Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Restoring circadian disrupted gut microbial metabolite rhythms with phytochemicals: a new avenue against metabolic disease.

Frontiers in microbiology·2026
Same author

Investigation of monotherapeutic high-intensity focused ultrasound therapy for thrombolysis in highly occluded vessels: an<i>in vitro</i>study.

Physics in medicine and biology·2026
Same author

Association of oral frailty and its dimensions with cognitive impairment among older adults in China: a cross-sectional study.

BMC oral health·2026
Same author

Triphenylphosphine bromide enhances the effect of nano-micellar drug delivery system loaded with ROS inhibitor TEMPO on acute lung injury.

Journal of biological engineering·2026
Same author

Prevalence and associated factors of obstructive sleep apnea in patients with pneumoconiosis: a cross-sectional study.

BMC pulmonary medicine·2026
Same author

DGHME:A Hierarchical Hybrid Expert Multi-task Learning Model for Disease Grouping in Diabetes Complication Prediction.

IEEE journal of biomedical and health informatics·2026

Related Experiment Video

Updated: Dec 25, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

936

Hardhat-Wearing Detection Based on a Lightweight Convolutional Neural Network with Multi-Scale Features and a

Lu Wang1,2, Liangbin Xie1, Peiyu Yang1

  • 1School of Computer Science and Engineering, Northeastern University, Shenyang 110016, China.

Sensors (Basel, Switzerland)
|April 2, 2020
PubMed
Summary

This study introduces a real-time automatic detector using a convolutional neural network to identify construction workers not wearing hardhats. The system achieves high accuracy, improving safety by enabling timely alerts for non-compliance.

Keywords:
convolutional neural networkhardhat-wearing detectionreal-time detection

More Related Videos

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

5.1K
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.8K

Related Experiment Videos

Last Updated: Dec 25, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

936
Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

5.1K
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.8K

Area of Science:

  • Computer Vision
  • Artificial Intelligence
  • Occupational Safety

Background:

  • Construction sites pose significant safety risks due to complex interactions.
  • Hardhats are essential personal protective equipment (PPE) for worker safety.
  • Manual inspection for hardhat compliance is inefficient and costly.

Purpose of the Study:

  • To develop an automated, real-time system for detecting workers not wearing hardhats.
  • To improve construction site safety through immediate identification and alerts.
  • To provide an efficient alternative to manual safety inspections.

Main Methods:

  • An end-to-end convolutional neural network (CNN) was designed for hardhat detection.
  • MobileNet was utilized as the backbone for real-time processing capabilities.
  • A top-down module enhanced feature extraction, and a residual-block-based module performed multi-scale detection.

Main Results:

  • The proposed method achieved an average precision of 87.4% for detecting workers without hardhats.
  • An average precision of 89.4% was obtained for detecting workers with hardhats.
  • The system operated at a speed of 62 frames per second, enabling real-time application.

Conclusions:

  • The developed CNN model effectively detects hardhat compliance in real-time.
  • The system offers a viable, automated solution for enhancing safety on construction sites.
  • This technology can significantly reduce risks associated with non-compliance of safety regulations.