Head-to-Body-Pose Classification in No-Pose VR Tracking Systems
PubDate: August 2018
Teams: Programming Systems Group;Machine Learning and Information Fusion Group
Writers: Tobias Feigl; Christopher Mutschler; Michael Philippsen
PDF: Head-to-Body-Pose Classification in No-Pose VR Tracking Systems
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 positional 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.