VIEW-BASED ROBOT LOCALIZATION USING ILLUMINATION-INVARIANT SPHERICAL HARMONICS DESCRIPTORS

Holger Friedrich, David Dederscheck, Martin Mutz, Rudolf Mester

2008

Abstract

In this work we present a view-based approach for robot self-localization using a hemispherical camera system. We use view descriptors that are based upon Spherical Harmonics as orthonormal basis functions on the sphere. The resulting compact representation of the image signal enables us to efficiently compare the views taken at different locations. With the view descriptors stored in a database, we compute a similarity map for the current view by means of a suitable distance metric. Advanced statistical models based upon principal component analysis introduced to that metric allows to deal with severe illumination changes, extending our method to real-world applications.

References

  1. Blaer, P. and Allen, P. (2002). Topological mobile robot localization using fast vision techniques. In Proc. ICRA, volume 1, pages 1031-1036.
  2. Burel, G. and Henoco, H. (1995). Determination of the orientation of 3D objects using Spherical Harmonics. Graphical Models and Image Procesing, 57(5):400- 408.
  3. Dietz, H. G. (2006). Fisheye digital imaging for under twenty dollars. Technical report, Univ. of Kentucky. http://aggregate.org/DIT/peepfish/.
  4. Friedrich, H., Dederscheck, D., Krajsek, K., and Mester, R. (2007). View-based robot localization using Spherical Harmonics: Concept and first experimental results. In Hamprecht, F., Schnörr, C., and Jähne, B., editors, DAGM 07, number 4713 in LNCS, pages 21- 31. Springer.
  5. Gonzalez-Barbosa, J.-J. and Lacroix, S. (2002). Rover localization in natural environments by indexing panoramic images. In Proc. ICRA, pages 1365-1370. IEEE Computer Society.
  6. Groemer, H. (1996). Geometric Applications of Fourier Series and Spherical Harmonics. Encyclopedia of Mathematics and Its Applications. Cambridge University Press.
  7. Jogan, M. and Leonardis, A. (2003). Robust localization using an omnidirectional appearance-based subspace model of environment. Robotics and Autonomous Systems, 45:57-72.
  8. Kazhdan, M., Funkhouser, T., and Rusinkiewicz, S. (2003). Rotation invariant Spherical Harmonic representation of 3D shape descriptors. In Kobbelt, L., Schröder, P., and Hoppe, H., editors, Eurographics Symp. on Geometry Proc.
  9. Kovacs, J. A. and Wriggers, W. (2002). Fast rotational matching. Acta Crystallographica Section D, 58(8):1282-1286.
  10. Kröse, B., Vlassis, N., Bunschoten, R., and Motomura, Y. (2001). A probabilistic model for appearancebased robot localization. Image and Vision Computing, 19(6):381-391.
  11. Labbani-Igbida, O., Charron, C., and Mouaddib, E. M. (2006). Extraction of Haar integral features on omnidirectional images: Application to local and global localization. In DAGM 06, pages 334-343.
  12. Levin, A. and Szeliski, R. (2004). Visual odometry and map correlation. In CVPR, volume I, pages 611-618.
  13. Makadia, A. (2006). Correspondenceless visual navigation under constrained motion. In Daniilidis, K. and Klette, R., editors, Imaging beyond the Pinhole Camera, pages 253-268.
  14. Makadia, A. and Daniilidis, K. (2003). Direct 3D-rotation estimation from spherical images via a generalized shift theorem. In CVPR, volume 2, pages 217-224.
  15. Makadia, A. and Daniilidis, K. (2006). Rotation recovery from spherical images without correspondences. PAMI, 28(7):1170-1175.
  16. Makadia, A., Sorgi, L., and Daniilidis, K. (2004). Rotation estimation from spherical images. In ICPR, volume 3.
  17. Mei, C. (2006). Omnidirectional calibration toolbox. http: //www.robots.ox.ac.uk/˜cmei/Toolbox.html.
  18. Menegatti, E., Maeda, T., and Ishiguro, H. (2004). Imagebased memory for robot navigation using properties of the omnidirectional images. Robotics and Autonomous Systems, 47(4).
  19. Menegatti, E., Zoccarato, M., Pagello, E., and Ishiguro, H. (2003). Hierarchical image-based localisation for mobile robots with Monte-Carlo localisation. In Proc. European Conference on Mobile Robots, pages 13- 20.
  20. Mester, R., Aach, T., and Dümbgen, L. (2001). Illumination-invariant change detection using a statistical colinearity criterion. In Pattern Recognition, number 2191 in LNCS.
  21. Mileva, Y., Bruhn, A., and Weickert, J. (2007). Illumination-robust variational optical flow with photometric invariants. In Hamprecht, F., Schnörr, C., and Jähne, B., editors, Pattern Recognition, volume 4713 of LNCS, pages 152-162. Springer.
  22. Mühlich, M. and Mester, R. (2004). A statistical unification of image interpolation, error concealment, and sourceadapted filter design. In Proc. SSIAI, pages 128-132. IEEE Computer Society.
  23. Pajdla, T. and Hlavac, V. (1999). Zero phase representation of panoramic images for image based localization. In Computer Analysis of Images and Patterns, pages 550-557.
  24. Reisert, M. and Burkhardt, H. (2006). Invariant features for 3D-data based on group integration using directional information and Spherical Harmonic expansion. In Proc. ICPR 2006, LNCS.
  25. Schulz, J., Schmidt, T., Ronneberger, O., Burkhardt, H., Pasternak, T., Dovzhenko, A., and Palme, K. (2006). Fast scalar and vectorial grayscale based invariant features for 3D cell nuclei localization and classification. In Franke, K. and al., E., editors, DAGM 2006, number 4174 in LNCS, pages 182-191. Springer.
  26. Steinbauer, G. and Bischof, H. (2005). Illumination insensitive robot self-localization using panoramic eigenspaces. In RoboCup 2004.
  27. The Blender Foundation (2007). Blender. http://www. blender.org.
  28. Thrun, S., Burgard, W., and Fox, D. (2005). Probabilistic Robotics. The MIT Press.
  29. Turk, M. and Pentland, A. (1991). Eigenfaces for recognition. J. of Cognitive Neuroscience, 3(1).
  30. Weisstein, E. W. (2007). Legendre polynomial. A Wolfram Web Resource. http://mathworld.wolfram. com/LegendrePolynomial.html.
Download


Paper Citation


in Harvard Style

Friedrich H., Dederscheck D., Mutz M. and Mester R. (2008). VIEW-BASED ROBOT LOCALIZATION USING ILLUMINATION-INVARIANT SPHERICAL HARMONICS DESCRIPTORS . In Proceedings of the Third International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2008) ISBN 978-989-8111-21-0, pages 543-550. DOI: 10.5220/0001083705430550


in Bibtex Style

@conference{visapp08,
author={Holger Friedrich and David Dederscheck and Martin Mutz and Rudolf Mester},
title={VIEW-BASED ROBOT LOCALIZATION USING ILLUMINATION-INVARIANT SPHERICAL HARMONICS DESCRIPTORS},
booktitle={Proceedings of the Third International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2008)},
year={2008},
pages={543-550},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001083705430550},
isbn={978-989-8111-21-0},
}


in EndNote Style

TY - CONF
JO - Proceedings of the Third International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2008)
TI - VIEW-BASED ROBOT LOCALIZATION USING ILLUMINATION-INVARIANT SPHERICAL HARMONICS DESCRIPTORS
SN - 978-989-8111-21-0
AU - Friedrich H.
AU - Dederscheck D.
AU - Mutz M.
AU - Mester R.
PY - 2008
SP - 543
EP - 550
DO - 10.5220/0001083705430550