Fusion of unsynchronized optical tracker and inertial sensor in EKF framework for in-car Augmented Reality delay reduction

Jason Raphael Rambach, Alain Pagani, Sebastian Lampe, Ruben Reiser, Manthan Pancholi, Didier Stricker

In: IEEE Adjunct Proceeding of. IEEE International Symposium on Mixed and Augmented Reality (ISMAR-17) October 9-13 Nantes France IEEE 2017.


In this paper we present a novel sensor fusion framework between unsychronized optical tracking systems and inertial measurement units based on an Extended Kalman Filter (EKF). The main benefit from the fusion is taking advantage of the faster speed of measurement availability of the inertial sensor in order to decrease the delay of the system while maintaining the accuracy of the optical tracking system. The tracking framework is applicable in a car cockpit Augmented Reality system displaying augmentations using the tracked 6 Degree of Freedom pose of a head mounted display.

UnsynchronizedVisualInertial.pdf (pdf, 5 MB)

German Research Center for Artificial Intelligence
Deutsches Forschungszentrum für Künstliche Intelligenz