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, 0210004(2022)

Multi Face Real-Time Tracking System Based on DTN in Multi Camera Field of View

Guoyin Ren1,2, Lü Xiaoqi1,2,3、*, and Yuhao Li2
Author Affiliations
  • 1School of Mechanical Engineering, Inner Mongolia University of Science & Technology, Baotou , Inner Mongolia 014010, China
  • 2School of Information Engineering,Inner Mongolia University of Science & Technology, Baotou , Inner Mongolia 014010, China
  • 3Inner Mongolia University of Technology, Hohhot , Inner Mongolia 010051, China
    • show less
    AbstractGet PDF(in Chinese)
    Figures&Tables (21)
    Equations (0)
    References (29)
    Cited By (1)
    Tools
    Paper Information
    Topics
    Figures & Tables(21)
    Flow chart of CW algorithm

    Fig. 1. Flow chart of CW algorithm

    Download full size
    Improved quadruplet network including two triplet networks

    Fig. 2. Improved quadruplet network including two triplet networks

    Download full size
    Training the loss function of WIDER FACE data set

    Fig. 3. Training the loss function of WIDER FACE data set

    Download full size
    Side face detection

    Fig. 4. Side face detection

    Download full size
    Small face detection

    Fig. 5. Small face detection

    Download full size
    CW algorithm clustering similar face nodes

    Fig. 6. CW algorithm clustering similar face nodes

    Download full size
    Clustering with nodes

    Fig. 7. Clustering with nodes

    Download full size
    Isosurface display map

    Fig. 8. Isosurface display map

    Download full size
    Learning rate varying with epoch

    Fig. 9. Learning rate varying with epoch

    Download full size
    Total loss varying with epoch

    Fig. 10. Total loss varying with epoch

    Download full size
    Accuracy varying with epoch

    Fig. 11. Accuracy varying with epoch

    Download full size
    Time varying with epoch

    Fig. 12. Time varying with epoch

    Download full size
    ROC for different networks when subspace number is 5

    Fig. 13. ROC for different networks when subspace number is 5

    Download full size
    ROC for different networks when subspace number is 10

    Fig. 14. ROC for different networks when subspace number is 10

    Download full size
    ROC for different networks when subspace number is 20

    Fig. 15. ROC for different networks when subspace number is 20

    Download full size
    ROC comparison between different networks and FaceNet

    Fig. 16. ROC comparison between different networks and FaceNet

    Download full size
    Multi camera face clustering based on Siam16

    Fig. 17. Multi camera face clustering based on Siam16

    Download full size
    Multi camera face tracking results of street view based on Siam16

    Fig. 18. Multi camera face tracking results of street view based on Siam16

    Download full size

    • Table 1. Performance comparison between CW algorithm and several clustering algorithms

      View table

      Table 1. Performance comparison between CW algorithm and several clustering algorithms

      ParameterK-meansDBSCANHACMCLCW
      Algorithm complexityO（n）O（n2）O（n3）O（n2）O（n）-O（n2）
      Unknown number of clusters××√√√
      Real-time monitoring××××√

    • Table 2. Comparison of recognition rates of multiple detection networks on LFW data set

      View table

      Table 2. Comparison of recognition rates of multiple detection networks on LFW data set

      ModelFeature sizeAccuracy /%
      1-DTNCNN16102499.47
      2-DTNCNN16409699.51
      3-MSMLCNN16102499.09
      4-MSMLCNN16409699.21
      5-TrHardCNN16102499.02
      6-TrHardCNN16409699.11
      7-QuadrupletCNN16102498.45
      8-QuadrupletCNN16409698.85
      9-TripletCNN16102498.25
      10-TripletCNN16409698.78
      11-SiamCNN16102495.99
      12-SiamCNN16409696.21
      13-ResNet50409695.87
      14-VGG-19409694.14
      15-VGG-16409692.46
      16-AlexNet409689.04

    • Table 3. Performance comparison on GOT-10k validation set

      View table

      Table 3. Performance comparison on GOT-10k validation set

      Tracker/YearSR0.5 /%SR0.75 /%AO /%
      LWL（*）［26］/202195.185.286.7
      LWL［27］/202092.482.284.6
      PrDiMP-50［28］/202089.672.877.8
      DiMP-50［29］/201988.768.875.3
      Siam16/202190.474.979.6
    Tools

    Get Citation

    Copy Citation Text

    Guoyin Ren, Lü Xiaoqi, Yuhao Li. Multi Face Real-Time Tracking System Based on DTN in Multi Camera Field of View[J]. Laser & Optoelectronics Progress, 2022, 59(2): 0210004

    Download Citation

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

    Category: Image Processing

    Received: Jan. 8, 2021

    Accepted: Mar. 9, 2021

    Published Online: Dec. 23, 2021

    The Author Email: Lü Xiaoqi (635302395@qq.com)

    DOI:10.3788/LOP202259.0210004

    Topics

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