• DocumentCode
    2708078
  • Title

    Detection of land cover change in Beijing from TM images

  • Author

    Cai, Guoyin ; Du, Mingyi ; Liu, Yang

  • Author_Institution
    Sch. of Geomatics & Urban Inf., Beijing Univ. of Civil Eng. & Archit., Beijing, China
  • fYear
    2011
  • fDate
    24-26 June 2011
  • Firstpage
    1
  • Lastpage
    6
  • Abstract
    This paper focuses on the detection of land cover change in Beijing using TM data collected on 22 May, 2002 and 20 May, 2010 respectively. For detailed analyzing the land cover change in different parts of Beijing, the central Beijing enclosed by fifth ring road was divided into 4 areas based on the ring roads. After image registration, mask and image clip, sample data of land cover types as water body, green land, bare land and construction land were trained, classification was performed using maximum likelihood method. Accuracy assessment was conducted according to ground truth of regions of interest. The conversion matrix was used to detect the land cover change from 2002 to 2010. The results showed that construction land increased in each area, and other land cover types decreased, especially for green land which diminished a lot during this period. This is consistent with the real status of the urbanization in Beijing.
  • Keywords
    geophysical image processing; geophysical techniques; image registration; terrain mapping; AD 2002 05 22; AD 2010 05 20; Beijing; China; TM images; bare land; construction land; green land; image clip; image registration; land cover change; maximum likelihood method; ring roads; water body; Accuracy; Distributed databases; Remote sensing; Roads; Satellites; Spatial resolution; Vegetation mapping; Beijing; TM; land cover change;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Geoinformatics, 2011 19th International Conference on
  • Conference_Location
    Shanghai
  • ISSN
    2161-024X
  • Print_ISBN
    978-1-61284-849-5
  • Type

    conf

  • DOI
    10.1109/GeoInformatics.2011.5980805
  • Filename
    5980805