AronBakes/Semantic-Segmentation-of-Aerial-Imagery

Semantic Segmentation of Aerial Imagery - Multi-modal deep learning models (U-net, SegFormer, logistic regression + CRF) trained on RGB and elevation data for aerial scene understanding.

22
/ 100
Experimental

This project helps urban planners, environmental analysts, or infrastructure managers automatically identify objects like buildings, vegetation, and roads in drone or aerial images. You input raw RGB and elevation data from aerial surveys, and it outputs detailed maps where each pixel is classified into categories such as 'building', 'vegetation', or 'water'. This allows for faster and more consistent analysis of large areas.

No commits in the last 6 months.

Use this if you need to precisely classify features in aerial or drone imagery for land-use mapping, environmental monitoring, or urban development planning, especially when elevation data is available.

Not ideal if you only need to detect the presence of objects without pixel-level classification, or if you don't have access to elevation data alongside your RGB imagery.

aerial-mapping urban-planning land-use-analysis environmental-monitoring drone-surveying
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 4 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

8

Forks

Language

Jupyter Notebook

License

MIT

Last pushed

Aug 06, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/AronBakes/Semantic-Segmentation-of-Aerial-Imagery"

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