EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Temporal Feature Interaction for Robust Remote Sensing Image Change Detection: A Taxonomy and Cross-Domain Comparative Study

Mostafa Mosaad iD, Mahmoud Ahmed iD, Fawzy Eltohamy, Tarek A Mahmoud iD, Mohamed E Hanafy iD

Journal of Imaging · 11.08.2026 · 12 (8) · 376

DOI: 10.3390/jimaging12080376 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Imaging, online erschienen am 11.08.2026. Verfasst von Mostafa Mosaad und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Aircraft Electrical Equipment, Military Technical College, Cairo 11766, Egypt. Die Arbeit nennt 23 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Remote sensing change detection (RSCD) has advanced through convolutional, attention-based, transformer, and hybrid architectures, yet models are commonly compared as whole architectural families rather than by how their temporal streams interact. This study introduces the Temporal Interaction Taxonomy (TIT), which characterizes temporal feature interaction by timing, direction, and operator. Nine representative models, ranging from early-fusion convolutional baselines to hybrid CNN–Transformer designs, were evaluated using faithful Open-CD implementations under a unified protocol on the LEVIR-CD and WHU-CD building change datasets. TIT provided a consistent basis for describing bi-temporal integration across architectures. Cross-dataset performance was model- and direction-dependent: ChangeFormer achieved the highest mIoU in both transfer directions, reaching 59.99% for WHU→LEVIR and 82.58% for LEVIR→WHU. The results suggest an association between interaction design and cross-dataset robustness, but the independent contribution of temporal interaction cannot be separated from other architectural differences. Transfer also showed model-dependent directional asymmetry; its causes could not be isolated because dataset characteristics and model design were not independently controlled. Overall, temporal interaction provides a useful dimension for interpreting model behavior across the two evaluated datasets. These findings are limited to building change detection on LEVIR-CD and WHU-CD and require task-specific validation before extension to other RSCD applications.

Schlagwörter

Stichwörter der Autor:innen

Open-CDbi-temporal fusionchange detectioncross-dataset generalizationdeep learningremote sensingtransformers

Autor:innen und Institutionen

  • Department of Aircraft Electrical Equipment, Military Technical College, Cairo 11766, Egypt.
  • Department of Electrical and Software Engineering, University of Calgary, Calgary, AB T2N 1N4, Canada.
  • Computer Engineering Department, Egypt University of Informatics, Cairo 19519, Egypt.

ORCID-Profile: Mostafa Mosaad, Mahmoud Ahmed, Tarek A Mahmoud, Mohamed E Hanafy

Zitieren

APA

Mosaad, M., Ahmed, M., Eltohamy, F., Mahmoud, T. A., & E Hanafy, M. (2026). Temporal Feature Interaction for Robust Remote Sensing Image Change Detection: A Taxonomy and Cross-Domain Comparative Study. Journal of Imaging, 12(8), 376. https://doi.org/10.3390/jimaging12080376

Vancouver

Mosaad M, Ahmed M, Eltohamy F, Mahmoud TA, E Hanafy M. Temporal Feature Interaction for Robust Remote Sensing Image Change Detection: A Taxonomy and Cross-Domain Comparative Study. Journal of Imaging. 2026;12(8):376. doi:10.3390/jimaging12080376

BibTeX
@article{Mosaad2026,
  author = {Mosaad, Mostafa and Ahmed, Mahmoud and Eltohamy, Fawzy and Mahmoud, Tarek A and E Hanafy, Mohamed},
  title = {Temporal Feature Interaction for Robust Remote Sensing Image Change Detection: A Taxonomy and Cross-Domain Comparative Study},
  journal = {Journal of Imaging},
  year = {2026},
  volume = {12},
  number = {8},
  pages = {376},
  doi = {10.3390/jimaging12080376}
}
Kostenlos starten →