An approach to the robust classification of pathway images for autonomous mobile robots

Abstract

An approach to the robust classification of pathway images for autonomous mobile robots is described. The proposed algorithm consists of different steps: first, a texture-based segmentation is used to divide the image coarsely into pathway and nonpathway regions; then an edge-based method is applied in order to localize the pathway boundaries. Finally their location is combined with the result of the segmentation to search object candidates on the pathway and junction candidates besides the pathway.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>