New development of stereo vision: A solution for motion stereo correspondence

Poster Session I
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1351)


This paper presents a new constraint, ie., projective transformation constraint, to solve the difficult problem of motion stereo correspondence in the context where the motion is dominated by rotation (for instance, 10 degrees of rotation with 1 cm of translation). Our observation here is that two consecutive images can be related to each other by a 2D projective transformation. Its coefficients are constants if the motion is a pure rotation (no use for depth recovery but helpful for 3D data fusion with rotating binocular vision and for active vision involving verging motion). The solution presented in this paper constitutes a closed form solution to motion stereo correspondence if the motion is a rotation or a quasi closed form solution if the motion is dominated by rotation (including translation needed for depth recovery). Experiments with real camera and real images prove the usefulness of the new constraint.


Motion Stereo Correspondence Projective Transformation 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    K. Kanatani, Group-Theoretical Methods in Image Understanding, Springer-Verlag, Berlin, p103–194 & 278–354, 1989.Google Scholar
  2. [2]
    O. Faugeras, Three-Dimensional Computer Vision: A Geometric Viewpoint, MIT Press, Cambridge, p33–69 & p165-40, 1993.Google Scholar
  3. [3]
    P. F. McLauchlan and D. W. Murray, Active Camera Calibration for a HeadEye Platform Using the Variable State-Dimension Filter, IEEE Trans. on PAMI, Vol.18, No.1, p15–22, January, 1996.Google Scholar
  4. [4]
    T. Vieville, E. Clergue, R. Enciso, and H. Mathieu, Experimenting with 3D vision on a robotic head, Robotics and Autonomous Systems 14, p1–27, 1995.Google Scholar
  5. [5]
    Z. Zhang, R. Deriche, O. Faugeras, and Q. T. Luong, A robust technique for matching two uncalibrated images through the recovery of the unknown epipolar geometry, Artificial Intelligence, Vol.78, p87–119, October 1995.Google Scholar
  6. [6]
    M. Xie, A cooperative strategy for the matching of multi-level edge primitives, Image and Vision Computing, Vol.13, No.2, p89–99, March, 1995.Google Scholar
  7. [7]
    M. Xie and L. Y. Liu, Color Stereo Vision: Use of Appearance Constraint and Epipolar Geometry For Feature Matching, 2nd Asian Conference on Computer Vision, Vol.1, p282–286, Dec 6–8, 1995.Google Scholar
  8. [8]
    J. You, E. Pissaloux, W. P. Zhu, and H. A. Cohen, Efficient Image Matching: A Hierarchical Chamfer Matching Scheme Via Distributed System, Real Time Imaging, Vol.1, No.4, p245–259, October, 1995.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1997

Authors and Affiliations

  • M. Xie
    • 1
  1. 1.School of Mechanical & Production EngineeringNanyang Technological UniversitySingapore

Personalised recommendations