A comparison of pixel and object-based land cover classification. A case study of the Asmara region, Eritrea

Araya, Ykealo; Hergarten, Christian (2008). A comparison of pixel and object-based land cover classification. A case study of the Asmara region, Eritrea. In: Mander, U.; Brebbia, C.A.; Martin-Duque, J.F. (eds.) Geo-environment and landscape evolution III. WIT transactions on the built environment: Vol. I (pp. 233-243). Southampton: Wit Press 10.2495/GEO080231

Full text not available from this repository.

In this paper we compare the performance of two image classification paradigms (object- and pixel-based) for creating a land cover map of Asmara, the capital of Eritrea and its surrounding areas using a Landsat ETM+ imagery acquired in January 2000. The image classification methods used were maximum likelihood for the pixel-based approach and Bhattacharyya distance for the object-oriented approach available in, respectively, ArcGIS and SPRING software packages. Advantages and limitations of both approaches are presented and discussed. Classifications outputs were assessed using overall accuracy and Kappa indices. Pixel- and object-based classification methods result in an overall accuracy of 78% and 85%, respectively. The Kappa coefficient for pixel- and object-based approaches was 0.74 and 0.82, respectively. Although pixel-based approach is the most commonly used method, assessment and visual interpretation of the results clearly reveal that the object-oriented approach has advantages for this specific case-study.

Item Type:	Conference or Workshop Item (Paper)
Division/Institute:	08 Faculty of Science > Institute of Geography > Geographies of Sustainability 08 Faculty of Science > Institute of Geography 10 Strategic Research Centers > Centre for Development and Environment (CDE)
UniBE Contributor:	Hergarten, Christian
ISBN:	978-1-84564-117-7
Series:	WIT transactions on the built environment
Publisher:	Wit Press
Language:	English
Submitter:	Factscience Import
Date Deposited:	04 Oct 2013 15:17
Last Modified:	05 Dec 2022 14:23
Publisher DOI:	10.2495/GEO080231
Web of Science ID:	000258182300023
Additional Information:	Paper presented at the Third International Conference on Evaluation, Monitoring, Simulation, Management and Remediation of the Geological Environment and Landscape in 2008
URI:	https://boris.unibe.ch/id/eprint/34411 (FactScience: 200450)