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 18, 1815011(2022)

Sorting and Detection of Impurity Glass Based on YOLOv4

Bo Yang1, Zhenming Xu1、*, and Jianxin Liu2
Author Affiliations
  • 1China-UK Low Carbon College, Shanghai Jiao Tong University, Shanghai 201306, China
  • 2Nanjing Institute of Electronic Technology, Nanjing 210039, Jiangsu , China
    • show less
    AbstractGet PDF(in Chinese)
    Figures&Tables (12)
    Equations (8)
    References (19)
    Tools
    Paper Information
    Topics
    Figures & Tables(12)
    Impurity glass samples. (a) Crystal; (b) glue; (c) laminated; (d) bar

    Fig. 1. Impurity glass samples. (a) Crystal; (b) glue; (c) laminated; (d) bar

    Download full size
    Three labelling methods for bar and copying. (a) Horizontal box; (b) rotated box; (c) square boxes; (d) small object copying

    Fig. 2. Three labelling methods for bar and copying. (a) Horizontal box; (b) rotated box; (c) square boxes; (d) small object copying

    Download full size
    Relationship between clustering effect of Kmeans++and k

    Fig. 3. Relationship between clustering effect of Kmeans++and k

    Download full size
    Clustering result of Kmeans++ algorithm

    Fig. 4. Clustering result of Kmeans++ algorithm

    Download full size
    YOLOv4 network structure and adjustment

    Fig. 5. YOLOv4 network structure and adjustment

    Download full size
    Loss and AP of validation set during training

    Fig. 6. Loss and AP of validation set during training

    Download full size
    Calculation method of occlusion proportion

    Fig. 7. Calculation method of occlusion proportion

    Download full size
    AP under different augmenting types before & after training

    Fig. 8. AP under different augmenting types before & after training

    Download full size
    Target pasting and detecting examples. (a)(b) Target attached with label; (c) interference; (d) occlusion

    Fig. 9. Target pasting and detecting examples. (a)(b) Target attached with label; (c) interference; (d) occlusion

    Download full size

    • Table 1. Accuracy comparison of different models in testset

      View table

      Table 1. Accuracy comparison of different models in testset

      MethodAPmAP
      BarCrystalGlueLaminated
      YOLOv488.7797.3198.9698.0495.76
      YOLOv4+93.9698.2699.9798.0497.55
      YOLOV4_t+95.4798.9899.0797.9997.88

    • Table 2. Positive and negative sample distribution

      View table

      Table 2. Positive and negative sample distribution

      Type of boxesBarCrystalGlueLaminated
      GT262117110102
      TP25511610999
      FP1992221

    • Table 3. Parameter size and detection performance of typical networks

      View table

      Table 3. Parameter size and detection performance of typical networks

      ParameterYOLOv4YOLOv3YOLOv4-tinyYOLOv3-tinyYOLOv4_t
      mAP0.960.920.880.860.98
      Speed/（frame·s-1）40.5438.51118.67158.2542.82
      Multi-Add/10929.7832.663.3928.96
      Params/106255.82246.1623.5217.90176.22
    Tools

    Get Citation

    Copy Citation Text

    Bo Yang, Zhenming Xu, Jianxin Liu. Sorting and Detection of Impurity Glass Based on YOLOv4[J]. Laser & Optoelectronics Progress, 2022, 59(18): 1815011

    Download Citation

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

    Category: Machine Vision

    Received: Jun. 15, 2021

    Accepted: Aug. 10, 2021

    Published Online: Aug. 29, 2022

    The Author Email: Xu Zhenming (zmxu@sjtu.edu.cn)

    DOI:10.3788/LOP202259.1815011

    Topics

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