A maximum entropy framework for space-time adaptive processing

In this paper we address the problem of devising and analyzing radar processors for space-time adaptive processing applications. We first define a class of adaptive filters based on the approximation of the overall disturbance with a multichannel autoregressive process. Thus we focus on a specific element of the family which exploits the modified square-root normalized maximum entropy algorithm for estimating the process coefficients. The performance assessment highlights the fast convergent capabilities of the novel processor, which for a limited number of training data, provides performances very close to the optimum filter. Finally we also devise and assess (both on simulated as well as on real radar data) two adaptive detectors which represent interesting solutions to deal with situations where a small number of training data is available. (C) 2004 Elsevier B.V. All rights reserved.