HSG-AIML/SSLTransformerRS

Code repository for "Self-supervised Vision Transformers for Land-cover Segmentation and Classification", CVPR EarthVision Workshop 2022 - Best Student Paper Award

35
/ 100
Emerging

This project helps environmental scientists, urban planners, and agricultural specialists analyze satellite images to identify different land cover types like forests, water bodies, or urban areas. You input raw Sentinel-1 and/or Sentinel-2 satellite imagery, and it outputs detailed maps showing distinct land classifications or segmented regions. This is ideal for professionals who need to accurately map and monitor geographical features over time.

No commits in the last 6 months.

Use this if you need to perform highly accurate land-cover classification or segmentation on Sentinel-1 and Sentinel-2 satellite data, even with limited labeled training examples.

Not ideal if your primary need is real-time processing of other image types (like aerial drone footage or street-level photos) or if you prefer off-the-shelf software with no programming involved.

remote-sensing land-cover-mapping satellite-imagery-analysis environmental-monitoring geospatial-analysis
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 8 / 25
Community 18 / 25

How are scores calculated?

Stars

92

Forks

17

Language

Python

License

Last pushed

Jan 23, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/HSG-AIML/SSLTransformerRS"

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