Abstract :
An analysis is conducted of the optimality of a decoupled tracking filtering algorithm for addressing the problem of tracking multiple targets with correlated measurements and maneuvers. It is proved that the decoupled filters are, in general, suboptimal and are not in fact Kalman filters. However, it is shown also that if the standard Kalman filter is asymptotically stable, the decoupled filters will converge asymptotically to the stable version of the standard Kalman filter. For the case of time-invariant measurement and process noise covariance, a simple sufficient condition guaranteeing the asymptotical stability of the decoupled filters are given
Keywords :
Kalman filters; filtering and prediction theory; stability; tracking systems; Kalman filters; asymptotical stability; correlated measurements; decoupled filters; decoupled multitarget tracking algorithm; filtering; multiple targets; optimal algorithm; process noise covariance; radar theory; time-invariant measurement; Aerodynamics; Algorithm design and analysis; Asymptotic stability; Covariance matrix; Filtering algorithms; Kalman filters; Noise measurement; Q measurement; Sufficient conditions; Target tracking;
