vannolimarco/classification-for-land-use-images-via-cnn

Performing a classification of the land-use image provided by a Remote sensing process using a Convolution-Neural-Network trained through pre-trained neural network VGG16 (transfer learning) 🛰️🛰️🛰️

23
/ 100
Experimental

This project helps urban planners, environmental analysts, and geographers automatically identify different land uses from satellite images. It takes raw satellite imagery and classifies each image into one of 21 categories, such as agricultural land, forests, or residential areas. The output is a clear classification of the land use, helping professionals quickly understand and map large geographical regions.

No commits in the last 6 months.

Use this if you need to automatically categorize satellite or aerial images to understand land use patterns across urban and rural areas.

Not ideal if you need to classify images for purposes other than land use (e.g., medical imaging, facial recognition) or if your images contain fewer than 21 distinct land-use categories.

remote-sensing urban-planning environmental-analysis geospatial-mapping land-cover-classification
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 8 / 25
Community 10 / 25

How are scores calculated?

Stars

14

Forks

2

Language

Python

License

Last pushed

Mar 10, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/vannolimarco/classification-for-land-use-images-via-cnn"

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