PERFORMANCE EVALUATION OF LIGHTWEIGHT OBJECT DETECTION MODELS FOR REAL-TIME PERSONAL PROTECTIVE EQUIPMENT DETECTION IN THE CONSTRUCTION SITES

The environment of construction industry was known to have a high risk and high number of occupational accidents and injuries. One of the main causes of the occurrences was the construction workers' negligence in wearing personal protection equipment. Computer vision-based approaches were deve...

Full description

Saved in:
Bibliographic Details
Main Authors: Herman, Sandy Alferro Dion, Andik Yulianto
Format: Article
Language:English
Published: Universitas Serang Raya 2025-03-01
Series:JSiI (Jurnal Sistem Informasi)
Online Access:https://e-jurnal.lppmunsera.org:443/index.php/jsii/article/view/9896
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849391587519365120
author Herman
Sandy Alferro Dion
Andik Yulianto
author_facet Herman
Sandy Alferro Dion
Andik Yulianto
author_sort Herman
collection DOAJ
description The environment of construction industry was known to have a high risk and high number of occupational accidents and injuries. One of the main causes of the occurrences was the construction workers' negligence in wearing personal protection equipment. Computer vision-based approaches were developed to assist in personal protective equipment adherence to address this issue. Using lightweight machine learning algorithms, object recognition can help to detect if the PPEs are worn correctly. We evaluated performance of YOLOv8-Nano and YOLOv9-Tiny (state of the art lightweight object detection models). Custom dataset was used for training the models and then metrics like F1 score, precision, recall mAP50 and mAP50-95 were used to evaluate both models’ performance. Results found that both models were able to show promising real time detections, but the YOLOv9-Tiny model was able to outperform the YOLOv8-Nano model on many evaluation metrics. Specifically, in terms of mAP, YOLOv8-Nano achieved an mAP50 of 81.48, while YOLOv9-Tiny attained a slightly higher mAP50 of 82.70. Higher efficiency in these parameters will help small industry to enforce PPE adherence monitoring using edge device at a relatively low cost. Lastly, enhanced enforcement of PPE regulations through automated detection system can contribute to improve workplace safety which in turns will lead to less injuries.   Keywords: Object Recognition, Computer Vision, Machine Learning, Lightweight, Personal Protective Equipment, YOLO
format Article
id doaj-art-843db7f3615e4c9fa795fdf4eb747b98
institution Kabale University
issn 2406-7768
2581-2181
language English
publishDate 2025-03-01
publisher Universitas Serang Raya
record_format Article
series JSiI (Jurnal Sistem Informasi)
spelling doaj-art-843db7f3615e4c9fa795fdf4eb747b982025-08-20T03:41:01ZengUniversitas Serang RayaJSiI (Jurnal Sistem Informasi)2406-77682581-21812025-03-01120110.30656/jsii.v12i1.9896PERFORMANCE EVALUATION OF LIGHTWEIGHT OBJECT DETECTION MODELS FOR REAL-TIME PERSONAL PROTECTIVE EQUIPMENT DETECTION IN THE CONSTRUCTION SITESHerman0Sandy Alferro Dion1Andik Yulianto2Universitas Internasional BatamUniversitas Internasional BatamUniversitas Internasional Batam The environment of construction industry was known to have a high risk and high number of occupational accidents and injuries. One of the main causes of the occurrences was the construction workers' negligence in wearing personal protection equipment. Computer vision-based approaches were developed to assist in personal protective equipment adherence to address this issue. Using lightweight machine learning algorithms, object recognition can help to detect if the PPEs are worn correctly. We evaluated performance of YOLOv8-Nano and YOLOv9-Tiny (state of the art lightweight object detection models). Custom dataset was used for training the models and then metrics like F1 score, precision, recall mAP50 and mAP50-95 were used to evaluate both models’ performance. Results found that both models were able to show promising real time detections, but the YOLOv9-Tiny model was able to outperform the YOLOv8-Nano model on many evaluation metrics. Specifically, in terms of mAP, YOLOv8-Nano achieved an mAP50 of 81.48, while YOLOv9-Tiny attained a slightly higher mAP50 of 82.70. Higher efficiency in these parameters will help small industry to enforce PPE adherence monitoring using edge device at a relatively low cost. Lastly, enhanced enforcement of PPE regulations through automated detection system can contribute to improve workplace safety which in turns will lead to less injuries.   Keywords: Object Recognition, Computer Vision, Machine Learning, Lightweight, Personal Protective Equipment, YOLO https://e-jurnal.lppmunsera.org:443/index.php/jsii/article/view/9896
spellingShingle Herman
Sandy Alferro Dion
Andik Yulianto
PERFORMANCE EVALUATION OF LIGHTWEIGHT OBJECT DETECTION MODELS FOR REAL-TIME PERSONAL PROTECTIVE EQUIPMENT DETECTION IN THE CONSTRUCTION SITES
JSiI (Jurnal Sistem Informasi)
title PERFORMANCE EVALUATION OF LIGHTWEIGHT OBJECT DETECTION MODELS FOR REAL-TIME PERSONAL PROTECTIVE EQUIPMENT DETECTION IN THE CONSTRUCTION SITES
title_full PERFORMANCE EVALUATION OF LIGHTWEIGHT OBJECT DETECTION MODELS FOR REAL-TIME PERSONAL PROTECTIVE EQUIPMENT DETECTION IN THE CONSTRUCTION SITES
title_fullStr PERFORMANCE EVALUATION OF LIGHTWEIGHT OBJECT DETECTION MODELS FOR REAL-TIME PERSONAL PROTECTIVE EQUIPMENT DETECTION IN THE CONSTRUCTION SITES
title_full_unstemmed PERFORMANCE EVALUATION OF LIGHTWEIGHT OBJECT DETECTION MODELS FOR REAL-TIME PERSONAL PROTECTIVE EQUIPMENT DETECTION IN THE CONSTRUCTION SITES
title_short PERFORMANCE EVALUATION OF LIGHTWEIGHT OBJECT DETECTION MODELS FOR REAL-TIME PERSONAL PROTECTIVE EQUIPMENT DETECTION IN THE CONSTRUCTION SITES
title_sort performance evaluation of lightweight object detection models for real time personal protective equipment detection in the construction sites
url https://e-jurnal.lppmunsera.org:443/index.php/jsii/article/view/9896
work_keys_str_mv AT herman performanceevaluationoflightweightobjectdetectionmodelsforrealtimepersonalprotectiveequipmentdetectionintheconstructionsites
AT sandyalferrodion performanceevaluationoflightweightobjectdetectionmodelsforrealtimepersonalprotectiveequipmentdetectionintheconstructionsites
AT andikyulianto performanceevaluationoflightweightobjectdetectionmodelsforrealtimepersonalprotectiveequipmentdetectionintheconstructionsites