Laser & Optoelectronics Progress, Volume. 58, Issue 16, 1610009(2021)

Nonlinear Grayscale Difference Image Registration Based on Stacked Autoencoder Network

Chao Huang, Hao Guo*, Yan Gao, and Jubai An
Author Affiliations
  • College of Information Science and Technology, Dalian Maritime University, Dalian, Liaoning 116026, China
  • show less
    Figures & Tables(10)
    Structure of the neighborhood sampling
    Flow of the feature matching algorithm
    Structure of the SAE network
    Image leuven of the light difference
    Sea ice image. (a) Bohai Sea image (ALOS); (b) Bohai Sea image (ASAR); (c) image with a resolution of 8 m; (d) image with a resolution of 100 m
    Average matching accuracy rates of different algorithms
    Matching results of our algorithm. (a) 1-2; (b) 1-3; (c) 1-4; (d) 1-5; (e) 1-6
    Mismatch elimination results of different algorithms. (a) RANSAC; (b) PSOSAC; (c) LMR; (d) our algorithm
    • Table 1. Matching results of sea ice images

      View table

      Table 1. Matching results of sea ice images

      Image pairSIFTLIOPAKAZEBRISKOurs
      NCorPrate/%NCorPrate/%NCorPrate/%NCorPrate/%NCorPrate/%
      Bohai_img1561444476818473934
      Nanji_img1219932445122654159
      Enhance_img81479223381491
    • Table 2. Matching accuracies of different mismatch elimination algorithms unit: %

      View table

      Table 2. Matching accuracies of different mismatch elimination algorithms unit: %

      AlgorithmRANSACPSOSACLMROurs
      Bohai_img1073734
      Nanji_img17265759
    Tools

    Get Citation

    Copy Citation Text

    Chao Huang, Hao Guo, Yan Gao, Jubai An. Nonlinear Grayscale Difference Image Registration Based on Stacked Autoencoder Network[J]. Laser & Optoelectronics Progress, 2021, 58(16): 1610009

    Download Citation

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

    Category: Image Processing

    Received: Nov. 12, 2020

    Accepted: Dec. 14, 2020

    Published Online: Aug. 19, 2021

    The Author Email: Guo Hao (guohao0512@dlmu.edu.cn)

    DOI:10.3788/LOP202158.1610009

    Topics