基于g^(n)Conv和GAM的YOLOv5钢管焊接缺陷检测方法

Detection Method for Welding Defects of YOLOv5 Steel Pipe Based on g^(n)Conv and GAM

针对基础yolov5算法检测钢管焊缝缺陷因缺陷目标小、背景复杂造成检测精度不够、特征提取不充分、速度慢的问题,提出了一种改进yolov5检测算法.首先,采用递归门控卷积g^(n)Conv替换网络中普通的卷积层,增强了模型空间交互能力,实现对特征的高效提取,间接提高了检测速度;其次,使用ASPP(Atrous Spatial Pyramid Pooling)模块替换基础算法中使用的SPP模块,在扩大了感受野范围的同时提高了检测速度;最后,在网络的预测端添加全局注意力机制GAM(Global Attention Mechanism)进一步加强特征提取,提高检测的精度.实验结果表明,改进的算法mAP达到了92.7%,比原算法提升了2.1个百分点,速度为50.8 f/s,满足钢管焊接缺陷检测的精度和实时性要求.

Aiming at the problems of low detection accuracy and slow detection speed caused by small target and complex background of steel pipe welding defects,an improved YOLOv5 detection algorithm is proposed.First,recursive gated convolution g^(n)Conv is used to replace the common convolution layer in the network,which enhances the interaction ability of model space,realizes efficient feature extraction,and indirectly improves the detection speed.Secondly,the use of ASPP(Atmosphere Spatial Pyramid Pooling)module not only expands the receptive field,but also improves the detection speed.Finally,GAM(Global Attention Mechanism)is added to the prediction end of the network to further enhance feature extraction and improve detection accuracy.The experimental results show that the improved al gorithm mAP achieves 92.7%,2.1 percentage points higher than the original algorithm,and the speed is 50.8 f/s,meeting the requirements of precision and real-time of steel pipe welding defect detection.