MUSIC, maximum likelihood and Cramer-Rao bound

The authors consider methods for solving the problem of finding the directions of multiple plane waves with linear arrays of sensors and the related one of estimating the parameters of multiple superimposed exponential signals in noise. Specifically, the MUSIC and maximum-likelihood (ML) methods have been proposed for solving these problems. The authors study the performance of the MUSIC and ML methods, and analyze their statistical efficiency. They also derive the Cramer-Rao bound (CRB) for the estimation problems mentioned above, and establish some useful properties of the CRB covariance matrix. The relationship between the MUSIC and ML estimators is investigated as well.<<ETX>>