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

Qiqi DING, Peng LI, Xuefeng YAN, Luming LIANG, Weiming WANG, Haoran XIE, Jonathan LI, Mingqiang WEI

Research output: Journal PublicationsJournal Article (refereed)peer-review

24 Citations (Scopus)

Abstract

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.
Original languageEnglish
Pages (from-to)10749-10759
Number of pages11
JournalIEEE Transactions on Intelligent Transportation Systems
Volume24
Issue number10
Early online date22 Jun 2023
DOIs
Publication statusPublished - 1 Oct 2023

Bibliographical note

Publisher Copyright:
IEEE

Publisher Copyright:
© 2000-2011 IEEE.

Funding

This work was supported in part by the National Natural Science Foundation of China under Grant 62172218; in part by the Shenzhen Science and Technology Program under Grant JCYJ20220818103401003 and Grant JCYJ20220530172403007; in part by the Natural Science Foundation of Guangdong Province under Grant 2022A1515010170; in part by the Hong Kong Metropolitan University Research Grant under Grant RD/2021/09; in part by the Direct Grant under Grant DR23B2; and in part by the Faculty Research Grant of Lingnan University, Hong Kong, under Grant DB23A3 and Grant DB23B2.

Keywords

  • CF-YOLO
  • Detectors
  • Feature extraction
  • Kernel
  • Meteorology
  • Object detection
  • RSOD dataset
  • Snow
  • Training
  • cross fusion
  • peak act
  • snowy object detection

Fingerprint

Dive into the research topics of 'CF-YOLO : Cross Fusion YOLO for Object Detection in Adverse Weather With a High-Quality Real Snow Dataset'. Together they form a unique fingerprint.

Cite this