Enhanced PolSAR Image Segmentation with Polarization Channel Fusion and Diffusion-Based Probability Modeling

With the advancement of polarimetric synthetic aperture radar (PolSAR) imaging technology and the growing demand for image interpretation, extracting meaningful land cover information from PolSAR images has become a key research focus. To address the segmentation challenge, we propose an innovative method. First, features from co-polarization and cross-polarization channels are separately used as dual inputs, and a cross-attention mechanism effectively fuses these features to capture correlations between different polarization information. Second, a diffusion framework is employed to jointly model target features and class probabilities, aiming to improve segmentation accuracy by learning and fitting the probabilistic distribution of target labels. Finally, experimental results demonstrate that the proposed method achieves superior performance in PolSAR image segmentation, effectively managing complex polarization relationships while offering robustness and broad application potential.