EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

SwinSegFormer: Advancing Aerial Image Semantic Segmentation for Flood Detection

Muhammad Tariq Shaheen, Hafsa Iqbal, Numan Khurshid, Haleema Sadia, Nasir Saeed

IEEE Open Journal of the Computer Society · 2025 · 6 · 645-657

DOI: 10.1109/ojcs.2025.3565185 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Open Journal of the Computer Society, 2025. Verfasst von Muhammad Tariq Shaheen und 4 weiteren Autor:innen. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: United Arab Emirates University, Advanced Research.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Semantic segmentation of aerial images is essential for unmanned aerial vehicle (UAV) applications in disaster management, particularly for identifying the flood-affected areas. Traditional techniques face challenges in capturing global semantic information due to their limited receptive fields, and high computational requirement. To address these issues, we propose a novel transformer-based model named SwinSegFormer, which feature a hierarchical encoder that efficiently generates multi-scale high-resolution features along with a lightweight decoder to reduce computational overhead. The proposed model is trained on FloodNet dataset and demonstrates efficient performance on challenging classes such as vehicles, pools, and flooded and non-flooded roads, which are crucial for effective disaster management. Additionally, we developed a post-processing module to categorize areas into flooded and non-flooded. The model achieves a validation mIoU of 75.1%, mDice of 85.4%, and mACC of 87.1%, representing a 10-12% improvement over state-of-the-art vision transformer-based methods. The effectiveness of model is further evaluated on real-world unlabeled flood imagery, highlighting its potential for supporting first aid activities during floods. Relevant codes are available at: https://github.com/Shaheen1998/SwinSegFormer.

Förderung

  • United Arab Emirates University
  • Advanced Research

Zitieren

APA

Shaheen, M. T., Iqbal, H., Khurshid, N., Sadia, H., & Saeed, N. (2025). SwinSegFormer: Advancing Aerial Image Semantic Segmentation for Flood Detection. IEEE Open Journal of the Computer Society, 6, 645-657. https://doi.org/10.1109/ojcs.2025.3565185

Vancouver

Shaheen MT, Iqbal H, Khurshid N, Sadia H, Saeed N. SwinSegFormer: Advancing Aerial Image Semantic Segmentation for Flood Detection. IEEE Open Journal of the Computer Society. 2025;6:645-657. doi:10.1109/ojcs.2025.3565185

BibTeX
@article{Shaheen2025,
  author = {Shaheen, Muhammad Tariq and Iqbal, Hafsa and Khurshid, Numan and Sadia, Haleema and Saeed, Nasir},
  title = {SwinSegFormer: Advancing Aerial Image Semantic Segmentation for Flood Detection},
  journal = {IEEE Open Journal of the Computer Society},
  year = {2025},
  volume = {6},
  pages = {645--657},
  doi = {10.1109/ojcs.2025.3565185}
}
Kostenlos starten →