Automatic road extraction using fuzzy mask concepts

In this paper, fuzzy concepts are used in order to realize road pixels extraction. The aim of the proposed algorithms is to attribute a road membership value to each pixel. A set of twelve fuzzy sets representing basic 2D road structures is first defined. The road structure, defined as a logical concatenation of these elementary predefined 2D structures, is then used in order to enhance the road membership values. The proposed approach is applied using a georeferenced SPOT panchromatic image acquired on August 1989 and representing the municipality of Charlesbourg, Quebec, Canada. Obtained results are encouraging in terms of detected road validity as well as in terms of noise resistance.