Fusion and Classification of SAR and Optical Data Using Multi-Image Color Components with Differential Gradients

This paper proposes a gradient-based data fusion and classification approach for Synthetic Aperture Radar (SAR) optical image. method is used to intuitively reflect the boundaries edges of land cover classes present in dataset. For SAR images, Sentinel 1A 2B covering Central State Farm Hissar (India) was used. The major agricultural crops grown this area include paddy, maize, cotton, pulses during kharif (summer) wheat, sugarcane, mustard, gram, peas rabi (winter) seasons. gradient using Sobel operator color components three directions (i.e., x, y, z) are image fusion. To judge quality fused image, several metrics calculated. After obtaining resultant based methods, including Stochastic Gradient Descent Classifier, Boosting Extreme final classification. accuracy represented overall kappa value. A comparison results indicates better performance by Classifier.