DynamicEarthNet: Daily Multi-Spectral Satellite Dataset for Semantic Change Segmentation

By Aysim Toker, L. Kondmann, Mark Weber, Marvin Eisenberger, Andrés Camero, Jingliang Hu, Ariadna Pregel Hoderlein, Çaglar Senaras, T. Davis, Daniel Cremers and 3 more. 2022

141 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Atmospheric Science, Media Technology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Atmospheric Science

In Media Technology

Citations in the corpus

Continual Barlow Twins: Continual Self-Supervised Learning for Remote Sensing Semantic Segmentation (2022, background): “interest in foundation models [15], [34], based also on new extensive datasets [14], [27], [28].”
OpenEarthMap: A Benchmark Dataset for Global High-Resolution Land Cover Mapping (2022, methodology): “Meter-level resolution satellite imagery have been used to map the world, as represented by GlobeLand30 [6], FROM-GLC [5], and recent benchmarks such as OpenSentinelMap [20] and DynamicEarthNet [44].”
Changer: Feature Interaction is What You Need for Change Detection (2022, methodology): “Driven by large amounts of RS data [31, 35, 36], change detection models based on ConvNet or Vision Transformer achieve more competitive MetaChanger is presented as a general architecture with alternative interaction layer ( e.g .”
SkySense: A Multi-Modal Remote Sensing Foundation Model Towards Universal Interpretation for Earth Observation Imagery (2023, methodology): “-S2 dataset [68] and iSAID dataset [78], and change detection with the Dyna.”