The Visual Computer

, Volume 19, Issue 6, pp 417–430 | Cite as

Vanishing points and three-dimensional lines from omni-directional video

  • Michael Bosse
  • Richard Rikoski
  • John Leonard
  • Seth Teller
Special issue on computational video
First Online:

Abstract

This paper describes a system for structure from motion using vanishing points and three-dimensional lines extracted from omni-directional video sequences. To track lines, we use a novel dynamic programming approach to improve ambiguity resolution, and we use delayed states to aid in the initialization of landmarks. By reobserving vanishing points we get direct measurements of the robot’s three-dimensional attitude that are independent of its position. Using vanishing points simplifies the representation since parallel lines share the same direction states. We show the performance of the system in various indoor and outdoor environments and include comparisons with independent two-dimensional reference maps for each experiment .

Keywords

Omni-directional video Vanishing points Structure from motion Visual navigation Image line tracking 
This is a preview of subscription content, log in to check access.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Antone M, Teller S (2000) Automatic recovery of relative camera rotations for urban scenes. In: International Conference on Computer Vision and Pattern Recognition, Vol II, pp 282–289 Google Scholar
  2. 2.
    Antone ME (2001) Robust camera pose recovery using stochastic geometry. PhD thesis, Massachusetts Institute of Technology Google Scholar
  3. 3.
    Bar-Shalom Y, Fortmann TE (1988) Tracking and data association. Academic Press Limited, San Diego, CA, 1988 Google Scholar
  4. 4.
    Bosse MC, Newman PM, Leonard JJ, Soika M, Feiten W, Teller S (2003) An atlas framework for scalable mapping. Proc. IEEE Int Conf Robot Autom (Forthcoming) Google Scholar
  5. 5.
    Castellanos JA, Montiel JMM, Neira J, Tardos JD (1999) The SPmap: a probabilistic framework for simultaneous localization and map building. IEEE Trans Robot Autom 15(5):948–952 CrossRefGoogle Scholar
  6. 6.
    Chiuso A, Favaro P, Jin H, Soatto S (2002) Structure from motion causally integrated over time. IEEE Trans Patt Anal Machine Intel 24(4):523–535 CrossRefGoogle Scholar
  7. 7.
    Cormen T, Leiserson C, Rivest R (2001) Introduction to algorithms. MIT Press; http://www.amazon.com/exec/obidos/ASIN/0262032937/ref%3Dnosim/necresearch-20/103-1702329-3847865 Google Scholar
  8. 8.
    Davison AJ (1998) Mobile robot navigation using active vision. PhD thesis, University of Oxford Google Scholar
  9. 9.
    Dissanayake MWMG, Newman P, Durrant-Whyte HF, Clark S, Csorba M (1999) An experimental and theoretical investigation into simultaneous localization and map building. In: Sixth International Symposium on Experimental Robotics, pp 265–274 Google Scholar
  10. 10.
    Faugeras O, Luong Q-T, Papadopoulo T (2001) The geometry of multiple images. MIT Press; http://www.amazon.com/exec/obidos/tg/detail/-/0262062208/qid=1057849899/sr=1-2/ref=sr_1_2/103-1702329-3847865?v=glance&s=books Google Scholar
  11. 11.
    Guivant J, Nebot E (2001) Optimization of the simultaneous localization and map building algorithm for real time implementation. IEEE Trans Robot Autom 17(3):242–257 CrossRefGoogle Scholar
  12. 12.
    Hartley RI, Zisserman A (2001) Multiple view geometry in computer vision. Cambridge University Press [ISBN: 0521623049] Google Scholar
  13. 13.
    Leonard JJ, Rikoski RJ, Newman PM, Bosse M (2002) Mapping partially observable features from multiple uncertain vantage points. Int J Robot Res 21(10):943–975 CrossRefGoogle Scholar
  14. 14.
    Lozano-Pérez T (1989) Foreword. In: Cox IJ, Wilfong GT (eds.) Autonomous robot vehicles. Springer, Berlin Google Scholar
  15. 15.
    Marr D (1982) Vision. Freeman, New York Google Scholar
  16. 16.
    McLauchlan PF (2000) A batch/recursive algorithm for 3d scene reconstruction. In: International Conference on Computer Vision and Pattern Recognition, Hilton Head, SC, Vol 2, pp 738–743 Google Scholar
  17. 17.
    Moutarlier P, Chatila R (1989) An experimental system for incremental environment modeling by an autonomous mobile robot. In: 1st International Symposium on Experimental Robotics, Montreal Google Scholar
  18. 18.
    Moutarlier P, Chatila R (1989) Stochastic multi-sensory data fusion for mobile robot location and environment modeling. In: 5th International Symposium on Robotics Research, pp 207–216 Google Scholar
  19. 19.
    Smith R, Self M, Cheeseman P (1990) Estimating uncertain spatial relationships in robotics. In: Cox IJ, Wilfong GT (eds) Autonomous Robot Vehicles, pp 167–193. Springer-Verlag Google Scholar
  20. 20.
    Smith SM, Brady JM (1997) Susan – a new approach to low level image processing. Int J Comput Vision 23(1):45–78 CrossRefGoogle Scholar
  21. 21.
    Taylor CJ, Kriegman DJ (1995) Structure and motion from line segments in multiple images. IEEE Trans Pattern Anal Mach Intell 17(11):1021–1032 CrossRefGoogle Scholar
  22. 22.
    Taylor CJ (2000) Videoplus: a method for capturing the structure and appearance of immersive environments. In: Second Workshop on 3D Structure from Multiple Images of Large-scale Environments, pp 187–204 Google Scholar
  23. 23.
    Teller S, Antone M, Bodnar Z, Bosse M, Coorg S (2001) Calibrated, registered images of an extended urban area. In: International Conference on Computer Vision and Pattern Recognition, Kauai, Hawaii, Vol 1, pp 813–820 Google Scholar
  24. 24.
    Thrun S (2001) An online mapping algorithm for teams of mobile robots. Int J Robot Res 20(5):335–363 CrossRefGoogle Scholar
  25. 25.
    Triggs B, Zisserman A, Szeliski R (eds.) (1999) Vision algorithms, theory and practice: International Workshop on Vision. Springer, Berlin Google Scholar

Copyright information

© Springer-Verlag 2003

Authors and Affiliations

  • Michael Bosse
    • 1
  • Richard Rikoski
    • 1
  • John Leonard
    • 1
  • Seth Teller
    • 1
  1. 1.Massachusetts Institute of TechnologyCambridgeUSA

Personalised recommendations