Infrared and Laser Engineering, Volume. 50, Issue 12, 20210233(2021)

Multi-view SAR target classification method based on principle of maximum entropy

Ning Li1... Junmin Wang1, Wenjie Si2, and Zexun Geng13 |Show fewer author(s)
Author Affiliations
  • 1School of Information Engineering, Pingdingshan University, Pingdingshan 467000, China
  • 2School of Electrical & Control Engineering, Henan University of Urban Construction, Pingdingshan 467000, China
  • 3Institute of Surveying and Mapping, Information Engineering University, Zhengzhou 450001, China
  • show less
    Figures & Tables(10)
    Flowchart of multi-view SAR target classification based on maximum entropy
    Illustration of the targets to be classified
    Classification results under SOC
    Comparison of average classification rates under depression angle variance
    Average classification rates under noise corruption
    • Table 1. Setup of samples under SOC

      View table
      View in Article

      Table 1. Setup of samples under SOC

      TypeTraining setTest set
      BMP2231193
      BTR70231194
      T72230194
      T62297271
      BRDM2296272
      BTR60254193
      ZSU23/4297272
      D7297272
      ZIL131297272
      2S1297272
    • Table 2. Comparison of average classificationrates under SOC

      View table
      View in Article

      Table 2. Comparison of average classificationrates under SOC

      MethodAverage classification accuracy
      Proposed99.36%
      Multi-view 198.74%
      Multi-view 299.13%
      Multi-view 399.21%
      CNN99.08%
    • Table 3. Setup of samples for configuration variance

      View table
      View in Article

      Table 3. Setup of samples for configuration variance

      BMP2BDRM2BTR70T72
      Training set231 (Sn_9563)296231230 (Sn_132)
      Test set424 (Sn_812)
      426 (Sn_9566)00571 (Sn_A04)
      427 (Sn_C21)571 (Sn_A05)
      571 (Sn_A07)
      565 (Sn_A10)
    • Table 4. Comparison of average classification rates under configuration variance

      View table
      View in Article

      Table 4. Comparison of average classification rates under configuration variance

      MethodAverage classification accuracy
      Proposed98.86%
      Multi-view 196.78%
      Multi-view 297.92%
      Multi-view 398.17%
      CNN96.02%
    • Table 5. Setup of samples under depression angle variance

      View table
      View in Article

      Table 5. Setup of samples under depression angle variance

      Depression angle/(°)2S1BDRM2ZSU23/4
      Training set17297296297
      Test set30286285286
      45301301301
    Tools

    Get Citation

    Copy Citation Text

    Ning Li, Junmin Wang, Wenjie Si, Zexun Geng. Multi-view SAR target classification method based on principle of maximum entropy[J]. Infrared and Laser Engineering, 2021, 50(12): 20210233

    Download Citation

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

    Category: Image processing

    Received: May. 25, 2021

    Accepted: --

    Published Online: Feb. 9, 2022

    The Author Email:

    DOI:10.3788/IRLA20210233

    Topics