Sentinel-2 Satellite Imagery based PopulationEstimation Strategies at FabSpace 2.0 LabDarmstadt

Abstract.This paper elaborates the Sentinel-2 image processing ap-proaches used for the estimation of the population of an area of interestat Image CLEF Remote 2017 lab by the FabSpace 2.0 Darmstadt team.The task is introduced by Image CLEF Lab as a new pilot task in 2017(Remote) which aims at exploring Copernicus Earth Observation data(i.e. Sentinel-2 satellite imagery) in order to estimate the population ofan area of interest [2]. Therefore, the pilot task is focusing on mappinghuman settlement to estimate population using Sentinel-2 data for hu-manitarian activities and/or establishing communication infrastructureetc. Human societies and civilizations have been expanding with con-sequent impact throughout the decades. The expansion of human soci-eties has wider implication in relation to the physical environment andother natural resources. Therefore, it could be a fundamental potentialof technological innovation in supporting human activities and suffer-ings throughout mapping diverse human societies in the world. Althoughthere exist a lot of previous studies used commercial and non-commercialhigh to moderate resolution satellite imagery for the estimation of thepopulation, this study will investigate the potential of the new Sentinel-2European satellites. They provide data with 10 m resolution imagery forfree, thanks to the Copernicus open data policy for all imagery in fivedays interval. Thus the use of Sentinel-2 data to develop any new appli-cation i.e. population estimation can be cost effective and is reasonablyaccurate.