Adaptive Radar Detection in the Presence of Missing-Data

This paper deals with the problem of adaptive radar detection in a context with missing-data where the complete observations (i.e., downstream information loss mechanisms) are characterized by homogeneous Gaussian disturbance with an unknown but possibly structured covariance matrix. The detection problem, formulated as a composite hypothesis test, is tackled by resorting to sub-optimal design strategies, leveraging the generalized likelihood ratio (GLR) criterion demanding appropriate maximum likelihood estimates (MLEs) of the unknowns under both hypotheses. Capitalizing on some possible a-priori knowledge about the interference covariance matrix structure, the optimization problems involved in the MLEs computation are handled by employing the expectation-maximization (EM) algorithm or its expectation-conditional maximization (ECM) and multi-cycle EM (M-EM) variants. At the analysis stage, the performance of the devised architectures is assessed both via Monte Carlo simulations and on measured data for some covariance matrix structures of practical interest.