Lightweight detection model for safe wear at worksites using GPD-YOLOv8 algorithm
Abstract To address the significantly elevated safety risks associated with construction workers’ improper use of helmets and reflective clothing, we propose an enhanced YOLOv8 model tailored for safety wear detection. Firstly, this study introduces the P2 detection layer within the YOLOv8 architect...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-024-83391-7 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841544857719406592 |
|---|---|
| author | Jian Xing Chenglong Zhan Jiaqiang Ma Zibo Chao Ying Liu |
| author_facet | Jian Xing Chenglong Zhan Jiaqiang Ma Zibo Chao Ying Liu |
| author_sort | Jian Xing |
| collection | DOAJ |
| description | Abstract To address the significantly elevated safety risks associated with construction workers’ improper use of helmets and reflective clothing, we propose an enhanced YOLOv8 model tailored for safety wear detection. Firstly, this study introduces the P2 detection layer within the YOLOv8 architecture, which substantially enriches semantic feature representation. Additionally, a lightweight Ghost module is integrated to replace the original backbone of YOLOv8, thereby reducing the parameter count and computational burden. Moreover, we incorporate a Dynamic Head (Dyhead) that employs an attention mechanism to effectively extract features and spatial location information critical for site safety wear detection. This adaptation significantly enhances the model’s representational power without adding computational overhead. Furthermore, we adopt an Exponential Moving Average (EMA) SlideLoss function, which not only boosts accuracy but also ensures the stability of our safety wear detection model’s performance. Comparative evaluation of the experimental results indicates that our proposed model achieves a 6.2% improvement in mean Average Precision (mAP) compared to the baseline YOLOv8 model, while also increasing the detection speed by 55.88% in terms of frames per second (FPS). |
| format | Article |
| id | doaj-art-f516d49d3af1446f8347b35a6b8b854d |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-f516d49d3af1446f8347b35a6b8b854d2025-01-12T12:16:34ZengNature PortfolioScientific Reports2045-23222025-01-0115111310.1038/s41598-024-83391-7Lightweight detection model for safe wear at worksites using GPD-YOLOv8 algorithmJian Xing0Chenglong Zhan1Jiaqiang Ma2Zibo Chao3Ying Liu4School of Electronic Information Technology, Northeast Forestry UniversitySchool of Electronic Information Technology, Northeast Forestry UniversitySchool of Electronic Information Technology, Northeast Forestry UniversitySchool of Electronic Information Technology, Northeast Forestry UniversitySchool of Electronic Information Technology, Northeast Forestry UniversityAbstract To address the significantly elevated safety risks associated with construction workers’ improper use of helmets and reflective clothing, we propose an enhanced YOLOv8 model tailored for safety wear detection. Firstly, this study introduces the P2 detection layer within the YOLOv8 architecture, which substantially enriches semantic feature representation. Additionally, a lightweight Ghost module is integrated to replace the original backbone of YOLOv8, thereby reducing the parameter count and computational burden. Moreover, we incorporate a Dynamic Head (Dyhead) that employs an attention mechanism to effectively extract features and spatial location information critical for site safety wear detection. This adaptation significantly enhances the model’s representational power without adding computational overhead. Furthermore, we adopt an Exponential Moving Average (EMA) SlideLoss function, which not only boosts accuracy but also ensures the stability of our safety wear detection model’s performance. Comparative evaluation of the experimental results indicates that our proposed model achieves a 6.2% improvement in mean Average Precision (mAP) compared to the baseline YOLOv8 model, while also increasing the detection speed by 55.88% in terms of frames per second (FPS).https://doi.org/10.1038/s41598-024-83391-7Deep learningSite safety wearable detectionYOLOv8Ghost module |
| spellingShingle | Jian Xing Chenglong Zhan Jiaqiang Ma Zibo Chao Ying Liu Lightweight detection model for safe wear at worksites using GPD-YOLOv8 algorithm Scientific Reports Deep learning Site safety wearable detection YOLOv8 Ghost module |
| title | Lightweight detection model for safe wear at worksites using GPD-YOLOv8 algorithm |
| title_full | Lightweight detection model for safe wear at worksites using GPD-YOLOv8 algorithm |
| title_fullStr | Lightweight detection model for safe wear at worksites using GPD-YOLOv8 algorithm |
| title_full_unstemmed | Lightweight detection model for safe wear at worksites using GPD-YOLOv8 algorithm |
| title_short | Lightweight detection model for safe wear at worksites using GPD-YOLOv8 algorithm |
| title_sort | lightweight detection model for safe wear at worksites using gpd yolov8 algorithm |
| topic | Deep learning Site safety wearable detection YOLOv8 Ghost module |
| url | https://doi.org/10.1038/s41598-024-83391-7 |
| work_keys_str_mv | AT jianxing lightweightdetectionmodelforsafewearatworksitesusinggpdyolov8algorithm AT chenglongzhan lightweightdetectionmodelforsafewearatworksitesusinggpdyolov8algorithm AT jiaqiangma lightweightdetectionmodelforsafewearatworksitesusinggpdyolov8algorithm AT zibochao lightweightdetectionmodelforsafewearatworksitesusinggpdyolov8algorithm AT yingliu lightweightdetectionmodelforsafewearatworksitesusinggpdyolov8algorithm |