Maximum likelihood parameter estimation for G0 distribution via EM algorithm

G0 distribution, a statistical model used for modeling SAR image data, has been widely used recently. Due to the complexity of G0 distribution, maximum likelihood estimator, which is statistically optimal, has not been used for the parameter estimation of G0 distribution. In this paper, a new deriva...

Full description

Saved in:
Bibliographic Details
Published inProceedings of 2013 10th International Bhurban Conference on Applied Sciences & Technology (IBCAST) pp. 89 - 93
Main Authors Xin Zhou, Ju Jiang, Congqing Wang
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.01.2013
Subjects
Clutter
Laboratories
Level set
Maximum likelihood estimation
Method of moments
Online AccessGet full text

Cover

More Information
Summary:G0 distribution, a statistical model used for modeling SAR image data, has been widely used recently. Due to the complexity of G0 distribution, maximum likelihood estimator, which is statistically optimal, has not been used for the parameter estimation of G0 distribution. In this paper, a new derivation of G0 distribution is first given, based on which, a maximum likelihood parameter estimation method via expectation maximization algorithm is proposed for the G0 distribution. Experiments based on simulated SAR data have been conducted to examine the performance of the proposed algorithm as well as to compare with other parameter estimation methods, and the results show the advantages of the proposed method.
ISBN:9781467344258
1467344257
DOI:10.1109/IBCAST.2013.6512136