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

Optics and Precision Engineering, Volume. 32, Issue 20, 3071(2024)

Infrared-visible remote sensing image registration method based on Kullback-Leibler divergence using variational approximation

Jia WANG1... Hao WU2,*, Ruigang FU3, Lingshuang KONG1 and Yi ZUO1 |Show fewer author(s)
Author Affiliations
  • 1School of Electronic Information and Electrical Engineering， Changsha University， Changsha40022， China
  • 2Institute of Dataspace， Hefei Comprehensive National Science Center， Hefei30000， China
  • 3College of Electronic Science and Technology， National University of Defense Technology， Changsha41007， China
    • show less
    AbstractGet PDF(in Chinese)
    Figures&Tables (11)
    Equations (25)
    References (45)
    Tools
    Paper Information
    Topics
    Figures & Tables(11)
    GMMs with different covariance matrix values

    Fig. 1. GMMs with different covariance matrix values

    Download full size
    View in Article
    Experimental results on synthetical dataset

    Fig. 2. Experimental results on synthetical dataset

    Download full size
    View in Article
    Infrared and visible image pairs

    Fig. 3. Infrared and visible image pairs

    Download full size
    View in Article
    Registration of aerial image at 4 000 meters

    Fig. 4. Registration of aerial image at 4 000 meters

    Download full size
    View in Article
    Registration of aerial image at 1 000 meters

    Fig. 5. Registration of aerial image at 1 000 meters

    Download full size
    View in Article
    Mosaic of infrared and visible images

    Fig. 6. Mosaic of infrared and visible images

    Download full size
    View in Article
    Registration results on Gaussian noise

    Fig. 7. Registration results on Gaussian noise

    Download full size
    View in Article
    Registration results of salt & pepper noise

    Fig. 8. Registration results of salt & pepper noise

    Download full size
    View in Article
    Box-plot of comparative experiments

    Fig. 9. Box-plot of comparative experiments

    Download full size
    View in Article

    • Table 1. Processing steps of our method

      View table
      View in Article

      Table 1. Processing steps of our method

      Step 1：对红外/可见光图像分别提取Sobel边缘特征点集；

      Step 2：对红外图像特征点集进行正射校正；

      Step 3：对红外/可见光特征点集分别构建高斯混合模型；

      Step 4：采用变分近似法解算两个GMM的KL散度值；

      Step 5：采用粒子群优化算法对配准参数进行迭代寻优；

      Step 6：重复Step 5，直到满足终止条件，输出配准参数。

    • Table 2. Statistic result of comparative experiments

      View table
      View in Article

      Table 2. Statistic result of comparative experiments

      评价指标对比方法
      ICP［30］CPD［31］FRICP［32］BCPD［33］Ours
      配准参数均方根误差均值13.6167.5064.4993.7142.501
      方差3.2794.7651.4821.7241.014
      运行时间/s均值3.3261.7151.6021.0961.557
      方差0.9520.2580.1920.0410.115
    Tools

    Get Citation

    Copy Citation Text

    Jia WANG, Hao WU, Ruigang FU, Lingshuang KONG, Yi ZUO. Infrared-visible remote sensing image registration method based on Kullback-Leibler divergence using variational approximation[J]. Optics and Precision Engineering, 2024, 32(20): 3071

    Download Citation

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

    Category:

    Received: May. 13, 2024

    Accepted: --

    Published Online: Jan. 10, 2025

    The Author Email: WU Hao (wuhao@idata.ah.cn)

    DOI:10.37188/OPE.20243220.3071

    Topics

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