GEOSCAN Search Results: Fastlink

GEOSCAN Menu


TitleAutomated extraction of visible floodwater in dense urban areas from RGB aerial photos
 
AuthorZhang, Y; Crawford, P
SourceRemote Sensing vol. 12, issue 14, 2198, 2020 p. 1-14, https://doi.org/10.3390/rs12142198 Open Access logo Open Access
Image
Year2020
Alt SeriesNatural Resources Canada, Contribution Series 20200327
Documentserial
Lang.English
Mediapaper; on-line; digital
File formatpdf; html
ProvinceAlberta
NTS82I/13; 82J/16; 82O/01; 82P/04
AreaCalgary
Lat/Long WENS-114.5000 -113.5000 51.2500 50.7500
Subjectshydrogeology; geophysics; Science and Technology; Nature and Environment; Health and Safety; floods; remote sensing; photogrammetric techniques; airphoto interpretation; urban geology; mapping techniques; 2013 Calgary Flood; automation; emergency services; methodology
Illustrationslocation maps; aerial photographs; tables; plots; bar graphs; flow diagrams; 3-D diagrams; geoscientific sketch maps
Released2020 07 09
AbstractRapid 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 ID327012

 
Date modified: