| Titre | Automated extraction of visible floodwater in dense urban areas from RGB aerial photos |
| |
| Auteur | Zhang, Y; Crawford, P |
| Source | Remote Sensing vol. 12, issue 14, 2198, 2020 p. 1-14, https://doi.org/10.3390/rs12142198  Accès ouvert |
| Image |  |
| Année | 2020 |
| Séries alt. | Ressources naturelles Canada, Contribution externe 20200327 |
| Document | publication en série |
| Lang. | anglais |
| DOI | https://doi.org/10.3390/rs12142198 |
| Media | papier; en ligne; numérique |
| Formats | pdf; html |
| Province | Alberta |
| SNRC | 82I/13; 82J/16; 82O/01; 82P/04 |
| Région | Calgary |
| Lat/Long OENS | -114.5000 -113.5000 51.2500 50.7500 |
| Sujets | inondations; télédétection; méthodes photogrammétriques; interprétation de photos aériennes; géologie urbaine; techniques de cartographie; Automatisation; Services d'urgence; Méthodologie; hydrogéologie;
géophysique; Sciences et technologie; Nature et environnement; Santé et sécurité |
| Illustrations | cartes de localisation; photographies aériennes; tableaux; graphiques; graphique à barres; organigrammes; diagrammes 3D; cartes géolscientiques généralisées |
| Diffusé | 2020 07 09 |
| Résumé | (disponible en anglais seulement)
Rapid response mapping of floodwater extents in urbanized areas, while essential for early damage assessment and rescue operations, also presents significant
image interpretation challenges. Images from visible band (red-green-blue (RGB)) remote sensors are the most common and cost-effective for real-time applications. Based on an understanding of the differing characteristics of turbid floodwater and
urban land surface classes, a robust method was developed and automatized to extract visible floodwater using RGB band digital numbers. The methodology was applied to delineate visible floodwater distribution from very high-resolution aerial image
data acquired during the 2013 Calgary flood event. The methodology development involved segment- and pixel-based feature analysis, rule development, automated feature extraction, and result validation processing. The accuracies for the visible
floodwater class were above 0.8394% and the overall accuracies were above 0.9668% at both pixel and segment levels for three test sites with diverse urban landscapes. |
| GEOSCAN ID | 327012 |
|
|