Self-Tuning Fusion Wiener Filter and Its Convergence

Abstract

For the multisensor system with unknown model parameters and noise variances, based on the system identification method, the online information fusion estimators of model parameters and noise variances can be obtained. Substituting them into the optimal fused Wiener filter weighted by scalars for components, a self-tuning information fusion Wiener filter weighted by scalars for components is presented. By the dynamic error system analysis (DESA) method and the dynamic variance error system analysis (DVESA) method, it is rigorously proved that the proposed self-tuning Wiener fuser converges to the optimal fusion Wiener fuser in a realization, so that it has asymptotic optimality. A simulation example applied to signal processing shows its effectiveness.