Unsafe behaviour detection with the improved YOLOv5 model
Abstract In industrial environments, workers should wear workwear for safety considerations. For the same reason, smoking is also prohibited. Due to the supervision of monitoring devices, workers have reduced smoking behaviours and started wearing workwear. To meet the requirements for detecting the...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2024-03-01
|
| Series: | IET Cyber-Physical Systems |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/cps2.12070 |
| _version_ | 1797263661177241600 |
|---|---|
| author | Li Ying Zhao Lei Geng Junwei Hu Jinhui Ma Lei Zhao Zilong |
| author_facet | Li Ying Zhao Lei Geng Junwei Hu Jinhui Ma Lei Zhao Zilong |
| author_sort | Li Ying |
| collection | DOAJ |
| description | Abstract In industrial environments, workers should wear workwear for safety considerations. For the same reason, smoking is also prohibited. Due to the supervision of monitoring devices, workers have reduced smoking behaviours and started wearing workwear. To meet the requirements for detecting these behaviours in real‐time monitoring videos with high speed and accuracy, the authors proposed an improved YOLOv5 model with the Triplet Attention mechanism. This mechanism strengthens the connection between channel and spatial dimensions, focuses the network on important parts, and improves feature extraction. Compared to the original YOLOv5 model, the addition of the mechanism increases the parameters by only 0.04%. The recall rate of the YOLOv5 model is enhanced while its prediction speed is maintained with only a minimal increase in parameters. Experiment results show that, compared to the original model, the improved YOLOv5 has a recall rate of 78.8%, 91%, and 89.3% for detecting smoking behaviour, not wearing helmets, and inappropriate workwear, respectively. |
| first_indexed | 2024-04-25T00:16:33Z |
| format | Article |
| id | doaj.art-4b0cca6cef2a4fd38eb16bb124d00eb6 |
| institution | Directory Open Access Journal |
| issn | 2398-3396 |
| language | English |
| last_indexed | 2024-04-25T00:16:33Z |
| publishDate | 2024-03-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Cyber-Physical Systems |
| spelling | doaj.art-4b0cca6cef2a4fd38eb16bb124d00eb62024-03-13T03:51:43ZengWileyIET Cyber-Physical Systems2398-33962024-03-0191879810.1049/cps2.12070Unsafe behaviour detection with the improved YOLOv5 modelLi Ying0Zhao Lei1Geng Junwei2Hu Jinhui3Ma Lei4Zhao Zilong5State Grid Beijing Electric Power Company Beijing ChinaState Grid Beijing Electric Power Company Beijing ChinaState Grid Beijing Electric Power Company Beijing ChinaState Grid Beijing Electric Power Company Beijing ChinaState Grid Beijing Electric Power Company Beijing ChinaNanjing Artificial Intelligence Research of IA (AiRiA) Nanjing Jiangsu ChinaAbstract In industrial environments, workers should wear workwear for safety considerations. For the same reason, smoking is also prohibited. Due to the supervision of monitoring devices, workers have reduced smoking behaviours and started wearing workwear. To meet the requirements for detecting these behaviours in real‐time monitoring videos with high speed and accuracy, the authors proposed an improved YOLOv5 model with the Triplet Attention mechanism. This mechanism strengthens the connection between channel and spatial dimensions, focuses the network on important parts, and improves feature extraction. Compared to the original YOLOv5 model, the addition of the mechanism increases the parameters by only 0.04%. The recall rate of the YOLOv5 model is enhanced while its prediction speed is maintained with only a minimal increase in parameters. Experiment results show that, compared to the original model, the improved YOLOv5 has a recall rate of 78.8%, 91%, and 89.3% for detecting smoking behaviour, not wearing helmets, and inappropriate workwear, respectively.https://doi.org/10.1049/cps2.12070learning (artificial intelligence)neural netsobject detection |
| spellingShingle | Li Ying Zhao Lei Geng Junwei Hu Jinhui Ma Lei Zhao Zilong Unsafe behaviour detection with the improved YOLOv5 model IET Cyber-Physical Systems learning (artificial intelligence) neural nets object detection |
| title | Unsafe behaviour detection with the improved YOLOv5 model |
| title_full | Unsafe behaviour detection with the improved YOLOv5 model |
| title_fullStr | Unsafe behaviour detection with the improved YOLOv5 model |
| title_full_unstemmed | Unsafe behaviour detection with the improved YOLOv5 model |
| title_short | Unsafe behaviour detection with the improved YOLOv5 model |
| title_sort | unsafe behaviour detection with the improved yolov5 model |
| topic | learning (artificial intelligence) neural nets object detection |
| url | https://doi.org/10.1049/cps2.12070 |
| work_keys_str_mv | AT liying unsafebehaviourdetectionwiththeimprovedyolov5model AT zhaolei unsafebehaviourdetectionwiththeimprovedyolov5model AT gengjunwei unsafebehaviourdetectionwiththeimprovedyolov5model AT hujinhui unsafebehaviourdetectionwiththeimprovedyolov5model AT malei unsafebehaviourdetectionwiththeimprovedyolov5model AT zhaozilong unsafebehaviourdetectionwiththeimprovedyolov5model |