Iterative methods for estimation of 2-D AR parameters using a data-adaptive Toeplitz approximation algorithm

A new two-dimensional (2-D) data-adaptive algorithm utilizing the iterative Toeplitz approximation method is presented. This algorithm provides a means for efficient estimation of 2-D AR parameters representing spatially variant data arrays. Its convergence performance is comparable to that of the 2-D recursive least squares (RLS) algorithm but is computationally more efficient. The savings in computation is realized by reducing the size of the matrix to be inverted when solving the AR model normal equations. The ability of the algorithm to estimate accurately the model parameters using very small data sets and various windowing schemes is evaluated. Single quadrant and combined quadrant spectral estimates are compared for quarter-plane and nonsymmetric half-plane regions of support