• DocumentCode
    3467258
  • Title

    3D Plant Modelling via Hyperspectral Imaging

  • Author

    Jie Liang ; Zia, Azhar ; Jun Zhou ; Sirault, Xavier

  • Author_Institution
    Australian Nat. Univ., Canberra, SA, Australia
  • fYear
    2013
  • fDate
    2-8 Dec. 2013
  • Firstpage
    172
  • Lastpage
    177
  • Abstract
    Plant phenomics research requires different types of sensors be employed to measure the physical traits of plant surface and to estimate the plant biomass. Of particular interest is the hyperspectral imaging device which captures wavelength indexed band images that characterise material properties of objects under study. In this paper, we introduce a proof of concept research that builds 3D plant model directly from hyperspectral images captured in a controlled lab environment. We show that hyperspectral imaging has shown clear advantages in segmenting plant from its background and is promising in generating comprehensive 3D plant models.
  • Keywords
    geophysical image processing; image segmentation; image sensors; vegetation; 3D plant modelling; controlled lab environment; hyperspectral imaging device; plant biomass; plant phenomics research; plant segmentation; plant surface; sensors; wavelength indexed band images; Cameras; Feature extraction; Hyperspectral imaging; Image segmentation; Solid modeling; Three-dimensional displays;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Computer Vision Workshops (ICCVW), 2013 IEEE International Conference on
  • Conference_Location
    Sydney, NSW
  • Type

    conf

  • DOI
    10.1109/ICCVW.2013.29
  • Filename
    6755894