Danish Airs and Grounds: A Dataset for Aerial-to-Street-Level Place Recognition and Localization

Andrea Vallone, Frederik Warburg, Hans Hansen, Søren Hauberg, Javier Civera

Research output: Contribution to journalJournal articleResearchpeer-review

64 Downloads (Pure)


Place recognition and visual localization are particularly challenging in wide baseline configurations. In this letter, we contribute with the Danish Airs and Grounds (DAG) dataset, a large collection of street-level and aerial images targeting such cases. Its main challenge lies in the extreme viewing-angle difference between query and reference images with consequent changes in illumination and perspective. The dataset is larger and more diverse than current publicly available data, including more than 50 km of roads in urban, suburban and rural areas. All images are associated with accurate 6-DoF metadata that allows the benchmarking of visual localization methods. Additionally, we validate our data by presenting the results of a simple map-to-image re-localization baseline. that first estimates a dense 3D reconstruction from the aerial images and then matches query street-level images to street-level renderings of the 3D model. The dataset can be downloaded at:.
Original languageEnglish
Article number9811266
JournalIEEE Robotics and Automation Letters
Issue number4
Pages (from-to)9207-9215
Publication statusPublished - 1 Oct 2022


  • Location awareness
  • Visualization
  • Cameras
  • Three-dimensional displays
  • Feature extraction
  • Image recognition
  • Databases


Dive into the research topics of 'Danish Airs and Grounds: A Dataset for Aerial-to-Street-Level Place Recognition and Localization'. Together they form a unique fingerprint.

Cite this