• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>IEEE Transactions on Industrial Electronics >Automatic and Robust Object Detection in X-Ray Baggage Inspection Using Deep Convolutional Neural Networks
【24h】

Automatic and Robust Object Detection in X-Ray Baggage Inspection Using Deep Convolutional Neural Networks

机译：深卷积神经网络X射线行李检测自动和鲁棒对象检测

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

For the purpose of ensuring public security, automatic inspection of X-ray scanners has been deployed at the entry points of many public places to detect dangerous objects. However, current surveillance systems cannot function without human supervision and intervention. In this article, we propose an effective method using deep convolutional neural networks to detect objects during X-ray baggage inspection. As a first step, a large amount of training data is generated by a specific data augmentation technique. Second, a feature enhancement module is used to improve feature extraction capabilities. Then, in order to address the foreground-background imbalance in the region proposal network, focal loss is adopted. Third, the multiscale fused region of interest is utilized to obtain more robust proposals. Finally, soft nonmaximum suppression is adopted to alleviate overlaps in baggage detection. As compared with existing algorithms, the proposed method proves that it is more accurate and robust when dealing with densely cluttered backgrounds during X-ray baggage inspection.
机译：为确保公共安全的目的，在许多公共场所的入学点进行了X射线扫描仪的自动检查，以检测危险物体。但是，当前监控系统无法运作，没有人为监督和干预。在本文中，我们提出了一种有效的方法，使用深卷积神经网络检测X射线行李检查期间的物体。作为第一步，通过特定的数据增强技术生成大量训练数据。其次，使用特征增强模块来改善特征提取功能。然后，为了解决区域提案网络中的前景背景不平衡，采用焦损。第三，利用MultiScale融合区域来获得更强大的建议。最后，采用柔软的非含糊抑制来缓解行李检测中的重叠。与现有算法相比，所提出的方法证明，在X射线行李检查期间处理密集杂乱的背景时，它更准确且稳健。

著录项

  • 来源
    《IEEE Transactions on Industrial Electronics》 |2021年第10期|10248-10257|共10页
  • 作者

    Gu Bangzhong; Ge Rongjun; Chen Yang; Luo Limin; Coatrieux Gouenou;

  • 作者单位

    Southeast Univ Sch Comp Sci & Technol Lab Image Sci & Technol Nanjing 210096 Peoples R China|Southeast Univ Sch Cyberspace Secur Nanjing 210096 Peoples R China|Southeast Univ Key Lab Comp Network & Informat Integrat Minist Educ Nanjing 210096 Peoples R China|Ctr Rech Informat Biomed Sino Francais F-35000 Rennes France;

    Southeast Univ Sch Comp Sci & Technol Lab Image Sci & Technol Nanjing 210096 Peoples R China|Southeast Univ Sch Cyberspace Secur Nanjing 210096 Peoples R China|Southeast Univ Key Lab Comp Network & Informat Integrat Minist Educ Nanjing 210096 Peoples R China|Ctr Rech Informat Biomed Sino Francais F-35000 Rennes France;

    Southeast Univ Sch Comp Sci & Technol Lab Image Sci & Technol Nanjing 210096 Peoples R China|Southeast Univ Sch Cyberspace Secur Nanjing 210096 Peoples R China|Southeast Univ Key Lab Comp Network & Informat Integrat Minist Educ Nanjing 210096 Peoples R China|Ctr Rech Informat Biomed Sino Francais F-35000 Rennes France;

    Southeast Univ Sch Comp Sci & Technol Lab Image Sci & Technol Nanjing 210096 Peoples R China|Southeast Univ Sch Cyberspace Secur Nanjing 210096 Peoples R China|Southeast Univ Key Lab Comp Network & Informat Integrat Minist Educ Nanjing 210096 Peoples R China|Ctr Rech Informat Biomed Sino Francais F-35000 Rennes France;

    INSERM Telecom Bretagne Inst Mines Telecom LaTIM U1101 F-29238 Brest France;

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

    X-ray imaging; Inspection; Object detection; Feature extraction; Proposals; Task analysis; Convolutional neural networks; Baggage detection; baggage inspection; convolutional neural networks (CNNs); X-ray images for security applications;

    机译：X射线成像;检查;对象检测;特征提取;提案;任务分析;卷积神经网络;行李检测;行李检测;卷积神经网络（CNNS）;用于安全应用的X射线图像;

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