OpenEarthMap: A Benchmark Dataset for Global High-Resolution Land Cover Mapping
This provides a benchmark dataset for researchers and practitioners in remote sensing and land cover analysis, enabling improved global mapping and domain adaptation studies.
The authors introduced OpenEarthMap, a global high-resolution land cover mapping dataset with 2.2 million segments from 5000 images across 44 countries, and showed that models trained on it generalize worldwide for applications like off-the-shelf semantic segmentation.
We introduce OpenEarthMap, a benchmark dataset, for global high-resolution land cover mapping. OpenEarthMap consists of 2.2 million segments of 5000 aerial and satellite images covering 97 regions from 44 countries across 6 continents, with manually annotated 8-class land cover labels at a 0.25--0.5m ground sampling distance. Semantic segmentation models trained on the OpenEarthMap generalize worldwide and can be used as off-the-shelf models in a variety of applications. We evaluate the performance of state-of-the-art methods for unsupervised domain adaptation and present challenging problem settings suitable for further technical development. We also investigate lightweight models using automated neural architecture search for limited computational resources and fast mapping. The dataset is available at https://open-earth-map.org.