Refugee Camp Population Estimates Using Automated Feature Extraction

Abstract

Throughout 2018, approximately 68.5 million people were forcibly displaced due to armed conflict, generalized violence, or human rights violations around the world; of those, 40 million were internally displaced persons (IDP), 25.4 million refugees, and 3.1 million asylum-seekers. Effective management of refugee and IDP camps rely on accurate, up-to-date, and comprehensive population estimates. However, obtaining this information is not always easy. Thus, the purpose of this study was to develop a methodology and custom toolset that estimates populations based on dwellings derived from automated feature extraction of high-resolution, multi-spectral orthorectified imagery. Estimates were determined for five Rohingya refugee camp populations and compared with United Nations High Commissioner for Human Rights (UNHCR) baseline data to determine accuracy.