Traffic safety helmet wear detection based on improved YOLOv5 network  

作　　者：GUI Dongdong SUN Bo 

机构地区：[1]College of Software,Southeast University,Suzhou 215123,China [2]Quanzhou Equipment Research Centre,Haixi Institute,Chinese Academy of Sciences,Quanzhou 350108,China

出　　处：《Optoelectronics Letters》2025年第1期35-42,共8页光电子快报(英文版)

摘　　要：Aiming at the problem that the current traffic safety helmet detection model can't balance the accuracy of detection with the size of the model and the poor generalization of the model,a method based on improving you only look once version 5(YOLOv5) is proposed.By incorporating the lightweight Ghost Net module into the YOLOv5 backbone network,we effectively reduce the model size.The addition of the receptive fields block(RFB) module enhances feature extraction and improves the feature acquisition capability of the lightweight model.Subsequently,the high-performance lightweight convolution,GSConv,is integrated into the neck structure for further model size compression.Moreover,the baseline model's loss function is substituted with efficient insertion over union(EIoU),accelerating network convergence and enhancing detection precision.Experimental results corroborate the effectiveness of this improved algorithm in real-world traffic scenarios.

关 键 词：NETWORK UNION BACKBONE 

分 类 号：G63[文化科学—教育学]