Robot Localization in Rough Terrains: Performance Evaluation

Author

Fazl-Ersi, Ehsan ; Tsotsos, John K.

Author_Institution

Dept. of Comput. Sci. & Eng., York Univ., Toronto, ON, Canada

fYear

2010

fDate

May 31 2010-June 2 2010

Firstpage

245

Lastpage

252

Abstract

The goal of this paper is to present an overview of two common processes involved in most visual robot localization techniques: data association and robust motion estimation. For each of them, we review some of the available solutions and compare their performance in the context of outdoor robot localization, where the robot is subject to 6-DOF motion. Our experiments with different combinations of data association and motion estimation techniques show the superiority of the Hessian-Affine feature detector and the SIFT feature descriptor for data association, and the Hough Transform for robust motion estimation.

Keywords

Hough transforms; motion estimation; robot vision; sensor fusion; stability; Hessian Affine feature detector; Hough transform; SIFT feature descriptor; data association; robust motion estimation; rough terrains; visual robot localization techniques; Computer vision; Detectors; Layout; Motion detection; Motion estimation; Robot kinematics; Robot localization; Robot vision systems; Robustness; Sonar navigation; Performance Evaluation; Robot Localization;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer and Robot Vision (CRV), 2010 Canadian Conference on

Conference_Location

Ottawa, ON

Print_ISBN

978-1-4244-6963-5

Type

conf

DOI

10.1109/CRV.2010.39

Filename

5479178