TR2009-067

Geolocalization Using Skylines from Omni-Images


    •  Ramalingam, S., Bouaziz, S., Sturm, P., Brand, M.E., "Geolocalization using Skylines from Omni-Images", IEEE International Conference on Computer Vision Workshops (ICCV), DOI: 10.1109/​ICCVW.2009.5457723, September 2009, pp. 23-30.
      BibTeX TR2009-067 PDF
      • @inproceedings{Ramalingam2009sep,
      • author = {Ramalingam, S. and Bouaziz, S. and Sturm, P. and Brand, M.E.},
      • title = {Geolocalization using Skylines from Omni-Images},
      • booktitle = {IEEE International Conference on Computer Vision Workshops (ICCV)},
      • year = 2009,
      • pages = {23--30},
      • month = sep,
      • doi = {10.1109/ICCVW.2009.5457723},
      • url = {https://www.merl.com/publications/TR2009-067}
      • }
  • MERL Contact:
  • Research Area:

    Computer Vision

Abstract:

We propose a novel method to accurately estimate the global position of a moving car using an omnidirectional camera and untextured 3D city models. The camera is oriented upwards to capture images of the immediate skyline, which is generally unique and serves as a fingerprint for a specific location in a city. Our goal is to estimate global position by matching skylines extracted from omni-directional images to skyline segments from coarse 3D city models. Our contributions include a sky segmentation algorithm for omni-directional images using graph cuts and a novel approach for matching omni-image skylines to 3D models.

 

  • Related News & Events