Next Article in Journal
Magnetoresistive Shunt as an Alternative to Wheatstone Bridge Sensors in Electrical Current Sensing
Previous Article in Journal
Survey of Deep Learning Accelerators for Edge and Emerging Computing
 
 
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Article

Real-Time Personal Protective Equipment Non-Compliance Recognition on AI Edge Cameras

by
Pubudu Sanjeewani
1,*,
Glenn Neuber
2,
John Fitzgerald
1,
Nadeesha Chandrasena
1,
Stijn Potums
1,
Azadeh Alavi
3 and
Christopher Lane
1
1
Research and Development, Smart AI Connect, Brisbane 4215, Australia
2
Research and Development, MaxusAI, Brisbane 4006, Australia
3
STEM College, School of Computing Technologies, RMIT University, Melbourne 3000, Australia
*
Author to whom correspondence should be addressed.
Electronics 2024, 13(15), 2990; https://doi.org/10.3390/electronics13152990 (registering DOI)
Submission received: 21 June 2024 / Revised: 15 July 2024 / Accepted: 24 July 2024 / Published: 29 July 2024

Abstract

Despite advancements in technology, safety equipment, and training within the construction industry over recent decades, the prevalence of fatal and nonfatal injuries and accidents remains a significant concern among construction workers. Hard hats and safety vests are crucial safety gear known to mitigate severe head trauma and other injuries. However, adherence to safety protocols, including the use of such gear, is often inadequate, posing potential risks to workers. Moreover, current manual safety monitoring systems are laborious and time-consuming. To address these challenges and enhance workplace safety, there is a pressing need to automate safety monitoring processes economically, with reduced processing times. This research proposes a deep learning-based pipeline for real-time identification of non-compliance with wearing hard hats and safety vests, enabling safety officers to preempt hazards and mitigate risks at construction sites. We evaluate various neural networks for edge deployment and find that the Single Shot Multibox Detector (SSD) MobileNet V2 model excels in computational efficiency, making it particularly suitable for this application-oriented task. The experiments and comparative analyses demonstrate the pipeline's effectiveness in accurately identifying instances of non-compliance across different scenarios, underscoring its potential for improving safety outcomes.
Keywords: instance segmentation; object detection; edge computing; personal protective equipment; deep learning; real-time AI instance segmentation; object detection; edge computing; personal protective equipment; deep learning; real-time AI

Share and Cite

MDPI and ACS Style

Sanjeewani, P.; Neuber, G.; Fitzgerald, J.; Chandrasena, N.; Potums, S.; Alavi, A.; Lane, C. Real-Time Personal Protective Equipment Non-Compliance Recognition on AI Edge Cameras. Electronics 2024, 13, 2990. https://doi.org/10.3390/electronics13152990

AMA Style

Sanjeewani P, Neuber G, Fitzgerald J, Chandrasena N, Potums S, Alavi A, Lane C. Real-Time Personal Protective Equipment Non-Compliance Recognition on AI Edge Cameras. Electronics. 2024; 13(15):2990. https://doi.org/10.3390/electronics13152990

Chicago/Turabian Style

Sanjeewani, Pubudu, Glenn Neuber, John Fitzgerald, Nadeesha Chandrasena, Stijn Potums, Azadeh Alavi, and Christopher Lane. 2024. "Real-Time Personal Protective Equipment Non-Compliance Recognition on AI Edge Cameras" Electronics 13, no. 15: 2990. https://doi.org/10.3390/electronics13152990

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Article metric data becomes available approximately 24 hours after publication online.
Back to TopTop