3D model-based tracking for UAV indoor localisation

This paper proposes a novel model-based tracking approach for 3D localisation. One main difficulty of standard model-based approach lies in the presence of low-level ambigui- ties between different edges. In this work, given a 3D model of the edges of the environment, we derive a multiple hypotheses...

Full description

Saved in:
Bibliographic Details
Published inIEEE transactions on cybernetics Vol. 45; no. 5; pp. 869 - 879
Main Authors Teulière, Céline, Marchand, Eric, Eck, Laurent
Format Journal Article
LanguageEnglish
Published IEEE 01.05.2015
Subjects
Computer Science
Robotics
Online AccessGet full text

Cover

More Information
Summary:This paper proposes a novel model-based tracking approach for 3D localisation. One main difficulty of standard model-based approach lies in the presence of low-level ambigui- ties between different edges. In this work, given a 3D model of the edges of the environment, we derive a multiple hypotheses tracker which retrieves the potential poses of the camera from the observations in the image. We also show how these candidate poses can be integrated into a particle filtering framework to guide the particle set toward the peaks of the distribution. Motivated by the UAV indoor localisation problem where GPS signal is not available, we validate the algorithm on real image sequences from UAV flights.
ISSN:2168-2267
DOI:10.1109/TCYB.2014.2337652