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

Detection of Black Holes01:10

Detection of Black Holes

2.2K
Although black holes were theoretically postulated in the 1920s, they remained outside the domain of observational astronomy until the 1970s.
Their closest cousins are neutron stars, which are composed almost entirely of neutrons packed against each other, making them extremely dense. A neutron star has the same mass as the Sun but its diameter is only a few kilometers. Therefore, the escape velocity from their surface is close to the speed of light.
Not until the 1960s, when the first neutron...
2.2K
Force Classification01:22

Force Classification

1.2K
Forces play a crucial role in the study of physics and engineering. They are essential in describing the motion, behavior, and equilibrium of objects in the physical world. Forces can be classified based on their origin, type, and direction of action.
Contact and non-contact forces are two of the most widely used categories of forces. As the name suggests, contact forces require physical contact between two objects to act upon each other. Examples of contact forces include frictional,...
1.2K

You might also read

Related Articles

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

Sort by
Same author

A novel object detection algorithm based on Swin Transformer.

Scientific reports·2026
See all related articles

Related Experiment Video

Updated: Jul 13, 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

568

A new method for safety helmet detection based on convolutional neural network.

YueJing Qian1, Bo Wang2

  • 1Zhejiang Industry and Trade Vocational College, Wenzhou, Zhejiang, China.

Plos One
|October 13, 2023
PubMed
Summary
This summary is machine-generated.

This study introduces an optimized YOLOv5 model for efficient safety helmet detection on devices with limited computing power. The enhanced model achieves faster inference speeds and improved accuracy for construction safety applications.

More Related Videos

A Test Bed to Examine Helmet Fit and Retention and Biomechanical Measures of Head and Neck Injury in Simulated Impact
07:30

A Test Bed to Examine Helmet Fit and Retention and Biomechanical Measures of Head and Neck Injury in Simulated Impact

Published on: September 21, 2017

9.0K
Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

10.7K

Related Experiment Videos

Last Updated: Jul 13, 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

568
A Test Bed to Examine Helmet Fit and Retention and Biomechanical Measures of Head and Neck Injury in Simulated Impact
07:30

A Test Bed to Examine Helmet Fit and Retention and Biomechanical Measures of Head and Neck Injury in Simulated Impact

Published on: September 21, 2017

9.0K
Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

10.7K

Area of Science:

  • Computer Vision
  • Artificial Intelligence
  • Engineering Safety

Background:

  • Designing robust safety helmet detection methods for engineering projects is challenging due to hardware cost and limited computing power on mobile/embedded devices.
  • Existing methods often struggle to balance accuracy and efficiency for real-time applications in resource-constrained environments.

Purpose of the Study:

  • To develop an optimized safety helmet detection method that is efficient and implementable on devices with limited computing power.
  • To improve the accuracy and inference speed of safety helmet detection systems for practical engineering applications.

Main Methods:

  • Optimized the BottleneckCSP structure within the YOLOv5 backbone network to reduce model complexity without altering input/output dimensions.
  • Designed an upsampling feature enhancement module to mitigate information loss during upsampling and boost semantic information.
  • Integrated a self-attention mechanism, including channel and location attention modules, for adaptive fusion of feature maps to enhance semantic and location precision.

Main Results:

  • The proposed method achieved a significantly faster inference speed, reaching 416 FPS, compared to existing fast methods under identical computational capabilities.
  • Demonstrated superior performance with a mean Average Precision (mAP) of 94.2%, indicating high detection accuracy.
  • The optimized model effectively reduces complexity while maintaining or improving detection performance.

Conclusions:

  • The developed approach offers an efficient and accurate solution for safety helmet detection on resource-limited devices.
  • The optimized YOLOv5 model with enhanced feature fusion and attention mechanisms provides a practical tool for improving safety in engineering projects.
  • This method addresses the trade-off between computational complexity and detection performance, making it suitable for real-world deployment.