Tracking of targets with state dependent measurement errors using recursive BLUE filters

In this paper, optimal best linear unbiased estimation (BLUE) filters are derived for cases where measurement errors depend on the state of the target. The standard Kalman filter fails to provide optimal estimates in these cases. Previously applied measurement models are reformulated in order to app...

Full description

Saved in:
Bibliographic Details
Main Authors: Stakkeland, M., Overrein, O., Brekke, E.F., Hallingstad, O.
Format: Conference Proceeding
Language:English
Subjects:
BLUE filters
extended targets
Information filtering
Information filters
jump Markov models
Measurement errors
measurement models
Noise measurement
Nonlinear filters
Position measurement
Radar measurements
Radar tracking
Recursive estimation
Target tracking
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper, optimal best linear unbiased estimation (BLUE) filters are derived for cases where measurement errors depend on the state of the target. The standard Kalman filter fails to provide optimal estimates in these cases. Previously applied measurement models are reformulated in order to apply BLUE filters, and two new measurement models with state dependent biases are proposed. It is shown how the higher order unscented transform may be used to approximate the terms in the BLUE filter when they are not available analytically. The BLUE filters are shown by Monte Carlo simulations to have better performance than other suboptimal filters.