Abstract
Recognising a curved surface from its outline in a single view is a major open problem in computer vision. This paper shows techniques for recognising a significant class of surfaces from a single perspective view. The approach uses geometrical facts about bitangencies, creases, and inflections to compute descriptions of the surface's shape from its image outline. These descriptions are unaffected by the viewpoint or the camera parameters. We show, using images of real scenes, that these representations identify surfaces from their outline alone. This leads to fast and effective recognition of curved surfaces.
The techniques we describe work for surfaces that have a rotational symmetry, or are projectively equivalent to a surface with a rotational symmetry, and can be extended to an even larger class of surfaces. All the results in this paper are for the case of full perspective. The results additionally yield techniques for identifying the line in the image plane corresponding to the axis of a rotationally symmetric surface, and for telling whether a surface is rotationally symmetric or not from its outline alone.
DAF acknowledges the support of Magdalen College, Oxford, of the University of Iowa, and of GE. JLM acknowledges the support of the GE Coolidge Fellowship. AZ acknowledges the support of SERC. CAR acknowledges the support of GE. The GE CRD laboratory is supported in part by the following: DARPA contract DACA-76-86-C-007, AFOSR contract F49620-89-C-003.
Chapter PDF
We’re sorry, something doesn't seem to be working properly.
Please try refreshing the page. If that doesn't work, please contact support so we can address the problem.
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
Brady, J.M. and Asada, H., “Smoothed Local Symmetries and their implementation,” IJRR-3, 3, 1984.
Brooks, R. A., “Model-Based Three-Dimensional Interpretations of Two Dimensional Images,” IEEE PAMI, Vol. 5, No. 2, p. 140, 1983.
Canny J.F. “Finding Edges and Lines in Images,” TR 720, MIT AI Lab, 1983.
Dhome, M., LaPreste, J.T, Rives, G., and Richetin, M. “Spatial localisation of modelled objects in monocular perspective vision,” Proc. First European Conference on Computer Vision, 1990.
D.A. Forsyth, J.L. Mundy, A.P. Zisserman, A. Heller, C. Coehlo and C.A. Rothwell (1991), “Invariant Descriptors for 3D Recognition and Pose,” IEEE Trans. Patt. Anal. and Mach. Intelligence, 13, 10.
Forsyth, D.A., “Recognising an algebraic surface by its outline,” Technical report, University of Iowa Department of Computer Science, 1992.
H. Freeman and R. Shapira, “Computer Recognition of Bodies Bounded by Quadric Surfaces from a set of Imperfect Projections,” IEEE Trans. Computers, C27, 9, 819–854, 1978.
Koenderink, J.J. Solid Shape, MIT Press, 1990.
Malik, J., “Interpreting line drawings of curved objects,” IJCV, 1, 1987.
J.L. Mundy and A.P. Zisserman, “Introduction,” in J.L. Mundy and A.P. Zisserman (ed.s) Geometric Invariance in Computer Vision, MIT Press, 1992.
J.L. Mundy and A.P. Zisserman, “Appendix” in J.L. Mundy and A.P. Zisserman (ed.s) Geometric Invariance in Computer Vision, MIT Press, 1992.
Ponce, J. “Invariant properties of straight homogenous generalised cylinders,” IEEE Trans. Patt. Anal. Mach. Intelligence, 11, 9, 951–965, 1989.
J. Ponce and D.J. Kriegman (1989), “On recognising and positioning curved 3 dimensional objects from image contours,” Proc. DARPA IU workshop, pp. 461–470.
Rothwell, C.A., Zisserman, A.P., Forsyth, D.A. and Mundy, J.L., “Using Projective Invariants for constant time library indexing in model based vision,” Proc. British Machine Vision Conference, 1991.
Rothwell, C.A., Zisserman, A.P., Forsyth, D.A. and Mundy, J.L., “Canonical frames for planar object recognition,” Proc. 2nd European Conference on Computer Vision, Springer Lecture Notes in Computer Science, 1992.
Rothwell, C.A., Zisserman, A.P., Forsyth, D.A. and Mundy, J.L., “Fast Recognition using Algebraic Invariants,” in J.L. Mundy and A.P. Zisserman (ed.s) Geometric Invariance in Computer Vision, MIT Press, 1992.
Terzopolous, D., Witkin, A. and Kass, M. “Constraints on Deformable Models: Recovering 3D Shape and Nonrigid Motion,” Artificial Intelligence, 36, 91–123, 1988.
Wayner, P.C. “Efficiently Using Invariant Theory for Model-based Matching,” Proceedings CVPR, p.473–478, 1991.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1992 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Forsyth, D.A., Mundy, J.L., Zisserman, A., Rothwell, C.A. (1992). Recognising rotationally symmetric surfaces from their outlines. In: Sandini, G. (eds) Computer Vision — ECCV'92. ECCV 1992. Lecture Notes in Computer Science, vol 588. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-55426-2_68
Download citation
DOI: https://doi.org/10.1007/3-540-55426-2_68
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-55426-4
Online ISBN: 978-3-540-47069-4
eBook Packages: Springer Book Archive