An automatic road extraction method using a map-guided approachcombined with neural networks for cartographic database validation purposes

Robert Fiset (1, 2) , François Cavayas (1) , Marie-Catherine Mouchot (2) , Basel Solaiman (2) , Robert Desjardins (3)

1 Département de géographie (Université de Montréal)
2 ITI - Département Image et Traitement Information
3 UQO - Université du Québec en Outaouais

A method is proposed to extract road intersections from a SPOT panchromatic image, using a map-guided approach combined with the application of a neural network. The results show an average increase of 36% of planimetric accuracy after applying the method instead of simply superimposing the roads on the geocoded image. Also, only 8 out 42 samples were previously correctly traced, compared to 27 after application of the algorithm.

Mots clés: SPOT; Automatic road extraction method

Domaines: Traitement du signal et de l'image [eess.SP]

Robert Fiset, François Cavayas, Marie-Catherine Mouchot, Basel Solaiman, Robert Desjardins. An automatic road extraction method using a map-guided approachcombined with neural networks for cartographic database validation purposes. IGARSS'96 : International Geoscience And Remote Sensing Symposium, May 1996, Lincoln, United States. pp.236 - 238, ⟨10.1109/IGARSS.1996.516302⟩. ⟨hal-02158668⟩