Towards Semi-Automated Satellite Mapping for Humanitarian Situational Awareness

Abstract

Very high resolution satellite imagery used to be a rare commodity, with infrequent satellite pass-over times over a specific area-of-interest obviating many useful applications. Today, more and more such satellite systems are available, with visual analysis and interpretation of imagery still important to derive relevant features and changes from satellite data. In order to allow efficient, obust and routine image analysis for humanitarian purposes, emi-automated feature extraction is of increasing importance or operational emergency mapping tasks. In the frame f the European Earth Observation program COPERNICUS and elated research activities under the European Union’s eventh ramework Program, substantial scientific developments and apping services are dedicated to satellite based humanitarian apping and monitoring. In this paper, recent results in methodological esearch and development of routine services in satellite mapping for humanitarian situational awareness are eviewed nd discussed. Ethical aspects of sensitivity and security of humanitarian apping are deliberated. Furthermore methods for onitoring and analysis of refugee/internally displaced persons amps in humanitarian settings are assessed. Advantages and imitations of object-based image analysis, sample supervised egmentation and feature extraction are presented and discussed.