swalpa/G2C-Conv3D-HSI

PyTorch implementation of the paper - Revisiting Deep Hyperspectral Feature Extraction Networks via Gradient Centralized Convolution

23
/ 100
Experimental

When analyzing satellite or aerial hyperspectral images to identify different land-cover types, it can be challenging to distinguish between areas with similar textures. This project helps improve the accuracy of pixel-level classification by extracting more robust and distinct features from these images. It takes raw hyperspectral image data and associated ground truth labels to produce more accurate classifications of land-cover types. This is ideal for remote sensing scientists, geographers, and environmental researchers working with hyperspectral imagery for tasks like land-use mapping.

No commits in the last 6 months.

Use this if you need to improve the accuracy of land-cover classification from hyperspectral images, especially when dealing with fine-grained textures or spectrally similar regions.

Not ideal if you are working with standard RGB images or do not require highly precise pixel-wise land-cover classification from hyperspectral data.

remote-sensing land-cover-mapping hyperspectral-imaging environmental-monitoring geospatial-analysis
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

32

Forks

Language

Jupyter Notebook

License

GPL-3.0

Last pushed

Mar 15, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/swalpa/G2C-Conv3D-HSI"

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