TY - JOUR
T1 - BigEarthNet-MM: A Large-Scale, Multimodal, Multilabel Benchmark Archive for Remote Sensing Image Classification and Retrieval [Software and Data Sets]
AU - Sumbul, Gencer
AU - De Wall, Arne
AU - Kreuziger, Tristan
AU - Marcelino, Filipe
AU - Costa, Hugo
AU - Benevides, Pedro
AU - Caetano, Mario
AU - Demir, Begum
AU - Markl, Volker
N1 - Sumbul, G., De Wall, A., Kreuziger, T., Marcelino, F., Costa, H., Benevides, P., Caetano, M., Demir, B., & Markl, V. (2021). BigEarthNet-MM: A Large-Scale, Multimodal, Multilabel Benchmark Archive for Remote Sensing Image Classification and Retrieval [Software and Data Sets]. IEEE Geoscience and Remote Sensing Magazine, 9(3), 174-180. https://doi.org/10.1109/MGRS.2021.3089174
PY - 2021/9/1
Y1 - 2021/9/1
N2 - This article presents the multimodal BigEarthNet (BigEarthNet-MM) benchmark archive consisting of 590,326 pairs of Sentinel-1 and Sentinel-2 image patches to support deep learning (DL) studies in multimodal, multilabel remote sensing (RS) image retrieval and classification. Each pair of patches in BigEarthNet-MM is annotated with multilabels provided by the CORINE Land Cover (CLC) map of 2018 based on its thematically most detailed level-3 class nomenclature. Our initial research demonstrates that some CLC classes are challenging to accurately describe by considering only (single-date) BigEarthNet-MM images. In this article, we also introduce an alternative class nomenclature as an evolution of the original CLC labels to address this problem. This is achieved by interpreting and arranging the CLC level-3 nomenclature based on the properties of BigEarthNet-MM images in a new nomenclature of 19 classes. In our experiments, we show the potential of BigEarthNet-MM for multimodal, multilabel image retrieval and classification problems by considering several state-of-the-art DL models.
AB - This article presents the multimodal BigEarthNet (BigEarthNet-MM) benchmark archive consisting of 590,326 pairs of Sentinel-1 and Sentinel-2 image patches to support deep learning (DL) studies in multimodal, multilabel remote sensing (RS) image retrieval and classification. Each pair of patches in BigEarthNet-MM is annotated with multilabels provided by the CORINE Land Cover (CLC) map of 2018 based on its thematically most detailed level-3 class nomenclature. Our initial research demonstrates that some CLC classes are challenging to accurately describe by considering only (single-date) BigEarthNet-MM images. In this article, we also introduce an alternative class nomenclature as an evolution of the original CLC labels to address this problem. This is achieved by interpreting and arranging the CLC level-3 nomenclature based on the properties of BigEarthNet-MM images in a new nomenclature of 19 classes. In our experiments, we show the potential of BigEarthNet-MM for multimodal, multilabel image retrieval and classification problems by considering several state-of-the-art DL models.
UR - http://www.scopus.com/inward/record.url?scp=85117337468&partnerID=8YFLogxK
UR - http://bigearth.net/
UR - https://www.webofscience.com/wos/woscc/full-record/WOS:000701246700020
U2 - 10.1109/MGRS.2021.3089174
DO - 10.1109/MGRS.2021.3089174
M3 - Article
SN - 2473-2397
VL - 9
SP - 174
EP - 180
JO - IEEE Geoscience and Remote Sensing Magazine
JF - IEEE Geoscience and Remote Sensing Magazine
IS - 3
ER -