DynamicEarthNet: Daily Multi-Spectral Satellite Dataset for Semantic Change Segmentation
This dataset addresses the need for high-frequency, labeled satellite data for semantic change segmentation in Earth observation, though it is incremental as it builds on existing satellite data and labeling practices.
The authors tackled the problem of monitoring land use evolution by introducing DynamicEarthNet, a dataset with daily multi-spectral satellite imagery and monthly semantic segmentation labels for 75 global areas, and proposed a new evaluation metric SCS for time-series semantic change segmentation.
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.