IGNF/FLAIR-1

Semantic segmentation from aerial imagery (baseline of the FLAIR #1 challenge)

47
/ 100
Emerging

This project helps classify land cover from aerial and satellite imagery, enabling precise mapping of areas like buildings, water, and different types of vegetation. It takes aerial images with RGB, infrared, and elevation data as input and produces detailed maps that label each pixel by land-cover type. This tool is designed for geographers, environmental scientists, urban planners, and anyone needing accurate, up-to-date land-use maps.

No commits in the last 6 months.

Use this if you need to automatically generate highly detailed land-cover maps from aerial or satellite imagery across large geographical areas.

Not ideal if you are looking for real-time analysis or if your primary input data is not high-resolution aerial or satellite imagery with multiple spectral bands.

land-cover-mapping remote-sensing environmental-monitoring urban-planning geospatial-analysis
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

72

Forks

23

Language

Python

License

Apache-2.0

Last pushed

Sep 18, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/IGNF/FLAIR-1"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.