DocumentCode :
497771
Title :
Extension of the Sliced Gaussian Mixture Filter with application to cooperative passive target tracking
Author :
Hörst, Julian ; Sawo, Felix ; Klumpp, Vesa ; Hanebeck, Uwe D. ; Franken, Dietrich
Author_Institution :
Intell. Sensor-Actuator-Syst. Lab. (ISAS), Univ. Karlsruhe (TH), Karlsruhe, Germany
fYear :
2009
fDate :
6-9 July 2009
Firstpage :
587
Lastpage :
594
Abstract :
This paper copes with the problem of nonlinear Bayesian state estimation. A nonlinear filter, the sliced Gaussian mixture filter (SGMF), employs linear substructures in the nonlinear measurement and prediction model in order to simplify the estimation process. Here, a special density representation, the sliced Gaussian mixture density, is used to derive an exact solution of the Chapman-Kolmogorov equation. The sliced Gaussian mixture density is obtained by a systematic and deterministic approximation of a continuous density minimizing a certain distance measure. In contrast to previous work, improvements of the SGMF presented here include an extended system model and the processing of multi-dimensional nonlinear subspaces. As an application for the SGMF, cooperative passive target tracking, where sensors take angular measurements from a target, is considered in this paper. Finally, the performance of the proposed estimator is compared to the marginalized particle filter (MPF) in simulations.
Keywords :
Bayes methods; Gaussian processes; nonlinear filters; target tracking; Chapman-Kolmogorov equation; angular measurements; cooperative passive target tracking; marginalized particle filter; multidimensional nonlinear subspaces; nonlinear Bayesian state estimation; nonlinear filter; nonlinear measurement; prediction model; sliced Gaussian mixture filter; Passive filters; Target tracking; Bearings-only tracking; Dirac mixture; Gaussian mixture; Rao-Blackwellization; nonlinear estimation;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Information Fusion, 2009. FUSION '09. 12th International Conference on
Conference_Location :
Seattle, WA
Print_ISBN :
978-0-9824-4380-4
Type :
conf
Filename :
5203865
Link To Document :
بازگشت