Building Disaster Damage Assessment in Satellite Imagery with Multi-Temporal Fusion
arXiv:2004.05525
Abstract
Automatic change detection and disaster damage assessment are currently procedures requiring a huge amount of labor and manual work by satellite imagery analysts. In the occurrences of natural disasters, timely change detection can save lives. In this work, we report findings on problem framing, data processing and training procedures which are specifically helpful for the task of building damage assessment using the newly released xBD dataset. Our insights lead to substantial improvement over the xBD baseline models, and we score among top results on the xView2 challenge leaderboard. We release our code used for the competition.
arXiv commentAccepted for presentation at the ICLR 2020 AI For Earth Sciences Workshop
References in corpus (5)
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- Building Damage Detection in Satellite Imagery Using Convolutional Neural Networks
- xView: Objects in Context in Overhead Imagery
- xBD: A Dataset for Assessing Building Damage from Satellite Imagery
- Benchmark Dataset for Automatic Damaged Building Detection from Post-Hurricane Remotely Sensed Imagery
Cited by in corpus (7)
- BDANet: Multiscale Convolutional Neural Network with Cross-directional Attention for Building Damage Assessment from Satellite Images
- Assessing Post-Disaster Damage from Satellite Imagery using Semi-Supervised Learning Techniques
- DamageCAT: A Deep Learning Transformer Framework for Typology-Based Post-Disaster Building Damage Categorization
- Cross-directional Feature Fusion Network for Building Damage Assessment from Satellite Imagery
- Multi-step feature fusion for natural disaster damage assessment on satellite images
- Learning Efficient Unsupervised Satellite Image-based Building Damage Detection
- Disaster mapping from satellites: damage detection with crowdsourced point labels