Unsupervised classification of polsar imagery based on consensus similarity network fusion

This paper proposes a PolSAR imagery unsupervised classification framework based on consensus similarity network fusion (CSNF), which is generally utilized for biomedical Sciences and for the first time used for PolSAR imagery classification in our work. First, the PolSAR image is divided into superpixels by a fast superpixel segmentation method and five groups of feature vectors are extracted based on the superpixels. Second, CSNF is performed on the five affinity matrixes constructed from the five groups of feature vectors to obtain a fused similarity matrix. Third, spectral clustering based on the fused similarity matrix is adopted to automatically achieve the classification results. Finally, a postprocessing procedure based on dissimilarity measure is performed to smooth the classification results and correct the misclassified pixels. The experimental results conducted on both a simulated PolSAR image and a real-world PolSAR image show the superiority of the proposed method.

[1]  Xingsi Xue,et al.  A novel spectral clustering method with superpixels for image segmentation , 2016 .

[2]  Huanxin Zou,et al.  Simulation of spatially correlated PolSAR images using inverse transform method , 2015 .

[3]  Jixian Zhang,et al.  Land Cover Classification from Polarimetric SAR Data Based on Image Segmentation and Decision Trees , 2015 .

[4]  Cuizhen Wang,et al.  Improved POLSAR Image Classification by the Use of Multi-Feature Combination , 2015, Remote. Sens..

[5]  Laurent Ferro-Famil,et al.  Unsupervised terrain classification preserving polarimetric scattering characteristics , 2004, IEEE Transactions on Geoscience and Remote Sensing.

[6]  Guoman Huang,et al.  Object-Oriented Classification of Polarimetric SAR Imagery Based on Texture Features , 2011, 2011 International Symposium on Image and Data Fusion.

[7]  Hiroyoshi Yamada,et al.  Four-component scattering model for polarimetric SAR image decomposition , 2005, IEEE Transactions on Geoscience and Remote Sensing.

[8]  Haixu Wang,et al.  An segmentation-based PolSAR image classification method via texture features and color features , 2015, 2015 IEEE Radar Conference (RadarCon).

[9]  Maoguo Gong,et al.  Unsupervised Classification of Fully Polarimetric SAR Images Based on Scattering Power Entropy and Copolarized Ratio , 2013, IEEE Geoscience and Remote Sensing Letters.

[10]  Eric Pottier,et al.  A review of target decomposition theorems in radar polarimetry , 1996, IEEE Trans. Geosci. Remote. Sens..

[11]  Ulrike von Luxburg,et al.  A tutorial on spectral clustering , 2007, Stat. Comput..

[12]  E. Krogager New decomposition of the radar target scattering matrix , 1990 .

[13]  Xiaohua Hu,et al.  Inferring microbial interaction networks based on consensus similarity network fusion , 2014, Science China Life Sciences.

[14]  Yue Zhang,et al.  A Fast Superpixel Segmentation Algorithm for PolSAR Images Based on Edge Refinement and Revised Wishart Distance , 2016, Sensors.