| | |
Summary: Robust Vision-based Localization for Mobile Robots
Using an Image Retrieval System Based on Invariant Features
J¨urgen Wolf
Wolfram Burgard
Hans Burkhardt
Department of Computer Science, University of Hamburg, 22527 Hamburg, Germany
Department of Computer Science, University of Freiburg, 79110 Freiburg, Germany
Abstract
In this paper we present a vision-based approach to mo-
bile robot localization, that integrates an image retrieval sys-
tem with Monte-Carlo localization. The image retrieval pro-
cess is based on features that are invariant with respect to
image translations, rotations, and limited scale. Since it fur-
thermore uses local features, the system is robust against dis-
tortion and occlusions which is especially important in popu-
lated environments. By using the sample-based Monte-Carlo
localization technique our robot is able to globally localize it-
self, to reliably keep track of its position, and to recover from
|
