首页|并行特征提取和渐进特征融合的计算机主板装配缺陷检测

并行特征提取和渐进特征融合的计算机主板装配缺陷检测

扫码查看
原文链接
  • 国家科技期刊平台
  • NETL
  • NSTL
  • 万方数据
针对计算机主板装配缺陷检测中的元器件位置分布复杂、缺陷目标不显著及多尺度等问题,本文提出了一种并行特征提取和互交叉渐进特征融合的端到端的缺陷检测算法.首先,结合部分卷积和视觉Transformer提出了一种并行残差特征提取网络,利用部分卷积的低计算复杂度的优势提取局部特征,同时利用视觉Transformer的长距离建模能力扩大模型的感受野,增强网络的特征提取能力.其次,引入注意力机制和特征渐进融合机制,提出了一种多尺度注意力互交叉的渐进特征融合网络,增强检测模型的特征融合能力.在公开数据集上的实验结果表明,该算法的平均精度均值(mAP)达到了94.63%,相较于基线模型YOLOv5提升了4.62%,并优于其他几种先进模型,检测速度达到了25 FPS.实现了较好的检测精度与速度的平衡,为实际工业环境下计算机主板表面装配缺陷检测自动化和智能化的实现提供了一种快速、有效的方法.
Computer motherboard assembly defect detection using parallel feature extraction and progressive feature fusion
In view of the complex distribution of component positions,lack of prominent defect targets,and multi-scale issues in the detection of defects in computer motherboard assembly,this paper proposed an end-to-end defect detection algorithm based on parallel feature extraction and cross-attention progres-sive feature fusion.Firstly,a parallel residual feature extraction network was proposed by combining par-tial convolution and visual Transformer.The low computational complexity of partial convolution was uti-lized to extract local features,while the long-distance modeling ability of visual Transformer was utilized to expand the receptive field of the model and enhance the feature extraction ability of the network.Sec-ondly,the cross-attention mechanism was introduced to progressively fuse multi-scale features,and a multi-scale cross-attention progressive feature fusion network was constructed to enhance the feature fusion ability of the detection model.The experimental results on the public dataset show that the mean average accuracy(mAP)of the algorithm reaches 94.63%,which is 4.62%higher than the baseline model YO-LOv5 and is superior to several other advanced models.The detection speed reaches 25 FPS,achieving a good balance between detection accuracy and speed.It provides a fast and effective method for the automa-tion and intelligence of surface assembly defect detection on computer motherboards in the actual industrial environment.

detection of defects in computer motherboard assemblyparallel feature extractionprogres-sive feature fusionvisual transformerpartial convolution

陈俊英、李朝阳、黄汉涛、董戌泽

展开 >

西安建筑科技大学 信息与控制工程学院,陕西 西安 710055

计算机主板装配缺陷检测 并行特征提取 渐进特征融合 视觉Transformer 部分卷积

国家自然科学基金陕西省自然科学基础研究计划

621033162023-JC-YB-562

2024

10.37188/OPE.20243210.1622

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(10)
  • 11