2-D Rayleigh autoregressive moving average model for SAR image modeling

Two-dimensional (2-D) autoregressive moving average (ARMA) models are commonly applied to describe real-world image data, usually assuming Gaussian or symmetric noise. However, data often present non-Gaussian signals, with asymmetrical distributions and strictly positive values. In particular, SAR images known be well characterized by the Rayleigh distribution. this context, ARMA model tailored for 2-D Rayleigh-distributed is introduced—the RARMA model. The derived conditional likelihood inferences discussed. proposed was submitted extensive Monte Carlo simulations evaluate performance of maximum estimators. Moreover, in context processing, two comprehensive numerical experiments were performed comparing anomaly detection modeling results traditional competing methods literature.