EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

TS-YOLO: a lightweight real-time traffic sign detector in resource-constrained environments

Hongxia Yu, Wenhui Liu, Tongwei Xu

PeerJ Computer Science · 03.11.2025 · 11 · e3268

DOI: 10.7717/peerj-cs.3268 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PeerJ Computer Science, online erschienen am 03.11.2025. Verfasst von Hongxia Yu und 2 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 62 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Yunnan Provincial Department of Education Science Research Fund Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Traffic sign detection is essential for ensuring driving safety in autonomous vehicles and advanced driver-assistance systems, particularly under limited computational resources and challenging real-world conditions such as extreme weather, occlusion, and diverse viewing angles. To address the trade-off between detection accuracy and computational efficiency, we propose TS-YOLO, a lightweight, real-time detector built on You Only Look Once version 8 (YOLOv8). TS-YOLO integrates a Repetition Cross Stage Partial (RepCSP) feature-enhancement module and a set of targeted training strategies designed to improve small-object recognition and to handle various challenging scenarios. Experimental results on the CCTSDB2021 dataset show that TS-YOLO achieves 98.4% mean Average Precision (mAP)@0.5 and 79.1% mAP@0.95, with an inference time of only 0.6 ms per frame on embedded hardware. Compared to state-of-the-art methods—including Faster Region-based Convolutional Neural Network (Faster R-CNN), Efficient Object Detection (EfficientDet), and the original YOLOv8—TS-YOLO demonstrates superior accuracy and faster inference. Further robustness evaluations confirm consistent performance across adverse weather (fog, rain, low light), various road types (urban, rural, unstructured), and challenging object characteristics (scale variation, occlusion, irregular shapes). These findings suggest that TS-YOLO is a practical, high-performance solution for traffic sign detection in resource-constrained, complex driving environments.

Förderung

  • Yunnan Provincial Department of Education Science Research Fund Project

Zitieren

APA

Yu, H., Liu, W., & Xu, T. (2025). TS-YOLO: a lightweight real-time traffic sign detector in resource-constrained environments. PeerJ Computer Science, 11, e3268. https://doi.org/10.7717/peerj-cs.3268

Vancouver

Yu H, Liu W, Xu T. TS-YOLO: a lightweight real-time traffic sign detector in resource-constrained environments. PeerJ Computer Science. 2025;11:e3268. doi:10.7717/peerj-cs.3268

BibTeX
@article{Yu2025,
  author = {Yu, Hongxia and Liu, Wenhui and Xu, Tongwei},
  title = {TS-YOLO: a lightweight real-time traffic sign detector in resource-constrained environments},
  journal = {PeerJ Computer Science},
  year = {2025},
  volume = {11},
  pages = {e3268},
  doi = {10.7717/peerj-cs.3268}
}
Kostenlos starten →