Abstract
In this paper we study the limitations of current verification strategies in object recognition and suggest how they may be enhanced. On the whole object topology is exploited little during verification. In practice, understanding the connectivity relationships between features in the image, or on the object, can lead to significantly more accurate evaluations of recognition hypotheses. We study how topology reasoning allows us to hypothesize the presence of occlusions in the image. Analysis of these hypotheses provides information which turns out to be crucial to the quality of our overall verification results.
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
N. Ayache and O. Faugeras. HYPER: A New Approach for the Recognition and Positioning of Two-Dimensional Objects. PAMI, 8(1):44–54, 1986.
R. Bolles and R. Horaud. 3DPO: A Three-dimensional Part Orientation System. IJRR, 5(3):3–26, 1986.
A. Califano and R. Mohan. Systematic design of indexing strategies for object recognition. Proc. CVPR, p.709–710, 1993.
R. Deriche and T. Blaszka. Recovering and characterizing image features using an efficient model based approach. Proc. CVPR, p.530–535, 1993.
O. Faugeras and M. Hébert. The representation, recognition, and locating of 3d shapes from range data. IJRR, 5:27–52, 1986.
W.E.L. Grimson and T. Lozano-Pérez. Localizing overlapping parts by searching the interpretation tree. PAMI, 9(4):469–482, 1987.
D. Huttenlocher and S. Ullman. Recognizing Solid Objects by Alignment with an Image. IJCV, 5(2): 195–212, 1990.
Y. Lamdan and H. Wolfson. Geometric Hashing: A General and Efficient Model-Based Recognition Scheme. Proc. ICCV, p.238–249, 1988.
S. Pollard, J. Porrill, J. Mayhew, and J. Frisby. Matching geometrical descriptions in three-space. IVC, 5(2):73–78, 1987.
C. Rothwell, J. Mundy, and W. Hoffman. Representing objects using topology. In preparation, 1996.
C. Rothwell. The importance of reasoning about occlusions during hypothesis verification in object recognition. TR 2673, INRIA, 1995.
C. Rothwell. Object recognition through invariant indexing. Oxford University Press, 1995.
F. Stein and G. Medioni. Structural Indexing: Efficient 3-D Object Recognition. PAMI, 14(2):125–145, 1992.
D. Thompson and J. Mundy. Three-dimensional model matching from an unconstrained viewpoint. Proc. ICRA, p.208–220, 1987.
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. (1996). Reasoning about occlusions during hypothesis verification. 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/BFb0015570
Download citation
DOI: https://doi.org/10.1007/BFb0015570
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