EUVIMEDEUVIMED entdecken
Crossref

ICGINet: Intratemporal and Cross-Temporal Graph Interaction Network for Misaligned Bitemporal Remote Sensing Image Change Detection

Kexin Zhu, Jun Pan, Yang Yang, Yuchuan Bai, Rui Xu, Junli Li

IEEE Transactions on Geoscience and Remote Sensing · 2025 · 63 · 1-15

DOI: 10.1109/tgrs.2025.3608469 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Geoscience and Remote Sensing, 2025. Verfasst von Kexin Zhu und 5 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 65 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Change detection (CD) identifies pixel-level land cover changes in multitemporal remote sensing imagery (RSI), playing a critical role in environmental monitoring and disaster management. Despite the advantages of high-resolution imagery in providing detailed spatial and contextual information, it significantly intensifies the complexity of fine-grained CD by exacerbating sensitivity to spatial misalignment. While accurate CD conventionally hinges on precise image registration, inevitable misalignments in practical scenarios often lead to spurious change responses and compromise the stability of feature representation learning. To address these challenges, this article proposes the intratemporal and cross-temporal graph interaction network (ICGINet), a novel architecture that enhances CD robustness under registration uncertainty by modeling intratemporal and cross-temporal dependencies through adaptive graph-based message passing and relational reasoning. Specifically, ICGINet employs a dual-branch design that combines convolutional neural networks (CNNs) for local semantic extraction with graph neural networks (GNNs) for global relational modeling, enabling the integration of fine-grained spatial details and long-range contextual dependencies. To reconcile intratemporal features from these heterogeneous branches, a dual-focus feature fusion (DFFF) module is proposed to facilitate attention-guided information exchange and semantic alignment. Furthermore, an adaptive neighborhood graph awareness (ANGA) module constructs a displacement-aware dynamic graph to capture cross-temporal neighborhood correspondences, thereby mitigating spatial misalignment during temporal interaction. Comprehensive experiments on two challenging datasets demonstrate that ICGINet achieves superior performance compared to state-of-the-art methods, both in terms of accuracy and robustness to registration error.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Zhu, K., Pan, J., Yang, Y., Bai, Y., Xu, R., & Li, J. (2025). ICGINet: Intratemporal and Cross-Temporal Graph Interaction Network for Misaligned Bitemporal Remote Sensing Image Change Detection. IEEE Transactions on Geoscience and Remote Sensing, 63, 1-15. https://doi.org/10.1109/tgrs.2025.3608469

Vancouver

Zhu K, Pan J, Yang Y, Bai Y, Xu R, Li J. ICGINet: Intratemporal and Cross-Temporal Graph Interaction Network for Misaligned Bitemporal Remote Sensing Image Change Detection. IEEE Transactions on Geoscience and Remote Sensing. 2025;63:1-15. doi:10.1109/tgrs.2025.3608469

BibTeX
@article{Zhu2025,
  author = {Zhu, Kexin and Pan, Jun and Yang, Yang and Bai, Yuchuan and Xu, Rui and Li, Junli},
  title = {ICGINet: Intratemporal and Cross-Temporal Graph Interaction Network for Misaligned Bitemporal Remote Sensing Image Change Detection},
  journal = {IEEE Transactions on Geoscience and Remote Sensing},
  year = {2025},
  volume = {63},
  pages = {1--15},
  doi = {10.1109/tgrs.2025.3608469}
}
Kostenlos starten →