Abstract
Combinatorial geometry is the study of order and incidence properties of groups of geometric features. Ordering properties for point sets in 2-D and 3-D can be seen as a generalization of ordering properties in 1-D and incidences are configurations of features that are non-generic such as collinearity of points. By defining qualitative shape properties using combinatorial geometry we get a common framework for metric and qualitative representations. Order and incidence form a natural hierarchy together with metric representations in terms of increasing abstraction
The problem of recognition can be structured in a similar hierarchy ranging from the recognition of specific objects from specific viewpoints, using calibrated cameras to that of calibration free, view independent recognition of generic objects. Order and incidence relations have invariance properties that make them especially interesting for general recognition problems.
We present an algorithm for 3-D object hypothesis generation from single images. The combinatorial properties of triplets of line segments are used to define an index to a model library. This library consists of line segment triplets for object model views. Every indexing of a model triplet by an image triplet is accumulated into a matching matrix between image and model line segments. From this matrix we can evaluate the strength of an hypothesis that a specific object is present.
Preview
Unable to display preview. Download preview PDF.
References
N. Ayache and B. Faverjon, Efficient registration of stereo images by matching graph descriptions of edge segments, IJCV 1, 1987, 107–131.
T.O. Binford and T.S. Levitt, Quasi-invariants: Theory and exploitation, IUW, 819–829. 1993
I. Biederman, Human image understanding: recent research and a theory, CVGIP 32, 1985, 29–73.
Bjorner, Las Vergnas, Sturmfels, White and Ziegler, Oriented Matroids, Encyclopedia of Mathematics and its Applications, Vol. 46, C.G.Rota editor, Cambridge University Press, 1993
R. Brooks, Symbolic reasoning among 3-D models and 2-D images, Artificial Intelligence, 17: 285–348, 1981
J.B. Burns and E.M. Riseman, Matching complex images to multiple 3D objects using view description networks, CVPR, 328–334. 1992
M. B. Clowes, On seeing things, AI, 2, 1, 79–116, 1971
M. Costa and L. Shapiro, Analysis of scenes containing multiple non-polyhedral 3D objects, Tech. Report Univ. of Washington 1995
S.J. Dickinson, A.P. Pentland, and A. Rosenfeld, 3-D shape recovery using distributed aspect matching, T-PAMI 14, 1992, 174–198.
O.D. Faugeras, What can be seen in three dimensions with an uncalibrated stereo rig?, ECCV, 563–578. 1992
O.D. Faugeras Stratification of 3-D vision: projective, affine, and metric representations, JOSA-A mar, 12, 465–484, 1995.
J. E. Goodman and R. Pollack, Multidimensional sorting SIAM J. Comput. 12 1983 484–507.
W.E.L. Grimson, Object Recognition by Computer-The Role of Geometric Constraints, MIT Press, Cambridge, MA, 1990.
R.I. Hartley, Estimation of relative camera positions for uncalibrated cameras, ECCV, 579–587. 1992
R. Horaud and T. Skordas, Stereo correspondence through feature grouping and maximal cliques, T-PAMI 11, 1989, 1168–1180.
R. Horaud, F. Veillon, and T. Skordas, Finding geometric and relational structures in an image, Proc. 1:st ECCV, 374–384. 1990
R. Horaud and H. Sossa, Polyhedral object recognition by indexing. Pattern recognition, Vol. 28, No. 12 pp. 1855–1870, 1995.
D. Huffman, Impossible objects as nonsense sentences, Machine Intelligence, 6, 1971
D.P. Huttenlocher and S. Ullman, Recognizing solid objects by alignment with an image, IJCV 5, 1990, 195–212.
J. J. Koenderink and A. von Doorn, The singularities of the visual mapping, Biological Cybernetics, 24, 51–59, 1976.
J. J. Koenderink and A. von Doorn, The internal representation of solid shape with respect to vision Biological Cybernetics, 32, 211–216, 1979.
D.J. Kriegman and J. Ponce, On recognizing and positioning curved 3-D objects from image contours, T-PAMI 12, 1990, 1127–1137.
Lamdan, Y., Schwartz, J.T. and Wolfson, H.J. Object recognition by affine invariant matching. In: Proc. CVPR-88, pp. 335–344. (1988)
D.G. Lowe, Perceptual Organization and Visual Recognition, Kluwer, Boston, 1984.
J. Malik, Interpreting line drawings of curved objects, IJCV 1, 1987, 73–103.
D. Marr and K. Nishihara, Representation and recognition of the spatial organization of three dimensional shapes, Proc. Roy. Soc. B 200: 269–294 1987.
R. Mohan and R. Nevatia, Perceptual organization for scene segmentation and description, T-PAMI 14, 1992, 616–635.
R. Mohr, Projective Geometry and Computer Vision, Handbook of Pattern Recognition and Computer Vision, (1992)
P.G. Mulgaonkar, L.G. Shapiro, and R.M. Haralick, Matching “sticks, plates, and blobs” objects using geometric and relational constraints, IVC 2, 1984, 85–98.
J.L. Mundy, P. Vrobel, and R. Joynson, Constraint-based modeling, IUW, 425–442. 1989
V.D. Nguyen, J.L. Mundy, and D. Kapur, Modeling generic polyhedral objects with constraints, CVPR, 479–485. 1991
S.B. Pollard, J. Porrill, and J.E.W. Mayhew, Recovering partial 3D wire frames descriptions from stereo dates, IVC 9, 1991, 58–65.
K. Pulli, TRIBORS: A triplet based object recognition system, Tech. Report Univ. of Washington 1995
Rothwell, C.A., Zisserman, A.P., Mundy, J.L., Forsyth, D.A., Efficient Model Library Access by Projectively Invariant Indexing Functions, In: Proc. CVPR-92, pp. 109–114. (1992)
Rothwell, C.A., Zisserman, A.P., Forsyth, D.A., Mundy, J.L. Canonical frames for planar object recognition. Proc. of 2nd ECCV, pp. 757–772. (1992)
Rothwell, C.A., Forsyth, D.A, Zisserman, A.P., Mundy, J.L. Extracting projective structure from single perspective views of 3D point sets, ICCV, 573–582. 1993
Stein F., and Medioni G., Structural Indexing: Efficient 2-D object Recognition, IEEE Trans. on Pattern Analysis and Machine Intelligence, 14, pp. 1198–1204, (1992)
J. Stolfi Oriented Projective Geometry: A Framework for Geometric Computations Academic Press New York, NY 1991
K. Sugihara, Machine Interpretation of Line Drawings, MIT Press, Cambridge, MA, 1986.
D. Weinshall, M. Werman, and Y. Gdalyahu, Canonical views, or the stability and likelihood of images of 3D objects, IUW, 967–971. 1994
M. Zerroug and R. Nevatia, Quasi-invariant properties and 3-D shape recovery of non-straight, non-constant generalized cylinders, CVPR, 96–103. 1993
S. Zhang, G.D. Sullivan, and K.D. Baker, The automatic construction of a view-independent relational model for 3-D object recognition, T-PAMI 15, 1993, 531–544.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1996 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Carlsson, S. (1996). Combinatorial geometry for shape representation and indexing. In: Ponce, J., Zisserman, A., Hebert, M. (eds) Object Representation in Computer Vision II. ORCV 1996. Lecture Notes in Computer Science, vol 1144. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-61750-7_23
Download citation
DOI: https://doi.org/10.1007/3-540-61750-7_23
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-61750-1
Online ISBN: 978-3-540-70673-1
eBook Packages: Springer Book Archive