基于多尺度轻量化注意力的钢材缺陷检测
CSTR:
作者:
作者单位:

1. 湘潭大学 自动化与电子信息学院,湖南 湘潭 411105;2. 湘潭大学 计算机学院cdot网络空间安全学院,湖南 湘潭 411105

作者简介:

通讯作者:

E-mail: yanzhou@xtu.edu.cn.

中图分类号:

TP183

基金项目:

国家自然科学基金项目(61773330);湖南省国家应用数学中心项目(2020YFA0712503);湖南省教育厅科研项目(19C1740);湖南省科技计划项目(2020GK2036);上海市科委项目(19511120900).


Steel defect detection based on multi-scale lightweight attention
Author:
Affiliation:

1. School of Automation and Electronic Information,Xiangtan University,Xiangtan 411105,China;2. School of Computer Science cdot Cyberspace Security,Xiangtan University,Xiangtan 411105,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:

    针对当前YOLOv5算法检测钢材表面缺陷精度不高、速度慢等问题,提出一种基于多尺度轻量化注意力的YOLO-Steel钢材表面缺陷检测方法.首先,提出一种轻型通道注意力模块,仅需少量计算成本即可有效关注重要通道;然后,利用空洞卷积扩大感受提出一种轻型空间注意力模块,能够在空间维度上提取有价值信息;接着,提出金字塔注意力结构,利用多级池化放缩特征图在不同分辨率特征图上使用空间注意力模块学习其空间依赖信息,对多级特征图使用通道注意力模块重构其通道相关信息,改善检测效果.实验结果表明,YOLO-Steel在钢材表面缺陷数据集上平均精度均值(mAP)可达77.2%,比YOLOv5s算法提高1.8%,模型时间、空间复杂度与YOLOv5s基本持平,在保证检测速度的基础上能够有效提高精确度.

    Abstract:

    Aiming at the problems that the current YOLOv5 algorithm detects steel surface defects with low accuracy and slow speed, a YOLO-Steel steel surface defect detection algorithm is proposed. First, a light-weight channel attention module is proposed, which can effectively focus on important channels with only a small computational cost. Secondly, by using atrous convolution to expand the receptive field, a light-weight spatial attention module is proposed. Finally, a pyramid attention structure is proposed, which uses multi-level pooling to scale feature maps, and uses spatial attention modules on feature maps of different resolutions to learn its spatial dependence information. After splicing in dimensions, the channel attention module is used to reconstruct its channel-related information, which can achieve better detection results for multi-scale detection targets. The experimental results show that the average mean precision(mAP) of YOLO-Steel on the steel surface defect data set can reach 77.2%, which is 1.8 percentage points higher than that of the YOLOv5s algorithm, and the model time and space complexity are basically the same as those of YOLOv5s. On the basis of ensuring the detection speed, the accuracy is effectively improved.

    参考文献
    相似文献
    引证文献
引用本文

周彦,孟江南,王冬丽,等.基于多尺度轻量化注意力的钢材缺陷检测[J].控制与决策,2024,39(3):901-909

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: 2024-02-25
  • 出版日期: 2024-03-20
文章二维码