Classification techniques for remotely sensed data

Varghese, Eldho and George, Grinson (2017) Classification techniques for remotely sensed data. In: Winter School on Structure and Function of the Marine Ecosystem : Fisheries, 1-21 December 2017, Kochi.

[img]
Preview
Text
Winter School on Structure and Functions of Ecosystem_27.pdf

Download (244kB) | Preview
Related URLs:

    Abstract

    Hyperspectral imaging sensors measure the radiance of the materials within each pixel area at a very large number of contiguous spectral wavelength bands. So, they can generate hundreds of images of a scene on the real surface. The radiance is converted into hyperspectral data cube digital form. The spectral information available in a hyperspectral image (cube) may serve to classify the nature of the target object because every material had a unique fixed spectrum and could be used as a spectral signature of the material and perhaps provide additional information for further processing and exploitation. Hyperspectral data contain extremely rich spectral attributes, which offer the potential to discriminate more detailed classes with classification accuracy.

    Item Type: Conference or Workshop Item (Paper)
    Subjects: Oceanography > Remote sensing
    Divisions: CMFRI-Kochi > Marine Capture > Fishery Resource Assessment
    Subject Area > CMFRI > CMFRI-Kochi > Marine Capture > Fishery Resource Assessment
    CMFRI-Kochi > Marine Capture > Fishery Resource Assessment
    Subject Area > CMFRI-Kochi > Marine Capture > Fishery Resource Assessment
    Depositing User: Arun Surendran
    Date Deposited: 28 May 2018 09:55
    Last Modified: 28 May 2018 09:55
    URI: http://eprints.cmfri.org.in/id/eprint/12768

    Actions (login required)

    View Item View Item