EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Enhanced object detection in low-visibility haze conditions with YOLOv9s

Yang Zhang, Bin Zhou iD, Xue Zhao, Xiaomeng Song

PLOS ONE · 24.02.2025 · 20 (2) · e0317852

DOI: 10.1371/journal.pone.0317852 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS ONE, online erschienen am 24.02.2025. Verfasst von Yang Zhang und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science and Technology, Shandong University of Technology, Zibo, Shandong, China. Hauptthemen laut MEDLINE: Algorithms, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 68 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Foundation of Shandong Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Low-visibility haze environments, marked by their inherent low contrast and high brightness, present a formidable challenge to the precision and robustness of conventional object detection algorithms. This paper introduces an enhanced object detection framework for YOLOv9s tailored for low-visibility haze conditions, capitalizing on the merits of contrastive learning for optimizing local feature details, as well as the benefits of multiscale attention mechanisms and dynamic focusing mechanisms for achieving real-time global quality optimization. Specifically, the framework incorporates Patchwise Contrastive Learning to fortify the correlation among positive samples within image patches, effectively reducing negative sample interference and enhancing the model’s capability to discern subtle local features of haze-impacted images. Additionally, the integration of Efficient Multi-Scale Attention and the Wise-IoU Dynamic Focusing Mechanism enhances the algorithm’s sensitivity to channel, spatial orientation, and locational information. Furthermore, the implementation of a nonmonotonic strategy for dynamically adjusting the loss function weights significantly boosts the model’s detection precision and training efficiency. Comprehensive experimental evaluations of the COCO2017 fog-augmented dataset indicate that the proposed algorithm surpasses current state-of-the-art techniques in various assessment metrics, including precision, recall, and mean average precision (mAP). Our source code is available at: https://github.com/PaTinLei/EOD .

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

AlgorithmsImage Processing, Computer-AssistedHumans

Autor:innen und Institutionen

  • School of Computer Science and Technology, Shandong University of Technology, Zibo, Shandong, China.

ORCID-Profile: Bin Zhou

Förderung

  • Natural Science Foundation of Shandong Province

Zitieren

APA

Zhang, Y., Zhou, B., Zhao, X., & Song, X. (2025). Enhanced object detection in low-visibility haze conditions with YOLOv9s. PLOS ONE, 20(2), e0317852. https://doi.org/10.1371/journal.pone.0317852

Vancouver

Zhang Y, Zhou B, Zhao X, Song X. Enhanced object detection in low-visibility haze conditions with YOLOv9s. PLOS ONE. 2025;20(2):e0317852. doi:10.1371/journal.pone.0317852

BibTeX
@article{Zhang2025,
  author = {Zhang, Yang and Zhou, Bin and Zhao, Xue and Song, Xiaomeng},
  title = {Enhanced object detection in low-visibility haze conditions with YOLOv9s},
  journal = {PLOS ONE},
  year = {2025},
  volume = {20},
  number = {2},
  pages = {e0317852},
  doi = {10.1371/journal.pone.0317852}
}
Kostenlos starten →