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. 61, Issue 20, 2011011(2024)

Luminance-Adaptive Infrared and Visible Image Fusion Based on Retinex Theory (Invited)

Yihang Cheng1,2、*, Zhengyu Qiao1,3, Yong Huang1,2,3, and Qun Hao1,2,3
Author Affiliations
  • 1School of Optics and Photonics, Beijing Institute of Technology, Beijing 100081, China
  • 2Yangtze Delta Region Academy, Beijing Institute of Technology, Jiaxing 314003, Zhejiang , China
  • 3National Key Laboratory on Near-Surface Detection, Beijing 100087, China
    • show less
    AbstractGet PDF(in Chinese)
    Figures&Tables (10)
    Equations (18)
    References (37)
    Tools
    Paper Information
    Topics
    Figures & Tables(10)
    Visible light image and its decomposed reflectivity image and illuminance image. (a) Visible light image; (b) reflectivity image; (c) illuminance image

    Fig. 1. Visible light image and its decomposed reflectivity image and illuminance image. (a) Visible light image; (b) reflectivity image; (c) illuminance image

    Download full size
    Overall framework of the proposed model

    Fig. 2. Overall framework of the proposed model

    Download full size
    Comparison test results of different methods at low light scene on LLVIP dataset

    Fig. 3. Comparison test results of different methods at low light scene on LLVIP dataset

    Download full size
    Comparison test results of different methods at night high light scene on LLVIP dataset

    Fig. 4. Comparison test results of different methods at night high light scene on LLVIP dataset

    Download full size
    Comparison test results of different methods at daytime scene on LLVIP dataset

    Fig. 5. Comparison test results of different methods at daytime scene on LLVIP dataset

    Download full size
    Comparison test results of different methods at different scenes on RoadScene dataset. (a) VIS; (b) IR; (c) ours; (d) DenseFuse; (e) FusionGAN; (f) GFF; (g) GTF; (h) SDNet; (i) U2Fusion; (j) DIVFusion

    Fig. 6. Comparison test results of different methods at different scenes on RoadScene dataset. (a) VIS; (b) IR; (c) ours; (d) DenseFuse; (e) FusionGAN; (f) GFF; (g) GTF; (h) SDNet; (i) U2Fusion; (j) DIVFusion

    Download full size
    Objective indicators of different methods for 32 pairs of test image fusion results on RoadScene dataset

    Fig. 7. Objective indicators of different methods for 32 pairs of test image fusion results on RoadScene dataset

    Download full size
    Results of ablation tests in different scenes on LLVIP dataset. (a) VIS; (b) IR; (c) RDBlock removing; (d) STBlock removing; (e) multi-scale feature extraction module removing; (f) proposed model

    Fig. 8. Results of ablation tests in different scenes on LLVIP dataset. (a) VIS; (b) IR; (c) RDBlock removing; (d) STBlock removing; (e) multi-scale feature extraction module removing; (f) proposed model

    Download full size

    • Table 1. Objective indicators of each method on 45 pairs of images of LLVIP dataset

      View table

      Table 1. Objective indicators of each method on 45 pairs of images of LLVIP dataset

      MethodAGSDSFMIENCCVIF
      DenseFuse7.716061.813021.77672.68454.79931.45070.8115
      FusionGAN4.311828.390310.60002.48224.48951.32920.1830
      GFF10.646751.814126.42333.35675.07991.34270.6269
      GTF8.415845.779721.01333.10774.74621.33170.3632
      SDNet9.007535.774821.65332.33284.68441.39900.3340
      U2Fusion8.066640.199518.93332.27284.67961.47830.4676
      DIVFusion6.612254.291915.65332.34465.0291.43410.7913
      Ours10.729758.927526.89673.00045.2031.32680.8214

    • Table 2. Objective metrics of ablation experiments for 45 pairs of images on LLVIP dataset

      View table

      Table 2. Objective metrics of ablation experiments for 45 pairs of images on LLVIP dataset

      MethodAGSDSFMIENCCVIF
      A13.082748.855923.62913.05797.30771.05750.5934
      B9.307843.556116.38022.75037.08431.44310.6488
      C13.806261.167424.59363.63897.72811.22610.8907
      Ours14.007963.561225.1743.72357.77981.21340.9255
    Tools

    Get Citation

    Copy Citation Text

    Yihang Cheng, Zhengyu Qiao, Yong Huang, Qun Hao. Luminance-Adaptive Infrared and Visible Image Fusion Based on Retinex Theory (Invited)[J]. Laser & Optoelectronics Progress, 2024, 61(20): 2011011

    Download Citation

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

    Category: Imaging Systems

    Received: Jul. 4, 2024

    Accepted: Aug. 27, 2024

    Published Online: Nov. 1, 2024

    The Author Email:

    DOI:10.3788/LOP241637

    CSTR:32186.14.LOP241637

    Topics

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