EUVIMEDEUVIMED entdecken
Crossref

CF-YOLO: Cross Fusion YOLO for Object Detection in Adverse Weather With a High-Quality Real Snow Dataset

Qiqi Ding, Peng Li, Xuefeng Yan, Ding Shi, Luming Liang, Weiming Wang, Haoran Xie, Jonathan Li, Mingqiang Wei

IEEE Transactions on Intelligent Transportation Systems · 2023-10 · 24 (10) · 10749-10759

DOI: 10.1109/tits.2023.3285035 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Intelligent Transportation Systems, 2023-10. Verfasst von Qiqi Ding und 8 weiteren Autor:innen. Die Arbeit wurde bisher 88-mal zitiert (Crossref) und nennt 43 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Shenzhen Science and Technology Program, Natural Science Foundation of Guangdong Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Snow is one of the toughest adverse weather conditions for object detection (OD). Currently, not only there is a lack of snowy OD datasets to train cutting-edge detectors, but also these detectors have difficulties of learning latent information beneficial for detection in snow. To alleviate the two above problems, we first establish a real-world snowy OD dataset, named RSOD. Besides, we develop an unsupervised training strategy with a distinctive activation function, called $Peak Act$ , to quantitatively evaluate the effect of snow on each object. Peak Act helps grade the images in RSOD into four-difficulty levels. To our knowledge, RSOD is the first quantitatively evaluated and graded real-world snowy OD dataset. Then, we propose a novel Cross Fusion (CF) block to construct a lightweight OD network based on YOLOv5s (called CF-YOLO). CF is a plug-and-play feature aggregation module, which integrates the advantages of Feature Pyramid Network and Path Aggregation Network in a simpler yet more flexible form. Both RSOD and CF lead our CF-YOLO to possess an optimization ability for OD in real-world snow. That is, CF-YOLO can handle unfavorable detection problems of vagueness, distortion and covering of snow. Experiments show that our CF-YOLO achieves better detection results on RSOD, compared to SOTAs. The code and dataset are available at https://github.com/qqding77/CF-YOLO-and-RSOD.

Förderung

  • National Natural Science Foundation of China
  • Shenzhen Science and Technology Program
  • Natural Science Foundation of Guangdong Province
  • Hong Kong Metropolitan University Research Grant
  • Direct Grant
  • Faculty Research Grant of Lingnan University, Hong Kong

Zitieren

APA

Ding, Q., Li, P., Yan, X., Shi, D., Liang, L., Wang, W., Xie, H., Li, J., & Wei, M. (2023). CF-YOLO: Cross Fusion YOLO for Object Detection in Adverse Weather With a High-Quality Real Snow Dataset. IEEE Transactions on Intelligent Transportation Systems, 24(10), 10749-10759. https://doi.org/10.1109/tits.2023.3285035

Vancouver

Ding Q, Li P, Yan X, Shi D, Liang L, Wang W, et al. CF-YOLO: Cross Fusion YOLO for Object Detection in Adverse Weather With a High-Quality Real Snow Dataset. IEEE Transactions on Intelligent Transportation Systems. 2023;24(10):10749-10759. doi:10.1109/tits.2023.3285035

BibTeX
@article{Ding2023,
  author = {Ding, Qiqi and Li, Peng and Yan, Xuefeng and Shi, Ding and Liang, Luming and Wang, Weiming and Xie, Haoran and Li, Jonathan and Wei, Mingqiang},
  title = {CF-YOLO: Cross Fusion YOLO for Object Detection in Adverse Weather With a High-Quality Real Snow Dataset},
  journal = {IEEE Transactions on Intelligent Transportation Systems},
  year = {2023},
  volume = {24},
  number = {10},
  pages = {10749--10759},
  doi = {10.1109/tits.2023.3285035}
}
Kostenlos starten →