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

Author

Fiset, R. ; Cavayas, F. ; Mouchot, M.C. ; Solaiman, B. ; Desjardins, R.

Author_Institution

Departement de Geographie, Univ. de Montreal, Que., Canada

Volume

1

fYear

1996

fDate

27-31 May 1996

Firstpage

236

Abstract

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

Keywords

cartography; feature extraction; geophysical signal processing; geophysical techniques; geophysics computing; neural nets; SPOT panchromatic image; automatic road extraction method; cartographic database validation; cartography; feature extraction; geophysical measurement technique; image processing; land surface; map-guided approach; neural net; neural network; optical imaging; planimetric accuracy; remote sensing; road intersection; terrain mapping; town city; urban area; Data mining; Image databases; Image segmentation; Neural networks; Performance evaluation; Photography; Roads; Satellites; Shape; Testing;

fLanguage

English

Publisher

ieee

Conference_Titel

Geoscience and Remote Sensing Symposium, 1996. IGARSS '96. 'Remote Sensing for a Sustainable Future.', International

Conference_Location

Lincoln, NE

Print_ISBN

0-7803-3068-4

Type

conf

DOI

10.1109/IGARSS.1996.516302

Filename

516302