An improved particle filter algorithm based on Markov Random Field modeling in stationary wavelet domain for SAR image despeckling

Particle filter (PF) is an effective approach to nonlinear and non-Gaussian Bayesian state estimation and has been successfully applied to wavelet-based synthetic aperture radar (SAR) image despeckling. In this paper, we propose an improved PF despeckling algorithm based on Markov Random Field (MRF) model that can preserve the edge, textural information and structural features of SAR images well. First, we show that the wavelet coefficients of SAR images which exhibit significantly non-Gaussian statistics can be described accurately by generalized Gaussian distribution (GGD) in stationary wavelet domain. Secondly, to amend the weight deviation, MRF model parameters are introduced to redefine the importance weight of the particles. At last, region-divided processing is implemented for the real time application of the proposed algorithm. The effectiveness of the proposed algorithm is demonstrated by application to simulated images and real SAR images.

► We propose an improved PF despeckling algorithm for SAR images.
► Wavelet coefficients of SAR images are described accurately by GGD in SWT domain.
► MRF and WLS are introduced to estimate the weight coefficients of the particles.
► The obtained weight coefficients can amend the weight deviation.
► Region-divided processing is implemented for the real time application.