EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

The Fine Feature Extraction and Attention Re-Embedding Model Based on the Swin Transformer for Pavement Damage Classification

Shizheng Zhang, Kunpeng Wang, Zhihao Liu, Min Huang, Sheng Huang

Algorithms · 18.06.2025 · 18 (6) · 369

DOI: 10.3390/a18060369 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Algorithms, online erschienen am 18.06.2025. Verfasst von Shizheng Zhang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Henan Provincial Department of Science and Technology Research Project, Key Scientific Research Projects of Higher Education Institutions in Henan Province, Mass Innovation Space Incubation Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The accurate detection and classification of pavement damage are critical for ensuring timely maintenance and extending the service life of road infrastructure. In this study, we propose a novel pavement damage recognition model based on the Swin Transformer architecture, specifically designed to address the challenges inherent in pavement imagery, such as low damage visibility, varying illumination conditions, and highly similar surface textures. Unlike the original Swin Transformer, the proposed model incorporates two key components: a fine feature extraction module and a multi-head self-attention re-embedding module. These additions enhance the model’s ability to capture subtle and complex damage patterns. Experimental evaluations demonstrate that the proposed model achieves a 2.07% improvement in classification accuracy and a 0.97% increase in F1 score compared to the baseline while maintaining comparable computational complexity. Overall, the model significantly outperforms the baseline Swin Transformer in pavement damage detection and classification, highlighting its practical applicability.

Förderung

  • Henan Provincial Department of Science and Technology Research Project
  • Key Scientific Research Projects of Higher Education Institutions in Henan Province
  • Mass Innovation Space Incubation Project
  • Key Research and Development Program of Shaanxi

Zitieren

APA

Zhang, S., Wang, K., Liu, Z., Huang, M., & Huang, S. (2025). The Fine Feature Extraction and Attention Re-Embedding Model Based on the Swin Transformer for Pavement Damage Classification. Algorithms, 18(6), 369. https://doi.org/10.3390/a18060369

Vancouver

Zhang S, Wang K, Liu Z, Huang M, Huang S. The Fine Feature Extraction and Attention Re-Embedding Model Based on the Swin Transformer for Pavement Damage Classification. Algorithms. 2025;18(6):369. doi:10.3390/a18060369

BibTeX
@article{Zhang2025,
  author = {Zhang, Shizheng and Wang, Kunpeng and Liu, Zhihao and Huang, Min and Huang, Sheng},
  title = {The Fine Feature Extraction and Attention Re-Embedding Model Based on the Swin Transformer for Pavement Damage Classification},
  journal = {Algorithms},
  year = {2025},
  volume = {18},
  number = {6},
  pages = {369},
  doi = {10.3390/a18060369}
}
Kostenlos starten →