改进YOLOv8的金属表面缺陷检测模型  

Improved YOLOv8 metal surface defect detection model

作　　者：龙阳 肖小玲[1] LONG Yang;XIAO Xiaoling(School of Computer Science,Yangtze University,Jingzhou 434100,CHN)

机构地区：[1]长江大学计算机科学学院,湖北荆州434100

出　　处：《制造技术与机床》2024年第8期187-194,共8页Manufacturing Technology & Machine Tool

基　　金：国家自然科学基金项目(61771354)。

摘　　要：针对工业制造中金属表面缺陷检测的检测精度低、漏检率和误检率高等问题,文章提出了一种改进YOLOv8的金属表面缺陷检测模型。首先采用CG模块替换掉Backbone的下采样卷积模块,增强模型的上下文信息理解能力;其次采用RepGFPN模块替换原始的特征金字塔网络,提高模型的多尺度特征提取能力;最后通过对检测头重设计,提出GDetect模块,提升模型的整体性能。实验结果表明,改进后的模型在GC10-DET数据集中准确率、召回率和m AP@0.5达到了71.2%、72.4%和74.5%,分别提高了2.8%、8.1%和6.0%,参数量和计算量分别减少了6%和22%。同时在PASCAL VOC和NEU-DET数据集验证了模型在不同数据集下的鲁棒性和泛化能力,提高了对目标的检测精度。所提出的改进模型在金属缺陷检测领域取得了显著进展,提高了检测精度,解决了常见问题,并在保持轻量级的同时实现了较高的性能,为金属表面缺陷检测提供了一种高效且可行的解决方案。In order to solve the problems of low detection accuracy,high miss detection rate and high false detection rate of metal surface defect detection in industrial manufacturing,an improved YOLOv8 metal surface defect detection model is proposed.Firstly,the CG module is used to replace Backbone's downsampling convolution module to enhance the model’s contextual information understanding ability;secondly,the RepGFPN module is used to replace the original feature pyramid network to improve the model's multi-scale feature extraction ability;finally,by redesigning the detection head,The GDetect module is proposed to improve the overall performance of the model.Experimental results show that the accuracy,recall and mAP@0.5 of the improved model reached 71.2%,72.4%and 74.5%in the GC10-DET data set,which increased by 2.8%,8.1%and 6.0%respectively.The number of parameters and calculation The volumes were reduced by 6%and 22%respectively.At the same time,the robustness and generalization ability of the model under different data sets were verified in the PASCAL VOC and NEU-DET data sets,and the detection accuracy of the target was improved.The proposed improved model has made significant progress in the field of metal defect detection,improved detection accuracy,solved common problems,and achieved high performance while maintaining lightweight,providing an efficient and feasible solution for metal surface defect detection.

关 键 词：金属表面缺陷检测 YOLOv8 CG RepGFPN GDetect 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]