Model construction and shape recognition from occluding contours
Chien, C.-H.
Aggarwal, J.K.
Comput. Vision Lab., Texas Univ., Austin, TX;
This paper appears in: Pattern Analysis and Machine Intelligence, IEEE Transactions on
Publication Date: Apr 1989
Volume: 11,
Issue: 4
On page(s): 372-389
ISSN: 0162-8828
References Cited: 37
CODEN: ITPIDJ
INSPEC Accession Number: 3401987
Digital Object Identifier: 10.1109/34.19034
Current Version Published: 2002-08-06
Abstract
A technique is presented for recognizing a 3D object (a model in
an image library) from a single 2D silhouette using information such as
corners (points with high positive curvatures) and occluding contours,
rather than straight line segments. The silhouette is assumed to be a
parallel projection of the object. Each model is stored as a set of the
principal quadtrees, from which the volume/surface octree of the model
is generated. Feature points (i.e. corners) are extracted to guide the
recognition process. Four-point correspondences between the 2D feature
points of the observed object and 3D feature points of each model are
hypothesized, and then verified by applying a variety of constraints to
their associated viewing parameters. The result of the hypothesis and
verification process is further validated by 2D contour matching. This
approach allows for a method of handling both planar and curved objects
in a uniform manner, and provides a solution to the recognition of
multiple objects with occlusion as demonstrated by the experimental
results
Index
Terms
Available to subscribers and IEEE members.
References
Available to subscribers and IEEE members.
Citing Documents
Available to subscribers and IEEE members.
Cart
