Self-tuning Centralized Fusion Wiener Filter with Applied to Signal Processing

Abstract

For the multisensor systems with unknown model parameters and noise variances, based on the system identification algorithm and correlation method, the estimators of model parameters and noise variances can be obtained. Based on the information matrix, a self-tuning centralized fusion Wiener filter is presented by substituting the estimators into the corresponding optimal filter. Using the dynamic error system analysis (DESA) method, it is proved that the self-tuning centralized fusion Wiener filter has asymptotic global optimality, i.e. it converges to the optimal centralized fusion Wiener filter. A simulation example applied to signal processing shows its effectiveness.