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  

Computer motherboard assembly defect detection using parallel feature extraction and progressive feature fusion

作　　者：陈俊英[1] 李朝阳 黄汉涛 董戌泽 CHEN Junying;LI Zhaoyang;HUANG Hantao;DONG Xuze(School of Information and Control Engineering,Xi'an University of Architecture and Technology,Xi'an 710055,China)

机构地区：[1]西安建筑科技大学信息与控制工程学院,陕西西安710055

出　　处：《光学精密工程》2024年第10期1622-1637,共16页Optics and Precision Engineering

基　　金：国家自然科学基金项目(No.62103316);陕西省自然科学基础研究计划项目(No.2023-JC-YB-562)。

摘　　要：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。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 progressive feature fusion.Firstly,a parallel residual feature extraction network was proposed by combining partial convolution and visual Transformer.The low computational complexity of partial convolution was utilized 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.Secondly,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 YOLOv5 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 automation and intelligence of surface assembly defect detection on computer motherboards in the actual industrial environment.

关 键 词：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 

分 类 号：TP394.1[自动化与计算机技术—计算机应用技术] TH691.9[自动化与计算机技术—计算机科学与技术]