rogerxujiang/dstl_unet

Dstl Satellite Imagery Feature Detection

48
/ 100
Emerging

This project helps interpret satellite imagery by automatically identifying and outlining ten types of objects, like buildings, roads, trees, and vehicles. You input multi-spectral satellite images and receive precise outlines (masks) of these features. It's designed for geospatial analysts or researchers who need to extract detailed information from satellite data.

145 stars. No commits in the last 6 months.

Use this if you need to automatically detect and map specific features within satellite imagery for large-scale analysis or monitoring.

Not ideal if you lack access to high-performance computing resources like a powerful GPU and significant RAM, or if your primary interest is in developing new deep learning architectures from scratch.

satellite-imagery-analysis feature-detection geospatial-mapping remote-sensing land-use-monitoring
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 22 / 25

How are scores calculated?

Stars

145

Forks

57

Language

Jupyter Notebook

License

MIT

Last pushed

Oct 18, 2017

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/rogerxujiang/dstl_unet"

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