VIS-Tracker: A Wearable Vision-Inertial Self-Tracker

  • Authors:
  • Eric Foxlin;Leonid Naimark

  • Affiliations:
  • -;-

  • Venue:
  • VR '03 Proceedings of the IEEE Virtual Reality 2003
  • Year:
  • 2003

Quantified Score

Hi-index 0.00

Visualization

Abstract

We present a demonstrated and commercially viableself-tracker, using robust software that fuses data frominertial and vision sensors.Compared to infrastructure-based trackers, self-trackers have the advantage thatobjects can be tracked over an extremely wide area,without the prohibitive cost of an extensive network ofsensors or emitters to track them.So far most AR researchhas focused on the long-term goal of a purely vision-basedtracker that can operate in arbitrary unpreparedenvironments, even outdoors.We instead chose to startwith artificial fiducials, in order to quickly develop the first self-tracker which is small enough to wear on a belt,low cost, easy to install and self-calibrate, and low enoughlatency to achieve AR registration.We also present aroadmap for how we plan to migrate from artificialfiducials to natural ones.By designing to the requirementsof AR, our system can easily handle the less challengingapplications of wearable VR systems and robot navigation.