Efficient Algorithm for Two-Dimensional Autoregressive Spectrum Estimation. (Reannouncement with New Availability Information).

摘要

An algorithm is presented for the efficient computation of two dimensional autoregressive spectrum estimates directly from the data. It is similar to the Burg algorithm for autoregressive estimation in one dimension. Coefficients of the filter used to decorrelate the signal are found recursively from the lower order filters. The coefficients needed to get the larger sized filters can be found at each stage of the recursion from the correlations of lower order filter outputs. Thus, the resulting estimate does not assume knowledge of ensemble averages. It offers a computational saving of 25 percent over the commonly used method, where an estimate of the correlation matrix is first computed and then inverted.