Structural stereopsis for 3-D vision

A novel approach to solving the stereo correspondence problem in computer vision is described. Structural descriptions of two two-dimensional views of a scene are extracted by one of possibly several available low-level processes, and a new theory of inexact matching for such structures is derived....

Full description

Saved in:
Bibliographic Details
Published inIEEE transactions on pattern analysis and machine intelligence Vol. 10; no. 2; pp. 144 - 166
Main Authors Boyer, K.L., Kak, A.C.
Format Journal Article
LanguageEnglish
Published Los Alamitos, CA IEEE 01.03.1988
IEEE Computer Society
Subjects
Applied sciences
Artificial intelligence
Computer aided manufacturing
Computer science; control theory; systems
Computer vision
Degradation
Distortion measurement
Exact sciences and technology
Layout
Manufacturing automation
Pattern recognition. Digital image processing. Computational geometry
Robot vision systems
Robotics and automation
Satellites
Stereo vision
Computer vision
Stereopsis
Robot
Scene analysis
Online AccessGet full text

Cover

More Information
Summary:A novel approach to solving the stereo correspondence problem in computer vision is described. Structural descriptions of two two-dimensional views of a scene are extracted by one of possibly several available low-level processes, and a new theory of inexact matching for such structures is derived. An entropy-based figure of merit for attribute selection and ordering is defined. Experimental results applying these techniques to real image pairs are presented. Some manipulation experiments are briefly presented.< >
Bibliography:ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 23
ISSN:0162-8828
1939-3539
DOI:10.1109/34.3880