Advertisement

Coarse Registration of Surface Patches with Local Symmetries

  • Joris Vanden Wyngaerd
  • Luc Van Gool
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2351)

Abstract

Most 3D recording methods generate multiple partial reconstructions that must be integrated to form a complete model. The coarse registration step roughly aligns the parts with each other. Several methods for coarse registration have been developed that are based on matching points between different parts. These methods look for interest points and use a point signature that encodes the local surface geometry to find corresponding points. We developed a technique that is complementary to these methods. Local descriptions can fail or can be highly inefficient when the surfaces contain local symmetries. In stead of discarding these regions, we introduce a method that first uses the Gaussian image to detect planar, cylindrical and conical regions and uses this information to compute the rigid motion between the patches. For combining the information from multiple regions to a single solution, we use a a Hough space that accumulates votes for candidate transformations. Due to their symmetry, they update a subspace of parameter space in stead of a single bin. Experiments on real range data from different views of the same object show that the method can find the rigid motion to put the patches in the same coordinates system.

Keywords

Surface Registration Surface geometry Shape 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    W.W. Adams and P. Loustaunau, An Introduction to Gröbner Bases, Graduate Studies in Mathematics, Vol. 3., American Mathematical Society, 1994Google Scholar
  2. 2.
    P. Besl, N. McKay, A method of registration of 3-D shapes, IEEE Trans. PAMI 12(2) pp. 239–256, 1992Google Scholar
  3. 3.
    R. M. Bolle and D. B. Cooper. On optimally combining pieces of information, with application to estimating 3-D complex-object position from range data. IEEE Trans. PAMI 8(5) pp. 619–638, 1986Google Scholar
  4. 4.
    P. Brou, Using the Gaussian Image to Find the Orientation of an Object, Int’l J. Robotics Research, vol. 3, pp. 89–125, 1983CrossRefGoogle Scholar
  5. 5.
    Y. Chen and G. Medioni, Object modeling by registration of multiple range images, Proc. Int. Conf. on Robotics and Automation, pp. 2724–2729, 1991Google Scholar
  6. 6.
    C.S. Chua and R. Jarvis, Point signatures: A new representation for 3D object recognition, Int. J. of Computer Vision, 25(1), pp. 63–85, 1997CrossRefGoogle Scholar
  7. 7.
    J. Feldmar and N. Ayache, Rigid, affine and locally affine registration of free-form surfaces, TR INRIA Epidaure, No. 2220, 1994Google Scholar
  8. 8.
    J. Feldmar, N. Ayache, and F. Betting, 3D-2D projective registration of free-form curves and surfaces, TR INRIA Epidaure, No. 2434, dec. 1994Google Scholar
  9. 9.
    H. Hebert, K. Ikeuchi, and H Delingette, A spherical representation for recognition of free-form surfaces, IEEE Trans. PAMI 17(7) pp. 681, 1995Google Scholar
  10. 10.
    Berthold K.P. Horn (1987), Closed-form solution of absolute orientation using unit quaternions, Journal of the Optical Society of America A, 4:629–642CrossRefGoogle Scholar
  11. 11.
    K. Ikeuchi., Recognition of 3-D Objects Using the Extended Gaussian, Image. In Proc. of Seventh IJCAI, pages 595–600, 1981.Google Scholar
  12. 12.
    A. Johnson and M. Hebert, Recognizing objects by matching oriented points, Proc. Conf. Computer Vision and Pattern Recognition, 684–689, San Juan, 1997Google Scholar
  13. 13.
    S.B. Kang and K. Ikeuchi, 3-D Object Pose Determination Using Complex EGI, T.R. CMU-RI-TR-90-18, Robotics Institute, Carnegie Mellon University, 1990Google Scholar
  14. 14.
    Y. Liu and M.A. Rodrigues, Essential Representation and Calibration of Rigid Body Transformations, Machine Graphics and Vision Journal Vol 9 (2000).Google Scholar
  15. 15.
    A. P. Pentland, Perceptual Organizations And The Representation Of Natural Form, Artificial Intelligence, vol. 28, no. 2, pp. 293–331, 1986CrossRefMathSciNetGoogle Scholar
  16. 16.
    C. Sun, and J. Sherrah, 3-D Symmetry Detection Using The Extended Gaussian Image, IEEE Trans. PAMI 19(2) pp. 164–168, 1997Google Scholar
  17. 17.
    Tina Y. Tian and Mubarak Shah. Recovering 3d motion of multiple objects using adaptative hough transform. IEEE Trans. PAMI, 19(10):1178Google Scholar
  18. 18.
    Vanden Wyngaerd, J., Van Gool, L., Koch, R., Proesmans, M., 1999. Invariant-based registration of surface patches. Proc. International Conference on Computer Vision, IEEE Computer Society Press, pp. 301–306.Google Scholar
  19. 19.
    P. Viola and W. Wells, Alignment by maximisation of mutual information, Proc. Int. Conf. on Computer Vision, pp. 16–23, 1995Google Scholar
  20. 20.
    N. Werghi R.B. Fisher, A. Ashbrook and C. Robertson, Faithful Recovering of Quadric Surfaces from 3D Range Data, Proc. 2nd Int. Conf. on 3-D Digital Imaging and Modeling, Ottawa, Canada, pp 280–289, October 1999Google Scholar
  21. 21.
    S. Yamany and A. Farag, Free-form surface registration using surface signatures, Int. Conf. on Computer Vision, pp. 1098–1104, 1999Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2002

Authors and Affiliations

  • Joris Vanden Wyngaerd
    • 1
  • Luc Van Gool
    • 1
    • 2
  1. 1.ESAT-PSIUniversity of LeuvenLeuvenBelgium
  2. 2.KommunikationstechnikETZZürichSwitzerland

Personalised recommendations