Improving urban land cover classification using fuzzy image segmentation

Lizarazo, Ivan and Elsner, Paul (2009) Improving urban land cover classification using fuzzy image segmentation. In: Gavrilova, M.L. and Tan, J.K. (eds.) Transactions on Computational Science. Lecture Notes in Computer Science 6 5730. Berlin, Germany: Springer Verlag, pp. 41-56. ISBN 9783642106484.

Abstract

The increasing availability of high spatial resolution images provides detailed and up-to-date representations of cities. However, ana-lysis of such digital imagery data using traditional pixel-wise approaches remains a challenge due to the spectral complexity of urban areas. Object-Based Image Analysis (OBIA) is emerging as an alternative method to produce landcover information. Standard OBIA approaches rely on ima-ge segmentation which partitions the image into a set of ’crisp’ non-overlapping image-objects. This step regularly requires significant user-interaction to parameterise a functional segmentation model. This paper proposes fuzzy image segmentation which produces fully overlapping image-regions with indeterminate boundaries that serves as alternative framework for the subsequent image classification. The new method uses three stages: (i) fuzzy image segmentation, (ii) feature analysis, and (iii) defuzzification, that were implemented applying Support Vector Machine (SVM) techniques and using open source software. The new method was tested against a benchmark land-cover classification that applied standard crisp image segmentation. Results show that fuzzy image segmentation can produce good thematic accuracy with little user input. It therefore provides a new and automated technique for producing accurate urban land cover data from high spatial resolution imagery.

Metadata

Statistics

DownloadsShow export options

Export as XMLJSONCSV

Activity Overview

6 month trend

0Downloads

6 month trend

641Hits

Additional statistics are available via IRStats2.

Archive Staff Only (login required)

Edit/View Item