Journal of Atmospheric and Environmental Optics, Volume. 18, Issue 5, 469(2023)

Infrared and visible images fusion with spatial multiscale residual networks

ZHANG Yimen1 and LIN Weiguo2、*
Author Affiliations
  • 1Beijing System Design Institute of Electro Mechanic Engineering, Beijing 100005, China
  • 2College of Information Science and Technology, Beijing University of Chemical Technology, Beijing 100029, China
  • show less
    Figures & Tables(6)
    Comparison of residual network structure before and after improvement. (a) Original residual network structure;(b) improve residual network structure
    Overall structure of the network
    Spatial multi-scale attention network structure based on infrared images
    [in Chinese]
    Loss function curve. (a) Loss of SSIM; (b) loss of MSE; (c) loss of gradient; (d) total loss
    • Table 1. Objective evaluation results of comparative experiments

      View table
      View in Article

      Table 1. Objective evaluation results of comparative experiments

      IndexDenseFuseDBNFusionGANDDcGANSMSRN
      SD24.4026.3431.4745.7751.68
      AG2.973.042.675.598.24
      SSIM0.630.710.620.570.73
      EN6.346.576.647.357.69
      SCD1.331.591.161.511.76
      Time/s0.260.140.510.820.32
    Tools

    Get Citation

    Copy Citation Text

    Yimen ZHANG, Weiguo LIN. Infrared and visible images fusion with spatial multiscale residual networks[J]. Journal of Atmospheric and Environmental Optics, 2023, 18(5): 469

    Download Citation

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

    Category:

    Received: Feb. 17, 2022

    Accepted: --

    Published Online: Dec. 1, 2023

    The Author Email: LIN Weiguo (linwg@mail.buct.edu.can)

    DOI:10.3969/j.issn.1673-6141.2023.05.007

    Topics