Localization of Unmanned Aerial Vehicles Using Terrain Classification from Aerial Images

  • Andreas Masselli
  • Richard Hanten
  • Andreas Zell
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 302)


In this paper we investigate the benefit of terrain classification for self-localization of a flying robot. The key idea is to use aerial images, which are already available from online databases such as GoogleMaps™, as reference map and to match images taken with a downward looking camera with this map. Using different terrain classes as features, we can make sure that our method is invariant to lighting/weather changes as well as seasonal variations or minor changes in the environment. A particle filter is used to register the query image with parts of the map. The proposed method has shown to work on image data from both simulated and real flights.


Visual localization Terrain classification Unmanned aerial vehicles 



The authors thank Stefan Laible for his contributions and hints regarding terrain classification, Norbert Morgenstern for performing the outdoor flights, and Sebastian Buck for providing ground truth data.


  1. 1.
    Herbert Bay, Tinne Tuytelaars, and Luc J. Van Gool. Surf: Speeded up robust features. In Ales Leonardis, Horst Bischof, and Axel Pinz, editors, ECCV (1), volume 3951 of Lecture Notes in Computer Science, pages 404–417. Springer, 2006.Google Scholar
  2. 2.
    Sbastien Bosch, Simon Lacroix, and Fernando Caballero. Autonomous detection of safe landing areas for an uav from monocular images. In IROS, pages 5522–5527. IEEE, 2006.Google Scholar
  3. 3.
    Leo Breiman. Random forests. Machine Learning, 45(1):5–32, October 2001.Google Scholar
  4. 4.
    Michael Calonder, Vincent Lepetit, Christoph Strecha, and Pascal Fua. Brief: binary robust independent elementary features. In Proceedings of the 11th European conference on Computer vision: Part IV, ECCV’10, pages 778–792, Berlin, Heidelberg, 2010. Springer-Verlag.Google Scholar
  5. 5.
    A. Cesetti, E. Frontoni, A. Mancini, P. Zingaretti, and S. Longhi. A vision-based guidance system for uav navigation and safe landing using natural landmarks. J. Intell. Robotics Syst., 57(1–4):233–257, January 2010.Google Scholar
  6. 6.
    Andrea Cesetti, Emanuele Frontoni, Adriano Mancini, Andrea Ascani, Primo Zingaretti, and Sauro Longhi. A visual global positioning system for unmanned aerial vehicles used in photogrammetric applications. Journal of Intelligent and Robotic Systems, 61(1–4):157–168, 2011.Google Scholar
  7. 7.
    Sara Erhard, Karl Engelbert Wenzel, and Andreas Zell. Flyphone: Visual Self-Localisation Using a Mobile Phone as Onboard Image Processor on a Quadrocopter. Journal of Intelligent & Robotic Systems, 57:451–465, 2009.Google Scholar
  8. 8.
    Robert Hudjakov and Mart Tamre. Aerial imagery terrain classification for long-range autonomous navigation. In R. Küttner, editor, Proc. of the 7th International Conference of DAAAM Baltic Industrial Engineering, pages 530–535, Tallinn, April 2010. Tallinn Technical University Press.Google Scholar
  9. 9.
    Yasir Niaz Khan, Andreas Masselli, and Andreas Zell. Visual terrain classification by flying robots. In IEEE International Conference on Robotics and Automation (ICRA), pages 498–503, St. Paul, Minnesota, USA, May 2012.Google Scholar
  10. 10.
    Rainer Kümmerle, Bastian Steder, Christian Dornhege, Alexander Kleiner, Giorgio Grisetti, and Wolfram Burgard. Large scale graph-based slam using aerial images as prior information. Auton. Robots, 30(1):25–39, January 2011.Google Scholar
  11. 11.
    Dongjin Lee, Yeongju Kim, and Hyochoong Bang. Vision-based terrain referenced navigation for unmanned aerial vehicles using homography relationship. Journal of Intelligent and Robotic Systems, 69(1–4):489–497, 2013.Google Scholar
  12. 12.
    Xiaoming Li. A software scheme for uav’s safe landing area discovery. In Wei Deng, editor, AASRI Conference on Intelligent Systems and Control, volume 4, pages 230–235, 2013.Google Scholar
  13. 13.
    David G. Lowe. Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vision, 60(2):91–110, November 2004.Google Scholar
  14. 14.
    Ethan Rublee, Vincent Rabaud, Kurt Konolige, and Gary Bradski. Orb: An efficient alternative to sift or surf. In International Conference on Computer Vision, Barcelona, 11/2011 2011.Google Scholar
  15. 15.
    B. Steder, G. Grisetti, C. Stachniss, and W. Burgard. Visual slam for flying vehicles. Trans. Rob., 24(5):1088–1093, October 2008.Google Scholar
  16. 16.
    S. Thrun, D. Fox, W. Burgard, and F. Dellaert. Robust monte carlo localization for mobile robots. Artificial Intelligence, 128(1–2):99–141, 2000.Google Scholar
  17. 17.
    Christoffer Valgren and Achim J. Lilienthal. Sift, surf & seasons: Appearance-based long-term localization in outdoor environments. Robot. Auton. Syst., 58(2):149–156, February 2010.Google Scholar

Copyright information

© Springer International Publishing Switzerland 2016

Authors and Affiliations

  • Andreas Masselli
    • 1
  • Richard Hanten
    • 1
  • Andreas Zell
    • 1
  1. 1.University of TuebingenTuebingenGermany

Personalised recommendations