Multichannel ARMA signal covariance intersection fusion wiener filter

The CI (Covariance Intersection) fusion method avoids the computation of the cross covariance, and gives the consistent fused estimation. By the CI fusion method, based on the modern time series analysis method, the multichannel ARMA signal CI fusion Wiener filter is presented for the two-sensor systems with unknown cross covariance. It is proved that its estimation accuracy is higher than those of the local Wiener filters, and is lower than that of the steady-state optimal weighted fused Wiener filter with known cross-covariance. A Monte-Carlo simulation result shows that the actual accuracy of the presented CI fusion Wiener filter is close to that of the corresponding steady-state optimal fused Wiener filter. And based on the covariance ellipse, the geometric interpretation of the accuracy relation is shown.