Helmet Wearing Detection Algorithm in Steel Rolling Workshops Based on Improved YOLOv7
Wearing helmets can protect the head of production workers from injuries caused by falling objects.There are problems such as large span of space,numerous operating devices,cluttered environment,large difference in lighting between day and night,dazzling light,and significant changes of monitoring target in steel rolling workshops,increasing the difficulty of helmet wearing de-tection.In response to the above problems,a helmet wearing detection scheme based on improved YOLOv7 model is designed in steel rolling workshops.Based on normalized Wasserstein distance(NWD)method,the algorithm improves the loss function to increase the accuracy of target detection,the BiFormer module is added on the SPPCSPC module,which makes the model have better detection accuracy for small targets without increasing the computational cost,it is superior to other attention mechanisms.The improved YOLOv7 model is trained on the self-constructed helmet dataset,the experimental results show that the improved YOLOv7 model has a mean average accuracy of 99.3％,with a detection speed of 82 FPS.comparing with other mainstream algorithms and improved al-gorithms,the improved YOLOv7 has the highest mAP index,the index of the improved YOLOv7 is much more than that of other models.At the same time,the detection speed is not much different from that before the improvement of the model,it does not signif-icantly reduce the detection speed because of the improvement of accuracy,which has a better effect.
steel rolling workshophelmet detectionYOLOv7NWDBiFormer
NETL
NSTL
万方数据
