Head-to-Body-Pose Classification in No-Pose VR Tracking Systems

Feigl T, Mutschler C, Philippsen M (2018)

Publication Language: English

Publication Type: Conference contribution, Conference Contribution

Publication year: 2018

Publisher: IEEE Xplore

Pages Range: 545-546

Conference Proceedings Title: Proceedings of the 25th IEEE Conference on Virtual Reality and 3D User Interfaces (IEEE VR 2018)

Event location: Reutlingen

ISBN: 978-1-5386-3365-6

URI: http://www2.informatik.uni-erlangen.de/publication/download/IEEE-VR2018b.pdf

DOI: 10.1109/VR.2018.8446495

Abstract

Pose tracking does not yet reliably work in large-scale interactive multi-user VR. Our novel head orientation estimation combines a single inertial sensor located at the user’s head with inaccurate posi- tional tracking. We exploit that users tend to walk in their viewing direction and classify head and body motion to estimate heading drift. This enables low-cost long-time stable head orientation. We evaluate our method and show that we sustain immersion.

Authors with CRIS profile

Tobias Feigl Lehrstuhl für Informatik 2 (Programmiersysteme) Christopher Mutschler Lehrstuhl für Informatik 2 (Programmiersysteme) Michael Philippsen Lehrstuhl für Informatik 2 (Programmiersysteme)

Related research project(s)

Recurrent Neuronal Networks (RNNs) for Real-Time Estimation of Nonlinear Motion Models (RuNN) Oct. 1, 2017 - March 31, 2021

How to cite

APA:

Feigl, T., Mutschler, C., & Philippsen, M. (2018). Head-to-Body-Pose Classification in No-Pose VR Tracking Systems. In Proceedings of the 25th IEEE Conference on Virtual Reality and 3D User Interfaces (IEEE VR 2018) (pp. 545-546). Reutlingen, DE: IEEE Xplore.

MLA:

Feigl, Tobias, Christopher Mutschler, and Michael Philippsen. "Head-to-Body-Pose Classification in No-Pose VR Tracking Systems." Proceedings of the 25th IEEE Conference on Virtual Reality and 3D User Interfaces (IEEE VR 2018), Reutlingen IEEE Xplore, 2018. 545-546.

BibTeX: Download