Learning Strategies for Radar Clutter Classification

In this paper, we address the problem of classifying clutter returns into statistically homogeneous subsets. The classification procedures are devised assuming latent variables, which represent classes to each range bin belongs, and three different models for structure covariance matrix. Then, expectation-maximization algorithm is exploited in conjunction with cyclic estimation come up suitable estimates unknown parameters. Finally, performed by maximizing posterior probability that a belongs specific class. performance analysis proposed classifiers conducted over synthetic data as well real recorded highlights they viable means cluster respect their range.