ChenHongruixuan/BRIGHT
[ESSD 2025 & IEEE GRSS DFC 2025] Bright: A globally distributed multimodal VHR dataset for all-weather disaster response
This project provides a comprehensive collection of satellite images to help scientists and disaster response teams assess damage after natural and man-made disasters. It takes in very high-resolution, multi-modal satellite imagery (like optical and radar) from before and after an event. The output is data that helps train and evaluate AI models for tasks such as identifying damaged buildings or changes on the ground, even in bad weather. It is used by researchers and practitioners involved in disaster management, humanitarian aid, and remote sensing analysis.
208 stars.
Use this if you need diverse, globally distributed satellite imagery to develop or test AI models for rapid, all-weather disaster assessment and change detection.
Not ideal if you are looking for real-time operational tools for immediate disaster response rather than a dataset for model development and evaluation.
Stars
208
Forks
31
Language
Python
License
Apache-2.0
Category
Last pushed
Feb 10, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/ChenHongruixuan/BRIGHT"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
Panagiotou/ImageToDEM
Generating Elevation Surface from a Single RGB Remotely Sensed Image Using Deep Learning
OpenDroneMap/SkyRemoval
Create sky masks to improve photogrammetric reconstruction
georgeslabreche/opssat-smartcam
On November 8, 2020, this project achieved the first use of deep convolutional neural networks...
geekysethi/Urbanization-change-detection
Urbanization detection using computer vision algorithms to reduce the reliance on the data of...
javgat/SkyMaskConvLSTM
Multi-frame cloud prediction in all-sky images from RGB images and segmented masks