欢迎访问《轻工机械》稿件在线采编系统!设为首页 | 加入收藏    
信息公告:  
文章检索:
稿件处理系统
期刊信息
  • 中国标准连:ISSN1005-2895
  • 续出版物号: CN 33-1180/TH
  • 主管单位:轻工业杭州机电设计研究院有限公司
  • 主办单位:轻工业杭州机电设计研究院有限公司、中国轻工机械协会、中国轻工业机械总公司
  • 社  长:刘安江
  • 主  编:黄丽珍
  • 地  址:杭州市余杭区高教路970号西溪联合科技广场4-711
  • 电子邮件:qgjxzz@126.com
理事单位          MORE>>
朱振宇1, 江文斌2, 袁嫣红1*.基于改进YOLOv5s的缫丝机绪下茧粒数检测[J].轻工机械,2024,42(6):73-81
基于改进YOLOv5s的缫丝机绪下茧粒数检测
Detection of Cocoon Number under Thread of Silk Spinning Machine Based on Improved YOLOv5s
  
DOI:10.3969/j.issn.1005 2895.2024.06.010
中文关键词:  目标检测  改进YOLOv5s  空间增强注意力模块  SE注意力机制  Soft NMS算法
英文关键词:object detection  improved YOLOv5s  SEAM(Spatially Enhanced Attention Module)  squeeze and excitation attention mechanism  Soft NMS
基金项目:
作者单位
朱振宇1, 江文斌2, 袁嫣红1* 1.浙江理工大学 机械工程学院 浙江 杭州310018  2.浙江理工大学 纺织科学与工程学院(国际丝绸学院) 浙江 杭州310018 
摘要点击次数: 21
全文下载次数: 0
中文摘要:
      为解决缫丝时绪下茧粒与工作背景辨识度较低、茧粒分布密集以及茧粒之间相互遮挡而漏检的问题,课题组提出了一种基于改进YOLOv5s的缫丝机绪下茧粒数检测算法。该算法在Backbone中引入RFB SE(receptive field block squeeze and excitation)模块,实现了对与工作背景辨识度较低茧粒的检测;使用空间增强注意力模块(spatially enhanced attention module,SEAM)来改进网络的颈部(Neck),解决了由于茧粒遮挡而造成漏检的问题;引入Soft NMS代替非极大值抑制(non max suppression,NMS),改变了原始模型对于预测框的处理方式,更好地改善了漏检问题。实验结果表明:该算法在数据集上召回率达到了98.3%;平均精度均值达到了98.8%,相比原始模型提高了3.3%。该算法解决了茧粒与工作背景辨识度低、茧粒间相互遮挡而造成的漏检问题。
英文摘要:
      To solve the problems of low recognition between the cocoons and the working background, dense distribution of cocoons, and mutual occlusion between cocoons during the silk reeling process, research group proposed an improved YOLOv5s based algorithm for detecting the number of cocoons in the silk reeling machine. This algorithm introduced the receptive field block squeeze and excitation(RFB SE) module in Backbone to detect cocoons with low recognition of work background. Using spatially enhanced attention module(SEAM) to improve the neck of the network solved the problem of missed detections caused by cocoon occlusion. The introduction of Soft NMS instead of non max suppression(NMS) changed the way of original model deal with the prediction box and better improved the problem of missed detections. The experimental results show that the algorithm has a recall rate of 98.3% and an average accuracy of 988% on the dataset in this paper, which is 3.3% higher than the original model. This algorithm solves the problem of missed detections caused by low recognition of cocoons and working background and mutual occlusion between cocoons.
查看全文  查看/发表评论  下载PDF阅读器
关闭