Acta Optica Sinica, Volume. 39, Issue 12, 1228001(2019)

Inversion Restoring Algorithm for Whiskbroom Scanning Images Synthesized with Deep Convolutional Neural Network

Chao Xu1,2, Guang Jin1, Xiubin Yang1、*, Tingting Xu1,2, and Lin Chang1
Author Affiliations
  • 1Department of Advanced Space Technology, Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun, Jilin 130033, China
  • 2College of Material Science and Opto-Electronic Technology, University of Chinese Academy of Sciences, Beijing 100049, China
  • show less
    Figures & Tables(14)
    Schematic of whiskbroom scanning imaging of space camera
    Distortion process of target image
    Calculation of pixel number of nadir ground scene perpendicular to track
    Schematic of corresponding pixels of distorted and extended images perpendicular to track
    Schematic of width of imaging area along track
    Schematics of corresponding pixels of distorted and extended images along track. (a) Original distorted image; (b) extended image
    Architecture of SRCNN
    Architecture of wbi-SRCNN
    Schematic of experimental device of satellite whiskbroom scanning imaging
    Distortion correction result of whiskbroom scanning image. (a) Ground truth; (b) simulated whiskbroom scanning image; (c) distortion-corrected whiskbroom scanning image
    Distortion correction result of whiskbroom scanning linear target. (a) Simulated whiskbroom scanning linear target; (b) distortion-corrected whiskbroom scanning linear target
    Enhanced results of distortion-corrected whiskbroom scanning images. (a) Distortion-corrected whiskbroom scanning images; (b) result of Bicubic; (c) result of SRCNN; (d) result of wbi-SRCNN. Left is wall and right is roof
    • Table 1. Parameters for on-orbit imaging and ground simulation

      View table

      Table 1. Parameters for on-orbit imaging and ground simulation

      On-orbit imaging parameterValueGround simulation parameterValue
      Radius of earth /km6400Curvature radius of LED screen /m32
      Focal length of camera /m8Focal length of camera /mm7
      Pixel size /μm8Pixel size /μm7
      Orbital height /km500Object distance /m4
      Ground resolution /m0.5Imaging resolution /m0.004
      Attitude angle /(°)±35Attitude angle /(°)±35
      Satellite speed relative to earth /(km·s-1)7.5Target movingspeed /(pixel·s-1)6
      Satellite whiskbroom angular speed /[(°)·s-1]8Turntable whiskbroom angular speed /[(°)·s-1]8
      Line shift time /s7.2×10-6Line shift time /s7.2×10-3
    • Table 2. NR-IQA results of test images

      View table

      Table 2. NR-IQA results of test images

      Evaluating indicatorNR-IQA result for Wall imageNR-IQA result for Roof image
      BicubicSRCNNwbi-SRCNNBicubicSRCNNwbi-SRCNN
      NPGD35.3271161.3976215.439653.1318240.5480343.1014
      EPS45.959088.3334104.627454.4708108.4588132.1151
      NIQE31.426827.276221.744830.529527.757924.7264
      PIQUE94.568990.069890.084989.436287.833784.3469
    Tools

    Get Citation

    Copy Citation Text

    Chao Xu, Guang Jin, Xiubin Yang, Tingting Xu, Lin Chang. Inversion Restoring Algorithm for Whiskbroom Scanning Images Synthesized with Deep Convolutional Neural Network[J]. Acta Optica Sinica, 2019, 39(12): 1228001

    Download Citation

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

    Category: Remote Sensing and Sensors

    Received: Jun. 13, 2019

    Accepted: Aug. 8, 2019

    Published Online: Dec. 6, 2019

    The Author Email: Yang Xiubin (yangxiubin@ciomp.ac.cn)

    DOI:10.3788/AOS201939.1228001

    Topics