• DocumentCode
    614264
  • Title

    Semi-automatic detection of rainfall-triggered landslides in segmented optical satellite images

  • Author

    Zortea, Maciel ; Salberg, A. ; Solberg, R.

  • Author_Institution
    Norwegian Comput. Center, Oslo, Norway
  • fYear
    2013
  • fDate
    21-23 April 2013
  • Firstpage
    254
  • Lastpage
    257
  • Abstract
    A new method for rapid mapping of recent rainfall-triggered landslides using a pair of multitemporal very-high spatial resolution images acquired by optical sensors is outlined. The algorithm analyzes image segments, obtained from the post-event image, that are used to guide spectral comparisons and shape analysis of merged candidate segments. The algorithm is tested on 14.9 km2 of satellite imagery acquired in Nova Friburgo (Brazil) in 2011. Most of the landslides were detected successfully.
  • Keywords
    geomorphology; geophysical image processing; geophysical techniques; image segmentation; AD 2011; Brazil; Nova Friburgo; merged candidate segment shape analysis; multitemporal very-high spatial resolution images; optical sensors; post-event image; rainfall-triggered landslide rapid mapping; segmented optical satellite images; semiautomatic detection; Image color analysis; Image segmentation; Optical imaging; Optical sensors; Shape; Terrain factors; Transforms;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Urban Remote Sensing Event (JURSE), 2013 Joint
  • Conference_Location
    Sao Paulo
  • Print_ISBN
    978-1-4799-0213-2
  • Electronic_ISBN
    978-1-4799-0212-5
  • Type

    conf

  • DOI
    10.1109/JURSE.2013.6550713
  • Filename
    6550713
    • Link To Document
    https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=614264