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

Acta Optica Sinica, Volume. 40, Issue 19, 1915001(2020)

Light-Weight Siamese Attention Network Object Tracking for Unmanned Aerial Vehicle

Zhoujuan Cui1,2、*, Junshe An1, Yufeng Zhang1,2, and Tianshu Cui1,2
Author Affiliations
  • 1Key Laboratory of Electronics and Information Technology for Space Systems, National Space Science Center, Chinese Academy of Sciences, Beijing 100190, China
  • 2University of Chinese Academy of Sciences, Beijing 100049, China
    • show less
    AbstractGet PDF(in Chinese)
    Figures&Tables (14)
    Equations (0)
    References (24)
    Cited By (2)
    Tools
    Paper Information
    Topics
    Figures & Tables(14)
    Framework of Siamese network with channel spatial coordination attention module

    Fig. 1. Framework of Siamese network with channel spatial coordination attention module

    Download full size
    Convolutional blocks of MobileNetV2

    Fig. 2. Convolutional blocks of MobileNetV2

    Download full size
    Convolution process abstract graph of MobileNetV2

    Fig. 3. Convolution process abstract graph of MobileNetV2

    Download full size
    Grad-CAM network visualization results. (a) No attention module; (b) with attention module

    Fig. 4. Grad-CAM network visualization results. (a) No attention module; (b) with attention module

    Download full size
    Channel spatial coordination attention module

    Fig. 5. Channel spatial coordination attention module

    Download full size
    Success rate comparison of different attention module combinations on OTB-2015

    Fig. 6. Success rate comparison of different attention module combinations on OTB-2015

    Download full size
    Precision comparison of different attention module combinations on OTB-2015

    Fig. 7. Precision comparison of different attention module combinations on OTB-2015

    Download full size
    Qualitative results of the nine tracking algorithms on different video sequences. (a) car6_5; (b) car17; (c) person9; (d) person1_s; (e) uav4; (f) wakeboard6

    Fig. 8. Qualitative results of the nine tracking algorithms on different video sequences. (a) car6_5; (b) car17; (c) person9; (d) person1_s; (e) uav4; (f) wakeboard6

    Download full size
    Results of problem sequence on uav1_1

    Fig. 9. Results of problem sequence on uav1_1

    Download full size
    Results of the tracking algorithms on OTB-2015. (a) Success plot; (b) precision plot

    Fig. 10. Results of the tracking algorithms on OTB-2015. (a) Success plot; (b) precision plot

    Download full size
    Tracking success plots of different attributes videos. (a) Scale variation; (b) aspect ratio change; (c) low resolution; (d) fast motion; (e) full occlusion; (f) partial occlusion; (g) out-of-view; (h) background clutter; (i) illumination variation; (j) viewpoint change; (k) camera motion; (l) similar object

    Fig. 11. Tracking success plots of different attributes videos. (a) Scale variation; (b) aspect ratio change; (c) low resolution; (d) fast motion; (e) full occlusion; (f) partial occlusion; (g) out-of-view; (h) background clutter; (i) illumination variation; (j) viewpoint change; (k) camera motion; (l) similar object

    Download full size
    Tracking precision plots of different attributes videos. (a) Scale variation; (b) aspect ratio change; (c) low resolution; (d) fast motion; (e) full occlusion; (f) partial occlusion; (g) out-of-view; (h) background clutter; (i) illumination variation; (j) viewpoint change; (k) camera motion; (l) similar object

    Fig. 12. Tracking precision plots of different attributes videos. (a) Scale variation; (b) aspect ratio change; (c) low resolution; (d) fast motion; (e) full occlusion; (f) partial occlusion; (g) out-of-view; (h) background clutter; (i) illumination variation; (j) viewpoint change; (k) camera motion; (l) similar object

    Download full size
    Quantitative analysis of some video sequences. (a) Scale variation and aspect ratio change; (b) CLE

    Fig. 13. Quantitative analysis of some video sequences. (a) Scale variation and aspect ratio change; (b) CLE

    Download full size

    • Table 1. Architecture of Siamese network based on MobieleNetV2

      View table

      Table 1. Architecture of Siamese network based on MobieleNetV2

      Layer nameInputOperatorExpansion factorChannelRepeat timeStrideCSCAM
      Input255×255×3Conv2d-3212No
      Layer1127×127×32Bottleneck11611No
      Layer 2127×127×16Bottleneck62422No
      Layer 363×63×24Bottleneck63232Yes
      Layer 431×31×32Bottleneck66441No
      Layer 531×31×64Bottleneck69631Yes
      Layer 631×31×96Bottleneck616031Yes
      Layer 731×31×160Bottleneck632011Yes
      Output31×31×320------
    Tools

    Get Citation

    Copy Citation Text

    Zhoujuan Cui, Junshe An, Yufeng Zhang, Tianshu Cui. Light-Weight Siamese Attention Network Object Tracking for Unmanned Aerial Vehicle[J]. Acta Optica Sinica, 2020, 40(19): 1915001

    Download Citation

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

    Category: Machine Vision

    Received: May. 13, 2020

    Accepted: Jun. 11, 2020

    Published Online: Oct. 12, 2020

    The Author Email: Cui Zhoujuan (constance669@126.com)

    DOI:10.3788/AOS202040.1915001

    Topics

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