Post Disaster Mapping With Semantic Change Detection in Satellite Imagery

Abstract

Accurate road maps are important for timely disaster relief efforts and risk management. Current disaster mapping is done manually by volunteers following a disaster and the process is slow and error prone. We propose a framework for identifying accessible roads in post-disaster satellite imagery by detecting changes from pre-disaster imagery, in conjunction with OpenStreetMap data. We validate our results with data from Indonesia 2018 tsunami, obtained from DigitalGlobe.