SD-YOLOv5: a rapid detection method for personal protective equipment on construction sites
With the rapid growth of urbanization, construction sites are increasingly confronted with severe safety hazards. Personal protective equipment (PPE), such as helmets and safety vests, plays a critical role in mitigating these risks; however, ensuring proper usage remains challenging. This paper pre...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-04-01
|
| Series: | Frontiers in Built Environment |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fbuil.2025.1563483/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850212204402442240 |
|---|---|
| author | ChunYa Li ChunYa Li Jianhua Wang Jianhua Wang Bingfeng Luo Tubing Yin Baohua Liu Baohua Liu Jianfei Lu |
| author_facet | ChunYa Li ChunYa Li Jianhua Wang Jianhua Wang Bingfeng Luo Tubing Yin Baohua Liu Baohua Liu Jianfei Lu |
| author_sort | ChunYa Li |
| collection | DOAJ |
| description | With the rapid growth of urbanization, construction sites are increasingly confronted with severe safety hazards. Personal protective equipment (PPE), such as helmets and safety vests, plays a critical role in mitigating these risks; however, ensuring proper usage remains challenging. This paper presents SD (Small object detection and DilateFormer attention mechanism)-YOLOv5s, an improved PPE detection algorithm based on YOLOv5s, designed to enhance the detection accuracy of small objects, such as helmets, in complex construction environments. The proposed model incorporates a dedicated feature layer for small target detection and integrates the DilateFormer attention mechanism to balance detection performance and computational efficiency. Experimental results on the CHV dataset demonstrate that SD-YOLOv5s achieves an average precision (AP) of 93.7%, representing an improvement of 2.8 percentage points over the baseline YOLOv5s (AP = 90.9%), while reducing the model’s parameter count by up to 14.6%. These quantitative improvements indicate that SD-YOLOv5s is a promising solution for real-time PPE monitoring on construction sites, although further validation on larger and more diverse datasets is warranted. |
| format | Article |
| id | doaj-art-0d5ad9a1c6d64d709324d2897cf265c9 |
| institution | OA Journals |
| issn | 2297-3362 |
| language | English |
| publishDate | 2025-04-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Built Environment |
| spelling | doaj-art-0d5ad9a1c6d64d709324d2897cf265c92025-08-20T02:09:24ZengFrontiers Media S.A.Frontiers in Built Environment2297-33622025-04-011110.3389/fbuil.2025.15634831563483SD-YOLOv5: a rapid detection method for personal protective equipment on construction sitesChunYa Li0ChunYa Li1Jianhua Wang2Jianhua Wang3Bingfeng Luo4Tubing Yin5Baohua Liu6Baohua Liu7Jianfei Lu8Wuhan University of Technology School of Management, Wuhan, ChinaShenzhen Yantian Port Real Estate Co., Ltd., Shenzhen, ChinaShenzhen Yantian Port Real Estate Co., Ltd., Shenzhen, ChinaCentral South University School of Resources and Safety Engineering, Changsha, ChinaShenzhen Port Group Co., Ltd., Shenzhen, ChinaCentral South University School of Resources and Safety Engineering, Changsha, ChinaShenzhen Yantian Port Real Estate Co., Ltd., Shenzhen, ChinaCentral South University School of Resources and Safety Engineering, Changsha, ChinaCentral South University School of Resources and Safety Engineering, Changsha, ChinaWith the rapid growth of urbanization, construction sites are increasingly confronted with severe safety hazards. Personal protective equipment (PPE), such as helmets and safety vests, plays a critical role in mitigating these risks; however, ensuring proper usage remains challenging. This paper presents SD (Small object detection and DilateFormer attention mechanism)-YOLOv5s, an improved PPE detection algorithm based on YOLOv5s, designed to enhance the detection accuracy of small objects, such as helmets, in complex construction environments. The proposed model incorporates a dedicated feature layer for small target detection and integrates the DilateFormer attention mechanism to balance detection performance and computational efficiency. Experimental results on the CHV dataset demonstrate that SD-YOLOv5s achieves an average precision (AP) of 93.7%, representing an improvement of 2.8 percentage points over the baseline YOLOv5s (AP = 90.9%), while reducing the model’s parameter count by up to 14.6%. These quantitative improvements indicate that SD-YOLOv5s is a promising solution for real-time PPE monitoring on construction sites, although further validation on larger and more diverse datasets is warranted.https://www.frontiersin.org/articles/10.3389/fbuil.2025.1563483/fullpersonal protective equipment (PPE) detectionYOLOv5small object detectionDilateFormer attention mechanismconstruction site safety |
| spellingShingle | ChunYa Li ChunYa Li Jianhua Wang Jianhua Wang Bingfeng Luo Tubing Yin Baohua Liu Baohua Liu Jianfei Lu SD-YOLOv5: a rapid detection method for personal protective equipment on construction sites Frontiers in Built Environment personal protective equipment (PPE) detection YOLOv5 small object detection DilateFormer attention mechanism construction site safety |
| title | SD-YOLOv5: a rapid detection method for personal protective equipment on construction sites |
| title_full | SD-YOLOv5: a rapid detection method for personal protective equipment on construction sites |
| title_fullStr | SD-YOLOv5: a rapid detection method for personal protective equipment on construction sites |
| title_full_unstemmed | SD-YOLOv5: a rapid detection method for personal protective equipment on construction sites |
| title_short | SD-YOLOv5: a rapid detection method for personal protective equipment on construction sites |
| title_sort | sd yolov5 a rapid detection method for personal protective equipment on construction sites |
| topic | personal protective equipment (PPE) detection YOLOv5 small object detection DilateFormer attention mechanism construction site safety |
| url | https://www.frontiersin.org/articles/10.3389/fbuil.2025.1563483/full |
| work_keys_str_mv | AT chunyali sdyolov5arapiddetectionmethodforpersonalprotectiveequipmentonconstructionsites AT chunyali sdyolov5arapiddetectionmethodforpersonalprotectiveequipmentonconstructionsites AT jianhuawang sdyolov5arapiddetectionmethodforpersonalprotectiveequipmentonconstructionsites AT jianhuawang sdyolov5arapiddetectionmethodforpersonalprotectiveequipmentonconstructionsites AT bingfengluo sdyolov5arapiddetectionmethodforpersonalprotectiveequipmentonconstructionsites AT tubingyin sdyolov5arapiddetectionmethodforpersonalprotectiveequipmentonconstructionsites AT baohualiu sdyolov5arapiddetectionmethodforpersonalprotectiveequipmentonconstructionsites AT baohualiu sdyolov5arapiddetectionmethodforpersonalprotectiveequipmentonconstructionsites AT jianfeilu sdyolov5arapiddetectionmethodforpersonalprotectiveequipmentonconstructionsites |