Research on the Detection Algorithm of Railway Worker's Hard Hat Based on YOLOv5 Improvement
At present,manual supervision is generally used on railways to detect whether workers wear safety helmets,but the supervision scope is too large,and it is impossible to timely track and manage all workers in practice.Therefore,in response to this problem,the deep learning target detection method is adopted,and the YOLOv5s target detection algorithm is improved to realize whether railway workers wear hard hats and vests.Specifically,based on the YOLOv5s algorithm,the GhostNet module is used to replace the convolution Conv in the original network to improve the real-time detection speed of the model;the more efficient and sim-ple multi-scale feature fusion BiFPN is used to make the feature fusion method simpler and more efficient to improve the detection speed and reduce the complexity of the model;The original CIOU loss function is replaced by the SIOU loss function to improve the accuracy of model.The research results show that the accuracy and recognition efficiency of the improved YOLOv5s-GBS algorithm can reach 95.7％and 45 fps,respectively,and the model size is reduced by half,and the accuracy rate of the model is increased by 4.5％.
hard hatdeep learningBiFPNSIOU loss functionYOLOv5s-GBS algorithm
万方数据
维普
