Robust 6-DOF immersive navigation using commodity hardware

摘要: In this paper we present a novel visual-inertial 6-DOF localization approach that can be directly integrated in wearable immersive system for simulation and training. context, while CAVE environments typically require complex expensive set-up, our relies on visual inertial information provided by commodity hardware, i.e. consumer monocular camera an Inertial Measurement Unit (IMU).We propose robust pipeline based state-of-the-art image-based sensor fusion approaches. A loosely-coupled approach, which makes use of orientation from the IMU, is employed to cope with failures tracking (e.g. due fast motion) order limit motion jitters. Fast smooth re-localization also track position following outage guarantee continued operation. The then used render consistently VR contents stereoscopic HMD. proposed system, demonstrated context Construction, runs at 30 fps standard PC requires very limited set-up its intended application.