Xbd Natural Disaster Image Dataset

The xBD dataset is the first building damage assessment dataset to date and is one of the largest and highest quality public datasets of annotated high-resolution satellite imagery.

The dataset contains 22,068 images, all of which are 1024*1024 high-resolution satellite remote sensing images, marked with 19 different events.Including earthquakes, floods, wildfires, volcanic eruptions and car accidents. These images include pre-disaster and post-disaster images, and the images can be used to construct two tasks: positioning and damage assessment.

Publishing Agency: Maxar/DigitalGlobe Open Data Initiative

Quantity included:22068 images

Data format:png

Data size:30.3 GB

Update time:August 2020

The dataset includes Train training set, Test test set, Holdout Keep Setand Tier3 Dataset:

• TrainImage pairs (before and after the disaster) and ground truth information about buildings and damage extent were provided for the pixel segmentation task.

• TestImages only, for challenge ranking purposes;

• HoldoutIt will be kept confidential during the challenge, with the purpose of testing the generalization performance of the results submitted by the verified challenge teams;

• Tier3 DatasetAvailable midway through the challenge and as additional/supplemental training sets covering additional hazard spans and geographic areas.

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