PTDNet: Progressive Temporal Difference Network With Global Guidance for Building Change Detection

As the spatial resolution of satellite remote sensing increases, high-resolution remote sensing (HRRS) images provide richer surface structure details, also make noise and artifacts more obvious than before. Therefore, the building change detection (BCD) task is affected by irrelevant features caused by explicit noise and artifacts, resulting in incoherent semantics and rough boundaries of buildings, which leads to fragmented change detection results and blurred boundaries between background and changes. To address this, we propose the progressive temporal difference network (PTDNet). PTDNet employs an interleaved convolutional neural network (CNN)-Transformer encoder to enhance semantic structural correlation, supplemented by a global information supplement module (GISM) for semantic alignment. The progressive temporal difference module (PTDM) then suppresses artifacts and reinforces change semantic coherence through multistage temporal difference fusion. Finally, a change guidance module (CGM) with deep semantic-guided attention refines change boundary. During this process, multiscale features are effectively aggregated layer-by-layer to produce the final binary prediction map. We conducted comparative experiments with other state-of-the-art (SOTA) methods on three public BCD datasets, namely, WHU-CD, LEVIR-CD, and SYSU-CD, and the results show that our PTDNet achieves the highest $F1$ -scores of 93.07%, 91.80%, and 83.46%, respectively. The code for this work is publicly available at https://github.com/Caijiaqi85/PTDNet-CD