EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

SC-YOLO: A Real-Time CSP-Based YOLOv11n Variant Optimized with Sophia for Accurate PPE Detection on Construction Sites

Teerapun Saeheaw

Buildings · 12.08.2025 · 15 (16) · 2854

DOI: 10.3390/buildings15162854 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Buildings, online erschienen am 12.08.2025. Verfasst von Teerapun Saeheaw. Die Arbeit wurde bisher 17-mal zitiert (Crossref) und nennt 63 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science, Research and Innovation Fund (NSRF).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Despite advances in YOLO-based PPE detection, existing approaches primarily focus on architectural modifications. However, these approaches overlook second-order optimization methods for navigating complex loss landscapes in object detection. This study introduces SC-YOLO, integrating CSPDarknet backbone with Sophia optimization (leveraging efficient Hessian estimates for curvature-aware updates) for enhanced PPE detection on construction sites. The proposed methodology includes three key steps: (1) systematic evaluation of EfficientNet, DINOv2, and CSPDarknet backbones, (2) integration of Sophia second-order optimizer with CSPDarknet for curvature-aware updates, and (3) cross-dataset validation in diverse construction scenarios. Traditional manual PPE inspection exhibits operational limitations, including high error rates (12–15%) and labor-intensive processes. SC-YOLO addresses these challenges through automated detection with potential for real-time deployment in construction safety applications. Experiments on VOC2007-1 and ML-31005 datasets demonstrate improved performance, achieving 96.3–97.6% mAP@0.5 and 63.6–68.6% mAP@0.5:0.95. Notable gains include a 9.03% improvement in detecting transparent objects. The second-order optimization achieves faster convergence with 7% computational overhead compared to baseline methods, showing enhanced robustness over conventional YOLO variants in complex construction environments.

Förderung

  • National Science, Research and Innovation Fund (NSRF)

Zitieren

APA

Saeheaw, T. (2025). SC-YOLO: A Real-Time CSP-Based YOLOv11n Variant Optimized with Sophia for Accurate PPE Detection on Construction Sites. Buildings, 15(16), 2854. https://doi.org/10.3390/buildings15162854

Vancouver

Saeheaw T. SC-YOLO: A Real-Time CSP-Based YOLOv11n Variant Optimized with Sophia for Accurate PPE Detection on Construction Sites. Buildings. 2025;15(16):2854. doi:10.3390/buildings15162854

BibTeX
@article{Saeheaw2025,
  author = {Saeheaw, Teerapun},
  title = {SC-YOLO: A Real-Time CSP-Based YOLOv11n Variant Optimized with Sophia for Accurate PPE Detection on Construction Sites},
  journal = {Buildings},
  year = {2025},
  volume = {15},
  number = {16},
  pages = {2854},
  doi = {10.3390/buildings15162854}
}
Kostenlos starten →