• Acta Photonica Sinica
  • Vol. 51, Issue 9, 0910002 (2022)
Manli WANG, Xiaolong WANG*, and Changsen ZHANG
Author Affiliations
  • School of Physics & Information Engineering,Henan Polytechnic University,Jiaozuo ,Henan 454000,China
  • show less
    DOI: 10.3788/gzxb20225109.0910002 Cite this Article
    Manli WANG, Xiaolong WANG, Changsen ZHANG. Infrared and Visible Image Fusion Algorithm Based on Dynamic Range Compression Enhancement and NSST[J]. Acta Photonica Sinica, 2022, 51(9): 0910002 Copy Citation Text show less
    Infrared and visible image fusion framework
    Fig. 1. Infrared and visible image fusion framework
    Comparison of visible images before and after enhancement
    Fig. 2. Comparison of visible images before and after enhancement
    Coefficients extracted by NSST decomposition
    Fig. 3. Coefficients extracted by NSST decomposition
    Fusion results of infrared and visible algorithms
    Fig. 4. Fusion results of infrared and visible algorithms
    Fusion results of T1~T4 images
    Fig. 5. Fusion results of T1~T4 images
    Comparison of objective data of images before and after fusion
    Fig. 6. Comparison of objective data of images before and after fusion
    The influence of the selection of threshold shrinkage coefficient on image objective data
    Fig. 7. The influence of the selection of threshold shrinkage coefficient on image objective data
    Fusion results of different threshold coefficients
    Fig. 8. Fusion results of different threshold coefficients
    Fusion results of “Road” images
    Fig. 9. Fusion results of “Road” images
    Fusion results of “Tent” images
    Fig. 10. Fusion results of “Tent” images
    Fusion results of mine images
    Fig. 11. Fusion results of mine images
    Fusion results of “Road” images with noise variance of 5
    Fig. 12. Fusion results of “Road” images with noise variance of 5
    Fusion results of “Road” images with noise variance of 10
    Fig. 13. Fusion results of “Road” images with noise variance of 10
    ImageMethodsSFIEEIAGCC
    RoadDCTWT10.0035.93322.8872.2390.677
    WLS⁃VSM13.3396.13835.3073.3970.649
    TE⁃MST11.8356.61935.1463.3600.558
    AUIF10.6764.89919.2861.8280.633
    DIDF10.8294.66320.1371.8890.629
    NSST⁃MGPCNN12.6526.27635.9683.3980.650
    NSST⁃PAPCNN11.7926.65635.1103.2760.623
    Proposed17.1736.69352.5585.0610.636
    Table 1. Objective evaluation results of the first two groups of fusion images
    ImageMethodsSFIEEIAGCC
    TentDCTWT8.5336.33328.2352.9710.521
    WLS⁃VSM11.3126.60741.2724.2450.515
    TE⁃MST12.6496.74148.2134.9050.375
    AUIF11.5936.92342.9044.2490.513
    DIDF11.5916.90443.4174.1990.509
    NSST⁃MGPCNN8.5586.83933.4523.1610.506
    NSST⁃PAPCNN7.3686.91731.0112.9230.465
    Proposed14.5497.31658.2445.8800.474
    Table 2. Objective evaluation results of the second two groups of fusion images
    MethodsDCTWTWLS⁃VSMTE⁃MSTAUIFDIDFNSST⁃MGPCNNNSST⁃PAPCNNProposed
    Time/s0.2251.1911.4091.0241.05374.15126.0847.711
    Table 3. The running time of eight fusion algorithms
    Noise varianceDCTWTWLS⁃VSMTE⁃MSTAUIFDIDFNSST⁃MGPCNNNSST⁃PAPCNNProposed
    54.8106.8856.7152.0261.4055.2125.1840.694
    109.49510.41313.1074.0452.69813.39310.6961.090
    Table 4. NV statistics of fusion images based on eight algorithms
    Manli WANG, Xiaolong WANG, Changsen ZHANG. Infrared and Visible Image Fusion Algorithm Based on Dynamic Range Compression Enhancement and NSST[J]. Acta Photonica Sinica, 2022, 51(9): 0910002
    Download Citation