PSD-YOLO: An Enhanced Real-Time Framework for Robust Worker Detection in Complex Offshore Oil Platform Environments
Sensors · 10.10.2025 · 25 (20) · 6264
DOI: 10.3390/s25206264 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 10.10.2025. Verfasst von Yikun Qin und 5 weiteren Autor:innen. Beteiligte Einrichtung: Southampton Ocean Engineering Joint Institute, Harbin Engineering University, Harbin 150001, China. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 59 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Supporting Fund of Intelligent Internet of Things and Crowd Computing.
Abstract (Originalsprache)
To address the safety challenges for personnel in the complex and hazardous environments of offshore drilling platforms, this paper introduces the Platform Safety Detection YOLO (PSD-YOLO), an enhanced, real-time object detection framework based on YOLOv10s. The framework integrates several key innovations to improve detection robustness: first, the Channel Attention-Aware (CAA) mechanism is incorporated into the backbone network to effectively suppress complex background noise interference; second, a novel C2fCIB_Conv2Former module is designed in the neck to strengthen multi-scale feature fusion for small and occluded targets; finally, the Soft-NMS algorithm is employed in place of traditional NMS to significantly reduce missed detections in dense scenes. Experimental results on a custom offshore platform personnel dataset show that PSD-YOLO achieves a mean Average Precision (mAP@0.5) of 82.5% at an inference speed of 232.56 FPS. The efficient and accurate detection framework proposed in this study provides reliable technical support for automated safety monitoring systems, holds significant practical implications for reducing accident rates and safeguarding personnel by enabling real-time warnings of hazardous situations, fills a critical gap in intelligent sensor monitoring for offshore platforms and makes a significant contribution to advancing their safety monitoring systems.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Southampton Ocean Engineering Joint Institute, Harbin Engineering University, Harbin 150001, China.
- College of Computer Science and Technology, Harbin Engineering University, Harbin 150001, China.
Förderung
- Supporting Fund of Intelligent Internet of Things and Crowd Computing
Zitieren
APA
Qin, Y., Dong, J., Li, W., Zhang, L., Feng, K., & Wang, Z. (2025). PSD-YOLO: An Enhanced Real-Time Framework for Robust Worker Detection in Complex Offshore Oil Platform Environments. Sensors, 25(20), 6264. https://doi.org/10.3390/s25206264
Vancouver
Qin Y, Dong J, Li W, Zhang L, Feng K, Wang Z. PSD-YOLO: An Enhanced Real-Time Framework for Robust Worker Detection in Complex Offshore Oil Platform Environments. Sensors. 2025;25(20):6264. doi:10.3390/s25206264
BibTeX
@article{Qin2025,
author = {Qin, Yikun and Dong, Jiawen and Li, Wei and Zhang, Linxin and Feng, Ke and Wang, Zijia},
title = {PSD-YOLO: An Enhanced Real-Time Framework for Robust Worker Detection in Complex Offshore Oil Platform Environments},
journal = {Sensors},
year = {2025},
volume = {25},
number = {20},
pages = {6264},
doi = {10.3390/s25206264}
}
EUVIMED