Safety Helmet Detection Using Deep Learning: Implementation and Comparative Study Using YOLOv5, YOLOv6, and YOLOv7

Nigel Dale Then Yung*, W. K. Wong, Filbert H. Juwono, Zee Ang Sim

*Corresponding author for this work

Research output: Chapter in Book or Report/Conference proceedingConference Proceedingpeer-review

29 Citations (Scopus)

Abstract

The safety of construction site personnel is highly dependent on the adherence of personal protective equipment (PPE) wearing. Safety helmet monitoring has become a popular topic in recent years as a result of the success in the field of image processing. Deep learning (DL) is widely used in object detection tasks due to its ability to create features based on raw data. Constant improvements in the DL models have led to numerous successful outcomes in the implementation of safety helmet detection tasks. The performance of different DL algorithms from previous studies will be assessed and studied in this review paper. The YOLOv5s (small) model, YOLOv6s (small) model, and the YOLOv7 model will be trained and evaluated in this paper.

Original languageEnglish
Title of host publication2022 International Conference on Green Energy, Computing and Sustainable Technology, GECOST 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages164-170
Number of pages7
ISBN (Electronic)9781665486637
DOIs
Publication statusPublished - 2022
Externally publishedYes
Event2022 International Conference on Green Energy, Computing and Sustainable Technology, GECOST 2022 - Virtual, Online, Malaysia
Duration: 26 Oct 202228 Oct 2022

Publication series

Name2022 International Conference on Green Energy, Computing and Sustainable Technology, GECOST 2022

Conference

Conference2022 International Conference on Green Energy, Computing and Sustainable Technology, GECOST 2022
Country/TerritoryMalaysia
CityVirtual, Online
Period26/10/2228/10/22

Keywords

  • YOLOv5
  • YOLOv6
  • YOLOv7
  • deep learning
  • safety helmet detection

Fingerprint

Dive into the research topics of 'Safety Helmet Detection Using Deep Learning: Implementation and Comparative Study Using YOLOv5, YOLOv6, and YOLOv7'. Together they form a unique fingerprint.

Cite this