基于改进YOLOv8n的钢材表面缺陷检测
DOI:
CSTR:
作者:
作者单位:

1.沈阳化工大学计算机科学与技术学院 沈阳 110142; 2.辽宁省化工过程工业智能化技术重点实验室 沈阳 110142

作者简介:

通讯作者:

中图分类号:

TN911

基金项目:

辽宁省教育厅基本科研项目面上项目(LJKMZ20220782)资助


Steel surface defect detection algorithm based on improved YOLOv8n
Author:
Affiliation:

1.School of Computer Science and Technology, Shenyang University of Chemical Technology,Shenyang 110142, China; 2.Liaoning Provincial Key Laboratory of Chemical Process Industry and Intelligent Technology,Shenyang 110142, China

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    为解决钢材表面缺陷检测中面临的缺陷类型繁多、尺寸差异显著以及现有模型复杂度高、检测精度不足等问题,本文提出了一种基于改进YOLOv8n的检测算法YOLOv8ODAW。首先,引入全维动态卷积(ODConv)增强对多维度特征的捕捉能力,减少信息损失;其次,嵌入渐进特征金字塔网络(AFPN)改善特征融合过程,实现了非相邻层级特征间的直接交互,有效缓解语义断层。最后,采用动态非单调聚焦机制的Wise-IoUv3损失函数优化边界框回归,加快网络收敛的同时提高检测精度。在NEU-DET数据集上进行多组实验,结果表明,改进后的YOLOv8-ODAW网络模型相比原网络模型mAP50%提升了7.3%、GFLOPs下降了21.95%,展现出对钢材表面缺陷更佳的定位与识别能力,且检测速度满足工业应用需求。

    Abstract:

    To address the challenges posed by the diverse types of defects, significant size variations, and high complexity of existing models with insufficient detection accuracy in steel surface defect detection, this paper proposes a detection algorithm named YOLOv8-ODAW based on an improved YOLOv8n. Firstly, Omni-dimensional Dynamic Convolution (ODConv) was introduced to enhance the capability of capturing multi-dimensional features and reduce information loss. Secondly, an Asymptotic Feature Pyramid Network (AFPN) was embedded to improve the feature fusion process, enabling direct interaction between non-adjacent level features and effectively alleviating semantic disconnection. Finally, the Wise-IoUv3 loss function with a dynamic non-monotonic focusing mechanism was adopted to optimize bounding box regression, accelerating network convergence while improving detection accuracy. A series of experiments were conducted on the NEU-DET dataset, and the results demonstrated that the modified YOLOv8-ODAW network model outperformed the original network model with a 7.3% increase in mAP at 50% and a 21.95% decrease in computational complexity (GFLOPs). This showcases superior localization and recognition capabilities for steel surface defects while meeting the speed requirements for industrial applications.

    参考文献
    相似文献
    引证文献
引用本文

赵洋,王军凯,林志毅,周忠祥,徐森.基于改进YOLOv8n的钢材表面缺陷检测[J].电子测量技术,2024,47(13):191-198

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:
  • 最后修改日期:
  • 录用日期:
  • 在线发布日期: 2024-11-07
  • 出版日期:
文章二维码