Journal
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
Volume 56, Issue 2, Pages 905-920Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TGRS.2017.2756621
Keywords
Expectation-maximization ( EM); polarimetric synthetic aperture radar (PolSAR) image classification; spatial-contextual information; WG Gamma distribution; Wishart mixture model (WMM)
Categories
Funding
- Natural Science Foundation of China [61772390, 61271297]
- Aeronautical Science Foundation of China [2016081011]
- Natural Science Basic Research Plan in Shaanxi Province of China [2017JM4022]
- Shanghai Aerospace Science and Technology Innovation Fund [SAST2016092]
Ask authors/readers for more resources
The WG Gamma model has been validated as an effective model for the characteristic of polarimetric synthetic aperture radar (PolSAR) data statistics. However, due to the complexity of natural scene and the influence of coherent wave, theWG Gamma model still needs to be improved to fully consider the polarimetric information. Then, we propose the WG Gamma mixture model (WG Gamma MM) for PolSAR data to maintain the correlations among statistics in PolSAR data. To further consider the spatial-contextual information in PolSAR image classification, we propose a novel mixture model, named mixture WG Gamma-Markov random field (MWG Gamma MRF) model, by introducing the MRF to improve the WG Gamma MM model for classification. In each law of the MWG Gamma-MRF model, the interaction term based on the edge penalty function is constructed by the edge-based multilevel-logistic model, while the likelihood term being constructed by the WG Gamma model, so that each law of the MWG Gamma-MRF model can achieve an energy function and has its contribution to the inference of attributive class. Then, the mixture energy function of the MWG Gamma-MRF model has the fusion of the weighted component, given the energy functions of every law. The mixture coefficient and the corresponding mean covariance matrix of the MWG Gamma-MRF model are estimated by the expectation- maximization algorithm, while the parameters of the WG Gamma model being estimated by the method of matrix log-cumulants. Experiments on simulated data and real PolSAR images demonstrate the effectiveness of the MWG Gamma-MRF model and illustrate that it can provide strong noise immunity, get smoother homogeneous areas, and obtain more accurate edge locations.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available