Feature Hierarchical Differentiation for Remote Sensing Image Change Detection
Gensheng Pei, Lulu Zhang
Abstract
Change detection (CD) is the localization of pixel-level differentiation between images in a specific setting, <i>i.e</i>., same-spatial different-temporal scenario. For high-resolution remote sensing (HRS) images, CD models should guarantee detection accuracy for the changes of interest and filter background noise for other regions. To this end, we propose a time-specific model, dubbed feature hierarchical differentiation (FHD), to achieve change perception aimed at HRS images. Specifically, we present the time-specific features (TSF) module to acquire each temporal image’s specific changes efficiently. Subsequently, the time-specific features from multi-temporal HRS images are adaptively fused by our proposed hierarchical differentiation (HD) module. Our FHD is subjected to elaborate experiments on four CD datasets. Quantitative and qualitative results outperform existing state-of-the-art methods. The ablation study further demonstrates the effectiveness of the proposed modules. Code is available at https://github.com/ZSVOS/FHD.