Remote sensing methods in medium spatial resolution satellite data land cover classification of large areas

  • Franklin S
  • Wulder M
  • 1

    Readers

    Mendeley users who have this article in their library.
  • N/A

    Citations

    Citations of this article.

Abstract

Numerous large-area, multiple image-based, multiple sensor land cover mapping programs exist of have been proposed, often within the context of national forest monitoring, mapping and modelling initiatives, worldwide. Common methodological steps have been identified that include data acquisition and preprocessing, map legend development, classification approach, stratification, incorporation of ancillary data and accuracy assessment. In general, procedures used in any large-area land cover classification must be robust and repeatable; because of data acquisition parameters, it is likely that compilation of the maps based on the classification will occur with original image acquisitions of different seasonality and perhaps acquired in different years and by different sensors. This situation poses some new challenges beyond those encountered in large-area single image classifications. The objective of this paper is to review and assess general medium spatial resolution satellite remote sensing land cover classification approaches with the goal of identifying the outstanding issues that must be overcome in order to implement a large-area, land cover classification protocol.

Author-supplied keywords

  • land cover mapping
  • large-area classification
  • remote sensing

Get free article suggestions today

Mendeley saves you time finding and organizing research

Sign up here
Already have an account ?Sign in

Authors

  • S E Franklin

  • M.a. A Wulder

Cite this document

Choose a citation style from the tabs below

Save time finding and organizing research with Mendeley

Sign up for free