EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification

DOI10.5281/zenodo.7711810Zenodo7711810MaRDI QIDQ6723897FDOQ6723897

Dataset published at Zenodo repository.

Benjamin Bischke, Andreas Dengel, Damian Borth, Patrick Helber

Publication date: 22 July 2018

Copyright license: MIT license

Description

EuroSAT is a land use and land cover classification dataset. The dataset is based on Sentinel-2 satellite imagery covering 13 spectral bands and consistsof 10 LULC classes with a total of27,000 labeled and geo-referenced images. The dataset is associated with the publications Introducing EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification and EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification. EuroSAT_RGB.zip contains the RGB version of the dataset, which includesthe optical R, G and B frequency bands encoded as JPEG images. EuroSAT_MS.zip contains the multi-spectral version of the EuroSAT dataset, which includesall 13 Sentinel-2 bandsin the original value range.

This page was built for dataset: EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification