MAP-IMAGE MATCHING USING A MULTILAYER PERCEPTRON - THE CASE OF THE ROAD NETWORK

To help automatize map revision at a scale of 1:50,000, a map-guided m ethod is described to update the road network of a map database. This paper describes the essential first step of the procedure, which consi sts of matching the roads present on both the image and the map databa se. This matching has to be performed precisely in order to generate m eaningful hypotheses on the location of new roads. The matching is con ducted by using a multi-layer perceptron (MLP) trained to recognize ro ad segments on the SPOT-HRV panchromatic image corresponding to the ca rtographic database being treated. Two template matching methods using the trained MLP weight matrix are developed. The first method locates all the road intersections on the image, while the second method loca tes the segments only. Both methods are not accurate enough to be used alone. However, combining both approaches gives results that are reli able enough to be used in the generation of the hypotheses needed to e xtract new roads. (C) 1998 Elsevier Science B.V. All rights reserved.