Title :
Structural stereopsis for 3-D vision
Author :
Boyer, K.L. ; Kak, A.C.
Author_Institution :
Sch. of Electr. Eng., Purdue Univ., West Lafayette, IN, USA
fDate :
3/1/1988 12:00:00 AM
Abstract :
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
Keywords :
computer vision; computerised pattern recognition; statistical analysis; 2D views; 3D comput vision; computerised pattern recognition; entropy-based figure of merit; image pairs; inexact matching; robot vision; stereo correspondence; structural stereopsis; Computer aided manufacturing; Computer vision; Degradation; Distortion measurement; Layout; Manufacturing automation; Robot vision systems; Robotics and automation; Satellites; Stereo vision;
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on
