Urban land cover classification using worldview-2 images and C4.5 algorithm

Mapping of urban land cover using remote sensing technology has been widely explored, especially with the recent availability of high resolution images and object-based analysis techniques. This study uses the InterIMAGE software and WorldView-2 sensor imagery, two recent technologies useful for urban studies, to classify land cover in a metropolitan area of Sao Paulo, Brazil. Therefore, this work aims to compare the classification performance of two urban land cover thematic maps produced by the object-based image analysis (OBIA) and C4.5 data mining algorithm. The results showed that data mining technique presented classification performance similar to the OBIA method but in a reduced computational time once the entire processing is optimized.

[1]  L. S. Galvão,et al.  Variation in spectral shape of urban materials , 2010 .

[2]  Jacob Cohen.  A Coefficient of Agreement for Nominal Scales , 1960 .

[3]  M. Carvalho,et al.  URBAN LAND COVER CLASSIFICATION WITH WORLDVIEW-2 IMAGES USING DATA MINING AND OBJECT-BASED IMAGE ANALYSIS , 2012 .

[4]  Leila Maria Garcia Fonseca,et al.  GeoDMA - A Novel System for Spatial Data Mining , 2008, 2008 IEEE International Conference on Data Mining Workshops.

[5]  G. H. Rosenfield,et al.  A coefficient of agreement as a measure of thematic classification accuracy. , 1986 .

[6]  Maria Isabel Sobral Escada,et al.  Remote‐sensing image mining: detecting agents of land‐use change in tropical forest areas , 2008 .

[7]  Ian H. Witten,et al.  Data mining: practical machine learning tools and techniques with Java implementations , 2002, SGMD.

[8]  Leila Maria Garcia Fonseca,et al.  MAPEAMENTO DA COBERTURA DO SOLO URBANO UTILIZANDO IMAGENS WORLDVIEW-II E O SISTEMA INTERIMAGE , 2011 .

[9]  R. Congalton,et al.  Accuracy assessment: a user's perspective , 1986 .

[10]  Raul Queiroz Feitosa,et al.  INTERIMAGE: AN OPEN SOURCE PLATFORM FOR AUTOMATIC IMAGE INTERPRETATION , 2007 .

[11]  Marcelo Gattass,et al.  TerraLib: Technology in Support of GIS Innovation , 2000 .

[12]  H. Kux,et al.  CONTRIBUTION OF THE NEW WORLDVIEW-2 SPECTRAL BANDS FOR URBAN MAPPING IN COASTAL AREAS: CASE STUDY SÃO LUÍS ( MARANHÃO STATE, BRAZIL) , 2012 .

[13]  Thomas Blaschke,et al.  Object based image analysis for remote sensing , 2010 .

[14]  Arno Schäpe,et al.  Multiresolution Segmentation : an optimization approach for high quality multi-scale image segmentation , 2000 .