La vitrine de diffusion des publications et contributions des chercheurs de l'ÉTS
RECHERCHER

Road extraction from high resolution remote sensing image using multiresolution in case of major disaster

Coulibaly, Idrissa et Spiric, N. et Sghaier, M. O. et Manzo-Vargas, W. et Lepage, Richard et St-Jacques, Michèle. 2014. « Road extraction from high resolution remote sensing image using multiresolution in case of major disaster ». In 2014 IEEE Geoscience and Remote Sensing Symposium. (IGARSS). Proceedings (Quebec, QC, Canada, July 13-18, 2014), p. 2712-2715. Piscataway, N. J., USA : IEEE.
Compte des citations dans Scopus : 2.

[img]
Prévisualisation
PDF
Lepage R. 2014 9062 Road extraction from high resolution remote sensing image.pdf

Télécharger (935kB) | Prévisualisation

Résumé

Road extraction is a topical research because of complexity due to his large topological variability. Increasing the spatial resolution generates noise which makes extraction difficult, especially in case of major disaster in an urban context. This problem increases false alarm rates and generally affects the performance of road extraction algorithm. Our aim is to improve the quality of roads extraction after adaptation of the Lowe’s SIFT descriptors (scale-invariant feature transform) jointly with spectral angle algorithm. The characterization is performed on two image at various resolution images, respectively representing a rural and urban disaster area, captured by Quickbird satellite. Our approach significantly reduces the amount of false detection and shows an overall accuracy of up to nearly 30% in some cases.

Type de document: Compte rendu de conférence
Professeur:
Professeur
Lepage, Richard
St-Jacques, Michèle
Affiliation: Génie de la construction, Génie de la production automatisée
Date de dépôt: 16 déc. 2014 21:59
Dernière modification: 10 nov. 2015 17:00
URI: http://espace2.etsmtl.ca/id/eprint/9062

Actions (Authentification requise)

Dernière vérification avant le dépôt Dernière vérification avant le dépôt

Statistiques de téléchargement

Plus de statistiques ...