基于改进YOLOv5s的烟梗物料目标检测算法

Improved YOLOv5s based target detection algorithm for tobacco stem material

在烟草生产线中烟梗输送下落过程中,存在背景信息干扰、目标数量多且形状不一、目标堆叠、下落速度过快等问题,传统图像处理算法难以解决.提出基于改进YOLOv5s的烟梗物料目标检测算法.对YOLOv5s网络的骨干和头部进行优化改进,显著提高检测精度,大幅缩小模型大小;将骨干网络优化为RepViT-m1结构,以提高信息提取的效率;采用重参数化技术,以更好地捕捉目标的特征,提高检测的精确性;引入基于注意力机制的目标检测头Dynamic Head,使模型更专注于潜在的目标区域,进一步提高检测精度.实验结果表明:在自建的烟梗数据集上,相较于原YOLOv5s模型,改进YOLOv5s模型的m AP@0.50为96.1%,提高了5.8个百分点;mAP@0.50∶0.95为94.7%,提高了5.7个百分点;模型大小为12.1 MB,减少了12.3%.模型可以为实时监控系统提供可靠且精确的支持.

There are problems such as background interference,multiple and irregularly shaped targets,target overlap,and rapid falling speeds during the transportation of tobacco stems in the tobacco production line.A tobacco stem material target detection algorithm based on improved YOLOv5s was proposed.The backbone and head of the YOLOv5s network were optimized,significantly improving the detection accuracy and substantially reducing the model size.Firstly,the network’s backbone was optimized into the RepViT-m1 structure,enhancing the information extraction efficiency.Secondly,reparameterization techniques were used to better capture the target features,thus improving the detection precision.Dynamic Head,a target detection head based on the attention mechanism,was introduced to make the model be focused on the potential target area to further improve the detection accuracy.Experimental results on self-constructed tobacco stem dataset demonstrated the effectiveness of the improved YOLOv5s model.Compared with the original YOLOv5s model,the improved model achieved an mAP@0.50 of 96.1%,which was improved by 5.8 percentage points;and achieved an mAP@0.50:0.95 of 94.7%,which was improved by 5.7 percentage points.Furthermore,the model size was 12.1 MB,which was decreased by 12.3%.The results provide reliable and accurate support for real-time monitoring systems.