首页|基于改进YOLOv5的镍板表面缺陷检测方法

基于改进YOLOv5的镍板表面缺陷检测方法

扫码查看
原文链接
  • NETL
  • NSTL
  • 万方数据
针对镍板表面缺陷检测智能化程度低的问题,提出了一种基于改进YOLOv5 的镍板表面缺陷检测方法.首先,对图像增强后的镍板数据集通过K-means++重新聚类锚框,提高锚框对本文数据集的适应度.其次,在主干网络Backbone中加入CBAM注意力机制,通过空间与通道信息融合来加强对感兴趣区域以及不清晰目标的特征识别.最后,在边界框回归时引入EIoU损失函数代替原CIoU损失函数,有效提高回归收敛速度,从而提高模型检测速度.实验结果表明,在自建的镍板缺陷数据集上,改进后的模型检测准确率高于Faster R-CNN、SSD、YOLOv3、YOLOv5 等模型,其平均精度均值达 81.4%,检测速度达 61 帧/s,模型在提高检测精度的同时也很好地满足了对检测速度的要求.
Nickel Plate Surface Defect Detection Based on Improved YOLOv5
Aiming at low intelligence in nickel plate surface defect detection,a detection method based on improved YOLOv5 was proposed.Firstly,the image-enhanced dataset of nickel plate was re-clustered by K-means++to improve the adaptability of the anchor frame to the dataset.Secondly,the convolutional block attention module(CBAM)was added into the Backbone network to strengthen the feature recognition of interest areas and unclear targets by integration of spatial and channel information.Finally,an efficient IoU(EIoU)loss was introduced to replace the original CIoU loss during bounding box regression to effectively improve the convergence speed of regression,thereby increasing the model detection speed.The experimental results show that with the self-established dataset of nickel plate defect,the improved model,compared to Faster R-CNN,SSD,YOLOv3 and YOLOv5,has higher detection accuracy up to 81.4%on average,with detection speed reaching 61 frames per second.It is concluded that this model can not only improve detection accuracy,but also satisfy the requirements for detection speed.

surface defectnickel platedefect detectionimage processingimage enhancement algorithmYOLOv5convolutional block attention module(CBAM)EIoU lossaccuracy rateaverage precisiondetection speed

谭沁源、唐勇、金岩、覃美满、吴伟

展开 >

长沙矿山研究院有限责任公司,湖南长沙 410012

国家金属采矿工程技术研究中心,湖南长沙 410012

金川集团股份有限责任公司,甘肃金昌 737100

表面缺陷 镍板 缺陷检测 图像处理 图像增强算法 YOLOv5 注意力机制 EIoU损失函数 准确率 平均精度 检测速度

湖南省科技成果转化及产业计划

2020GK2087

2024

10.3969/j.issn.0253-6099.2024.02.035

矿冶工程
长沙矿冶研究院有限责任公司 中国金属学会

矿冶工程

CSTPCD北大核心
影响因子：1.137
ISSN：0253-6099
年,卷(期)：2024.44(2)
  • 12