Object-based image analysis for urban land cover classification in the city of Campinas-SP, Brazil
David G. M. França, Rodolfo G. Lotte, Cláudia M. de Almeida, Sacha M. O. Siani, Thales S. Körting, Leila G. M. Fonseca, and Luiz T. da Silva
Download paper
Abstract
Classifiers that make use of pixel-by-pixel approaches are limited in the high spatial and radiometric resolution of intra-urban regions. That happens because of noise in the image and confusion in the targets spectral response that display similarity in it’s signal like: ceramic roofs and bare soil. Because of that, the literature favors approaches that make use of object-oriented analysis for image segmentation, those approaches make a better use of the high spatial resolution and don’t use only the target’s spectral response. Assuming that the object-oriented analysis is a favorable approach to be implemented in intra-urban areas, this paper will assess the results of such approach through an implementation of it in an urbanized area from the city of Campinas (Brazil), which has a size close to twelve square kilometers. Making use of the fusion of high spatial resolution image from Worldview-2 sensor and it’s panchromatic band, the experiments were performed with the use of E-Cognition TM Developer 8 as the segmentation platform, and the classification being based on a decision tree generated by C4.5 algorithm on the software WEKA. This work also assess which approach best suits the experiment needs, being an optimal attribute selection achieved through a Wrapper filter, with a final kappa statistic of 0.9425.
Info! Dear researcher/scientist/academic, you may find some Wikipedia references in this page, which are totally directed for those that might not be familiar with terms and need a more illustrative and didatical understanding. Please, fell free to contribute at any moment.
Contextualization
Cite this paper
@inproceedings{franca2015,
title={Object-based image analysis for urban land cover classification in the city of Campinas-SP, Brazil},
author={Fran{\c{c}}a, David GM and Lotte, Rodolfo G and de Almeida, Cl{\'a}udia M and Siani, Sacha MO and
K{\"o}rting, Thales S and Fonseca, Leila GM and da Silva, Luiz T},
booktitle={Urban Remote Sensing Event (JURSE), 2015 Joint},
pages={1--4},
year={2015},
organization={IEEE}
}
