A Hierarchical Heterogeneous Graph for Unsupervised SAR Image Change Detection
Jun Wang, Tianchen Zhao, Xiaoliang Jiang, Kun Lan
Abstract
This letter presents a novel graph-driven synthetic aperture radar (SAR) image change detection approach. A hierarchical heterogeneous graph is proposed, combining two distinct graphs: a weighted graph based on adjacency of superpixels of an initial over-segmentation, and the dual-weighted heterogeneous graph. The superpixel-based regional affinities are coupled with pixel-based heterogeneous affinities, being embedded into the structure of hierarchical heterogeneous graph. The difference image generation relies on the matching of the bitemporal graphs, as well as the multiscale features of vertex domain. Finally, traditional graph cuts algorithm is applied to separate the difference image into changed and unchanged areas. Experiments on three real SAR datasets show that the proposed approach outperforms other experimental approaches and is a good candidate for SAR image change detection tasks.