Perceptual organization for scene segmentation and description
Mohan, R.
Nevatia, R.
IBM Thomas J. Watson Res. Center, Yorktown Heights, NY;
This paper appears in: Pattern Analysis and Machine Intelligence, IEEE Transactions on
Publication Date: Jun 1992
Volume: 14,
Issue: 6
On page(s): 616-635
ISSN: 0162-8828
References Cited: 74
CODEN: ITPIDJ
INSPEC Accession Number: 4219579
Digital Object Identifier: 10.1109/34.141553
Current Version Published: 2002-08-06
Abstract
A data-driven system for segmenting scenes into objects and their
components is presented. This segmentation system generates hierarchies
of features that correspond to structural elements such as boundaries
and surfaces of objects. The technique is based on perceptual
organization, implemented as a mechanism for exploiting geometrical
regularities in the shapes of objects as projected on images. Edges are
recursively grouped on geometrical relationships into a description
hierarchy ranging from edges to the visible surfaces of objects. These
edge groupings, which are termed collated features, are abstract
descriptors encoding structural information. The geometrical
relationships employed are quasi-invariant over 2-D projections and are
common to structures of most objects. Thus, collations have a high
likelihood of corresponding to parts of objects. Collations serve as
intermediate and high-level features for various visual processes.
Applications of collations to stereo correspondence, object-level
segmentation, and shape description are illustrated
Index
Terms
Available to subscribers and IEEE members.
References
Available to subscribers and IEEE members.
Citing Documents
Available to subscribers and IEEE members.
Cart
