Disaster mapping from satellites: damage detection with crowdsourced point labels
This addresses the need for efficient disaster response planning by enabling broad situational awareness of critical infrastructure damage, though it is incremental as it builds on existing crowdsourcing and deep learning methods.
The paper tackles the problem of rapid disaster damage mapping from satellite imagery by using crowdsourced point labels to train a neural network, reducing the required effort from hundreds of expert hours to just a few hours in real time.
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.