• DocumentCode
    1441832
  • Title

    Effects of polarization and resolution on SAR ATR

  • Author

    Novak, L.M. ; Halversen, S.D. ; Owirka, G.J. ; Hiett, M.

  • Author_Institution
    Lincoln Lab., MIT, Lexington, MA, USA
  • Volume
    33
  • Issue
    1
  • fYear
    1997
  • Firstpage
    102
  • Lastpage
    116
  • Abstract
    Lincoln Laboratory is investigating the detection and classification of stationary ground targets using high resolution, fully polarimetric, synthetic aperture radar (SAR) imagery. A study is summarized in which data collected by the Lincoln Laboratory 33 GHz SAR were used to perform a comprehensive comparison of automatic target recognition (ATR) performance for several polarization/resolution combinations. The Lincoln Laboratory baseline ATR algorithm suite was used, and was optimized for each polarization/resolution case. Both the HH polarization alone and the optimal combination of HH, HV, and VV were evaluated; the resolutions evaluated were 1 ft×1 ft and 1 m×1 m. The data set used for this study contained approximately 74 km2 of clutter (56 km2 of mixed clutter plus 18 km2 of highly cultural clutter) and 136 tactical target images (divided equally between tanks and howitzers).
  • Keywords
    electromagnetic wave polarisation; image classification; image recognition; performance evaluation; radar clutter; radar polarimetry; radar target recognition; synthetic aperture radar; 33 GHz; ATR algorithm; Lincoln Laboratory; SAR ATR; SAR imagery; automatic target recognition; classification; detection; howitzers; polarimetric synthetic aperture radar; polarization/resolution combinations; stationary ground targets; tactical target images; tanks; Clutter; Cultural differences; Image resolution; Laboratories; Performance gain; Polarization; Radar detection; Surveillance; Synthetic aperture radar; Target recognition;
  • fLanguage
    English
  • Journal_Title
    Aerospace and Electronic Systems, IEEE Transactions on
  • Publisher
    ieee
  • ISSN
    0018-9251
  • Type

    jour

  • DOI
    10.1109/7.570713
  • Filename
    570713