• Corpus ID: 227227614

Assessing Post-Disaster Damage from Satellite Imagery using Semi-Supervised Learning Techniques

@article{Lee2020AssessingPD,
  title={Assessing Post-Disaster Damage from Satellite Imagery using Semi-Supervised Learning Techniques},
  author={Jihyeon Lee and Joseph Z. Xu and Kihyuk Sohn and Wenhan Lu and David Berthelot and Izzeddin Gur and Pranav Khaitan and Ke Huang and Kyriacos M. Koupparis and Bernhard Kowatsch},
  journal={ArXiv},
  year={2020},
  volume={abs/2011.14004}
}
To respond to disasters such as earthquakes, wildfires, and armed conflicts, humanitarian organizations require accurate and timely data in the form of damage assessments, which indicate what buildings and population centers have been most affected. Recent research combines machine learning with remote sensing to automatically extract such information from satellite imagery, reducing manual labor and turn-around time. A major impediment to using machine learning methods in real disaster… 
6 Citations

Figures and Tables from this paper

Self-Supervised Learning for Building Damage Assessment from Large-scale xBD Satellite Imagery Benchmark Datasets

A self-supervised comparative learning approach to address the task without the requirement of labeled data is proposed and a novel asymmetric twin network architecture is constructed and tested its performance on the xBD dataset.

Building Damage Mapping with Self-PositiveUnlabeled Learning

It is shown how models trained with self-PU techniques may achieve comparable performance as supervised learning using different datasets collected from the 2011 Tohoku earthquake, the 2018 Palu tsunami, and the 2018 Hurricane Michael.

Disaster mapping from satellites: damage detection with crowdsourced point labels

This work presents methods for aggregating potentially inconsistent damage marks to train a neural network damage detector that significantly decreases the required analysis time for response during the disaster.

TDA-Net: A Novel Transfer Deep Attention Network for Rapid Response to Building Damage Discovery

A new transfer-learning deep attention network (TDA-Net) that can achieve a balance of accuracy and efficiency and is pretrained on a large-scale dataset of disaster-damaged buildings is proposed.

A Golden Decade of Deep Learning: Computing Systems & Applications

  • J. Dean
  • Computer Science
    Daedalus
  • 2022
This essay examines the reasons for this progress, including the confluence of progress in computing hardware designed to accelerate machine learning and the emergence of open-source software frameworks to dramatically expand the set of people who can use machine learning effectively.

References

SHOWING 1-10 OF 30 REFERENCES

Building Damage Detection in Satellite Imagery Using Convolutional Neural Networks

This work compares the performance of four different convolutional neural network models in detecting damaged buildings in the 2010 Haiti earthquake and quantifies how well the models will generalize to future disasters by training and testing models on different disaster events.

Creating xBD: A Dataset for Assessing Building Damage from Satellite Imagery

xBD provides pre- and post-event multi-band satellite imagery from a variety of disaster events with building polygons, classification labels for damage types, ordinal labels of damage level, and corresponding satellite metadata, and will be the largest building damage assessment dataset to date.

Identifying Collapsed Buildings Using Post-Earthquake Satellite Imagery and Convolutional Neural Networks: A Case Study of the 2010 Haiti Earthquake

In this study, the convolutional neural network was utilized to identify collapsed buildings from post-event satellite imagery with the proposed workflow and demonstrated that the building collapsed information can be retrieved by using post- event imagery.

RescueNet: Joint Building Segmentation and Damage Assessment from Satellite Imagery

  • Rohit GuptaM. Shah
  • Computer Science
    2020 25th International Conference on Pattern Recognition (ICPR)
  • 2021
RescueNet is proposed, a unified model that can simultaneously segment buildings and assess the damage levels to individual buildings and can be trained end-to-end, and achieves significantly better building segmentation and damage classification performance than previous methods and achieves generalization across varied geographical regions and disaster types.

Building Disaster Damage Assessment in Satellite Imagery with Multi-Temporal Fusion

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 are reported.

Structural Building Damage Detection with Deep Learning: Assessment of a State-of-the-Art CNN in Operational Conditions

An advanced CNN for visible structural damage detection is tested to shed some light on what deep learning networks can currently deliver, and its adoption in realistic operational conditions after earthquakes and explosions is critically discussed.

Detection of Urban Damage Using Remote Sensing and Machine Learning Algorithms: Revisiting the 2010 Haiti Earthquake

Spatial features of texture and structure were far more important in algorithmic classification than spectral information, highlighting the potential for future implementation of machine learning algorithms which use panchromatic or pansharpened imagery alone.

Satellite-based damage mapping following the 2006 Indonesia earthquake - How accurate was it?

  • N. Kerle
  • Environmental Science
    Int. J. Appl. Earth Obs. Geoinformation
  • 2010

SATELLITE IMAGE CLASSIFICATION OF BUILDING DAMAGES USING AIRBORNE AND SATELLITE IMAGE SAMPLES IN A DEEP LEARNING APPROACH

A CNN framework using residual connections and dilated convolutions is used considering both manned and unmanned aerial image samples to perform the satellite image classification of building damages.

Remote Sensing and Earthquake Damage Assessment: Experiences, Limits, and Perspectives

A survey of the techniques and data sets used to evaluate earthquake damages using remote sensing data is presented, and proposed algorithms for data interpretation and earthquake damage extraction are presented.