A model to image straight line matching method for vision-based indoor mobile robot self-location

Author

Aider, Omar Ait ; Hoppenot, Philippe ; Colle, Etienne

Author_Institution

CEMIF-Complex Syst. Group, Univ. of Evry, France

Volume

1

fYear

2002

fDate

2002

Firstpage

460

Abstract

An efficient and simple method for matching image features to a model is presented It is designed to indoor mobile robot self-location. It is a two stage method based on the interpretation tree search approach using straight line correspondences. In the first stage a set of matching hypothesis is generated. Exploiting the specificity of the mobile robotics context, the global interpretation tree is divided into two sub-trees and then two geometric constraints are defined directly on 2D-3D correspondences in order to improve the pruning and search efficiency. In the second stage, the pose is calculated for each matching hypothesis and the best one is selected according to a defined error function. Test results illustrate the performances of the approach.

Keywords

edge detection; feature extraction; image matching; mobile robots; object recognition; path planning; robot vision; tree searching; feature matching; indoor mobile robot; model-based localisation; object recognition; pruning; self-location; straight line; straight line matching; tree search; vision-based localisation; Cameras; Dead reckoning; Layout; Mobile robots; Navigation; Object recognition; Robot vision systems; Shape; Trajectory; Uncertainty;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Robots and Systems, 2002. IEEE/RSJ International Conference on

Print_ISBN

0-7803-7398-7

Type

conf

DOI

10.1109/IRDS.2002.1041433

Filename

1041433