Feature based object recognition using statistical occlusion modelswith one-to-one correspondence
Zhengrong Ying
Castanon, D.
Dept. of Electr. & Comput. Eng., Boston Univ., MA;
This paper appears in: Computer Vision, 2001. ICCV 2001. Proceedings. Eighth IEEE International Conference on
Publication Date: 2001
Volume: 1,
On page(s): 621-627 vol.1
Meeting Date: 07/07/2001 - 07/14/2001
Location: Vancouver, BC, Canada
ISBN: 0-7695-1143-0
References Cited: 17
INSPEC Accession Number: 7024229
Digital Object Identifier: 10.1109/ICCV.2001.937576
Current Version Published: 2002-08-07
Abstract
In this paper we present a new Bayesian framework for partially
occluded object recognition with one-to-one correspondence. We introduce
two different statistical models for occlusion: One model assumes that
each feature in the model can be occluded independent of whether any
other features are occluded, whereas the second model uses spatially
correlated occlusion to represent the extent of occlusion. Using these
models, the object recognition problem reduces to finding the object
hypothesis with largest generalized likelihood We develop fast
algorithms for finding the optimal one-to-one correspondence between
scene features and object model features to compute the generalized
likelihood. We evaluate our algorithms using examples extracted from
synthetic aperture radar imagery, and illustrate the performance
advantages of our approach over alternative algorithms proposed by
others
Index
Terms
Available to subscribers and IEEE members.
References
Available to subscribers and IEEE members.
Citing Documents
Available to subscribers and IEEE members.
Cart
