mapbox/robosat

Semantic segmentation on aerial and satellite imagery. Extracts features such as: buildings, parking lots, roads, water, clouds

50
/ 100
Established

This project helps urban planners, cartographers, and environmental analysts automatically identify and map real-world features like buildings, roads, and water bodies from aerial and satellite imagery. You provide raw satellite or aerial images, and it generates clean, simplified GeoJSON polygons of the identified features. It is ideal for anyone who needs to create or update geographic data from overhead imagery efficiently.

2,052 stars. No commits in the last 6 months.

Use this if you need to extract specific geographic features from aerial or satellite images to generate precise vector data for mapping or analysis.

Not ideal if you're looking for a user-friendly, point-and-click desktop application or if you need to process highly obscure or nuanced features not typically found in open-source mapping datasets.

cartography GIS urban-planning remote-sensing geospatial-analysis
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 24 / 25

How are scores calculated?

Stars

2,052

Forks

388

Language

Python

License

MIT

Last pushed

Aug 27, 2020

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/mapbox/robosat"

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