期刊文献+

基于YOLOv3的布匹瑕疵检测方法

Defect Detection Method for Textile Fabrics Based on YOLOv3
下载PDF
导出
摘要 针对布匹瑕疵差异较大、分布不均匀等问题,在YOLOv3中引入SwinTransformerBlock模块,用自注意力机制专注于有效特征排除无效特征的干扰,解决瑕疵差异大、分布不均等问题.同时用可变形卷积v2替换普通卷积,增大网络的感受野和多尺度建模能力,更好地适应瑕疵的形状和位置变化,从而提高目标检测的准确性和鲁棒性.实验结果表明,改进后算法在mAP上比原算法提高了3.80%,在检测速度上下降了2.86帧每秒. Regarding the problem of large differences in fabric defects and uneven distribution,this paper solves the problem of large differences in defects and uneven distribution by introducing the SwinTrans-formerBlock module in YOLOv3.The self-attention mechanism focuses on effective feature exclusion of inval-id feature interference.At the same time,deformable convolution is used to replace ordinary convolution to in-crease the network’s receptive field and multi-scale modeling ability so as to better adapt to the shape and po-sition changes of defects,thereby improving the accuracy and robustness of object detection.Experimental re-sults show that the improved algorithm has increased by 3.80%in mAP compared to the original algorithm,and decreased by 2.86 frames in detection speed.
作者 伍洪健 邓作杰 章银萍 张金召 王小康 WU Hongjian;DENG Zuojie;ZHANG Yinping;ZHANG Jinzhao;WANG Xiaokang(College of Computer and Communication,Hunan Institute of Engineering,Xiangtan 411104,China)
出处 《湖南工程学院学报(自然科学版)》 2023年第3期39-43,共5页 Journal of Hunan Institute of Engineering(Natural Science Edition)
基金 湖南省教育厅科研重点项目(21A0451).
关键词 布匹瑕疵检测 目标检测 SwinTransformerBlock 可变形卷积v2 fabric defect detection object detection SwinTransformerBlock deformable ConvNets v2
  • 相关文献

参考文献3

二级参考文献22

共引文献37

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部