Journal of
Geography and Regional Planning

  • Abbreviation: J. Geogr. Reg. Plann.
  • Language: English
  • ISSN: 2070-1845
  • DOI: 10.5897/JGRP
  • Start Year: 2008
  • Published Articles: 392

Full Length Research Paper

Comparison of object-based and pixel based infrared airborne image classification methods using DEM thematic layer

Dehvari A.1* and Heck R. J.2
  1University of Guelph, N1G2W1, Guelph, Canada. 2University of Guelph, N1G4S7, Guelph, Canada.
Email: [email protected]

  •  Accepted: 03 March 2007
  •  Published: 30 April 2007

Abstract

 

An airborne infrared image was used to produce a map of land cover types in the Eastern shore of Lake Huron, Ontario province of Canada. Maximum likelihood pixel-based and nearest neighbor object-based methods were used in this approach. Land cover classes that obtained traditional pixel-based classification approaches showed a salt-and-pepper effect having the lowest producer accuracy (59.5%). Overall classification results increased up to 80% in object- based approach but still failed to distinguish buildings and creeks. Contours and DEM thematic layers enhanced classification results to a higher level (94%) and increased the producer accuracy for buildings and creek by creating reasonable objects in segmentation process in the object-based approach.

 

Key words: Infrared image classification, pixel-based, object-based, DEM thematic layer, land cover mapping.