Overview

BRIGHT is the first open-access, globally distributed, event-diverse multimodal dataset specifically curated to support AI-based disaster response. It covers five types of natural disasters and two types of man-made disasters across 12 regions worldwide, with a particular focus on developing countries. About 4,500 paired optical and SAR images containing over 350,000 building instances in BRIGHT, with a spatial resolution between 0.3 and 1 meters, provides detailed representations of individual buildings, making it ideal for precise damage assessment.

IEEE GRSS Data Fusion Contest 2025

BRIGHT also serves as the official dataset of IEEE GRSS DFC 2025 Track II.

Please download dfc25_track2_trainval.zip and unzip it. It contains training images & labels and validation images.

Benchmark code related to the DFC 2025 can be found at this Github repo.

The official leaderboard is located on the Codalab-DFC2025-Track II page.

Paper & Reference

Details of BRIGHT can be refer to our paper.

If BRIGHT is useful to research, please kindly consider cite our paper

@article{chen2025bright,
   title={BRIGHT: A globally distributed multimodal building damage assessment dataset with very-high-resolution for all-weather disaster response}, 
   author={Hongruixuan Chen and Jian Song and Olivier Dietrich and Clifford Broni-Bediako and Weihao Xuan and Junjue Wang and Xinlei Shao and Yimin Wei and Junshi Xia and Cuiling Lan and Konrad Schindler and Naoto Yokoya},
   journal={arXiv preprint arXiv:2501.06019},
   year={2025},
   url={https://arxiv.org/abs/2501.06019}, 
}

License

Label data of BRIGHT are provided under the same license as the optical images, which varies with different events.

With the exception of two events, Hawaii-wildfire-2023 and La Palma-volcano eruption-2021, all optical images are from Maxar Open Data Program, following CC-BY-NC-4.0 license. The optical images related to Hawaii-wildifire-2023 are from High-Resolution Orthoimagery project of NOAA Office for Coastal Management. The optical images related to La Palma-volcano eruption-2021 are from IGN (Spain) following CC-BY 4.0 license.

The SAR images of BRIGHT is provided by Capella Open Data Gallery and Umbra Space Open Data Program, following CC-BY-4.0 license.

Damage Assessment _ OD (Method 4)

## Overview

Damage Assessment _ OD (Method 4) is a dataset for object detection tasks - it contains Building NkZI OtwB Qct9 91zE Q0iP VXWQ Building NkZI OtwB U1It EayD WPSw annotations for 412 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).

RescueNet dataset created by Tashnim Chowdhury, Robin Murphy and Maryam Rahnemoonfar and presented in RescueNet: A High Resolution UAV Semantic Segmentation Benchmark Dataset for Natural Disaster Damage Assessment paper in August of 2021. This dataset is released under the Community Data License Agreement (permissive). It features 4494 post disaster high resolution images (3000x4000) of buildings and landscapes after Hurricane Michael, captured from UAV (Unmanned Aerial Vehicle), namely DJI Mavic Pro and their respective General Truth maps. General Truth maps features 12 classes: background, debris, water, building-no-damage, building-medium-damage, building-major-damage, building-total-destruction, vehicle, road, tree, pool and sand. For better understanding of each class and it's purpouse refer to original work. For models trained on this dataset refer to the Github page. Note: this dataset can also be obtained from the Google drive link that be found on the github page. When downloading from this source as one zip archive, due to the large file size download error (namely Network error and on resume a Forbidden error) might occur. If it persists one should try downloading individual folders as they will be divided into parts that can be downloaded properly.

Additional fields such as Category and Structure Type are based off fields needed in the Incident Status Summary (ICS 209).

Please review the DINS database dictionary for additional information.

This repository contains the data description and processing for the paper titled "SkySense++: A Semantic-Enhanced Multi-Modal Remote Sensing Foundation Model for Earth Observation." The code is in here

🔥🔥🔥 Last Updated on 2025.03.14 🔥🔥🔥

• [2025.3.14] updated optical images of JL-16 dataset (https://huggingface.co/datasets/KKKKKKang/JL-16)
• [2025.3.12] updated sentinel-1 images and labels of JL-16 dataset
• [2025.3.9] updated pretrain and evaluation data

We conduct semantic-enhanced pretraining on the RS-Semantic dataset, which consists of 13 datasets with pixel-level annotations. Below are the specifics of these datasets.

* for time-series data.

We evaluate our SkySense++ on 12 typical Earth Observation (EO) tasks across 7 domains: agriculture, forestry, oceanography, atmosphere, biology, land surveying, and disaster management. The detailed information about the datasets used for evaluation is as follows.

* for time-series data.

This dataset compliments the ‘An Assessment of Thatching Needs in County Roscommon’ survey carried out by Fidelma Mullane, for Roscommon County Council. Published in October 2009. For this study, thirty-one structures with thatch or with previously thatched roofs were investigated. The details of the existing thatch roofs and their condition are noted. Ten further thatched structures were identified and listed for future assessment. This assessment of thatching needs in County Roscommon was funded by Roscommon County Council & the Heritage Council as an action of the County Roscommon Heritage Plan.

Contact: Roscommon County Council Heritage Officer.Dataset Publisher: Roscommon County Council, Dataset language: English, Spatial Projection: Web Mercator,Date of Creation: 2009Update Frequency: N / A Roscommon County Council provides this information with the understanding that it is not guaranteed to be accurate, correct or complete. Roscommon County Council accepts no liability for any loss or damage suffered by those using this data for any purpose.