A robust image processing approach used to ALV road following

Abstract

A robust image processing approach used for ALV (autonomous land vehicle) road following is presented. The approach can cope with illumination variation, bad road surface condition such as shadows, defects, dirt and water stains. And it is effective for images of multi-branched road intersections. The approach consists of key techniques: color band automatic selection; adaptive road area segmentation; binary image post-processing and knowledge-based road trend line fitting. The approach is easy to implement in real time because its processing stages can be arranged into a pipeline. A set of experimental results is also presented.<>