An approach of lane detection based on Inverse Perspective Mapping

Abstract

Urban lane detection is an essential task for unmanned vehicle system. This paper describes an approach of lane detection algorithm based on Inverse Perspective Mapping, first using overall optimal threshold method to obtain binary image for reducing noise; next using Inverse Perspective Mapping to transform binary image space to top view space; then using k-means clustering algorithm to analysis linear discriminant for reducing interference affect; finally, fitting lane discontinuous on the top view space according road models. Experimental results are presented to demonstrate the effectiveness and superiority of the urban lane detection algorithm.