EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Accuracy–Efficiency Trade-Off: Optimizing YOLOv8 for Structural Crack Detection

Jiahui Zhang iD, Zoia Vladimirovna Beliaeva iD, Yue Huang iD

Sensors · 21.06.2025 · 25 (13) · 3873

DOI: 10.3390/s25133873 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 21.06.2025. Verfasst von Jiahui Zhang und 2 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Civil Engineering and Architecture, Ural Federal University, St. Mira19, 620002 Yekaterinburg, Russia. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 64 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: China Scholarship Council, Ural Federal University.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

To address the accuracy–efficiency trade-off faced by deep learning models in structural crack detection, this paper proposes an optimized version of the YOLOv8 model. YOLO (You Only Look Once) is a real-time object detection algorithm known for its high speed and decent accuracy. To improve crack feature representation, the backbone is enhanced with the SimAM attention mechanism. A lightweight C3Ghost module reduces parameter count and computation, while a bidirectional multi-scale feature fusion structure replaces the standard neck to enhance efficiency. Experimental results show that the proposed model achieves a mean Average Precision (mAP) of 88.7% at 0.5 IoU and 69.4% for mAP@0.5:0.95, with 12.3% fewer Giga Floating Point Operations (GFlops), and faster inference. These improvements significantly enhance the detection of fine cracks while maintaining real-time performance, making it suitable for engineering scenarios.

Schlagwörter

Stichwörter der Autor:innen

C3GhostSimAMYOLOv8accuracy–efficiency trade-offattention mechanismcrack detectionfeature pyramid

Autor:innen und Institutionen

  • Institute of Civil Engineering and Architecture, Ural Federal University, St. Mira19, 620002 Yekaterinburg, Russia.

ORCID-Profile: Jiahui Zhang, Zoia Vladimirovna Beliaeva, Yue Huang

Förderung

  • China Scholarship Council
  • Ural Federal University

Zitieren

APA

Zhang, J., Beliaeva, Z. V., & Huang, Y. (2025). Accuracy–Efficiency Trade-Off: Optimizing YOLOv8 for Structural Crack Detection. Sensors, 25(13), 3873. https://doi.org/10.3390/s25133873

Vancouver

Zhang J, Beliaeva ZV, Huang Y. Accuracy–Efficiency Trade-Off: Optimizing YOLOv8 for Structural Crack Detection. Sensors. 2025;25(13):3873. doi:10.3390/s25133873

BibTeX
@article{Zhang2025,
  author = {Zhang, Jiahui and Beliaeva, Zoia Vladimirovna and Huang, Yue},
  title = {Accuracy–Efficiency Trade-Off: Optimizing YOLOv8 for Structural Crack Detection},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {13},
  pages = {3873},
  doi = {10.3390/s25133873}
}
Kostenlos starten →