Wideband array signal processing using MCMC methods

Abstract

This paper proposes a novel wideband structure for array signal processing. The method lends itself well to a Bayesian approach for jointly estimating the model order (number of sources) and the DOA through a reversible jump Markov chain Monte Carlo (MCMC) procedure. The source amplitudes are estimated through a maximum a posteriori (MAP) procedure. Advantages of the proposed method include joint detection of model order and estimation of the DOA parameters, and the fact that meaningful results can be obtained using fewer observations than previous methods. The DOA estimation performance of the proposed method is compared with the theoretical Cramer-Rao lower bound (CRLB) for this problem. Simulation results demonstrate the effectiveness and robustness of the method.