Estimation of the Covariance Matrix Based on Multiple A-Priori Models

This paper deals with the problem of estimating the disturbance covariance matrix when a limited number of training data, due to environmental heterogeneity, is present. To this end, we suppose that some a-priori spectral models for the the disturbance in the cell under test are available and determine the Maximum Likelihood (ML) estimate of the actual inverse covariance (and hence of the covariance itself) as a suitable combination of the a-priori models. At the analysis stage, we show the capabilities of the new technique to track the actual clutter Power Spectral Density (PSD) and its superiority with respect to adaptive techniques based on the sample covariance matrix.