azavea/raster-vision

An open source library and framework for deep learning on satellite and aerial imagery.

52
/ 100
Established

This tool helps geospatial analysts and remote sensing specialists automatically identify and categorize features within large satellite and aerial images. You provide your imagery and some example labels, and it outputs maps with classified areas, detected objects, or segmented regions, making sense of vast datasets efficiently. It's designed for professionals working with Earth observation data.

2,210 stars. No commits in the last 6 months.

Use this if you need to build and run deep learning models on satellite, aerial, or drone imagery without being a deep learning expert, especially for tasks like classifying land cover, detecting specific objects, or segmenting areas.

Not ideal if your primary task involves processing standard photographic images rather than geo-referenced geospatial data, or if you need to develop deep learning models from scratch without a framework.

geospatial-analysis remote-sensing image-intelligence earth-observation urban-planning
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 24 / 25

How are scores calculated?

Stars

2,210

Forks

395

Language

Python

License

Apache-2.0

Last pushed

Sep 29, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/azavea/raster-vision"

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