Heterogeneous SAR texture characterization by means of Markov random fields
暂无分享,去创建一个
The purpose of this paper is to develop a new method for heterogeneous SAR texture modeling and characterization. It reposed on a Markov random field modeling. The K-distribution, derived under multiplicative model assumption, is shown to be an efficient model to characterize SAR signals at global scale. In order to characterize details of the texture, a local Markov model "auto-gamma" is derived and based on the global model.
[1] E. Jakeman. On the statistics of K-distributed noise , 1980 .
[2] E. Jakeman,et al. Generalized K distribution: a statistical model for weak scattering , 1987 .