Disaster mapping from satellites : damage detection with crowdsourced point labels

Kuzin, Danil and Simmons, Brooke and Isupova, Olga and Reece, Steven (2021) Disaster mapping from satellites : damage detection with crowdsourced point labels. In: NeurIPS 2021, 2021-12-06 - 2021-12-14, Virtual.

Text (Disaster mapping with crowdsourcing arXiv version)
2111.03693.pdf - Accepted Version
Download (4MB)

Abstract

High-resolution satellite imagery available immediately after disaster events is crucial for response planning as it facilitates broad situational awareness of critical infrastructure status such as building damage, flooding, and obstructions to access routes. Damage mapping at this scale would require hundreds of expert person-hours. However, a combination of crowdsourcing and recent advances in deep learning reduces the effort needed to just a few hours in real time. Asking volunteers to place point marks, as opposed to shapes of actual damaged areas, significantly decreases the required analysis time for response during the disaster. However, different volunteers may be inconsistent in their marking. This work presents methods for aggregating potentially inconsistent damage marks to train a neural network damage detector.