融合选择核注意力的无纺布缺陷检测

Nonwoven Defect Detection by Fusing Selection Kernel Attention

针对无纺布缺陷检测算法实时性差,检测准确率低的问题,设计了一种基于改进YOLOv5的无纺布缺陷检测算法N-YOLO。该算法结合产线实际情况和产品特性运用视觉检测技术,在YOLOv5算法的基础上引入FasterNet网络作为主干特征提取网络进行轻量化改进,利用部分卷积进行特征提取减少模型计算量。同时在C3模块中增加SK注意力机制提高模型检测精度,并采用WIoUv1损失函数计算边界框回归损失,提高边界框定位精度。实验结果表明N-YOLO算法与YOLOv5s相比浮点计算量减少85.4%,参数量由7 020 913减少到3 368 105,减少了52%,模型大小为6.63 MB,平均检测精度能达到99.2%,召回率达到99.2%,与Faster R-CNN和SSD等目标检测算法相比具有明显优势,无需昂贵的硬件设备即可在高速生产情况下对无纺布缺陷进行实时检测。

Aiming at the problems of poor real-time performance and low detection accuracy of non-woven defect detec-tion algorithm,a non-woven defect detection algorithm N-YOLO based on improved YOLOv5 is designed.Based on the actual situation of the production line and product characteristics,the algorithm uses visual detection technology.Firstly,based on the YOLOv5 algorithm,FasterNet network is introduced as the backbone feature extraction network for light-weight improvement,and partial convolution is used for feature extraction to reduce the model computation.At the same time,SK attention mechanism is added in C3 module to improve the model detection accuracy,and WIoUv1 loss function is used to calculate the boundary frame regression loss to improve the boundary frame positioning accuracy.Experimental results show that compared with YOLOv5,N-YOLO algorithm reduces floating point computation by 85.4%,parameter number by 52%from 7020913 to 3368105,model size is 6.63 MB,average detection accuracy can reach 99.2%,recall rate can reach 99.2%.Compared with target detection algorithms such as Faster R-CNN and SSD,it has obvious advantages,and can detect defects of non-wovens in real time under high-speed production without expensive hardware equipment.