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. 58, Issue 14, 1410024(2021)

Infrared and Visible Image Fusion Method Based on Dual-Channel Generative Adversarial Network

Chunping Hou1, Xiaocong Wang1, Han Xia2, and Yang Yang1、*
Author Affiliations
  • 1School of Electrical and Information Engineering,Tianjin University, Tianjin 300072, China
  • 2Tianjin International Engineering Institute, Tianjin University, Tianjin 300072, China
    • show less
    AbstractGet PDF(in Chinese)
    Figures&Tables (9)
    Equations (0)
    References (23)
    Cited By (2)
    Tools
    Paper Information
    Topics
    Figures & Tables(9)
    Network architecture of our method

    Fig. 1. Network architecture of our method

    Download full size
    GAN structure based on dual-channel

    Fig. 2. GAN structure based on dual-channel

    Download full size
    Structure of the pixel attention module

    Fig. 3. Structure of the pixel attention module

    Download full size
    Structure of the discriminator network

    Fig. 4. Structure of the discriminator network

    Download full size
    Fusion results of different methods. (a)--(e) Image 1--image 5

    Fig. 5. Fusion results of different methods. (a)--(e) Image 1--image 5

    Download full size
    Partial enlarged view of Fig. 5(d). (a) IR; (b) VI; (c) CVT; (d) MSVD; (e) Wavelet; (f) CSR; (g) DLF; (h) FusionGAN; (i) DenseFuse; (g) LatLRR; (k) PMGI; (l) our method

    Fig. 6. Partial enlarged view of Fig. 5(d). (a) IR; (b) VI; (c) CVT; (d) MSVD; (e) Wavelet; (f) CSR; (g) DLF; (h) FusionGAN; (i) DenseFuse; (g) LatLRR; (k) PMGI; (l) our method

    Download full size
    Results of ablation experiments.(a)--(c) Image 1--image 3

    Fig. 7. Results of ablation experiments.(a)--(c) Image 1--image 3

    Download full size

    • Table 1. Evaluation indicators of different fusion methods

      View table

      Table 1. Evaluation indicators of different fusion methods

      EvaluationENSDCCSSIMQ_CVQ_CB
      CVT6.58327.0290.6080.712370.720.508
      MSVD6.40823.7440.6300.743401.3140.491
      Wavelet6.32123.1940.6360.773356.3500.487
      CSR6.41525.0300.6260.743390.7680.491
      DLF6.53535.2790.6350.716317.8500.461
      FusionGAN6.33625.0300.5170.647627.3130.421
      DenseFuse7.04839.3060.5940.670350.9090.489
      LatLRR6.34323.5100.6350.772365.9840.483
      PMGI6.96434.0120.6280.706419.2410.522
      Ours6.83632.6380.6150.779626.4440.525

    • Table 2. Image fusion results of different methods

      View table

      Table 2. Image fusion results of different methods

      EvaluationENSDCCSSIMQ_CVQ_CB
      no_att&single_ch6.78428.2310.6010.834377.7940.470
      no_att&double_ch7.30045.7450.6460.799405.5440.496
      att&single_ch6.47625.4540.6100.6541052.1100.479
      att&double_ch6.79228.4800.6540.864688.3660.513
    Tools

    Get Citation

    Copy Citation Text

    Chunping Hou, Xiaocong Wang, Han Xia, Yang Yang. Infrared and Visible Image Fusion Method Based on Dual-Channel Generative Adversarial Network[J]. Laser & Optoelectronics Progress, 2021, 58(14): 1410024

    Download Citation

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

    Category: Image Processing

    Received: Aug. 17, 2020

    Accepted: Sep. 30, 2020

    Published Online: Jul. 6, 2021

    The Author Email: Yang Yang (yang_yang@tju.edu.cn)

    DOI:10.3788/LOP202158.1410024

    Topics

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