LG-YOLOv8: A Lightweight Safety Helmet Detection Algorithm Combined with Feature Enhancement

In the realm of construction site monitoring, ensuring the proper use of safety helmets is crucial. Addressing the issues of high parameter values and sluggish detection speed in current safety helmet detection algorithms, a feature-enhanced lightweight algorithm, LG-YOLOv8, was introduced. Firstly,...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhipeng Fan, Yayun Wu, Wei Liu, Ming Chen, Zeguo Qiu
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/14/22/10141
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846154520938151936
author Zhipeng Fan
Yayun Wu
Wei Liu
Ming Chen
Zeguo Qiu
author_facet Zhipeng Fan
Yayun Wu
Wei Liu
Ming Chen
Zeguo Qiu
author_sort Zhipeng Fan
collection DOAJ
description In the realm of construction site monitoring, ensuring the proper use of safety helmets is crucial. Addressing the issues of high parameter values and sluggish detection speed in current safety helmet detection algorithms, a feature-enhanced lightweight algorithm, LG-YOLOv8, was introduced. Firstly, we introduce C2f-GhostDynamicConv as a powerful tool. This module enhances feature extraction to represent safety helmet wearing features, aiming to improve the efficiency of computing resource utilization. Secondly, the Bi-directional Feature Pyramid (BiFPN) was employed to further enrich the feature information, integrating feature maps from various levels to achieve more comprehensive semantic information. Finally, to enhance the training speed of the model and achieve a more lightweight outcome, we introduce a novel lightweight asymmetric detection head (LADH-Head) to optimize the original YOLOv8-n’s detection head. Evaluations on the SWHD dataset confirm the effectiveness of the LG-YOLOv8 algorithm. Compared to the original YOLOv8-n algorithm, our approach achieves a mean Average Precision (mAP) of 94.1%, a 59.8% reduction in parameters, a 54.3% decrease in FLOPs, a 44.2% increase in FPS, and a 2.7 MB compression of the model size. Therefore, LG-YOLOv8 has high accuracy and fast detection speed for safety helmet detection, which realizes real-time accurate detection of safety helmets and an ideal lightweight effect.
format Article
id doaj-art-1a9e19e1fd8a4b6dbba543df8d6a267c
institution Kabale University
issn 2076-3417
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-1a9e19e1fd8a4b6dbba543df8d6a267c2024-11-26T17:47:38ZengMDPI AGApplied Sciences2076-34172024-11-0114221014110.3390/app142210141LG-YOLOv8: A Lightweight Safety Helmet Detection Algorithm Combined with Feature EnhancementZhipeng Fan0Yayun Wu1Wei Liu2Ming Chen3Zeguo Qiu4School of Computer and Information Engineering, Harbin University of Commerce, Harbin 150028, ChinaSchool of Computer and Information Engineering, Harbin University of Commerce, Harbin 150028, ChinaSchool of Computer and Information Engineering, Harbin University of Commerce, Harbin 150028, ChinaSchool of Computer and Information Engineering, Harbin University of Commerce, Harbin 150028, ChinaSchool of Computer and Information Engineering, Harbin University of Commerce, Harbin 150028, ChinaIn the realm of construction site monitoring, ensuring the proper use of safety helmets is crucial. Addressing the issues of high parameter values and sluggish detection speed in current safety helmet detection algorithms, a feature-enhanced lightweight algorithm, LG-YOLOv8, was introduced. Firstly, we introduce C2f-GhostDynamicConv as a powerful tool. This module enhances feature extraction to represent safety helmet wearing features, aiming to improve the efficiency of computing resource utilization. Secondly, the Bi-directional Feature Pyramid (BiFPN) was employed to further enrich the feature information, integrating feature maps from various levels to achieve more comprehensive semantic information. Finally, to enhance the training speed of the model and achieve a more lightweight outcome, we introduce a novel lightweight asymmetric detection head (LADH-Head) to optimize the original YOLOv8-n’s detection head. Evaluations on the SWHD dataset confirm the effectiveness of the LG-YOLOv8 algorithm. Compared to the original YOLOv8-n algorithm, our approach achieves a mean Average Precision (mAP) of 94.1%, a 59.8% reduction in parameters, a 54.3% decrease in FLOPs, a 44.2% increase in FPS, and a 2.7 MB compression of the model size. Therefore, LG-YOLOv8 has high accuracy and fast detection speed for safety helmet detection, which realizes real-time accurate detection of safety helmets and an ideal lightweight effect.https://www.mdpi.com/2076-3417/14/22/10141safety helmet testinglightweight networkC2f-GhostDynamicConvBiFPNLADH-Head
spellingShingle Zhipeng Fan
Yayun Wu
Wei Liu
Ming Chen
Zeguo Qiu
LG-YOLOv8: A Lightweight Safety Helmet Detection Algorithm Combined with Feature Enhancement
Applied Sciences
safety helmet testing
lightweight network
C2f-GhostDynamicConv
BiFPN
LADH-Head
title LG-YOLOv8: A Lightweight Safety Helmet Detection Algorithm Combined with Feature Enhancement
title_full LG-YOLOv8: A Lightweight Safety Helmet Detection Algorithm Combined with Feature Enhancement
title_fullStr LG-YOLOv8: A Lightweight Safety Helmet Detection Algorithm Combined with Feature Enhancement
title_full_unstemmed LG-YOLOv8: A Lightweight Safety Helmet Detection Algorithm Combined with Feature Enhancement
title_short LG-YOLOv8: A Lightweight Safety Helmet Detection Algorithm Combined with Feature Enhancement
title_sort lg yolov8 a lightweight safety helmet detection algorithm combined with feature enhancement
topic safety helmet testing
lightweight network
C2f-GhostDynamicConv
BiFPN
LADH-Head
url https://www.mdpi.com/2076-3417/14/22/10141
work_keys_str_mv AT zhipengfan lgyolov8alightweightsafetyhelmetdetectionalgorithmcombinedwithfeatureenhancement
AT yayunwu lgyolov8alightweightsafetyhelmetdetectionalgorithmcombinedwithfeatureenhancement
AT weiliu lgyolov8alightweightsafetyhelmetdetectionalgorithmcombinedwithfeatureenhancement
AT mingchen lgyolov8alightweightsafetyhelmetdetectionalgorithmcombinedwithfeatureenhancement
AT zeguoqiu lgyolov8alightweightsafetyhelmetdetectionalgorithmcombinedwithfeatureenhancement