A Glove-Wearing Detection Algorithm Based on Improved YOLOv8
Wearing gloves during machinery operation in workshops is essential for preventing accidental injuries, such as mechanical damage and burns. Ensuring that workers are wearing gloves is a key strategy for accident prevention. Consequently, this study proposes a glove detection algorithm called YOLOv8...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-12-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/24/9906 |
| _version_ | 1827573560683528192 |
|---|---|
| author | Shichu Li Huiping Huang Xiangyin Meng Mushuai Wang Yang Li Lei Xie |
| author_facet | Shichu Li Huiping Huang Xiangyin Meng Mushuai Wang Yang Li Lei Xie |
| author_sort | Shichu Li |
| collection | DOAJ |
| description | Wearing gloves during machinery operation in workshops is essential for preventing accidental injuries, such as mechanical damage and burns. Ensuring that workers are wearing gloves is a key strategy for accident prevention. Consequently, this study proposes a glove detection algorithm called YOLOv8-AFPN-M-C2f based on YOLOv8, offering swifter detection speeds, lower computational demands, and enhanced accuracy for workshop scenarios. This research innovates by substituting the head of YOLOv8 with the AFPN-M-C2f network, amplifying the pathways for feature vector propagation, and mitigating semantic discrepancies between non-adjacent feature layers. Additionally, the introduction of a superficial feature layer enriches surface feature information, augmenting the model’s sensitivity to smaller objects. To assess the performance of the YOLOv8-AFPN-M-C2f model, this study conducted multiple experiments using a factory glove detection dataset compiled for this study. The results indicate that the enhanced YOLOv8 model surpasses other network models. Compared to the baseline YOLOv8 model, the refined version shows a 2.6% increase in mAP@50%, a 63.8% rise in FPS, and a 13% reduction in the number of parameters. This research contributes an effective solution for the detection of glove adherence. |
| first_indexed | 2024-03-08T20:21:59Z |
| format | Article |
| id | doaj.art-5c891b663a0c456e8eb0c05a5607362c |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-08T20:21:59Z |
| publishDate | 2023-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-5c891b663a0c456e8eb0c05a5607362c2023-12-22T14:41:40ZengMDPI AGSensors1424-82202023-12-012324990610.3390/s23249906A Glove-Wearing Detection Algorithm Based on Improved YOLOv8Shichu Li0Huiping Huang1Xiangyin Meng2Mushuai Wang3Yang Li4Lei Xie5Jiuli Campus, School of Mechanical Engineering, Southwest Jiaotong University, Chengdu 610031, ChinaJiuli Campus, School of Mechanical Engineering, Southwest Jiaotong University, Chengdu 610031, ChinaJiuli Campus, School of Mechanical Engineering, Southwest Jiaotong University, Chengdu 610031, ChinaJiuli Campus, School of Mechanical Engineering, Southwest Jiaotong University, Chengdu 610031, ChinaJiuli Campus, School of Mechanical Engineering, Southwest Jiaotong University, Chengdu 610031, ChinaJiuli Campus, School of Mechanical Engineering, Southwest Jiaotong University, Chengdu 610031, ChinaWearing gloves during machinery operation in workshops is essential for preventing accidental injuries, such as mechanical damage and burns. Ensuring that workers are wearing gloves is a key strategy for accident prevention. Consequently, this study proposes a glove detection algorithm called YOLOv8-AFPN-M-C2f based on YOLOv8, offering swifter detection speeds, lower computational demands, and enhanced accuracy for workshop scenarios. This research innovates by substituting the head of YOLOv8 with the AFPN-M-C2f network, amplifying the pathways for feature vector propagation, and mitigating semantic discrepancies between non-adjacent feature layers. Additionally, the introduction of a superficial feature layer enriches surface feature information, augmenting the model’s sensitivity to smaller objects. To assess the performance of the YOLOv8-AFPN-M-C2f model, this study conducted multiple experiments using a factory glove detection dataset compiled for this study. The results indicate that the enhanced YOLOv8 model surpasses other network models. Compared to the baseline YOLOv8 model, the refined version shows a 2.6% increase in mAP@50%, a 63.8% rise in FPS, and a 13% reduction in the number of parameters. This research contributes an effective solution for the detection of glove adherence.https://www.mdpi.com/1424-8220/23/24/9906glove-wearing detectionYOLOv8feature pyramid networkfeature layer |
| spellingShingle | Shichu Li Huiping Huang Xiangyin Meng Mushuai Wang Yang Li Lei Xie A Glove-Wearing Detection Algorithm Based on Improved YOLOv8 Sensors glove-wearing detection YOLOv8 feature pyramid network feature layer |
| title | A Glove-Wearing Detection Algorithm Based on Improved YOLOv8 |
| title_full | A Glove-Wearing Detection Algorithm Based on Improved YOLOv8 |
| title_fullStr | A Glove-Wearing Detection Algorithm Based on Improved YOLOv8 |
| title_full_unstemmed | A Glove-Wearing Detection Algorithm Based on Improved YOLOv8 |
| title_short | A Glove-Wearing Detection Algorithm Based on Improved YOLOv8 |
| title_sort | glove wearing detection algorithm based on improved yolov8 |
| topic | glove-wearing detection YOLOv8 feature pyramid network feature layer |
| url | https://www.mdpi.com/1424-8220/23/24/9906 |
| work_keys_str_mv | AT shichuli aglovewearingdetectionalgorithmbasedonimprovedyolov8 AT huipinghuang aglovewearingdetectionalgorithmbasedonimprovedyolov8 AT xiangyinmeng aglovewearingdetectionalgorithmbasedonimprovedyolov8 AT mushuaiwang aglovewearingdetectionalgorithmbasedonimprovedyolov8 AT yangli aglovewearingdetectionalgorithmbasedonimprovedyolov8 AT leixie aglovewearingdetectionalgorithmbasedonimprovedyolov8 AT shichuli glovewearingdetectionalgorithmbasedonimprovedyolov8 AT huipinghuang glovewearingdetectionalgorithmbasedonimprovedyolov8 AT xiangyinmeng glovewearingdetectionalgorithmbasedonimprovedyolov8 AT mushuaiwang glovewearingdetectionalgorithmbasedonimprovedyolov8 AT yangli glovewearingdetectionalgorithmbasedonimprovedyolov8 AT leixie glovewearingdetectionalgorithmbasedonimprovedyolov8 |