%0 Conference Proceedings
%4 dpi.inpe.br/plutao@80/2009/12.22.14.51.09
%2 dpi.inpe.br/plutao@80/2009/12.22.14.51.10
%@doi 10.1109/IGARSS.2009.5417646
%@isbn 9781424433957
%F lattes: 1958394372634693 3 GoltzArcAguRudMae:2009:DAMITR
%T Data mining by decision tree for object oriented classification of the sugar cane cut kinds
%D 2009
%A Goltz, Elizabeth,
%A Arcoverde, Gustavo B. F.,
%A Aguiar, Daniel Alves de,
%A Rudorff, Bernardo Friedrich Theodor,
%A Maeda, Eduardo Eiji,
%@affiliation Instituto Nacional de Pesquisas Espaciais (INPE)
%@affiliation Instituto Nacional de Pesquisas Espaciais (INPE)
%@affiliation undefined
%@affiliation Instituto Nacional de Pesquisas Espaciais (INPE)
%@affiliation University of Helsinki – Finland
%@electronicmailaddress
%@electronicmailaddress
%@electronicmailaddress daniel@dsr.inpe.br
%B International Geoscience and Remote Sensing Symposium, (IGARSS).
%C Cape Town
%8 12-17 Jul. 2009
%I IEEE
%P 405-408
%S Proceedings
%1 The Institute of Electrical and Electronics Engineers; Geoscience and Remote Sensing Society
%K : Atmospheric pollution, Dry leaves, Multi-attributes, Object oriented classification, Public health, Remote sensing satellites, Soil types, Sugar cane harvesting, Tree data structures, Air pollution, Classification (of information), Data structures, Decision trees, Geology, Harvesting, Image analysis, Image classification, Remote sensing, Soils, Sugar (sucrose), Sugar cane.
%X Brazil is the worlds largest sugarcane producer with almost 9 million ha of cultivated area in 2008. Great part of the harvested area is manually cut using the practice of burning the dry leaves prior to the stalk harvest. This practice cause atmospheric pollution and damage to public health, in particular, to local inhabitants. In São Paulo State an environmental protocol was signed to establish the burning practice should stop by 2017. Remote sensing satellite images are useful to discriminate different sugar cane harvest types. This study analyzed the generation of decision trees using mean and multi-attributes extracted from objects in TM/Landsat sensor images aiming the classification of types of sugar cane harvesting under different soil types. The classifications performances were between 0.69 up 0.84 kappa indexes. The classifications were sensitives to the different soils and the use of multi-attributes did not contribute to the improvement of the classifications.
%@language en
%3 0500405goltz.pdf