2009 | OriginalPaper | Buchkapitel
Improving Urban Land Cover Classification Using Fuzzy Image Segmentation
verfasst von : Ivan Lizarazo, Paul Elsner
Erschienen in: Transactions on Computational Science VI
Verlag: Springer Berlin Heidelberg
Aktivieren Sie unsere intelligente Suche um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
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.