In this paper, a high-degree cubature information filter (CIF) is proposed for multiple sensor estimation. Astatistical linear error propagation method incorporates the high-degree cubature integration rule into the extended information filtering (EIF) framework such that more accurate estimation can be achieved than the extended information filter as well as the unscented information filter (UIF). In addition, the high-degree CIF maintains close performance to the Gauss-Hermite Quadrature information filter (GHQIF) but uses significantly fewer quadrature points. As a result, the curse of dimensionality problem existing in the tensor product based GHQIF can be greatly alleviated. Besides the improved estimation accuracy and computational efficiency, the high-degree CIF also exhibits the desirable robustness under unknown noise statistics. The proposed CIF is compared with other information filters (e.g., EIF, UIF, GHQIF) via a target tracking problem and demonstrates the best performance.
Multiple sensor estimation using a high-degree cubature information filter
Sensors and Systems for Space Applications VI ; 2013 ; Baltimore,Maryland,USA
Proc. SPIE ; 8739
2013-05-21
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Multiple sensor estimation using a high-degree cubature information filter [8739-30]
British Library Conference Proceedings | 2013
|British Library Conference Proceedings | 2015
|