RECOGNIZING WHITE LINE MARKINGS FOR VISION-GUIDED VEHICLE NAVIGATION BY FUZZY-REASONING

This paper presents a new method for recognizing white line markings f or navigation of an autonomous vehicle that operates in out-door envir onments. A fuzzy-reasoning-based general technique fcr edge detection is used to classify a pixel in an image into a border region or a unif orm region based on luminance differences between this pixel and its n eighboring pixels. The idea of this paper is to integrate special know ledge about white line markings into a fuzzy rule base using this gene ral technique. The method is implemented on the THMR-III mobile robot, and experiments show that this method is robust to noise and environm ent changes. (C) 1997 Elsevier Science B.V.