Helmet wearing detection algorithm based on improved YOLOv5
Abstract In industrial production, workers need to wear safety helmets at all times. However, due to different lighting, viewing angles, and the tendency of people to block each other, the precision of target detection is not high enough. Aiming at this problem, a real-time detection of helmets was...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-04-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-024-58800-6 |
| _version_ | 1797199429442207744 |
|---|---|
| author | Yiping Liu Benchi Jiang Huan He Zhijun Chen Zhenfa Xu |
| author_facet | Yiping Liu Benchi Jiang Huan He Zhijun Chen Zhenfa Xu |
| author_sort | Yiping Liu |
| collection | DOAJ |
| description | Abstract In industrial production, workers need to wear safety helmets at all times. However, due to different lighting, viewing angles, and the tendency of people to block each other, the precision of target detection is not high enough. Aiming at this problem, a real-time detection of helmets was achieved by improving the YOLOv5 algorithm. This algorithm introduces the lightweight network structure FasterNet, which uses partial convolution as the main operator to reduce the amount of calculations and parameters of the network; the boundary regression loss function Wise-IoU loss function with a dynamic focusing mechanism replaces the original loss function in YOLOv5; finally, the CBAM attention mechanism is introduced to obtain global context information and improve the detection ability of small targets. The experimental results show that the parameters of the improved YOLOv5 model are reduced by 12.68%, the computational amount is reduced by 10.8%, the mAP is increased from 88.3 to 92.3%, and the inference time is reduced by 81.5%, which is better than the performance of the original model and can detect helmet wearing effectively and in real time. |
| first_indexed | 2024-04-24T07:15:37Z |
| format | Article |
| id | doaj.art-d5938d62ec76413c87c6ccdf17a500ba |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-04-24T07:15:37Z |
| publishDate | 2024-04-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-d5938d62ec76413c87c6ccdf17a500ba2024-04-21T11:19:24ZengNature PortfolioScientific Reports2045-23222024-04-0114111110.1038/s41598-024-58800-6Helmet wearing detection algorithm based on improved YOLOv5Yiping Liu0Benchi Jiang1Huan He2Zhijun Chen3Zhenfa Xu4School of Mechanical Engineering, Anhui Polytechnic UniversitySchool of Artificial Intelligence, Anhui Polytechnic UniversitySchool of Artificial Intelligence, Anhui Polytechnic UniversityYangtze River Delta HIT Robot Technology Research InstituteAnHui Key Laboratory of Detection Technology and Energy Saving Devices, AnHui Polytechnic UniversityAbstract In industrial production, workers need to wear safety helmets at all times. However, due to different lighting, viewing angles, and the tendency of people to block each other, the precision of target detection is not high enough. Aiming at this problem, a real-time detection of helmets was achieved by improving the YOLOv5 algorithm. This algorithm introduces the lightweight network structure FasterNet, which uses partial convolution as the main operator to reduce the amount of calculations and parameters of the network; the boundary regression loss function Wise-IoU loss function with a dynamic focusing mechanism replaces the original loss function in YOLOv5; finally, the CBAM attention mechanism is introduced to obtain global context information and improve the detection ability of small targets. The experimental results show that the parameters of the improved YOLOv5 model are reduced by 12.68%, the computational amount is reduced by 10.8%, the mAP is increased from 88.3 to 92.3%, and the inference time is reduced by 81.5%, which is better than the performance of the original model and can detect helmet wearing effectively and in real time.https://doi.org/10.1038/s41598-024-58800-6Deep learningTarget detectionYOLOv5Network structureAttention mechanism |
| spellingShingle | Yiping Liu Benchi Jiang Huan He Zhijun Chen Zhenfa Xu Helmet wearing detection algorithm based on improved YOLOv5 Scientific Reports Deep learning Target detection YOLOv5 Network structure Attention mechanism |
| title | Helmet wearing detection algorithm based on improved YOLOv5 |
| title_full | Helmet wearing detection algorithm based on improved YOLOv5 |
| title_fullStr | Helmet wearing detection algorithm based on improved YOLOv5 |
| title_full_unstemmed | Helmet wearing detection algorithm based on improved YOLOv5 |
| title_short | Helmet wearing detection algorithm based on improved YOLOv5 |
| title_sort | helmet wearing detection algorithm based on improved yolov5 |
| topic | Deep learning Target detection YOLOv5 Network structure Attention mechanism |
| url | https://doi.org/10.1038/s41598-024-58800-6 |
| work_keys_str_mv | AT yipingliu helmetwearingdetectionalgorithmbasedonimprovedyolov5 AT benchijiang helmetwearingdetectionalgorithmbasedonimprovedyolov5 AT huanhe helmetwearingdetectionalgorithmbasedonimprovedyolov5 AT zhijunchen helmetwearingdetectionalgorithmbasedonimprovedyolov5 AT zhenfaxu helmetwearingdetectionalgorithmbasedonimprovedyolov5 |