EUVIMEDEUVIMED entdecken
Crossref

MSFAF-Net: A Multi-Scale Frequency-Attentive Fusion Network for Pavement Crack Detection

Xi Li, Yu-Qi Wang, Qiang Zhou, Hua-Kun Luo, You-Lin Chen

IEEE Transactions on Intelligent Transportation Systems · 2026-06 · 27 (6) · 6816-6828

DOI: 10.1109/tits.2026.3658095 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Intelligent Transportation Systems, 2026-06. Verfasst von Xi Li und 4 weiteren Autor:innen. Die Arbeit nennt 51 Literaturangaben. Gefördert von: National Natural Science Foundation of China, China Postdoctoral Science Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Cracks are one of the most common types of pavement damage. If not repaired promptly, they can significantly shorten the pavement’s service life and increase the risk of traffic accidents. Existing crack segmentation methods often misclassify cracks as discontinuous segments due to complex textures and backgrounds. This results in noise misclassification and inaccurate segmentation. To address these challenges, this paper proposes a Multi-Scale Frequency-Attentive Fusion Network (MSFAF-Net) for improved crack feature detection. The network uses a U-shaped structure and combines multi-scale frequency feature fusion with an attention mechanism. First, a Frequency-Enhanced Multi-scale Fusion Skip (FEMF-Skip) module integrates features from multiple scales. Additionally, a Multi-Scale Feature-Enhanced Bottleneck (MSFEB) is introduced. The MSFEB consists of a Multi-Scale Convolutional Block (MSCB) and a Weighted Spatial Channel Attention Block (WSCA). It focuses on different convolutional scales to extract enriched features and adjust feature weights using the attention mechanism. Finally, the decoder applies a Multi-Scale Feature Fusion (MSFF) strategy for more accurate segmentation. The model is evaluated on four publicly available crack datasets: CRACK500, DeepCrack, CFD, and EdmCrack600. Six metrics were used for objective assessment. Experimental results demonstrate that MSFAF-Net consistently outperforms existing methods.

Förderung

  • National Natural Science Foundation of China
  • China Postdoctoral Science Foundation

Zitieren

APA

Li, X., Wang, Y., Zhou, Q., Luo, H., & Chen, Y. (2026). MSFAF-Net: A Multi-Scale Frequency-Attentive Fusion Network for Pavement Crack Detection. IEEE Transactions on Intelligent Transportation Systems, 27(6), 6816-6828. https://doi.org/10.1109/tits.2026.3658095

Vancouver

Li X, Wang Y, Zhou Q, Luo H, Chen Y. MSFAF-Net: A Multi-Scale Frequency-Attentive Fusion Network for Pavement Crack Detection. IEEE Transactions on Intelligent Transportation Systems. 2026;27(6):6816-6828. doi:10.1109/tits.2026.3658095

BibTeX
@article{Li2026,
  author = {Li, Xi and Wang, Yu-Qi and Zhou, Qiang and Luo, Hua-Kun and Chen, You-Lin},
  title = {MSFAF-Net: A Multi-Scale Frequency-Attentive Fusion Network for Pavement Crack Detection},
  journal = {IEEE Transactions on Intelligent Transportation Systems},
  year = {2026},
  volume = {27},
  number = {6},
  pages = {6816--6828},
  doi = {10.1109/tits.2026.3658095}
}
Kostenlos starten →