.png){kind=icon}
.png){kind=icon}
Return
Resolution-Difference Embedded Network for Cross-Resolution Remote Sensing Image Change Detection
.png){kind=icon}
PRE
AI
DOI：10.1109/TGRS.2025.3600397.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
At present, most remote sensing image change detection (CD) methods are applicable to equal-resolution scenarios, that is, the bitemporal images are assumed to have the same spatial resolution. Real-world tasks such as disaster emergency response have put forward the need for a CD of bitemporal images with different spatial resolutions, that is, a cross-resolution CD. However, due to the significant differences in spatial details between high-resolution (HR) images and low-resolution (LR) images, it is difficult to extract the spatial features of changed landcovers in complex scenarios and distinguish between changed landcovers and unchanged landcovers. To overcome the above issues, we propose a resolution-difference embedding network (RDENet). RDENet combines two innovative methods: pseudo-continuous resolution sequence representation (PRSR) and bitemporal resolution-difference modulation (BRDM). The PRSR method effectively extracts features of landcovers in complex scenarios by constructing a pseudo-image sequence with a smooth transition of resolution and developing a resolution-guided feature fusion (RGFF) module. The BRDM method significantly enhances the model’s ability to distinguish between changed and unchanged landcovers in complex scenarios through the design of a resolution-aware self-modulation (RASM) module and resolution-aware mutual-modulation (RAMM) module, which utilizes the resolution-difference factor as prior knowledge to dynamically enhance key features of changed landcovers in cross-resolution image pairs. Extensive experiments conducted on three publicly available CD datasets demonstrate that the proposed RDENet achieves superior detection performance in cross-resolution scenarios.
Keywords:
Change detection (CD)
cross resolution
deep learning
feature interaction
pseudo-image sequence
Journal
IF:
8.6
Papers:
2.1W
Citations:
10.7W