Point matching for registration of free-form surfaces

  • Zhengyou Zhang
3-D Vision
Part of the Lecture Notes in Computer Science book series (LNCS, volume 719)


A method has been developed for registering two dense 3-D maps obtained by using a correlation-based stereo system. Geometric matching in general is a difficult unsolved problem in computer vision. Fortunately, in many practical applications, some a priori knowledge exists which considerably simplifies the problem. In visual navigation, for example, the motion between successive positions is usually either small or approximately known. From this initial estimate, our algorithm allows to compute the motion with very good precision, which is required for environment modeling. Objects are represented by a set of 3-D points, which are considered as the samples of a surface. No constraint is imposed on the form of the objects. The proposed algorithm is based on iteratively matching points of one view to the closest points of the another view. A statistical method based on the distance distribution is used to discard the outliers. A least-squares technique is used to estimate 3-D motion from the point correspondences, which reduces the average distance between curves in the two sets. Real data have been used to test the algorithm. The results show that it is efficient and robust, and yields an accurate motion estimate.


Free-Form Surface Matching 3-D Registration Motion Estimation Robot Vision 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    K.S. Arun, T.S. Huang, and S.D. Blostein. Least-squares fitting of two 3-D point sets. IEEE Trans. PAMI, 9(5):698–700, September 1987.Google Scholar
  2. 2.
    O.D. Faugeras and M. Hebert. The representation, recognition, and locating of 3D shapes from range data. Int'l J. Robotics Res., 5(3):27–52, 1986.Google Scholar
  3. 3.
    P. Fua. A parallel stereo algorithm that produces dense depth maps and preserves image features. Machine Vision and Applications, 1992. Accepted for publication.Google Scholar
  4. 4.
    D. B. Goldgof, T. S. Huang, and H. Lee. Feature extraction and terrain matching. In Proc. IEEE Conf. Comput. Vision Pattern Recog., pages 899–904, Ann Arbor, Michigan, June 1988.Google Scholar
  5. 5.
    M. Hebert, C. Caillas, E. Krotkov, I. S. Kweon, and T. Kanade. Terrain mapping for a roving planetary explorer. In Proc. Int'l Conf. Robotics Automation, pages 997–1002, 1989.Google Scholar
  6. 6.
    N. Kehtarnavaz and S. Mohan. A framework for estimation of motion parameters from range images. Comput. Vision, Graphics Image Process., 45:88–105, 1989.Google Scholar
  7. 7.
    I. S. Kweon, M. Hebert, and T. Kanade. Perception for rugged terrain. 1988 Year End Report “Autonomous Planetary Rover at Carnegie Mellon” CMU-RI-TR-89-3, Carnegie Mellon University, The Robotics Institute, Pittsburgh, PA 15213, January 1989.Google Scholar
  8. 8.
    I.S. Kweon and T. Kanade. High-resolution terrain map from multiple sensor data. IEEE Trans. PAMI, 14(2):278–292, February 1992.Google Scholar
  9. 9.
    P. Liang and J. S. Todhunter. Representation and recognition of surface shapes in range images: A differential geometry approach. Comput. Vision, Graphics Image Process., 52:78–109, 1990.Google Scholar
  10. 10.
    E. E. Milios. Shape matching using curvature processes. Comput. Vision, Graphics Image Process., 47:203–226, 1989.Google Scholar
  11. 11.
    F. Preparata and M. Shamos. Computational Geometry, An Introduction. Springer, Berlin, Heidelberg, New-York, 1986.Google Scholar
  12. 12.
    R. E. Sampson. 3D range sensor-phase shift detection. Computer, 20:23–24, 1987.Google Scholar
  13. 13.
    R. Szeliski. Estimating motion from sparse range data without correspondence. In Proc. Second Int'l Conf. Comput. Vision, pages 207–216, Tampa, FL, December 1988. IEEE.Google Scholar
  14. 14.
    M. W. Walker, L. Shao, and R. A. Volz. Estimating 3-D location parameters using dual number quaternions. CVGIP: Image Understanding, 54(3):358–367, November 1991.Google Scholar
  15. 15.
    D. Walters. Selection of image primitives for general-purpose visual processing. Comput. Vision, Graphics Image Process., 37(3):261–298, 1987.Google Scholar
  16. 16.
    Z. Zhang. Recalage de deux nuages de points 3D. Traitement du Signal, 1993. In press.Google Scholar
  17. 17.
    Z. Zhang, O.D. Faugeras, and N. Ayache. Analysis of a sequence of stereo scenes containing multiple moving objects using rigidity constraints. In Proc. Second Int'l Conf. Comput. Vision, pages 177–186, Tampa, FL, December 1988. Also as a chapter in R. Kasturi and R.C. Jain (eds), Computer Vision: Principles, IEEE computer society press, 1991.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1993

Authors and Affiliations

  • Zhengyou Zhang
    • 1
  1. 1.INRIA Sophia-AntipolisSophia-Antipolis CedexFrance

Personalised recommendations