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.
@article{arxiv.2203.12560,
title = {DynamicEarthNet: Daily Multi-Spectral Satellite Dataset for Semantic Change Segmentation},
author = {Aysim Toker and Lukas Kondmann and Mark Weber and Marvin Eisenberger and Andrés Camero and Jingliang Hu and Ariadna Pregel Hoderlein and Çağlar Şenaras and Timothy Davis and Daniel Cremers and Giovanni Marchisio and Xiao Xiang Zhu and Laura Leal-Taixé},
journal= {arXiv preprint arXiv:2203.12560},
year = {2022}
}
Comments
Accepted to CVPR 2022, evaluation webpage: https://codalab.lisn.upsaclay.fr/competitions/2882