Fusing visual tags and inertial information for indoor navigation

Author

Zachariah, Dave ; Jansson, Magnus

Author_Institution

ACCESS Linnaeus Centre, KTH R. Inst. of Technol., Stockholm, Sweden

fYear

2012

fDate

23-26 April 2012

Firstpage

535

Lastpage

540

Abstract

We present a navigation system based on a monocular camera and an inertial measurement unit. The system detects visual tags and fuses the measurements on the image plane with inertial signals to perform pose estimation and localization using a Sigma-Point Kalman filter. The tags are detected by edge-based feature extraction and channel codes. During periods in which tags are not visible, epipolar constraints, arising from past views, are exploited to significantly reduce the position error growth rate. The experimental results in an office building indicate capabilities for indoor navigation.

Keywords

Kalman filters; cameras; edge detection; feature extraction; navigation; channel codes; edge-based feature extraction; epipolar constraints; image plane; indoor navigation; inertial information; inertial measurement unit; inertial signals; monocular camera; navigation system; office building; pose estimation; position error growth rate; sigma-point Kalman filter; visual tags; Digital TV; Navigation; Noise measurement; inertial navigation; monocular camera; pose estimation; visual tag;

fLanguage

English

Publisher

ieee

Conference_Titel

Position Location and Navigation Symposium (PLANS), 2012 IEEE/ION

Conference_Location

Myrtle Beach, SC

ISSN

2153-358X

Print_ISBN

978-1-4673-0385-9

Type

conf

DOI

10.1109/PLANS.2012.6236924

Filename

6236924