Enumeration of Dwellings in Darfur Camps From GeoEye-1 Satellite Images Using Mathematical Morphology

This paper presents a methodology for the detection of dwelling structures in Darfur camps to estimate the total number of dwellings per camp using GeoEye-1 satellite images. The method is based on a translation of the visual characterization of the searched structures into a morphological image processing chain. Two variants are described: the first variant extracts dwellings fully automatic for enumeration, while the second links the area covered by dwellings to visual interpretation results of representative samples for estimation of the total number of dwellings. Compared to the visual interpretation both produce similar results with correlation coefficients of 0.65 and 0.66 respectively leading to a mean error of 6% in the total number of dwellings. In complex camp settings, the area-based approach might be preferred, since it provides some more control due to the visual interpretation included.