EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Enhanced Real-Time Highway Object Detection for Construction Zone Safety Using YOLOv8s-MTAM

Wen-Piao Lin iD, Chun-Chieh Wang, En-Cheng Li, Chien-Hung Yeh

Sensors · 17.10.2025 · 25 (20) · 6420

DOI: 10.3390/s25206420 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 17.10.2025. Verfasst von Wen-Piao Lin und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electrical Engineering, Chang Gung University, Taoyuan 33303, Taiwan. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Project of Chang Gung University.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Reliable object detection is crucial for autonomous driving, particularly in highway construction zones where early hazard recognition ensures safety. This paper introduces an enhanced YOLOv8s-based detection system incorporating a motion-temporal attention module (MTAM) to improve robustness under high-speed and dynamic conditions. The proposed architecture integrates a cross-stage partial (CSP) backbone, feature pyramid network-path aggregation network (FPN-PAN) feature fusion, and advanced loss functions to achieve high accuracy and temporal consistency. MTAM leverages temporal convolutions and attention mechanisms to capture motion cues, enabling effective detection of blurred or partially occluded objects. A custom dataset of 34,240 images, expanded through extensive data augmentation and 9-Mosaic transformations, is used for training. Experimental results demonstrate strong performance with mAP(IoU[0.5]) of 90.77 ± 0.68% and mAP(IoU[0.5:0.95]) of 70.20 ± 0.33%. Real-world highway tests confirm recognition rates of 96% for construction vehicles, 92% for roadside warning signs, and 84% for flag bearers. The results validate the framework’s suitability for real-time deployment in intelligent transportation systems.

Schlagwörter

Stichwörter der Autor:innen

YOLOv8autonomous drivingconstruction vehicledata augmentationmotion-temporal attentionobject detectionwarning sign

Autor:innen und Institutionen

  • Department of Electrical Engineering, Chang Gung University, Taoyuan 33303, Taiwan.
  • Department of Electrical Engineering, Ming Chi University of Technology, New Taipei City 243303, Taiwan.
  • Department of Photonics, Feng Chia University, Taichung 40724, Taiwan.

ORCID-Profile: Wen-Piao Lin

Förderung

  • Project of Chang Gung University

Zitieren

APA

Lin, W. P., Wang, C. C., Li, E. C., & Yeh, C. H. (2025). Enhanced Real-Time Highway Object Detection for Construction Zone Safety Using YOLOv8s-MTAM. Sensors, 25(20), 6420. https://doi.org/10.3390/s25206420

Vancouver

Lin WP, Wang CC, Li EC, Yeh CH. Enhanced Real-Time Highway Object Detection for Construction Zone Safety Using YOLOv8s-MTAM. Sensors. 2025;25(20):6420. doi:10.3390/s25206420

BibTeX
@article{Lin2025,
  author = {Lin, Wen-Piao and Wang, Chun-Chieh and Li, En-Cheng and Yeh, Chien-Hung},
  title = {Enhanced Real-Time Highway Object Detection for Construction Zone Safety Using YOLOv8s-MTAM},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {20},
  pages = {6420},
  doi = {10.3390/s25206420}
}
Kostenlos starten →