Advertisement

International Journal of Computer Vision

, Volume 74, Issue 3, pp 219–236 | Cite as

Omnidirectional Vision Based Topological Navigation

  • Toon GoedeméEmail author
  • Marnix Nuttin
  • Tinne Tuytelaars
  • Luc Van Gool
Article

Abstract

In this work we present a novel system for autonomous mobile robot navigation. With only an omnidirectional camera as sensor, this system is able to build automatically and robustly accurate topologically organised environment maps of a complex, natural environment. It can localise itself using such a map at each moment, including both at startup (kidnapped robot) or using knowledge of former localisations. The topological nature of the map is similar to the intuitive maps humans use, is memory-efficient and enables fast and simple path planning towards a specified goal. We developed a real-time visual servoing technique to steer the system along the computed path.

A key technology making this all possible is the novel fast wide baseline feature matching, which yields an efficient description of the scene, with a focus on man-made environments.

Keywords

omnidirectional vision topological maps wide baseline matching visual servoing 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Aliaga, D. 2001. Accurate catadioptric calibration for real-time pose estimation in room-size environments. In Proc. IEEE Int. Conf. Computer Vision (ICCV), Vancouver, pp. 127–134.Google Scholar
  2. Arya, S., Mount, D., Netanyahu, N., Silverman, R., and Wu, A. 1998. An optimal algorithm for approximate nearest neighbor searching. Journal of the ACM, 45:891–923.zbMATHCrossRefGoogle Scholar
  3. Basri, R., Rivlin, E., and Shimshoni, I. 1998. Visual homing: Surfing on the epipoles. In IEEE International Conference on Computer Vision ICCV’98, Bombay, pp. 863–869.Google Scholar
  4. Beevers, K. and Huang, W. 2005. Loop Closing in Topological Maps. ICRA.Google Scholar
  5. Bischof, H., Wildenauer, H., and Leonardis, A. 2001. Illumination insensitive eigenspaces. In Proc. ICCV01, IEEE Computer Society, pp. 233–238.Google Scholar
  6. Cartwright, B. and Collett, T. 1987. Landmark maps for Honeybees. Biol. Cybernetics, 57:85–93.CrossRefGoogle Scholar
  7. Chen, C. and Wang, H. 2005. Appearance-based topological Bayesian inference for loop-closing detection in cross-country environment. IROS, Edmonton, pp. 322–327.Google Scholar
  8. Davison, A. 2003. Real-time simultaneous localisation and mapping with a single camera. Intl. Conf. on Computer Vision, Nice.Google Scholar
  9. Dempster, A.P. 1967. Upper and lower probabilities induced by a multivalued mapping. The Annals of Statistics, (28):325–339.Google Scholar
  10. Demeester, E., Nuttin, M., Vanhooydonck, D., and Van Brussel, H. 2003. Fine motion planning for shared wheelchair control: Requirements and preliminary experiments. International Conference on Advanced Robotics, Coimbra, pp. 1278–1283.Google Scholar
  11. Dijkstra, E.W. 1959. A note on two problems in connection with graphs. Numerische Mathematik, 1:269–271.zbMATHCrossRefGoogle Scholar
  12. Fischler, M. and Bolles, R. 1981. Random sample consensus: A paradigm for model fitting with applications to image analysis. Comm. of the ACM, 24:381–395.CrossRefGoogle Scholar
  13. Franz, M., Schölkopf, B., Mallot, H., and Bülthoff, H. 1998. Where did I take that snapshot? Scene-based homing by image matching. Biological Cybernetics, 79:191–202.zbMATHCrossRefGoogle Scholar
  14. Geyer, C. and Daniilidis, K. 2003. Mirrors in motion: Epipolar geometry and motion estimation. Proc. ICCV, Nice, p. 766.Google Scholar
  15. Goedemé, T., Tuytelaars, T., and Van Gool, L. 2004. Fast wide baseline matching with constrained camera position. Computer Vision and Pattern Recognition. Washington, DC, pp. 24–29.Google Scholar
  16. Goedemé, T., Tuytelaars, T., Vanacker, G., Nuttin, M., and Van Gool, L. 2005. Feature based omnidirectional sparse visual path following. IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2005, Edmonton.Google Scholar
  17. Haralick, R., Lee, C., Ottenberg, K., and Nölle, M. 1994. Review and analysis of solutions of the three point perspective pose estimation problem. International Journal of Computer Vision, 13(3):331–356.CrossRefGoogle Scholar
  18. Hartley, R. 1992. Estimation of relative camera positions for uncalibrated cameras. In 2nd European Conference on Computer Vision, Springer-Verlag, LNCS 588, pp. 579–587.Google Scholar
  19. Jain, A. 1989. Fundamentals of Digital Image Processing. Prentice Hall.Google Scholar
  20. Jogan, M. and Leonardis, A. 1999. Panoramic eigenimages for spatial localisation, In Proceedings 8th International Conference on Computer Analysis of Images and Patterns(1689), F. Solina, and A. Leonardis, (Eds.), Ljubljana, pp. 558–567.Google Scholar
  21. Jogan, M. and Leonardis, A. 2000. Robust localization using panoramic view-based recogniton, In Proceedings 15th International Conference on Pattern Recognition ICPR’00, Barcelona, Spain, pp. 136–139.Google Scholar
  22. Koenig, S. and Simmons, R. 1996. Unsupervised Learning of Probabilistic Models for Robot Navigation, ICRA.Google Scholar
  23. Košecká, J. and Yang, X. 2004. Global localization and relative pose estimation based on scale-invariant features. ICPR, (4):319–322.Google Scholar
  24. Kröse, B., Porta, J., van Breemen, A., Crucq, K., Nuttin, M., and Demeester, E. 2003. Lino, the User-Interface Robot, First European Symposium on Ambient Intelligence (EUSAI 2003), Veldhoven, The Netherlands, pp. 264–274.Google Scholar
  25. Ledwich, L. and Williams, S. 2004. Reduced SIFT features for image retrieval and indoor localisation. Australasian Conf. on Robotics and Automation ACRA, Canberra.Google Scholar
  26. Loeffler, C., Ligtenberg, A., and Moschytz, G. 1989. Practical Fast 1-D DCT Algoritmh with 11 Multiplications, ICASSP, pp. 988–991.Google Scholar
  27. Lowe, D. 1999. Object recognition from local scale-invariant features. In International Conference on Computer Vision, pp. 1150–1157.Google Scholar
  28. Matas, J., Chum, O., Urban, M., and Pajdla, T. 2002. Robust wide baseline stereo from maximally stable extremal regions. British Machine Vision Conference, Cardiff, Wales, pp. 384–396.Google Scholar
  29. Mariottini, G., Alunno, E., Piazzi, J., and Prattichizzo, D. 2005. Epipole-Based Visual Servoing with Central Catadioptric Camera. IEEE ICRA05, Barcelona.Google Scholar
  30. Mikolajczyk, K. and Schmid, C. 2002. An affine invariant interest point detector. ECCV, 1:128–142.Google Scholar
  31. Millnert, O., Goedemé, T., Tuytelaars, T., Van Gool, L., Huntemann, A., and Nuttin, M. 2006. Range determination for mobile robots using one omnidirectional camera. In International Conference on Informatics in Control, Automation and Robotics, ICINCO 2006, Setubal.Google Scholar
  32. Mindru, F., Moons, T., and Van Gool, L. 1999. Recognizing color patters irrespective of viewpoint and illumination. Computer Vision and Pattern Recognition, 1:368–373.Google Scholar
  33. Nistér, D., Naroditsky, O., and Bergen, J. 2004. Visual Odometry, Conference on Computer Vision and Pattern Recognition. Washington, DC.Google Scholar
  34. Nuttin, M., Demeester, E., Vanhooydonck, D., and Van Brussel, H. 2001. Shared autonomy for wheelchair control: Attempts to assess the user’s autonomy. Autonome Mobile Systeme, pp. 127–133.Google Scholar
  35. Nuttin, M., Vanhooydonck, D., Demeester, E., Van Brussel, H., Buijsse, K., Desimpelaere, L., Ramon, P., and Verschelden, T. 2003. A Robotic Assistant for Ambient Intelligent Meeting Rooms, First European Symposium on Ambient Intelligence (EUSAI 2003), Veldhoven, The Netherlands, pp. 304–317.Google Scholar
  36. Okuma, T., Sakaue, K., Takemura, H., and Yokoya, N. 2000. Real-time camera parameter estimation from images for a Mixed Reality system. In Proc. ICPR, Barcelona, Spain.Google Scholar
  37. Pérer-Fontán, F., Sanmartin, B., Steingaß, A., Lehner, A., Kubista, E., Martin, M.J., and Arbesser-Rastburg, B. 2004. Measurements and modelling of the satellite-to-indoor channel for Galileo. European Navigation Conference GNSS, Rotterdam.Google Scholar
  38. Pollefeys, M., Van Gool, L., Vergauwen, M., Verbiest, F., Cornelis, K., Tops, J., and Koch, R. 2004. Visual modeling with a hand-held camera. International Journal of Computer Vision, 59(3):207–232.CrossRefGoogle Scholar
  39. Ranganathan, A., Menegatti, E., and Dellaert, F. 2005. Bayesian inference in the space of topological maps. IEEE Transactions on Robotics Google Scholar
  40. Rekimoto, J. and Ayatsuka, Y. 2000. CyberCode: Designing augmented reality environments with visual tags. Designing Augmented Reality Environments (DARE 2000).Google Scholar
  41. Schmid, C., Mohr, R., and Bauckhage, C. 1997. Local grey-value invariants for image retrieval. International Journal on Pattern Analysis an Machine Intelligence, 19(5):872–877.Google Scholar
  42. Se, S., Lowe, D., and Little, J. 2001. Local and global localization for mobile robots using visual landmarks. In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS ’01), Hawaii, USA.Google Scholar
  43. Shafer, G. 1976. A Mathematical Theory of Evidence. Princeton University Press.Google Scholar
  44. Shatkay, H. and Kaelbling, L.P. 1997. Learning topological maps with weak local odometric information. IJCAI, (2):920–929.Google Scholar
  45. Shi, J. and Tomasi, C. 1994. Good features to track. Computer Vision and Pattern Recognition, Seattle, pp. 593–600.Google Scholar
  46. Stricker, D., Daehne, P., Seibert, F., Christou, I.T., Almeida, L., Carlucci, R., and Ioannidis, N.I. 2001. Design and development issues for archeoguide: An augmented reality based cultural heritage on-site guide. In International Conference on Augmented, Virtual Environments and Three-Dimensional Imaging, Mykonos.Google Scholar
  47. Svoboda, T., Pajdla, T., and Hlaváč V. 1998. Motion estimation using panoramic cameras. In Conf. on Intelligent Vehicles, Stuttgart, pp. 335–340.Google Scholar
  48. Svoboda, T. 2000. Central Panoramic Cameras, Design, Geometry, Egomotion, PhD Thesis, Czech Technical University.Google Scholar
  49. Tapus, A. and Siegwart, R. 2005. Incremental Robot Mapping with Fingerprints of Places, IROS, Edmonton.Google Scholar
  50. Tuytelaars, T., Van Gool, L., D’haene, L., and Koch, R. 1999. Matching of affinely invariant regions for visual servoing. International Conferemce on Robotics and Automation, pp. 1601–1606.Google Scholar
  51. Tuytelaars, T. and Van Gool, L. 2000. Wide baseline stereo based on local, affinely invariant regions. British Machine Vision Conference, Bristol, UK, pp. 412–422.Google Scholar
  52. Ulrich, I. and Nourbakhsh, I. 2000. Appearance-based place recognition for topological localisation. In IEEE International Conference on Robotics and Automatisation, San Francisco, pp. 1023–1029.Google Scholar
  53. van Veen, H., Distler, H.K., Braun, S.J., and Bülthoff, H.H. 1998. Navigating through a virtual city: Using virtual reality technology to study human action and perception. Future Generation Computer Systems, 14:231–242.CrossRefGoogle Scholar
  54. Vale, A. and Isabel Ribeiro, M. 2003. Environment Mapping as a Topological Representation. ICAR, Coimbra, Portugal.Google Scholar
  55. Zivkovic, Z., Bakker, B., and Kröse, B. 2005. Hierarchical Map Building Using Visual Landmarks and Geometric Constraints, IROS, Edmonton, pp. 7–12.Google Scholar

Copyright information

© Springer Science+Business Media, LLC 2006

Authors and Affiliations

  • Toon Goedemé
    • 1
    Email author
  • Marnix Nuttin
    • 2
  • Tinne Tuytelaars
    • 3
  • Luc Van Gool
    • 4
    • 5
  1. 1.ESAT - PSI - VISICSUniversity of LeuvenLeuvenBelgium
  2. 2.PMAUniversity of LeuvenLeuvenBelgium
  3. 3.ESAT - PSI - VISICSUniversity of LeuvenLeuvenBelgium
  4. 4.ESAT - PSI - VISICSUniversity of LeuvenLeuvenBelgium
  5. 5.BIWIETH ZürichSwitzerland

Personalised recommendations