

Accurate and robust lane detection, especially the curve lane detection, is the premise of a Lane Departure Warning System (LDWS) and a Forward Collision Warning System (FCWS). Lane detection on the structural roads under challenging scenarios such as the dashed lane markings and vehicle occlusion is a difficult task because of unreliable lane feature points. In this paper, a robust curve lane detection method based on the Improved River Flow (IRF) and the Random Sample Consensus (RANSAC) method is proposed to detect a curve lane under challenging conditions. The lane markings are grouped into a near vision field of a straight line and a far vision field of a curve line. The curve lanes are based on a Hyperbola-pair model. To determine the coefficient of curvature, a novel method is proposed based on the Improved River Flow method and the RANSAC method. In the new method, the Improved River Flow method is employed to search feature points in the far vision field guided by the results of detected straight lines in the near vision field or the curve lines from the last frame, which can connect dashed lane markings or obscured lane markings. So, it is robust on dashed lane markings and vehicle occlusion. Then, the RANSAC is utilized to calculate the curvature, which can eliminate noisy feature points obtained from the Improved River Flow. The experimental results show that the proposed method can robustly and accurately detect some challenging markings, such as the dashed lane markings and vehicle occlusion.