首页|改进轻量化VTG-YOLOv7-tiny的钢材表面缺陷检测

改进轻量化VTG-YOLOv7-tiny的钢材表面缺陷检测

扫码查看
原文链接
  • 国家科技期刊平台
  • NETL
  • NSTL
  • 万方数据
针对钢材表面缺陷形态多样、结构复杂且存在检测目标漏检现象和算法参数量过大等问题,提出一种轻量化VTG-YOLOv7-tiny的钢材缺陷检测算法.该方法一是设计VoVGA-FPN网络,以减少信息传递过程中的丢失,增强网络特征融合能力;二是构建三重坐标注意力机制,提升模型对空间和通道信息的特征提取能力;三是引入鬼影混洗卷积,在提高精度的同时降低模型参数量和计算量;四是增加大目标检测层,改善特征图中部分缺陷占比较大,导致检测精度低的问题.在NEU-DET和Severstal钢材缺陷数据集进行实验验证,改进后算法与原模型相比,mAP分别提升5.7%和8.5%;参数量和计算量分别降低0.61 M和4.2 G;精确度和召回率分别提升7.1%,1.8%和8.9%,7.0%.实验结果表明,改进后的算法更好地平衡了检测精度和轻量化,为边缘终端设备提供了参考.
Improving the lightweight VTG-YOLOv7-tiny for steel surface defect detection
To address the problems of diverse and complex shapes of steel surface defects,detection target missing,and large number of algorithm parameters,a lightweight VTG-YOLOv7-tiny steel defect detec-tion algorithm was proposed.The method first designed VoVGA-FPN network to reduce the loss of infor-mation during information transmission and enhance the network feature fusion ability;second,it con-structed a triple coordinate attention mechanism to improve the model's feature extraction ability of spatial and channel information;third,it introduceed ghost shuffle convolution to reduce the model parameters and computation while improving the accuracy;fourth,it added a large target detection layer to improve the problem that some defects in the feature map occupy a large proportion,resulting in low detection accu-racy.The improved algorithm was verified on the NEU-DET and Severstal steel defect datasets.Com-pared with the original model,the mAP of the improved algorithm is increased by 5.7%and 8.5%,re-spectively;the parameters and computation are reduced by 0.61 M and 4.2 G,respectively;the accuracy and recall are increased by 7.1%,1.8%and 8.9%,7.0%,respectively.The experimental results show that the improved algorithm better balances the detection accuracy and lightweight,and provides a refer-ence for edge terminal devices.

defect detectionLightweight YOLOv7-tinyVoVGA-FPN networkTriplet Coordinate Attention(TCA)Ghost Shuffle Convolution(GSConv)

梁礼明、龙鹏威、冯耀、卢宝贺

展开 >

江西理工大学 电气工程与自动化学院,江西 赣州 341000

缺陷检测 轻量化YOLOv7-tiny VoVGA-FPN网络 三重坐标注意力 鬼影混洗卷积

国家自然科学基金资助项目国家自然科学基金资助项目江西省自然科学基金资助项目江西省教育厅科学技术研究重点项目

51365017614630120192BAB205084GJJ170491

2024

10.37188/OPE.20243208.1227

光学精密工程
中国科学院长春光学精密机械与物理研究所 中国仪器仪表学会

光学精密工程

CSTPCD北大核心
影响因子：2.059
ISSN：1004-924X
年,卷(期)：2024.32(8)
  • 30