Abstract
In stereoscopic images, the behavior of a curve in space is related to the appearance of the curve in the left and right image planes. Formally, this relationship is governed by the projective geometry induced by the stereo camera configuration and by the differential structure of the curve in the scene. We propose that the correspondence problem-matching corresponding points in the image planes-can be solved by relating the differential structure in the left and right image planes to the geometry of curves in space. Specifically, the compatibility between two pairs of corresponding points and tangents at those points is related to the local approximation of a space curve using an osculating helix. To guarantee robustness against small changes in the camera parameters, we select a specific osculating helix. A relaxation labeling network demonstrates that the compatibilities can be used to infer the appropriate correspondences in a scene. Examples on which standard approaches fail are demonstrated.
Research supported by AFOSR
Chapter PDF
References
H. H. Baker and T. O. Binford. Depth from edge and intensity based stereo. In Proceeding of the 7 th Joint Conference of Artificial Intelligence, pages 631–636, 1981.
S.T. Barnard and W.B. Thompson. Disparity analysis of images. PAMI, PAMI-2(4):333–340, July 1980.
E.D. Bloch. A First Course in Geometric Topology and Differential Geometry. Birkhauser, Boston, MA., 1997.
C. David and S.W. Zucker. Potentials, valleys and dynamic global coverings. International Journal of Computer Vision, 5(3):219–238, 1990.
Olivier Faugeras. Three dimensional computer vision. MIT Press, 1993.
J.P. Frisby and S.B. Pollard. Computational issues in solving the stereo correspondance problem. In M.S. Landy and J.A. Movshon, editors, Computational Models of Visual Processing, chapter 21, pages 331–357. MIT Press, Cambridge, MA, 1991.
W.E. Grimson. A computer implementation of a theory of human stereo vision. In Philisophical Transactions of the Royal Society of London, volume B292, pages 217–253. 1981.
Robert Hummel and Steven Zucker. On the foundations of relaxation labelling processes. IEEE Trans. Pattern Analysis and Machine Intelligence, 5(3):267–287, 1983.
B.J. Rogers I.P. Howard. Binocular Vision and Stereopsis. Oxford Psychology Series No. 29. Oxford, 1995.
Lee Iverson and Steven Zucker. Logical/linear operators for image curves. IEEE Trans. Pattern Analysis and Machine Intelligence, 17(10):982–996, October 1995.
Jesse Jin, W.K. Yeap, and B.G. Cox. A stereo model using log and gabor filtering. Spatial Vision, 10(1):3–13, 1996.
David Jones and Jitendra Malik. Determining three-dimensional shape from orientation and spatial frequency disparities. ECCV 92, pages 661–669, 1992.
David Marr and T. Poggio. A theory of human stereo vision. Proceedings of the Royal Society of London, B 204:301–328, 1979.
G. Medioni and R. Nevatia. Segment-based stereo matching. Computer Vision,Graphics and Image Processing, 31:2–18, July 1985.
Pierre Parent and Steven Zucker. Trace inference, curve consistency and curve detection. IEEE Trans. Pattern Analysis and Machine Intelligence, 11(8):823–839, August 1989.
Doron Sherman and Shmuel Peleg. Stereo by incremental matching of contours. IEEE Trans. Pattern Analysis and Machine Intelligence, 12(11):1102–1106, November 1990.
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 2000 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Alibhai, S., Zucker, S.W. (2000). Contour-Based Correspondence for Stereo. In: Computer Vision - ECCV 2000. ECCV 2000. Lecture Notes in Computer Science, vol 1842. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45054-8_21
Download citation
DOI: https://doi.org/10.1007/3-540-45054-8_21
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-67685-0
Online ISBN: 978-3-540-45054-2
eBook Packages: Springer Book Archive