• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>IEEE transactions on industrial informatics >Two Deep Learning Networks for Rail Surface Defect Inspection of Limited Samples With Line-Level Label
【24h】

Two Deep Learning Networks for Rail Surface Defect Inspection of Limited Samples With Line-Level Label

机译：具有线级标签的有限样品的轨道表面缺陷检查的两个深度学习网络

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Rail surface defect (RSD) inspection is an essential routine maintenance task. Computer vision testing is suitable for RSD inspection with its intuitiveness and rapidity. Deep learning techniques, which can extract deep semantic features, have been applied to inspect RSDs in recent years. However, these methods demand thousands of samples. And sample collection requires hard-working and costs high. To address the issue, a novel inspection scheme for RSDs is presented for limited samples with a line-level label, which regards defect images as sequence data and classifies pixel lines. Thousands of pixel lines are easy to be collected and labeling line-level is a simple task in labeling works. Then two methods OC-IAN and OC-TD are designed for inspecting express rail defects and common/heavy rail defects, respectively. OC-IAN and OC-TD both employ one-dimensional convolutional neural network (ODCNN) to extract features and long- and short-term memory (LSTM) network to extract context information. The main differences between OC-IAN and OC-TD are that OC-TD applies a double-branch structure and removes the attention module. Experimental results on RSDDs dataset demonstrate that our methods are effective and outperform the state-of-the-art methods on defect-level metrics (Type-I: Rec-0.9314, Pre-0.8421, F1-0.8845; Type-II: Rec-0.9427, Pre-0.9176, F1-0.9300).
机译：轨道表面缺陷（RSD）检查是一个必不可少的日常维护任务。计算机视觉测试适用于RSD检查，以其直观和快速。可以提取深入语义特征的深度学习技术已应用于近年来检查RSD。但是，这些方法需要数千个样本。并采样收集需要努力工作和成本高。为了解决此问题，针对具有线级标签的有限样本呈现了一个新的RSD的检验方案，这将缺陷图像视为序列数据并对像素线进行分类。数千条像素线路易于收集，标签级别是标签工作中的简单任务。然后，两种方法oc-ian和oc-td专为检查快速轨道缺陷和共同/重导轨缺陷而设计。 OC-IAN和OC-TD都采用一维卷积神经网络（ODCNN）来提取特征和长期内存（LSTM）网络以提取上下文信息。 OC-IAN和OC-TD之间的主要差异是OC-TD应用双分支结构并删除注意模块。 RSDDS数据集上的实验结果表明，我们的方法是有效和优于缺陷级度量的最先进的方法（I型：REC-0.9314，0.8421，F1-0.8845; II型：REC- 0.9427，0.9176，F1-0.9300）。

著录项

  • 来源
    《IEEE transactions on industrial informatics》 |2021年第10期|6731-6741|共11页
  • 作者

    Zhang Defu; Song Kechen; Wang Qi; He Yu; Wen Xin; Yan Yunhui;

  • 作者单位

    Northeastern Univ Sch Mech Engn & Automat Shenyang 110819 Peoples R China|Northeastern Univ Key Lab Vibrat & Control Aeroprop Syst Minist Educ China Shenyang 110819 Peoples R China;

    Northeastern Univ Sch Mech Engn & Automat Shenyang 110819 Peoples R China|Northeastern Univ Key Lab Vibrat & Control Aeroprop Syst Minist Educ China Shenyang 110819 Peoples R China;

    Northeastern Univ Sch Mech Engn & Automat Shenyang 110819 Peoples R China|Northeastern Univ Key Lab Vibrat & Control Aeroprop Syst Minist Educ China Shenyang 110819 Peoples R China;

    Northeastern Univ Sch Mech Engn & Automat Shenyang 110819 Peoples R China|Northeastern Univ Key Lab Vibrat & Control Aeroprop Syst Minist Educ China Shenyang 110819 Peoples R China;

    Shenyang Univ Technol Sch Software Shenyang 110870 Peoples R China;

    Northeastern Univ Sch Mech Engn & Automat Shenyang 110819 Peoples R China|Northeastern Univ Key Lab Vibrat & Control Aeroprop Syst Minist Educ China Shenyang 110819 Peoples R China;

  • 收录信息
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

    Deep learning techniques; limited samples; line-level label; rail surface defect (RSD); sequence data;

    机译：深度学习技术;限制样品;线级标签;轨道表面缺陷（RSD）;序列数据;

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号