An Open Hyperspectral Dataset with Sea-Land-Cloud Ground-Truth from the HYPSO-1 Satellite
This provides an open dataset for Earth observation research, addressing a data bottleneck in hyperspectral imaging, though it is incremental as it focuses on a specific domain.
The authors tackled the lack of labeled hyperspectral datasets for satellite remote sensing by introducing the HYPSO-1 Sea-Land-Cloud-Labeled Dataset, which includes 200 hyperspectral images with 38 labeled ones containing about 25 million pixel-level annotations, and they demonstrated its utility by optimizing a deep learning model that achieved superior performance to the current state of the art.
Hyperspectral Imaging, employed in satellites for space remote sensing, like HYPSO-1, faces constraints due to few labeled data sets, affecting the training of AI models demanding these ground-truth annotations. In this work, we introduce The HYPSO-1 Sea-Land-Cloud-Labeled Dataset, an open dataset with 200 diverse hyperspectral images from the HYPSO-1 mission, available in both raw and calibrated forms for scientific research in Earth observation. Moreover, 38 of these images from different countries include ground-truth labels at pixel-level totaling about 25 million spectral signatures labeled for sea/land/cloud categories. To demonstrate the potential of the dataset and its labeled subset, we have additionally optimized a deep learning model (1D Fully Convolutional Network), achieving superior performance to the current state of the art. The complete dataset, ground-truth labels, deep learning model, and software code are openly accessible for download at the website https://ntnu-smallsat-lab.github.io/hypso1_sea_land_clouds_dataset/ .