Estimation of the 2-D ARMA model parameters based on the equivalent MA approach

Abstract

The parameter estimation problem of a two-dimensional autoregressive moving average (2-D ARMA) model having a quarter-plane (QP) region of support (ROS) driven by an unobservable white noise process is addressed. For the solution of this problem, we have considered the relation between the parameters of this ARMA model and its equivalent moving average (EMA) model. On the basis of this relation, a new computationally efficient algorithm is proposed for determining the parameters of the QP 2-D ARMA model from the coefficients of the 2-D EMA model. Simulation results and comparisons demonstrating the performance of the new algorithm are included.