The Dataset

The (Land Cover from Aerial Imagery) dataset is a dataset for automatic mapping of buildings, woodlands and water from aerial images.

Dataset features

  • land cover from Poland, Central Europe 1
  • three spectral bands - RGB
  • 33 orthophotos with 25 cm per pixel resolution (~9000x9500 px)
  • 8 orthophotos with 50 cm per pixel resolution (~4200x4700 px)
  • segmentation masks for three classes: buildings, woodlands and water
  • total area of 216.27 km2 (1.85 km2 of buildings, 72.22 km2 of woodlands, 13.25 km2 of water)

Dataset format

  • rasters are three channel GeoTiffs with EPSG:2180 spatial reference system
  • masks are single channel GeoTiffs with EPSG:2180 spatial reference system and contain information about buildings (1), woodlands (2) and water (3)

Reproduce and compare

We provide to split images into 512x512 pieces and following files: train.txt, val.txt and test.txt containing lists of pieces used for training, validation and testing respectively.

  1. Image source: Head Office of Geodesy and Cartography, Poland ↩︎


You can find a full description of the dataset here.


To cite our work please export citation from arXiv.



The dataset can be downloaded from here.


If you encounter any problem or have any feedback, please contact (e-mail soon)