-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Toker_2022_CVPR, author = {Toker, Aysim and Kondmann, Lukas and Weber, Mark and Eisenberger, Marvin and Camero, Andr\'es and Hu, Jingliang and Hoderlein, Ariadna Pregel and \c{S}enaras, \c{C}a\u{g}lar and Davis, Timothy and Cremers, Daniel and Marchisio, Giovanni and Zhu, Xiao Xiang and Leal-Taix\'e, Laura}, title = {DynamicEarthNet: Daily Multi-Spectral Satellite Dataset for Semantic Change Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {21158-21167} }
DynamicEarthNet: Daily Multi-Spectral Satellite Dataset for Semantic Change Segmentation
Abstract
Earth observation is a fundamental tool for monitoring the evolution of land use in specific areas of interest. Observing and precisely defining change, in this context, requires both time-series data and pixel-wise segmentations. To that end, we propose the DynamicEarthNet dataset that consists of daily, multi-spectral satellite observations of 75 selected areas of interest distributed over the globe with imagery from Planet Labs. These observations are paired with pixel-wise monthly semantic segmentation labels of 7 land use and land cover (LULC) classes. DynamicEarthNet is the first dataset that provides this unique combination of daily measurements and high-quality labels. In our experiments, we compare several established baselines that either utilize the daily observations as additional training data (semi-supervised learning) or multiple observations at once (spatio-temporal learning) as a point of reference for future research. Finally, we propose a new evaluation metric SCS that addresses the specific challenges associated with time-series semantic change segmentation. The data is available at: https://mediatum.ub.tum.de/1650201.
Related Material