基于SMT-YOLOv8的PCB缺陷检测研究
DOI:
作者:
作者单位:

江西理工大学 机电工程学院

作者简介:

通讯作者:

中图分类号:

TP391.4

基金项目:

江西省重大科技研发专项(20223AAG02019)


Research on PCB defect detection based on SMT-YOLOv8
Author:
Affiliation:

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PCB缺陷检测中目标尺寸小、权重文件庞大难以部署的问题,提出一种改进的YOLOv8小目标缺陷检测方法。该方法将SE注意力机制融入C2f中,使网络能够根据通道域的信息给图像不同位置赋予不同的权重,获取更重要的特征信息;在SPPF中引入Basic RFB以增强网络感受野,提升网络的特征提取能力;新增小目标检测尺度,提升模型对微小缺陷的检测能力;舍弃大目标检测尺度,降低计算负荷并缩小权重文件。实验结果表明,在公开的PCB缺陷数据集上,改进后的YOLOv8较原算法平均精度提升了4.7%、权重文件缩小了27.3%、FPS达到28.9ms/帧。

    Abstract:

    Aiming at the problem of small target size and huge weight file difficult to deploy in PCB defect detection, an improved YOLOv8 small target defect detection method is proposed. The method incorporates the SE attention mechanism into C2f, which enables the network to assign different weights to different locations in the image based on the information in the channel domain to obtain more important feature information; introduces Basic RFB in SPPF to enhance the network sensing field and improve the feature extraction capability of the network; adds a new small target detection scale to improve the model"s ability to detect tiny defects; discards the large target detection scale to reduce the computational load and shrink the weight file. The experimental results show that the improved YOLOv8 improves the average accuracy by 4.7%, shrinks the weight file by 27.3%, and achieves an FPS of 28.9ms/frame over the original algorithm in the publicly available PCB defective dataset.

    参考文献
    相似文献
    引证文献
引用本文
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:2024-05-09
  • 最后修改日期:2024-07-09
  • 录用日期:2024-07-09
  • 在线发布日期:
  • 出版日期: