Researching

Journals
  • Advanced Photonics
  • Photonics Insights
  • Advanced Photonics Nexus
  • Photonics Research
  • Advanced Imaging
  • View All Journals
  • Chinese Optics Letters
  • High Power Laser Science and Engineering
    • Articles
  • Optics
  • Physics
  • Geography
  • View All Subjects
    • Conferences
  • CIOP
  • HPLSE
  • AP
  • View All Events
    • News
    About CLP
    Search by keywords or author
    Journals >Laser & Optoelectronics Progress >Volume 56 >Issue 11 >Page 111001 > Article
    • Laser & Optoelectronics Progress
    • Vol. 56, Issue 11, 111001 (2019)
    Multimodal Remote Sensing Image Classification with Small Sample Size Based on High-Level Feature Fusion
    Qi He1, Yao Li1, Wei Song1, Dongmei Huang1,2,*..., Shengqi He1 and Yanling Du1|Show fewer author(s)
    Author Affiliations
  • 1 College of Information Technology, Shanghai Ocean University, Shanghai 201306, China
  • 2 Shanghai University of Electric Power, Shanghai 200090, China
    • show less
    DOI: 10.3788/LOP56.111001 Cite this Article Set citation alerts
    Qi He, Yao Li, Wei Song, Dongmei Huang, Shengqi He, Yanling Du. Multimodal Remote Sensing Image Classification with Small Sample Size Based on High-Level Feature Fusion[J]. Laser & Optoelectronics Progress, 2019, 56(11): 111001 Copy Citation Text show less
    Multimodal deep learning network. (a) Pixel-level fusion strategy; (b) feature-level fusion strategy; (c) high-level feature-level fusion strategy
    Fig. 1. Multimodal deep learning network. (a) Pixel-level fusion strategy; (b) feature-level fusion strategy; (c) high-level feature-level fusion strategy
    Download full size
    Multimodal remote sensing image datasets. (a) High-resolution remote sensing images; (b) low-resolution remote sensing images
    Fig. 2. Multimodal remote sensing image datasets. (a) High-resolution remote sensing images; (b) low-resolution remote sensing images
    Download full size
    Network structureFormulaOutputFeature size
    cov1X'cov1k=ReLU(Kcov1k*xi+b1)X'cov1kk=116208×208
    pool1X'pool1=fX'cov1k+b2X'pool1104×104
    cov2X'cov2k=ReLU(Kcov2k*X'pool1k+b3)X'cov2kk=116104×104
    pool2X'pool2=fX'cov2k+b4X'pool2104×104
    ful1X'ful1=X'pool21±X'pool22±…±X'pool2104+b5X'ful11×173056
    Z'ful1Z'ful1=W1X'ful1±W2Y'ful1+b6Z'ful1128×128
    ful2Z'ful2=Z'ful1×Kful1+b7Z'ful21×128
    Table 1. Network structure of feature extractor
    Parameter8kernels16kernels32kernels8/batch16/batch32/batch
    Time /s1356.92456.24828.11431.42452.24418.32
    Accuracy /%95.39092.6509082.2
    Table 2. Influence of MRSIC model parameter setting on classification accuracy
    Network structureDatasetAmountAccuracy /%
    THRSI-LeNetNW100083.2
    THRSI-LeNetNW50074.6
    TLRSI-LeNetUC100077.3
    TLRSI-LeNetUC50067.2
    H&L-LeNetNW、UC100082.5
    HUL-LeNetNW、UC100072.0
    NanoNetUC50077.1
    VGGNW、UC50070.4
    In Fig. 1(b)NW、UC100085.0
    MRSICNW、UC100090.5
    MRSICNW、UC50090.0
    Table 3. Accuracy of seven classification models
    CategoryMRSICaccuracy /%THRSI-LeNetaccuracy /%
    bd, golf9074.6
    te, st8773.8
    bd, golf, te, st75.364
    Table 4. Robustness verification of MRSIC
    Abstract
    Get PDF(in Chinese)
    Figures&Tables (6)
    Equations (0)
    References (50)
    Cited By (5)
    Get Citation
    Copy Citation Text
    Qi He, Yao Li, Wei Song, Dongmei Huang, Shengqi He, Yanling Du. Multimodal Remote Sensing Image Classification with Small Sample Size Based on High-Level Feature Fusion[J]. Laser & Optoelectronics Progress, 2019, 56(11): 111001
    Download Citation
    Set citation alerts for the article
    Tools
    Share
    Set citation alerts for the article
    Save the article for my favorites
    Paper Information
    Recommended Topics
    laser devices and laser physics
    Lasers and Laser Optics
    Laser physics
    laser manufacturing
    Instrumentation, Measurement and Metrology