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

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