mratsim/Amazon-Forest-Computer-Vision
Amazon Forest Computer Vision: Satellite Image tagging code using PyTorch / Keras with lots of PyTorch tricks
This project helps environmental scientists and conservationists automatically analyze satellite images of the Amazon rainforest. It takes raw satellite imagery as input and outputs classifications or 'tags' for what's visible in the images, such as deforestation, rivers, roads, or cloud cover. This tool is designed for specialists who need to process large volumes of satellite data to monitor changes in the environment.
371 stars. No commits in the last 6 months.
Use this if you need to build or adapt a computer vision model to automatically categorize features in satellite imagery, especially for environmental monitoring.
Not ideal if you're looking for a ready-to-use application with a graphical interface, as this project provides underlying code for model training.
Stars
371
Forks
73
Language
Jupyter Notebook
License
—
Category
Last pushed
Nov 08, 2019
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/mratsim/Amazon-Forest-Computer-Vision"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
blutjens/awesome-forests
🌳 A curated list of ground-truth forest datasets for the machine learning and forestry community.
jasonmanesis/Satellite-Imagery-Datasets-Containing-Ships
This repository provides a comprehensive list of radar and optical satellite datasets curated...
google-deepmind/forest_typology
Datasets to protect Earth's forests and biodiversity
vipulchaturvedi/treesense-imaging
Deep Learning based web application to automate tree enumeration in forest areas using satellite imagery.
ishaanshah/botanical-trees
Unofficial implementation of the paper "Learning to reconstruct botanical trees from single images"