Improving urban land cover classification using fuzzy image segmentation

  • Authors:

  • Ivan Lizarazo;Paul Elsner

  • Affiliations:

  • Cadastral Engineering and Geodesy Department, Universidad Distrital Francisco Jose de Caldas, Bogota, Colombia;School of Geography, Birkbeck College, University of London, London, UK

  • Venue:
  • Transactions on Computational Science VI
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

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.