Comparing object-based and pixel-based classifications for mapping savannas

Whiteside, Tim, Boggs, Guy and Maier, Stefan (2011) Comparing object-based and pixel-based classifications for mapping savannas. International Journal of Applied Earth Observation and Geoscience, 13 (6). pp. 884-893. ISSN 0303-2434

[img] PDF
Restricted to Repository staff only
Available under License Creative Commons Attribution Non-commercial No Derivatives.

Download (2MB) | Request a copy


The development of robust object-based classification methods suitable for medium to high resolution satellite imagery provides a valid alternative to ‘traditional’ pixel-based methods. This paper compares the results of an object-based classification to a supervised per-pixel classification for mapping land cover in the tropical north of the Northern Territory. The object-based approach involved the segmentation of image data into objects at multiple scale levels. Objects were assigned classes using Nearest Neighbour supervised algorithm and fuzzy classification. The supervised pixel-based classification involved the selection of training areas and a classification using the maximum likelihood classifier algorithm. Site-specific accuracy assessment using confusion matrices of both classifications were undertaken based on 256 reference sites. A comparison of the results shows a statistically significant higher overall accuracy of the object-based classification over the pixel-based classification. The incorporation of a digital elevation model (DEM) layer and associated class rules into the object-based classification produced slightly higher accuracies overall and for the associated classes; however this was not statistically significant over the object-based using spectral information solely. The difference in accuracies between the per-pixel method and the object-based method are shown to be statistically significant; indicating object-based analysis has great potential for extracting land cover information from satellite imagery captured over spatially heterogeneous land covers of tropical Australia.

Item Type: Article
Keywords: object-based image analysis accuracy assessment tropical savanna northern Australia
Field of Research (2008): 05 Environmental Sciences > 0502 Environmental Science and Management > 050209 Natural Resource Management
09 Engineering > 0909 Geomatic Engineering > 090905 Photogrammetry and Remote Sensing
Subjects: G Geography. Anthropology. Recreation > G Geography (General)
Q Science > Q Science (General)
Related URLs:
Date Deposited: 19 Oct 2011 22:25
Last Modified: 19 Oct 2011 22:29

Actions (login required)

View Item
View Item