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. 57, Issue 12, 120005(2020)

Review of Deep Learning Based Object Detection Methods and Their Mainstream Frameworks

Zhongjing Duan1, Shaobo Li1,2、*, Jianjun Hu2, Jing Yang2, and Zheng Wang2
Author Affiliations
  • 1Key Laboratory of Advanced Manufacturing Technology of Ministry of Education, Guizhou University, Guiyang, Guizhou 550025, China
  • 2School of Mechanical Engineering, Guizhou University, Guiyang, Guizhou 550025, China
    • show less
    AbstractGet PDF(in Chinese)
    Figures&Tables (15)
    Equations (0)
    References (70)
    Cited By (19)
    Tools
    Paper Information
    Topics
    Figures & Tables(15)
    LeNet network structure[9]

    Fig. 1. LeNet network structure[9]

    Download full size
    AlexNet network structure[10]

    Fig. 2. AlexNet network structure[10]

    Download full size
    VGG16 network structure[15]

    Fig. 3. VGG16 network structure[15]

    Download full size
    GoogLeNet network structure[19]

    Fig. 4. GoogLeNet network structure[19]

    Download full size
    Basic module of ResNet network[20]

    Fig. 5. Basic module of ResNet network[20]

    Download full size
    DenseNet network structure[21]

    Fig. 6. DenseNet network structure[21]

    Download full size
    Overview of target detection algorithms proposed from November 2013 to October 2019

    Fig. 7. Overview of target detection algorithms proposed from November 2013 to October 2019

    Download full size
    R-CNN implementation flow chart[22]

    Fig. 8. R-CNN implementation flow chart[22]

    Download full size
    Schematic diagram of SPP-Net implementation[24]

    Fig. 9. Schematic diagram of SPP-Net implementation[24]

    Download full size
    Fast R-CNN implementation flow chart[25]

    Fig. 10. Fast R-CNN implementation flow chart[25]

    Download full size
    Flow chart of Faster R-CNN implementation[27]

    Fig. 11. Flow chart of Faster R-CNN implementation[27]

    Download full size
    Implementation process comparison of R-CNN, Fast R-CNN, and Faster R-CNN

    Fig. 12. Implementation process comparison of R-CNN, Fast R-CNN, and Faster R-CNN

    Download full size
    Flow chart of Mask R-CNN implementation[33]

    Fig. 13. Flow chart of Mask R-CNN implementation[33]

    Download full size
    FSAF implementation flow chart

    Fig. 14. FSAF implementation flow chart

    Download full size

    • Table 1. Comparison of R-CNN, Fast R-CNN, and Faster R-CNN

      View table

      Table 1. Comparison of R-CNN, Fast R-CNN, and Faster R-CNN

      ModelUsed methodDisadvantageImprovement
      R-CNN1) Region proposal (SS);2) extraction feature(ConvNet); 3) classification(SVM); 4) regression(Candidate Bbox)1) Complex training steps;2) training and testing areslow and take up a lot of diskspace; 3) CNN features arenot learned and updatedduring SVM and regression1) Refresh mAP of DPMHSC from 34.3% to 66%;2) region proposal andconvolution network are used
      Fast R-CNN1) Region proposal(SS);2) extraction feature(ConvNet);3) classification(softmax);4) Bbox regression(multi-task loss function)1) RP is still extracted withSS (consuming time of 2-3 s);2) difficult to meetreal-time requirements;3) GPU is utilized,but the region proposalmethod is implemented on CPU1) mAP is increased by 4% from 66%;2) speeds of training and testing are improved
      Faster R-CNN1) Region proposalnetwork(RPN);2) extraction feature(ConvNet);3) classification(softmax);4) Bbox regression(multi-task loss function)1) Real-time object detectionis not realized;2) computation ofobtaining region proposaland reclassification isvery large1) It only takes 10 ms to generate suggestion box by usingconvolution network;2) accuracy and speed of detection are improved; 3) implement end-to-end target detection framework
    Tools

    Get Citation

    Copy Citation Text

    Zhongjing Duan, Shaobo Li, Jianjun Hu, Jing Yang, Zheng Wang. Review of Deep Learning Based Object Detection Methods and Their Mainstream Frameworks[J]. Laser & Optoelectronics Progress, 2020, 57(12): 120005

    Download Citation

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

    Category: Reviews

    Received: Nov. 11, 2019

    Accepted: Dec. 6, 2019

    Published Online: Jun. 3, 2020

    The Author Email: Li Shaobo (lishaobo@gzu.edu.cn)

    DOI:10.3788/LOP57.120005

    Topics

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