eduzhai > Applied Sciences > Engineering >

Illumination invariant hyperspectral image unmixing based on a digital surface model

  • king
  • (0) Download
  • 20210506
  • Save

... pages left unread,continue reading

Document pages: 13 pages

Abstract: Although many spectral unmixing models have been developed to addressspectral variability caused by variable incident illuminations, the mechanismof the spectral variability is still unclear. This paper proposes an unmixingmodel, named illumination invariant spectral unmixing (IISU). IISU makes thefirst attempt to use the radiance hyperspectral data and a LiDAR-deriveddigital surface model (DSM) in order to physically explain variableilluminations and shadows in the unmixing framework. Incident angles, skyfactors, visibility from the sun derived from the LiDAR-derived DSM support theexplicit explanation of endmember variability in the unmixing process fromradiance perspective. The proposed model was efficiently solved by astraightforward optimization procedure. The unmixing results showed that theother state-of-the-art unmixing models did not work well especially in theshaded pixels. On the other hand, the proposed model estimated more accurateabundances and shadow compensated reflectance than the existing models.

Please select stars to rate!


0 comments Sign in to leave a comment.

    Data loading, please wait...