Li Ying, Zhao Lei, Geng Junwei, Hu Jinhui, Ma Lei, Zhao Zilong
{"title":"Unsafe behaviour detection with the improved YOLOv5 model","authors":"Li Ying, Zhao Lei, Geng Junwei, Hu Jinhui, Ma Lei, Zhao Zilong","doi":"10.1049/cps2.12070","DOIUrl":null,"url":null,"abstract":"<p>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.</p>","PeriodicalId":36881,"journal":{"name":"IET Cyber-Physical Systems: Theory and Applications","volume":null,"pages":null},"PeriodicalIF":1.7000,"publicationDate":"2023-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/cps2.12070","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IET Cyber-Physical Systems: Theory and Applications","FirstCategoryId":"1085","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1049/cps2.12070","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"COMPUTER SCIENCE, INFORMATION SYSTEMS","Score":null,"Total":0}
引用次数: 0
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.