DocumentCode :
2990806
Title :
A hybrid parallel-serial approach to nonlinear filtering
Author :
Modugno, F.J. ; Johnson, G.W. ; Cohen, A.O.
Author_Institution :
IBM Shipboard and Defense Systems, Manassas, VA, USA
Volume :
10
fYear :
1985
fDate :
31138
Firstpage :
1770
Lastpage :
1772
Abstract :
Nonlinear filtering is often accomplished using algorithms, such as the extended Kalman filter, which process data serially by linearizing the state equations about single solution hypotheses. This linearization introduces losses which may ultimately cause these procedures to diverge at low signal-to-noise ratios. Parallel filtering techniques eliminate these linearization losses at the price of more processing. A new hybrid approach is presented which exploits the advantages of both procedures, threshold reduction with parallel filtering and processing efficiency with serial filtering. An example from bearings only target state estimation is provided.
Keywords :
Covariance matrix; Filtering algorithms; Kalman filters; Maximum a posteriori estimation; Nonlinear equations; Nonlinear filters; Parallel processing; Probability; Signal to noise ratio; State estimation;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Acoustics, Speech, and Signal Processing, IEEE International Conference on ICASSP '85.
Type :
conf
DOI :
10.1109/ICASSP.1985.1168178
Filename :
1168178
Link To Document :
بازگشت