PARAMETER-ESTIMATION OF 2-DIMENSIONAL MOVING AVERAGE RANDOM-FIELDS

This paper considers the problem of estimating the parameters of two-d imensional (2-D) moving average random (MA) fields. We first address t he problem of expressing the covariance matrix of nonsymmetrical half- plane, noncausal, and quarter-plane MA random fields in terms of the m odel parameters. Assuming the random field is Gaussian, we derive a cl osed-form expression for the Cramer-Rao lower bound (CRLB) on the erro r variance in jointly estimating the model parameters. A computational ly efficient algorithm for estimating the parameters of the MA model i s developed. The algorithm initially fits a 2-D autoregressive model t o the observed field and then uses the estimated parameters to compute the MA model. A maximum-likelihood algorithm for estimating the MA mo del parameters is also presented. The performance of the proposed algo rithms is illustrated by Monte-Carlo simulations and is compared with the Cramer-Rao bound.