PASTIS is a benchmark dataset for panoptic and semantic segmentation of agricultural parcels from satellite image time series. It is composed of 2433 one square kilometer-patches in the French metropolitan territory for which sequences of satellite observations are assembled into a four-dimensional spatio-temporal tensor. The dataset contains both semantic and instance annotations, assigning to each pixel a semantic label and an instance id. There is an official 5 fold split provided in the dataset's metadata.

The dataset can be downloaded from zenodo. This repository also contains a PyTorch dataset class in dataloader.py that can be readily used to load data for training.

Please open an issue to submit new entries.

Models that we re-implemented are denoted with a star (*).

The agricultural parcels are grouped into 18 different crop classes as shown in the table below.

Additional information about the dataset can be found in the doc.pdf document.

If you use PASTIS please cite the related paper:

@article{garnot2021panoptic,
  title={Panoptic Segmentation of Satellite Image Time Series
with Convolutional Temporal Attention Networks},
  author={Sainte Fare Garnot, Vivien  and Landrieu, Loic },
  journal={arxiv},
  year={2021}
}

• The satellite imagery used in PASTIS was retrieved from THEIA: "Value-added data processed by the CNES for the Theia www.theia.land.fr data cluster using Copernicus data. The treatments use algorithms developed by Theia’s Scientific Expertise Centres. "

• The annotations used in PASTIS stem from the French land parcel identification system produced by IGN, the French mapping agency.

• This work was partly supported by ASP, the French Payment Agency.