Natural disasters have devastating effects on communities, necessitating swift and accurate damage assessment.
Manual assessment methods are time-consuming and costly, emphasizing the significance of semiautomatic ap-
proaches employing remote sensing and drone data. However, current datasets primarily focus on Western
countries’ infrastructure, lacking information on damaged buildings in other regions specifically Africa. To
bridge this gap, we present the EDDA dataset, comprising of VHR orthorectified mosaic images from drone imagery with building footprint labels classified by damage extent of rural and urban areas of Mozambique affected by Cyclone Ida.
Consists of two subsets arhived as rar files to reduce download size. Each subset consists of a combination of tiff images and shapefile labels. The tiff contain ortorectificed VHR orthomosaics images stored in ZSTD compression to dramatically reduce image size. This compression requires the use of designated GIS software (ArcGIS, QGIS, etc..) or libraries built on GDAL (python libraries GDAL, Arcpy, Rasterio, etc..). The label part of each subset are arhived as shapefiles and can be opened using designated GIS software (ArcGIS, QGIS, etc..) or libraries (python libraries Arcpy, Geopandas, PyProj).
Details of First Publication
Date Issued of First Publication:
Earth Resources and Environmental Remote Sensing/GIS Applications XIV (SPIE Remote Sensing, 2023, Amsterdam, Netherlands)