SEN12MS - A Curated Dataset of Georeferenced Multi-Spectral Sentinel-1/2 Imagery for Deep Learning and Data Fusion

By Michael Schmitt, Lloyd H. Hughes, Chunping Qiu, Xiaoxiang Zhu. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2019

357 citations recorded by the source corpus.

Abstract. The availability of curated large-scale training data is a crucial factor for the development of well-generalizing deep learning methods for the extraction of geoinformation from multi-sensor remote sensing imagery. While quite some datasets have already been published by the community, most of them suffer from rather strong limitations, e.g. regarding spatial coverage, diversity or simply number of available samples. Exploiting the freely available data acquired by the Sentinel satellites of the Copernicus program implemented by the European Space Agency, as well as the cloud computing facilities of Google Earth Engine, we provide a dataset consisting of 180,662 triplets of dual-pol synthetic aperture radar (SAR) image patches, multi-spectral Sentinel-2 image patches, and MODIS land cover maps. With all patches being fully georeferenced at a 10 m ground sampling distance and covering all inhabited continents during all meteorological seasons, we expect the dataset to support the community in developing sophisticated deep learning-based approaches for common tasks such as scene classification or semantic segmentation for land cover mapping.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/3b4bf01b942d2ce59b92603dbff4f6801fa6bb10

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

Self-Supervised Learning in Remote Sensing: A review (2022, methodology): “• We provide quantiﬁcation of performance benchmarks on established SSL methodologies utilizing the ImageNet dataset [2], and extend the analysis to three multi-spectral satellite imagery datasets: BigEarthNet [13], SEN12MS [14], and So2Sat-LCZ42 [15].”
Deep Learning Meets SAR: Concepts, models, pitfalls, and perspectives (2020, background): “SEN12MS4 [187] 180,748 corresponding image triplets containing Sentinel-1 dual-pol SAR data, Sentinel-2 multi-spectral imagery, and MODIS-derived land cover maps, covering all inhabited continents during all meteorological seasons.”
Cloud removal in Sentinel-2 imagery using a deep residual neural network and SAR-optical data fusion (2020, neutral): “To assess the cloud coverage of the optical images, the cloud detector described in Schmitt et al. (2019a) was used.”
Self-Supervised Remote Sensing Feature Learning: Learning Paradigms, Challenges, and Future Works (2022, neutral): “[67] constructed a large-scale multimodality land cover classification dataset, SEN12MS, based on Sentinel-1 and Sentinel-2 satellite data, which contains 180 662 SARmultispectral image pairs sampled from different regions and seasons, and thus, has a wide temporal and spatial coverage.”