Processing math: 50%
Unscented von Mises–Fisher Filtering | IEEE Journals & Magazine | IEEE Xplore

Unscented von Mises–Fisher Filtering


Abstract:

We introduce the unscented von Mises–Fisher filter (UvMFF), a nonlinear filtering algorithm for dynamic state estimation on the n-dimensional unit hypersphere. Estimati...Show More

Abstract:

We introduce the unscented von Mises–Fisher filter (UvMFF), a nonlinear filtering algorithm for dynamic state estimation on the n-dimensional unit hypersphere. Estimation problems on the unit hypersphere occur in computer vision, e.g., when using omnidirectional cameras, as well as in signal processing. As approaches in literature are limited to very simple system and measurement models, we propose a deterministic sampling scheme on the unit hypersphere, which allows us to handle nonlinear system and measurement models. The proposed approach can be seen as a hyperspherical variant of the unscented Kalman filter (UKF). The advantages of the novel method are shown by means of simulations.
Published in: IEEE Signal Processing Letters ( Volume: 23, Issue: 4, April 2016)
Page(s): 463 - 467
Date of Publication: 19 February 2016

ISSN Information:


References

References is not available for this document.