EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

YOLO-Crack: Geometry-Guided Real-Time Crack Detection Framework Toward Edge Deployment

Zhe Wei iD, Rui Wang, Rong Dai, Haibo Xu, Huan Zhang, Yurong Zou iD

Sensors · 18.06.2026 · 26 (12) · 3892

DOI: 10.3390/s26123892 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 18.06.2026. Verfasst von Zhe Wei und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science and Artificial Intelligence, Civil Aviation Flight University of China, Guanghan 618307, China. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Sichuan Provincial Engineering Research Center of Smart Operation and Maintenance of Civil Aviation Airports, Fundamental Research Funds for the Central Universities.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Crack detection in mobile inspection scenarios is constrained by both the extremely slender geometry of crack targets and the real-time inference requirements on edge devices, which expose systematic limitations of general-purpose object detectors. This paper proposes YOLO-Crack, a closed-loop solution that couples geometry-statistics-driven module design with end-to-end edge deployment validation. On the algorithmic side, we first quantify crack geometric properties and then introduce (i) a crack-aware cross-dimensional fusion attention (CFCA) module to strengthen feature representations, (ii) a dual-path feature enhancement module (DFEM) to preserve fine details during upsampling, and (iii) an empirical smooth quality window adjustment with shape consistency regularization to stabilize bounding-box regression for slender cracks. Experiments on the Crack500 dataset show that YOLO-Crack achieves 78.8% precision, 51.4% recall, and 65.7% mAP@0.5, improving over the YOLOv11n baseline by 4.2, 1.7, and 2.9 percentage points, respectively. On the engineering side, we deploy YOLO-Crack on a Jetson Orin NX mobile robot platform and evaluate it in a real ROS pipeline; the measured end-to-end throughput reaches 25.5 FPS, meeting real-time video processing requirements. The proposed framework provides a practical reference workflow for edge vision tasks, from geometry analysis to engineering verification.

Schlagwörter

Stichwörter der Autor:innen

TensorRT deploymentYOLOv11attention mechanismcrack detectiongeometric constraints

Autor:innen und Institutionen

  • School of Computer Science and Artificial Intelligence, Civil Aviation Flight University of China, Guanghan 618307, China.
  • Guanghan Flight College, Civil Aviation Flight University of China, Guanghan 618307, China.

ORCID-Profile: Zhe Wei, Yurong Zou

Förderung

  • Sichuan Provincial Engineering Research Center of Smart Operation and Maintenance of Civil Aviation Airports
  • Fundamental Research Funds for the Central Universities

Zitieren

APA

Wei, Z., Wang, R., Dai, R., Xu, H., Zhang, H., & Zou, Y. (2026). YOLO-Crack: Geometry-Guided Real-Time Crack Detection Framework Toward Edge Deployment. Sensors, 26(12), 3892. https://doi.org/10.3390/s26123892

Vancouver

Wei Z, Wang R, Dai R, Xu H, Zhang H, Zou Y. YOLO-Crack: Geometry-Guided Real-Time Crack Detection Framework Toward Edge Deployment. Sensors. 2026;26(12):3892. doi:10.3390/s26123892

BibTeX
@article{Wei2026,
  author = {Wei, Zhe and Wang, Rui and Dai, Rong and Xu, Haibo and Zhang, Huan and Zou, Yurong},
  title = {YOLO-Crack: Geometry-Guided Real-Time Crack Detection Framework Toward Edge Deployment},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {12},
  pages = {3892},
  doi = {10.3390/s26123892}
}
Kostenlos starten →