Estimating the Parameters of the K Distribution in the Intensity Domain

Abstract : This paper reviews a number of different moment-based methods for estimating the parameters of the K distribution. The K distribution is a model for the statistics of synthetic aperture radar (SAR) imagery that is formed from the product of two independent distributions, one representing the radar cross-section, and the other representing speckle that is a characteristic of coherent imaging. A method for synthesizing correlated K-distributed random fields is reviewed. Moments of intensity, log intensity and amplitude statistics are used to compute measures which are inverted to give estimates of the mean and order parameters of the K distribution. A method based on the normalized logarithm of intensity is shown to give the best performance, confirming the results of Oliver (1993) and Blacknell (1994). The effect of correlation upon order parameter estimation and its role in the K distribution's underlying component pertaining to the radar cross-section is briefly considered. This work will be used to development target detection algorithms to find targets of interest in SAR imagery.

[1]  Donald B. Percival,et al.  Maximum likelihood estimation of K distribution parameters for SAR data , 1993, IEEE Trans. Geosci. Remote. Sens..

[2]  Philip B. Chapple,et al.  Stochastic model-based processing for detection of small targets in non-Gaussian natural imagery , 2001, IEEE Trans. Image Process..

[3]  C. Oliver.  A Model for Non-Rayleigh Scattering Statistics , 1984 .

[4]  D. Blacknell,et al.  Texture simulation and analysis in coherent imagery , 1995 .

[5]  Hugh Griffiths,et al.  Modelling Spatially Correlated K-Distributed Clutter , 1991 .

[6]  D. Blacknell,et al.  Accurate approximation to the optimum parameter estimate for K-distributed clutter , 1996 .

[7]  E. Jakeman.  On the statistics of K-distributed noise , 1980 .

[8]  C. R. Dietrich,et al.  A fast and exact method for multidimensional gaussian stochastic simulations , 1993 .

[9]  Brian D. Ripley,et al.  Stochastic Simulation , 2005 .

[10]  D. Blacknell,et al.  Comparison of parameter estimators for K-distribution , 1994 .

[11]  H. Saunders,et al.  Probability, Random Variables and Stochastic Processes (2nd Edition) , 1989 .

[12]  R. S. Raghavan.  A model for spatially correlated radar clutter , 1991 .

[13]  P. A. P. Moran,et al.  The estimation of standard errors in Monte Carlo simulation experiments , 1975 .

[14]  Christopher J. Oliver,et al.  Optimum texture analysis of SAR images , 1994, Defense, Security, and Sensing.

[15]  C. Oliver.  The interpretation and simulation of clutter textures in coherent images , 1986 .

[16]  E. Jakeman,et al.  Significance of K Distributions in Scattering Experiments , 1978 .

[17]  C. R. Dietrich,et al.  Fast and Exact Simulation of Stationary Gaussian Processes through Circulant Embedding of the Covariance Matrix , 1997, SIAM J. Sci. Comput..

[18]  Charles W. Therrien,et al.  Discrete Random Signals and Statistical Signal Processing , 1992 .

[19]  Pierfrancesco Lombardo,et al.  Effect of noise on order parameter estimation for K-distributed clutter , 1995 .

[20]  K. Ward.  Compound representation of high resolution sea clutter , 1980 .

[21]  C J Oliver,et al.  Correlated K-distributed Clutter Models , 1985 .

[22]  D. Blacknell,et al.  A comparison of simulation techniques for correlated gamma and K-distributed images for SAR applications , 1994, Proceedings of IGARSS '94 - 1994 IEEE International Geoscience and Remote Sensing Symposium.

[23]  Pierfrancesco Lombardo,et al.  Estimation of texture parameters in K-distributed clutter , 1994 .

[24]  C J Oliver,et al.  On the Simulation of Correlated K-distributed Random Clutter , 1986 .

[25]  E. Jakeman,et al.  A model for non-Rayleigh sea echo , 1976 .

[26]  R. S. Raghavan,et al.  A method for estimating parameters of K-distributed clutter , 1991 .

[27]  C. Oliver.  Optimum texture estimators for SAR clutter , 1993 .

[28]  Pierfrancesco Lombardo,et al.  Estimating the correlation properties of k-distributed SAR clutter , 1995 .

[29]  E. Jakeman,et al.  Generalized K distribution: a statistical model for weak scattering , 1987 .

[30]  C J Oliver.  The sensitivity of texture measures for correlated random clutter , 1989 .

[31]  C. J. Oliver,et al.  Models For Natural Clutter In Coherent Imaging , 1989, Other Conferences.