Journals Articles Conferences News About CLP
Submit a paper Email Alert
Search
Search
Articles
Journals
News
Advanced Search
Top Searches
2D MaterialsTransformation opticsQuantum PhotonicsSmall lasersSemiconductor UV PhotonicsSupersymmetric microring laser arrays

Laser & Optoelectronics Progress, Volume. 59, Issue 2, 0210011(2022)

Recognition Algorithm of Dangerous Goods in Security Inspection Based on Multi-Layer Attention Mechanism

Wen Wang1, Yatong Zhou1、*, Baojun Shi2, Hao He1, and Jianwei Zhang1
Author Affiliations
  • 1School of Electronic Information Engineering, Hebei University of Technology, Tianjin 300401, China
  • 2School of Mechanical Engineering, Hebei University of Technology, Tianjin 300401, China
    • show less
    AbstractGet PDF(in Chinese)
    Figures&Tables (11)
    Equations (8)
    References (29)
    Tools
    Paper Information
    Topics
    Figures & Tables(11)
    Structure of the dangerous goods security inspection algorithm based on multi-layer attention mechanism

    Fig. 1. Structure of the dangerous goods security inspection algorithm based on multi-layer attention mechanism

    Download full size
    Principle of the channel attention mechanism

    Fig. 2. Principle of the channel attention mechanism

    Download full size
    Principle of the spatial attention mechanism

    Fig. 3. Principle of the spatial attention mechanism

    Download full size
    Structure of the ResNet101

    Fig. 4. Structure of the ResNet101

    Download full size
    Images in the security image data set

    Fig. 5. Images in the security image data set

    Download full size
    Number of five types of dangerous goods

    Fig. 6. Number of five types of dangerous goods

    Download full size
    Loss values in the training process of six algorithms

    Fig. 7. Loss values in the training process of six algorithms

    Download full size
    Optimal accuracy of six algorithms

    Fig. 8. Optimal accuracy of six algorithms

    Download full size
    Visualization result of feature map. (a) Example 1; (b) example 2

    Fig. 9. Visualization result of feature map. (a) Example 1; (b) example 2

    Download full size

    • Table 1. Results of ablation experiments

      View table

      Table 1. Results of ablation experiments

      AlgorithmResNet101CHRA1A2A3mAP/%
      ResNet101+CHR√√81.57
      ResNet101+CHR+A1√√√81.46
      ResNet101+CHR+A2√√√82.99
      ResNet101+CHR+A3√√√82.97
      ResNet101+CHR+A2A3√√√√83.26
      ResNet101+CHR+A1A2A3√√√√√82.79

    • Table 2. Results of comparative experiment

      View table

      Table 2. Results of comparative experiment

      AlgorithmmAP

      SIFT+SVM

      ResNet50+CHR

      73.65

      80.68

      ResNet101+CHR

      DenseNet+CHR

      ResNet50+CHR+A2A3（ours）

      ResNet101+CHR+A2A3（ours）

      81.57

      82.06

      82.34

      83.26

      DenseNet+CHR+A2A3（ours）83.89
    Tools

    Get Citation

    Copy Citation Text

    Wen Wang, Yatong Zhou, Baojun Shi, Hao He, Jianwei Zhang. Recognition Algorithm of Dangerous Goods in Security Inspection Based on Multi-Layer Attention Mechanism[J]. Laser & Optoelectronics Progress, 2022, 59(2): 0210011

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Set citation alerts for article
    Save article for my favorites
    Paper Information

    Category: Image Processing

    Received: Dec. 14, 2020

    Accepted: Mar. 16, 2021

    Published Online: Dec. 23, 2021

    The Author Email: Zhou Yatong (zhouyatong_zw@126.com)

    DOI:10.3788/LOP202259.0210011

    Topics

    laser devices and laser physics
    Lasers and Laser Optics
    Laser physics
    laser manufacturing
    Instrumentation, Measurement and Metrology