Please use this identifier to cite or link to this item:
|Title:||Performance of Built-up Area Classifications Using High-Resolution SAR Data|
|Authors:||MOLCH Katrin; GAMBA Paolo; KAYITAKIRE Francois|
|Citation:||CANADIAN JOURNAL OF REMOTE SENSING vol. 36 no. 3 p. 197-210|
|Publisher:||CANADIAN AERONAUTICS SPACE INST|
|Type:||Articles in periodicals and books|
|Abstract:||Identification of the built-up area from satellite imagery can provide a crucial information layer in disaster mitigation and management and for monitoring urban sprawl, e.g., in developing countries. Spaceborne radar imagery is at an advantage in regions where environmental conditions impede the acquisition of optical image data. Automated exploitation procedures are imperative for efficient, large-area coverage. However, methodologies must be developed or adapted to account for the specific characteristics of synthetic aperture radar (SAR) data. This study evaluates the identification of the built-up area on RADARSAT-1 fine mode and Environmental Satellite (ENVISAT) image mode data using the texture-based, anisotropic, rotation-invariant built-up presence index. Data selection and processing parameters are discussed. User¿s accuracies of up to 77.5% and overall accuracies of up to 81.3% were achieved in this comparative study without any postclassification editing.|
|JRC Institute:||Sustainable Resources|
Files in This Item:
There are no files associated with this item.
Items in repository are protected by copyright, with all rights reserved, unless otherwise indicated.