Abstract: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 YOLOv5 is proposed. By incorporating the lightweight GhostNet 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 light-weight convolution, GSConv, is integrated into the neck structure for further model size compression. Moreover, the baseline model's loss function is substituted with EIoU, accelerating network convergence and enhancing de-tection precision. Experimental results corroborate the effectiveness of this improved algorithm in real-world traffic scenarios.