EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

PEAK-U-Net: A Progressive Edge-Aware Attention KAN U-Net With Sliding Window for Crack Segmentation

Priyo Suprobo, Andrew Prasetyo, I Ketut Eddy Purnama, Eko Mulyanto Yuniarno

IEEE Access · 2025 · 13 · 208590-208611

DOI: 10.1109/access.2025.3641518 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Access, 2025. Verfasst von Priyo Suprobo und 3 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 54 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Indonesia Endowment Fund for Education Lembaga Pengelola Dana Pendidikan (LPDP), Ministry of Finance, Republic of Indonesia.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Crack detection and quantification in concrete structures remains a critical challenge in structural health monitoring. Traditional manual inspection methods are time-consuming and prone to human error, while existing deep learning approaches struggle with fine-grained edge detection and accurate dimensional quantification. This paper introduces PEAK-U-Net (Progressive Edge-Aware Attention Kolmogorov-Arnold U-Net), a novel architecture addressing these limitations through three key innovations. First, we propose a progressive edge-aware attention mechanism that adaptively focuses on crack boundaries across multiple scales. Second, we present the integration of Kolmogorov-Arnold Networks (KAN) into U-Net architecture, replacing traditional MLP layers with learnable activation functions for superior feature approximation. Third, we develop a multi-scale sliding window framework maintaining sub-millimeter measurement precision based on calibrated pixel resolution. The PEAK-U-Net employs an encoder-decoder structure with enhanced KAN modules in bottleneck and decoder sections, incorporating attention gates and edge-aware convolutions. Our sliding window approach processes images through systematic patch extraction and reconstructs results with maintained spatial accuracy for precise crack width measurements. Extensive experimental validation demonstrates that PEAK-U-Net achieves state-of-the-art performance, particularly excelling in small crack detection with 99.45% accuracy, 81.85% DICE coefficient, and 74.75% Mean IOU on the CrackForest dataset. The method demonstrates superior precision (84.31%) and recall (82.36%) with the lowest loss value (0.21), while successfully classifying crack severity from Hairline (0.07 mm) to Medium (0.20-0.25 mm). PEAK-U-Net represents a transformative contribution to computer vision-based structural health monitoring, offering significant potential to enhance preventive maintenance strategies and provide a robust foundation for next-generation automated inspection systems.

Förderung

  • Indonesia Endowment Fund for Education Lembaga Pengelola Dana Pendidikan (LPDP), Ministry of Finance, Republic of Indonesia

Zitieren

APA

Suprobo, P., Prasetyo, A., Purnama, I. K. E., & Yuniarno, E. M. (2025). PEAK-U-Net: A Progressive Edge-Aware Attention KAN U-Net With Sliding Window for Crack Segmentation. IEEE Access, 13, 208590-208611. https://doi.org/10.1109/access.2025.3641518

Vancouver

Suprobo P, Prasetyo A, Purnama IKE, Yuniarno EM. PEAK-U-Net: A Progressive Edge-Aware Attention KAN U-Net With Sliding Window for Crack Segmentation. IEEE Access. 2025;13:208590-208611. doi:10.1109/access.2025.3641518

BibTeX
@article{Suprobo2025,
  author = {Suprobo, Priyo and Prasetyo, Andrew and Purnama, I Ketut Eddy and Yuniarno, Eko Mulyanto},
  title = {PEAK-U-Net: A Progressive Edge-Aware Attention KAN U-Net With Sliding Window for Crack Segmentation},
  journal = {IEEE Access},
  year = {2025},
  volume = {13},
  pages = {208590--208611},
  doi = {10.1109/access.2025.3641518}
}
Kostenlos starten →