Sar And Optical Data Fusion Based On Anisotropic Diffusion With Pca And Classification Using Patch-Based Svm With Lbp

Abstract

SAR (VV and VH polarization) and optical data are widely used in image fusion to use the complimentary information of each other and to obtain the better-quality image (in terms of spatial and spectral features) for the improved classification results. The optical data acquisition depends on whether conditions while SAR data can acquire the data in presence of clouds. This paper uses anisotropic diffusion with PCA for the fusion of SAR (Sentinel 1 (S1)) and Optical (Sentinel 2 (S2)) data for patch-based SVM Classification with LBP (LBP-PSVM). Fusion results with VV polarization performed better than VH polarization using considered fusion method. Classification results suggests that the LBP-PSVM classifier is more effective in comparison to SVM and PSVM classifiers for considered data.