A Bayesian approach for jointly estimating the model order and the DOAs

In this paper, a new array signal model structure based on signal reconstruction is proposed, that allows us to define a posterior distribution on the parameter space, which is applicable to both wideband and narrowband signal. The proposed method lends itself well to a Bayesian approach for jointly estimating the model order and the DOAs. We develop a hybrid MCMC algorithm based on reversible jump Markov chain Monte Carlo method to perform the Bayesian computation. Computer simulation results show that the correctness and efficiency of the new method, and significantly fewer observations and only real arithmetic is required.