Untethered, inside-out tracking is considered a new goalpost for virtual reality, which became attainable with advent of machine learning in SLAM. Yet computer vision-based navigation is always at risk of a tracking failure due to poor illumination or saliency of the environment. An extension for a navigation system is proposed, which recognizes agents motion and stillness states with 87% accuracy from accelerometer data. 40% reduction in navigation drift is demonstrated in a repeated tracking failure scenario on a challenging dataset.
@article{arxiv.2107.12030,
title = {Pluto: Motion Detection for Navigation in a VR Headset},
author = {Dmitri Kovalenko and Artem Migukin and Svetlana Ryabkova and Vitaly Chernov},
journal= {arXiv preprint arXiv:2107.12030},
year = {2021}
}
Comments
to appear in 2021 International Conference on Indoor Positioning and Indoor Navigation (IPIN), 29 Nov. - 2 Dec. 2021, Lloret de Mar, Spain