A Comparison Between Stereo-Vision Techniques for the Reconstruction of 3-D Coordinates of Objects

Author

Anchini, Rosario ; Liguori, Consolatina ; Paciello, Vincenzo ; Paolillo, Alfredo

Author_Institution

Dept. of Inf. & Electr. Eng., Salerno Univ.

Volume

55

Issue

5

fYear

2006

Firstpage

1459

Lastpage

1466

Abstract

This paper deals with the problems in setting up stereo-vision systems for contactless measurement of dimensional parameters in industrial environments. Two implicit calibration algorithms for the reconstruction of three-dimensional (3-D) real-world coordinates of objects from pairs of two-dimensional image coordinates have been implemented and compared. The former is based on a direct linear transformation, while the latter on an Artificial Neural Network (ANN). The results of the comparison made on artificial and real objects are finally reported in terms of statistical analysis of the reconstruction error

Keywords

image reconstruction; neural nets; statistical analysis; stereo image processing; 2D image coordinates; 3D object coordinate; 3D real-world coordinates; 3D reconstruction; ANN; artificial neural network; calibration; contact less measurement; dimensional parameters; direct linear transformation; industrial environments; reconstruction error; statistical analysis; stereo image processing; stereo-vision techniques; vision systems; Application software; Area measurement; Artificial neural networks; Calibration; Cameras; Image reconstruction; Machine vision; Shape measurement; Three dimensional displays; Vibration measurement; Artificial neural networks (ANNs); calibration; image processing; stereo vision; three-dimensional (3-D) reconstruction; vision systems;

fLanguage

English

Journal_Title

Instrumentation and Measurement, IEEE Transactions on

Publisher

ieee

ISSN

0018-9456

Type

jour

DOI

10.1109/TIM.2006.881034

Filename

1703886