Acta Optica Sinica, Volume. 38, Issue 7, 0728001(2018)

Airport Detection Method with Improved Region-Based Convolutional Neural Network

Mingming Zhu*, Yuelei Xu, Shiping Ma, Hong Tang, Peng Xin, and Hongqiang Ma
Author Affiliations
  • Graduate School, Air Force Engineering University, Xi'an, Shaanxi 710038, China
  • show less
    Figures & Tables(8)
    Schematic of overall architecture
    Schematic of RPN structure
    Schematic of cascaded RPN structure
    Comparison among loss functions
    Various airport detection results
    • Table 1. Airport detection rates under different λ

      View table

      Table 1. Airport detection rates under different λ

      λ0.1110100
      DR /%91.2593.7596.2594.4
    • Table 2. Comparison among regional proposal methods

      View table

      Table 2. Comparison among regional proposal methods

      MethodRPNCascaded RPN
      DR /%93.7596.25
      Average processing time /s0.20.2
    • Table 3. Comparison among different airport detection methods

      View table

      Table 3. Comparison among different airport detection methods

      MethodDR /%FAR /%Average processing time /s
      Ref. [14]6522.52.46
      Ref. [15]71.8827.5>100
      Ref. [5]83.133521.37
      Faster R-CNN90.63150.16
      Proposed method96.257.50.20
    Tools

    Get Citation

    Copy Citation Text

    Mingming Zhu, Yuelei Xu, Shiping Ma, Hong Tang, Peng Xin, Hongqiang Ma. Airport Detection Method with Improved Region-Based Convolutional Neural Network[J]. Acta Optica Sinica, 2018, 38(7): 0728001

    Download Citation

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

    Category: Remote Sensing and Sensors

    Received: Jan. 3, 2018

    Accepted: --

    Published Online: Sep. 5, 2018

    The Author Email: Zhu Mingming (ming_paper@163.com)

    DOI:10.3788/AOS201838.0728001

    Topics