• Infrared and Laser Engineering
  • Vol. 51, Issue 4, 20220167 (2022)
Peng Sun, Yue Yu, Jiaxin Chen, and Hanlin Qin
Author Affiliations
  • School of Optoelectronic Engineering, Xidian University, Xi'an 710071, China
  • show less
    DOI: 10.3788/IRLA20220167 Cite this Article
    Peng Sun, Yue Yu, Jiaxin Chen, Hanlin Qin. Highly dynamic aerial polymorphic target detection method based on deep spatial-temporal feature fusion (Invited)[J]. Infrared and Laser Engineering, 2022, 51(4): 20220167 Copy Citation Text show less
    Deep spatial-temporal feature fusion detection network
    Fig. 1. Deep spatial-temporal feature fusion detection network
    Weighted bidirectional cyclic feature pyramid network
    Fig. 2. Weighted bidirectional cyclic feature pyramid network
    Switchable atrous convolution module
    Fig. 3. Switchable atrous convolution module
    Pyramid LK optical flow
    Fig. 4. Pyramid LK optical flow
    3D convolution module
    Fig. 5. 3D convolution module
    Comparison of target recognition results of UAV in three consecutive frames
    Fig. 6. Comparison of target recognition results of UAV in three consecutive frames
    Comparison of UAV target recognition results by traditional methods
    Fig. 7. Comparison of UAV target recognition results by traditional methods
    MethodAccuracySpeed/FPSRun memory/GB
    C3 D[17]82.31%25.92.32
    TSN[18]85.73%23.33.58
    ECO[19]86.57%27.63.14
    3DLocalCNN[20]85.78%21.62.79
    TADa[21]87.41%29.14.01
    Proposed method89.87%27.02.19
    Table 1. Comparison of detection performance of different algorithms on self-built dataset
    Peng Sun, Yue Yu, Jiaxin Chen, Hanlin Qin. Highly dynamic aerial polymorphic target detection method based on deep spatial-temporal feature fusion (Invited)[J]. Infrared and Laser Engineering, 2022, 51(4): 20220167
    Download Citation