Advertisement

Registration of Range Images Based on Segmented Data

  • Bojan Kverh
  • Aleš Leonardis
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1689)

Abstract

We present a new method for registration of range images, which is based on the results we obtain from the segmentation process. To obtain the first set of points needed for registration, we use set of points from first range image. The novelty is how we obtain the second set of points. To obtain the second set we project the first set of points onto geometric parametric models obtained in the second range image. Then we compute the transformation between the two sets of points. The results have shown a significant improvement in precision of the registration in comparison with traditional approach.

Keywords

registration segmentation range images 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    P. J. Besl and N. D. McKay. A method for registration of 3-D shapes. IEEE Transactions on PAMI, 14(2):239–256, February 1992.Google Scholar
  2. 2.
    B. Kverh. Segmentation and registration of range images as a tool for modelling objects. Msc. thesis, Faculty for Computer and Information Science, University of Ljubljana, 1998. Due to a double blind review procedure, the reference will be provided in the final version of the paper.Google Scholar
  3. 3.
    B. Kverh, A. Jakliĉ, A. Leonardis, and F. Solina. Recover-and-select paradigm on triangulated data. In Proceedings of the Sixth Electrotechnical and Computer Science Conference ERK'97, volume B, pages 241–244, September 1997. Due to a double blind review procedure, the reference will be provided in the final version of the paper.Google Scholar
  4. 4.
    B. Kverh and A. Leonardis. Using recover-and-select paradigm for simultaneous recovery of planes, second order surfaces and spheres from triangulated data. In Proceedings of the Computer Vision Winter Workshop CVWW'98, pages 26–37, February 1998. Due to a double blind review procedure, the reference will be provided in the final version of the paper.Google Scholar
  5. 5.
    A. Leonardis, A. Gupta, and R. Bajcsy. Segmentation of range images as the search for geometric parametric models. International Journal of Computer Vision, 14:253–277, 1995.CrossRefGoogle Scholar
  6. 6.
    G. Lukács, A. D. Marshall, and R. R. Martin. Geometric least-squares fitting of spheres, cylinders, cones and tori. In R. R. Martin and T. V. ady, editors, RECCAD Deliverable Documents 2 and 3 Copernicus Project No. 1068 Part I, Report on Basic Geometry and Geometry Model Creation with further contributions on Data Acquisition and advanced material on Merging and Applications, GML 1997/5, Computer and Automation Institute, Hungarian Academy of Sciences, Budapest, 1997.Google Scholar
  7. 7.
    G. Lukács, A. D. Marshall, and R. R. Martin. Faithful least-squares fitting of spheres, cylinders, cones and tori for reliable segmentation. In ECCV98 — Proceedings of the 5th European Conference on Computer Vision, volume I, pages 671–686, June 1998.Google Scholar
  8. 8.
    A. D. Marshall and R. R. Martin. Computer Vision, Models and Inspection, volume 4 of World Scientific Series in Robotics and Automated Systems. World Scientific, September 1991.Google Scholar
  9. 9.
    T. Masuda, K. Sakaue, and N. Yokoya. Registration and integration of multiple range images for 3-D model construction. In Proceedings of the 13th International Conference on Pattern Recognition, pages 879–883, August 1996.Google Scholar
  10. 10.
    T. Pajdla, V. Hlaváĉ, and D. Veĉerka. Semi-automatic building of complete 3D models from range images. In R. R. Martin and T. Varady, editors, RECCAD Deliverable Documents 2 and 3 Copernicus Project No. 1068 Part II, Report on Basic Geometry and Geometry Model Creation with further contributions on Data Acquisition and advanced material on Merging and Applications, GML 1997/5, Computer and Automation Institute, Hungarian Academy of Sciences, Budapest, 1997.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1999

Authors and Affiliations

  • Bojan Kverh
    • 1
  • Aleš Leonardis
    • 1
  1. 1.Faculty of Computer and Information ScienceUniversity of LjubljanaLjubljanaSlovenia

Personalised recommendations