You Are Here: Geolocation by Embedding Maps and Images

Research output: Contribution to conferenceConference Paperpeer-review

158 Downloads (Pure)


We present a novel approach to geolocalising panoramic images on a 2-D cartographic map based on learning a low dimensional embedded space, which allows a comparison between an image captured at a location and local neighbourhoods of the map. The representation is not sufficiently discriminatory to allow localisation from a single image, but when concatenated along a route, localisation converges quickly, with over 90% accuracy being achieved for routes of around 200m in length when using Google Street View and Open Street Map data. The method generalises a previous fixed semantic feature based approach and achieves significantly higher localisation accuracy and faster convergence.
Original languageEnglish
Number of pages17
Publication statusPublished - 28 Aug 2020
Event16th European Conference on Computer Vision - Online
Duration: 23 Aug 202028 Aug 2020


Conference16th European Conference on Computer Vision
Abbreviated titleECCV20
Internet address


  • Geolocalisation
  • image-map embeddings
  • cross domain localisation
  • representation learning


Dive into the research topics of 'You Are Here: Geolocation by Embedding Maps and Images'. Together they form a unique fingerprint.

Cite this