RF-HoDRF: High-Order Hybrid Discriminative Random Field Improved by Two-Layer Random Forest for SAR Image Change Detection

For better exploiting discriminative texture features and encoding high-level structures, this letter presents a high-order hybrid discriminative random field (DRF) improved by two-layer random forest (TL-RF), abbreviated as RF-HoDRF, for synthetic aperture radar (SAR) image change detection. First, RF-HoDRF constructs a TL-RF model to realize the selection of high-dimensional texture features and then provides the class probabilities for constructing the unary potential in RF-HoDRF. Second, it defines a high-order potential on high-order cliques generated by superpixels to encode the high-level structures and maintain the region consistency. Finally, considering the pairwise potential by the improved generalized Ising model and the statistics by the generalized Gamma distribution (
$\text{G}\Gamma \text{D}$
), the RF-HoDRF model is derived under the discriminative model framework. Then, by iteratively maximizing the local posterior probabilities, the class labels and the parameters are optimally estimated until they converge. Extensive comparisons and ablation experiments on measured SAR images verify the effectiveness of our method and demonstrate that discriminative feature selection and high-order structure maintenance have great contributions to improving change detection performances.