Real-time safety helmet detection using enhanced YOLOv5 object detection
Personal Protective Equipment (PPE) regulations require construction workers to wear safety helmets to ensure site safety. However, monitoring PPE compliance consistently in fast-paced, dynamic construction environments poses a significant challenge. In response, we developed a sophisticated object...
Saved in:
Main Authors: | , , , , , |
---|---|
Format: | Proceeding Paper |
Language: | English English |
Published: |
IEEE
2023
|
Subjects: | |
Online Access: | http://irep.iium.edu.my/110164/1/110164_Real-time%20safety%20helmet%20detection.pdf http://irep.iium.edu.my/110164/7/110164_Real-Time%20Safety%20Helmet%20Detection%20Using%20Enhanced%20YOLOv5%20Object%20Detection_SCOPUS.pdf http://irep.iium.edu.my/110164/ https://ieeexplore.ieee.org/abstract/document/10373456 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
my.iium.irep.110164 |
---|---|
record_format |
dspace |
spelling |
my.iium.irep.1101642024-05-21T03:26:48Z http://irep.iium.edu.my/110164/ Real-time safety helmet detection using enhanced YOLOv5 object detection Muhammad Zamri, Fatin Najihah Zulkurnain, Nurul Fariza Gunawan, Teddy Surya Kartiwi, Mira Md Yusoff, Nelidya Nur, Levy Olivia TK7885 Computer engineering Personal Protective Equipment (PPE) regulations require construction workers to wear safety helmets to ensure site safety. However, monitoring PPE compliance consistently in fast-paced, dynamic construction environments poses a significant challenge. In response, we developed a sophisticated object detection system that automates the real-time verification of helmet use, thereby improving safety standards and reducing the likelihood of accidents. Extensive research was conducted to analyze all feasible algorithms that can be implemented in the safety helmet detection system and compare the proposed model with an existing one to ensure the proposed system can give high accuracy and high inference speed. Therefore, YOLOv5 was identified as the ideal choice in terms of accuracy and speed, and it was then enhanced with optimized transfer learning. We began our methodology by pre-training a comprehensive Kaggle dataset before refining the model using Roboflow on a specialized dataset. Using PyTorch and YOLOv5, we conducted exhaustive model training, testing, and evaluation. Our system achieved a lightning-fast inference speed of 39.8 milliseconds and a remarkable 91.4 percent accuracy in identifying helmet compliance. The implementation of such object detection technologies has the potential to significantly increase safety helmet compliance, thereby creating a safer environment for construction workers. IEEE 2023-10-18 Proceeding Paper PeerReviewed application/pdf en http://irep.iium.edu.my/110164/1/110164_Real-time%20safety%20helmet%20detection.pdf application/pdf en http://irep.iium.edu.my/110164/7/110164_Real-Time%20Safety%20Helmet%20Detection%20Using%20Enhanced%20YOLOv5%20Object%20Detection_SCOPUS.pdf Muhammad Zamri, Fatin Najihah and Zulkurnain, Nurul Fariza and Gunawan, Teddy Surya and Kartiwi, Mira and Md Yusoff, Nelidya and Nur, Levy Olivia (2023) Real-time safety helmet detection using enhanced YOLOv5 object detection. In: IEEE 9th International Conference on Smart Instrumentation, Measurement and Applications (ICSIMA 2023), 17th - 18th October 2023, Kuala Lumpur, Malaysia. https://ieeexplore.ieee.org/abstract/document/10373456 10.1109/ICSIMA59853.2023.10373456 |
institution |
Universiti Islam Antarabangsa Malaysia |
building |
IIUM Library |
collection |
Institutional Repository |
continent |
Asia |
country |
Malaysia |
content_provider |
International Islamic University Malaysia |
content_source |
IIUM Repository (IREP) |
url_provider |
http://irep.iium.edu.my/ |
language |
English English |
topic |
TK7885 Computer engineering |
spellingShingle |
TK7885 Computer engineering Muhammad Zamri, Fatin Najihah Zulkurnain, Nurul Fariza Gunawan, Teddy Surya Kartiwi, Mira Md Yusoff, Nelidya Nur, Levy Olivia Real-time safety helmet detection using enhanced YOLOv5 object detection |
description |
Personal Protective Equipment (PPE) regulations require construction workers to wear safety helmets to ensure site safety. However, monitoring PPE compliance consistently in fast-paced, dynamic construction environments poses a significant challenge. In response, we developed a sophisticated object detection system that automates the real-time verification of helmet use, thereby improving safety standards and reducing the likelihood of accidents. Extensive research was conducted to analyze all feasible algorithms that can be implemented in the safety helmet detection system and compare the proposed model with an existing one to ensure the proposed system can give high accuracy and high inference speed. Therefore, YOLOv5 was identified as the ideal choice in terms of accuracy and speed, and it was then enhanced with optimized transfer learning. We began our methodology by pre-training a comprehensive Kaggle dataset before refining the model using Roboflow on a specialized dataset. Using PyTorch and YOLOv5, we conducted exhaustive model training, testing, and evaluation. Our system achieved a lightning-fast inference speed of 39.8 milliseconds and a remarkable 91.4 percent accuracy in identifying helmet compliance. The implementation of such object detection technologies has the potential to significantly increase safety helmet compliance, thereby creating a safer environment for construction workers. |
format |
Proceeding Paper |
author |
Muhammad Zamri, Fatin Najihah Zulkurnain, Nurul Fariza Gunawan, Teddy Surya Kartiwi, Mira Md Yusoff, Nelidya Nur, Levy Olivia |
author_facet |
Muhammad Zamri, Fatin Najihah Zulkurnain, Nurul Fariza Gunawan, Teddy Surya Kartiwi, Mira Md Yusoff, Nelidya Nur, Levy Olivia |
author_sort |
Muhammad Zamri, Fatin Najihah |
title |
Real-time safety helmet detection using enhanced YOLOv5 object detection |
title_short |
Real-time safety helmet detection using enhanced YOLOv5 object detection |
title_full |
Real-time safety helmet detection using enhanced YOLOv5 object detection |
title_fullStr |
Real-time safety helmet detection using enhanced YOLOv5 object detection |
title_full_unstemmed |
Real-time safety helmet detection using enhanced YOLOv5 object detection |
title_sort |
real-time safety helmet detection using enhanced yolov5 object detection |
publisher |
IEEE |
publishDate |
2023 |
url |
http://irep.iium.edu.my/110164/1/110164_Real-time%20safety%20helmet%20detection.pdf http://irep.iium.edu.my/110164/7/110164_Real-Time%20Safety%20Helmet%20Detection%20Using%20Enhanced%20YOLOv5%20Object%20Detection_SCOPUS.pdf http://irep.iium.edu.my/110164/ https://ieeexplore.ieee.org/abstract/document/10373456 |
_version_ |
1800081778414714880 |
score |
13.160551 |