Solution of stereo correspondence in real scene: an analogic CNN algorithm

Author

Radványi, András G.

Author_Institution

Analogic & Neural Comput. Syst. Lab., Hungarian Acad. of Sci., Budapest, Hungary

fYear

1994

fDate

18-21 Dec 1994

Firstpage

231

Lastpage

236

Abstract

A multilayer analogic CNN (cellular neural network) algorithm is proposed to reconstruct surfaces from real scene stereo-pairs consisting of two images shot from one and the same camera position. The whole scene is illuminated by randomly structured light to provide texture on otherwise “empty” surfaces. One image is that of the illuminated background, the other one is the image of illuminated objects in front of the same background

Keywords

cellular neural nets; feedforward neural nets; image reconstruction; image texture; lighting; multilayer perceptrons; realistic images; stereo image processing; camera position; empty surfaces; illuminated background; illuminated objects; multilayer analogic cellular neural network algorithm; randomly structured light; real scene stereo-pairs; stereo correspondence solution; surface reconstruction; texture; Automation; Cellular neural networks; Image reconstruction; Laboratories; Layout; Matched filters; Nonhomogeneous media; Stereo vision; Surface reconstruction; Surface texture;

fLanguage

English

Publisher

ieee

Conference_Titel

Cellular Neural Networks and their Applications, 1994. CNNA-94., Proceedings of the Third IEEE International Workshop on

Conference_Location

Rome

Print_ISBN

0-7803-2070-0

Type

conf

DOI

10.1109/CNNA.1994.381674

Filename

381674