Using textural and geometric information for an automatic bridge detection system - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2004

Using textural and geometric information for an automatic bridge detection system

Résumé

We present some results on systems for automatically detecting bridges in high-resolution (2.5m) panchromatic IKONOS satellite images using texture information, geometric models, and combinations of both. A system using simple geometric models gives good results for bridges over roads and railroads, and very bad results for bridges over larger regions such as rivers. In contrast, a system using a texture-based classification and hand-made rules applied to that classification gives good results for bridges over rivers and railroads, and bad results for bridges over roads. We have explored several methods for combining both approaches to achieve an improved detection rate with only a moderate increase in the false alarm rate. Validation showed an increase in detection rate from 57% (geometry-based) and 33% (texture-based) to 71% (best combined system).
Fichier principal
Vignette du fichier
TGARS-2003-09.pdf (587.49 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-00136304 , version 1 (13-03-2007)

Identifiants

  • HAL Id : hal-00136304 , version 1

Citer

Roger Trias-Sanz, Nicolas Loménie, Jérôme Barbeau. Using textural and geometric information for an automatic bridge detection system. Sep 2004, pp.325-332. ⟨hal-00136304⟩
76 Consultations
203 Téléchargements

Partager

Gmail Facebook X LinkedIn More