Maximum-likelihood parameter estimation of the harmonic, evanescent, and purely indeterministic components of discrete homogeneous random fields

This paper presents a maximum-likelihood solution to the general problem of fitting a parametric model to observations from a single realization of a two-dimensional (2-D) homogeneous random field with mixed spectral distribution. On the basis of a 2-D Wold-like decomposition, the field is represented as a sum of mutually orthogonal components of three types: purely indeterministic, harmonic, and evanescent. The suggested algorithm involves a two-stage procedure. In the first stage, we obtain a suboptimal initial estimate for the parameters of the spectral support of the evanescent and harmonic components. In the second stage, we refine these initial estimates by iterative maximization of the conditional likelihood of the observed data, which is expressed as a function of only the parameters of the spectral supports of the evanescent and harmonic components. The solution for the unknown spectral supports of the harmonic and evanescent components reduces the problem of solving for the other unknown parameters of the field to a linear least squares. The Cramer-Rao lower bound on the accuracy of jointly estimating the parameters of the different components is derived, and it is shown that the bounds on the purely indeterministic and deterministic components are decoupled. Numerical evaluation of the bounds provides some insight into the effects of various parameters on the achievable estimation accuracy. The performance of the maximum-likelihood algorithm is illustrated by Monte Carlo simulations and is compared with the Cramer-Rao bound.

[1]  M. Ekstrom,et al.  Two-dimensional spectral factorization with applications in recursive digital filtering , 1976 .

[2]  J. M. Francos,et al.  A Wold-Like Decomposition of 2-D Discrete Homogeneous Random Fields , 1995 .

[3]  H. Helson,et al.  Prediction theory and Fourier Series in several variables , 1958 .

[4]  Joseph M. Francos,et al.  A unified texture model based on a 2-D Wold-like decomposition , 1993, IEEE Trans. Signal Process..

[5]  P. Whittle.  ON STATIONARY PROCESSES IN THE PLANE , 1954 .

[6]  Venkatesh Nagesha,et al.  Spectral analysis based on the canonical autoregressive decomposition , 1996, IEEE Trans. Signal Process..

[7]  Petre Stoica,et al.  Maximum likelihood estimation of the parameters of multiple sinusoids from noisy measurements , 1989, IEEE Trans. Acoust. Speech Signal Process..

[8]  Rangasami L. Kashyap,et al.  Estimation of close sinusoids in colored noise and model discrimination , 1987, IEEE Trans. Acoust. Speech Signal Process..

[9]  J. Doob.  Stochastic processes , 1953 .

[10]  Steven Kay,et al.  Spectral analysis based on the canonical autoregressive decomposition , 1991, [Proceedings] ICASSP 91: 1991 International Conference on Acoustics, Speech, and Signal Processing.

[11]  A. M. Walker.  On the estimation of a harmonic component in a time series with stationary independent residuals , 1971 .

[12]  R. Kumaresan,et al.  A two-dimensional technique for frequency-wavenumber estimation , 1981, Proceedings of the IEEE.

[13]  M. Priestley.  The analysis of two-dimensional stationary processes with discontinuous spectrat , 1964 .

[14]  James H. McClellan,et al.  The extension of Pisarenko's method to multiple dimensions , 1982, ICASSP.

[15]  M. R. Osborne.  Some Special Nonlinear Least Squares Problems , 1975 .