Lane and obstacle detection based on fast inverse perspective mapping algorithm

Abstract

A fast inverse perspective mapping algorithm (FIPMA) is presented for a fast and accurate recovery of road surface from a given 2D road image. FIPMA is able to simplify the system design without losing reliability and flexibility. A novel lane and obstacle detection method, using only a single CCD camera, is proposed based on a recovered road surface image by FIPMA. This method includes five parts: recovering the road surface from the input road image using FIPMA; processing the recovered surface image; detecting lane and estimating lane parameters; updating camera parameters adaptively; and detecting obstacles.