JAEarly/MIL-Land-Cover-Classification
Code for the paper "Scene-to-Patch Earth Observation: Multiple Instance Learning for Land Cover Classification".
This project helps environmental scientists and remote sensing analysts classify land cover across large geographical areas by automatically analyzing satellite or aerial imagery. It takes raw Earth observation scenes as input and identifies different land types, such as forests, urban areas, or water bodies, providing detailed maps of land cover. Users who need to monitor environmental changes or map ecosystems would find this tool valuable.
No commits in the last 6 months.
Use this if you need to accurately classify land cover types from satellite imagery across broad regions without having to label every single pixel individually.
Not ideal if you require very fine-grained, pixel-level classification where precise boundary definitions for every object are critical and you have extensive pixel-level ground truth available.
Stars
14
Forks
1
Language
Python
License
MIT
Category
Last pushed
Nov 16, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/JAEarly/MIL-Land-Cover-Classification"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
maja601/EuroCrops
The official repository for the EuroCrops dataset.
dida-do/eurocropsml
EuroCropsML is a ready-to-use benchmark dataset for few-shot crop type classification using...
langnico/global-canopy-height-model
This repository contains the code used in the paper: A high-resolution canopy height model of...
raoofnaushad/Land-Cover-Classification-using-Sentinel-2-Dataset
Application of deep learning on Satellite Imagery of Sentinel-2 satellite that move around the...
clejae/europe_land_iacs_prep
Preprocessing and harmonization scripts for IACS/GSA data.