Parameter estimation in MRF line process models

Author

Nadabar, Sateesha G. ; Jain, Anil K.

Author_Institution

Dept. of Comput. Sci., Michigan State Univ., East Lansing, MI, USA

fYear

1992

fDate

15-18 Jun 1992

Firstpage

528

Lastpage

533

Abstract

A scheme for the estimation of the Markov random field (MRF) line process parameters that uses geometric CAD models of the objects in the scene is presented. The models are used to generate synthetic images of the objects from random viewpoints. The edge maps computed from the synthesized images are used as training samples to estimate the line process parameters using a least squares method. It is shown that this parameter estimation method is useful for detecting edges in range as well as intensity images

Keywords

Markov processes; computational geometry; computer vision; least squares approximations; parameter estimation; Markov random field line process models; edges detection; geometric CAD models; intensity images; least squares method; line process parameters; parameter estimation; synthesized images; synthetic images; Computer science; Context modeling; Frequency estimation; Image edge detection; Labeling; Lattices; Layout; Markov random fields; Parameter estimation; Solid modeling;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer Vision and Pattern Recognition, 1992. Proceedings CVPR '92., 1992 IEEE Computer Society Conference on

Conference_Location

Champaign, IL

ISSN

1063-6919

Print_ISBN

0-8186-2855-3

Type

conf

DOI

10.1109/CVPR.1992.223140

Filename

223140