OpenEarthMap: A Benchmark Dataset for Global High-Resolution Land Cover Mapping

By Junshi Xia, Naoto Yokoya, Bruno Adriano, Clifford Broni-Bediako. 2022

155 citations recorded by the source corpus.

We introduce OpenEarthMap, a benchmark dataset, for global high-resolution land cover mapping. OpenEarth-Map 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. Se-mantic segmentation models trained on the OpenEarth-Map 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.

Subfields: Computer Vision and Pattern Recognition, Media Technology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

Continual Barlow Twins: Continual Self-Supervised Learning for Remote Sensing Semantic Segmentation (2022, background): “interest in foundation models [15], [34], based also on new extensive datasets [14], [27], [28].”
Cross-City Matters: A Multimodal Remote Sensing Benchmark Dataset for Cross-City Semantic Segmentation using High-Resolution Domain Adaptation Networks (2023, methodology): “In contrast to certain well-known HR or VHR datasets, such as OpenEarthMap [42], it’s worth noting that our C2Seg datasets encompass three distinct RS modalities, even though they maintain a GSD of only 10 meters.”