Abstract
This paper presents a general framework for the computation of projective invariants of arbitrary degree of freedom (dof) trihedral polyhedra. We show that high dof. figures can be broken down into sets of connected four dof. polyhedra, for which known invariants exist. Although the more general shapes do not possess projective properties as a whole (when viewed by a single camera), each subpart does yield a projective description which is based on the butterfly invariant. Furthermore, planar projective invariants can be measured which link together the subparts, and so we can develop a local-global description for general trihedral polyhedra. We demonstrate the recovery of polyhedral shape descriptions from images by exploiting the local-global nature of the invariants.
Chapter PDF
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
S. Carlsson. Multiple image invariance using the double algebra. In Applications of Invariance in Computer Vision, volume 825 of LNCS, p. 145–164. Springer-Verlag, 1994.
R. Duda and P. Hart. Pattern Classification and Scene Analysis. Wiley, 1973.
G. Ettinger. Large hierarchical object recognition using libraries of parameterized model sub-parts. Proc. CVPR, p.32–41, 1988.
M. Kass, A. Witkin, and D. Terzopoulos. Snakes: Active contour models. Proc. ICCV, p.259–268, 1987.
C. Rothwell, J. Mundy, and W. Hoffman. Representing objects using topology. In preparation, 1996.
C. Rothwell, J. Mundy, W. Hoffman, and V.-D. Nguyen. Driving vision by topology. Proc. IEEE International Symposium on Computer Vision, p.395–400, 1995.
C. Rothwell, D. Forsyth, A. Zisserman, and J. Mundy. Extracting projective information from single views of 3D point sets. TR 1927/92, Oxford Univ. Dept Eng. Sci., 1992.
C. Rothwell, D. Forsyth, A. Zisserman, and J. Mundy. Extracting projective structure from single perspective views of 3D point sets. Proc. ICCV, p.573–582 1993.
C. Rothwell and J. Stern. Understanding the shape properties of trihedral polyhedra. TR 2661, INRIA, 1995.
C. Rothwell. Object recognition through invariant indexing. Oxford University Press, 1995.
K. Sugihara. Machine Interpretation of Line Drawings. MIT Press, 1986.
A. Sugimoto. Geometric invariant of noncoplanar lines in a single view. Proc. ICPR, p. 190–195, 1994.
A. Zisserman, D. Forsyth, J. Mundy, C. Rothwell, J. Liu, and N. Pillow. 3D object recognition using invariance. TR 2027/94, Oxford Univ. Dept Eng. Sci., 1994, to appear the AI Journal.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1996 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Rothwell, C., Stern, J. (1996). Understanding the shape properties of trihedral polyhedra. In: Buxton, B., Cipolla, R. (eds) Computer Vision — ECCV '96. ECCV 1996. Lecture Notes in Computer Science, vol 1064. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0015534
Download citation
DOI: https://doi.org/10.1007/BFb0015534
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-61122-6
Online ISBN: 978-3-540-49949-7
eBook Packages: Springer Book Archive