Object-oriented classifications for land use/land cover using Cosmo-SkyMed and LandSat 7 satellite data: An example of Erbil/Iraq
Conference: EUSAR 2014 - 10th European Conference on Synthetic Aperture Radar
06/03/2014 - 06/05/2014 at Berlin, Germany
Proceedings: EUSAR 2014
Pages: 4Language: englishTyp: PDF
Personal VDE Members are entitled to a 10% discount on this title
Authors:
Al-Hameedawi, Amjed (Institute for Cartography, Dresden University of Technology, 01062 Dresden, Germany; University of Technology, Baghdad, Iraq)
Buchroithner, Manfred (Institute for Cartography, Dresden University of Technology, 01062 Dresden, Germany)
Abstract:
Classification of SAR data is used to compensate for the lack of authoritative map data for decision support planning purposes. Landuse/landcover mapping of the study area has been performed using multi-sensor (SAR, optical) data in combination with object-oriented classification. The results have been evaluated on the basis of an accuracy assessment with a reference to substantial ground truth. The Cosmo-SkyMed image has been classified before and after the fusion with LandSat 7, and the results have been compared according to an accuracy assessment. An overall classification accuracy of 92% and 86.50% has been accomplished.