Discover adugnag/S1-S2_Transformer Open Source project

Stars
8
Rank 2,099,232 (Top 42 %)
Language
Python
License
MIT License
Created about 2 years ago
Updated almost 2 years ago

adugnag

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

This implementation uses Google Earth Engine Python API to process Sentinel-1 SAR and Sentinel-2 optical timeseries for tropical dry forest disturbance mapping. It also uses Tensorflow to build a siamese transformer architecture to implicitly learn the seasonality in the two series to make a forest and non-forest inference.

gee_s1_ard

Creates an analysis ready sentinel-1 SAR image collection in Google Earth Engine by applying additional border noise correction, speckle filtering and radiometric terrain normalization.

Python

231

deSpeckNet-TF-GEE

This implementation uses python to seamlessly integrate Sentinel-1 SAR image preparation in GEE with deep learning in Tensorflow for SAR image despeckling.

Jupyter Notebook

deSpeckNet

These are a set of scripts to train a deep learning based SAR image despeckling method.

MATLAB

CV-deSpeckNet

This repo implements a complex-valued multi-stream fully convolutional network for PolSAR data despeckling.