CSW-YOLO: A traffic sign small target detection algorithm based on YOLOv8
PLOS ONE · 20.03.2025 · 20 (3) · e0315334
DOI: 10.1371/journal.pone.0315334 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS ONE, online erschienen am 20.03.2025. Verfasst von Qian Shen und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Automation, Huaiyin Institute of Technology, Huaian, Jiangsu, China. Hauptthemen laut MEDLINE: Automobile Driving, Detection Algorithms. Die Arbeit wurde bisher 17-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Huaian Municipality.
Abstract (Originalsprache)
In order to improve the real-time and feasibility of traffic sign detection for autonomous driving in complex traffic environments, this paper proposes a small target detection algorithm for traffic signs based on the YOLOv8 model. First, the bottleneck of the C2f module in the original yolov8 network is replaced with the residual Faster-Block module in FasterNet, and then the new channel mixer convolution GLU (CGLU) in TransNeXt is combined with it to construct the C2f-faster-CGLU module, reducing the number of model parameters and computational load; Secondly, the SPPF module is combined with the large separable kernel attention (LSKA) to construct the SPPF-LSKA module, which greatly enhances the feature extraction ability of the model; Then, by adding a small target detection layer, the accuracy of small target detection such as traffic signs is greatly improved; Finally, the Inner-IoU and MPDIoU loss functions are integrated to construct WISE-Inner-MPDIoU, which replaces the original CIoU loss function, thereby improving the calculation accuracy. The model has been validated on two datasets Tsinghua-Tencent 100K (TT100K) and CSUST Chinese Traffic Sign Detection Benchmark 2021 (CCTSDB 2021), achieving Map50 of 89.8% and 98.9% respectively. The model achieves precision on par with existing mainstream algorithms, while being simpler, significantly reducing computational requirements, and being more suitable for small target detection tasks. The source code and test results of the models used in this study are available at https://github.com/lyzzzzyy/CSW-YOLO.git.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- School of Automation, Huaiyin Institute of Technology, Huaian, Jiangsu, China.
- Intelligent Energy Research Institute, Huaiyin Institute of Technology, Huaian, China.
ORCID-Profile: Qian Shen
Förderung
- National Natural Science Foundation of China
- Natural Science Foundation of Huaian Municipality
Zitieren
APA
Shen, Q., Li, Y., Zhang, Y., Zhang, L., Liu, S., & Wu, J. (2025). CSW-YOLO: A traffic sign small target detection algorithm based on YOLOv8. PLOS ONE, 20(3), e0315334. https://doi.org/10.1371/journal.pone.0315334
Vancouver
Shen Q, Li Y, Zhang Y, Zhang L, Liu S, Wu J. CSW-YOLO: A traffic sign small target detection algorithm based on YOLOv8. PLOS ONE. 2025;20(3):e0315334. doi:10.1371/journal.pone.0315334
BibTeX
@article{Shen2025,
author = {Shen, Qian and Li, Yi and Zhang, YuXiang and Zhang, Lei and Liu, ShiHao and Wu, Jinhua},
title = {CSW-YOLO: A traffic sign small target detection algorithm based on YOLOv8},
journal = {PLOS ONE},
year = {2025},
volume = {20},
number = {3},
pages = {e0315334},
doi = {10.1371/journal.pone.0315334}
}
EUVIMED