Fully Statistical, Wavelet-based conditional random field (FSWCRF) for SAR image segmentation

作者：

Highlights：

• A new statistical conditional random field is proposed for SAR image segmentation.

• The generalized Gaussian distribution of wavelet coefficients is applied in the CRF.

• The unary potential is constructed based on the generalized Gaussian distribution.

• The Kullback–Leibler distance improves the pairwise potential results.

摘要

•A new statistical conditional random field is proposed for SAR image segmentation.•The generalized Gaussian distribution of wavelet coefficients is applied in the CRF.•The unary potential is constructed based on the generalized Gaussian distribution.•The Kullback–Leibler distance improves the pairwise potential results.

论文关键词：Conditional Random Field (CRF),Generalized Gaussian Distributions (GGD),Kullback–Leibler Distance (KLD),Synthetic Aperture Radar (SAR) image segmentation

论文评审过程：Received 8 December 2019, Revised 22 November 2020, Accepted 23 November 2020, Available online 28 November 2020, Version of Record 8 December 2020.

论文官网地址：https://doi.org/10.1016/j.eswa.2020.114370