<?xml version="1.0" encoding="ISO-8859-1"?>
<metadatalist>
	<metadata ReferenceType="Conference Proceedings">
		<site>marte2.sid.inpe.br 802</site>
		<holdercode>{isadg {BR SPINPE} ibi 8JMKD3MGPCW/3DT298S}</holdercode>
		<identifier>8JMKD3MGP6W34M/3PSLQ99</identifier>
		<repository>sid.inpe.br/marte2/2017/10.27.12.37.28</repository>
		<lastupdate>2017:10.27.12.37.28 dpi.inpe.br/marte2/2013/05.17.15.03.06 banon</lastupdate>
		<metadatarepository>sid.inpe.br/marte2/2017/10.27.12.37.29</metadatarepository>
		<metadatalastupdate>2018:06.06.03.05.07 dpi.inpe.br/marte2/2013/05.17.15.03.06 administrator {D 2017}</metadatalastupdate>
		<isbn>978-85-17-00088-1</isbn>
		<label>59441</label>
		<citationkey>RodriguesRodTagCarCam:2017:DeAcSI</citationkey>
		<title>Desempenho e acurácia dos SIGs Terra View e Idrisi e seus respectivos classificadores supervisionados</title>
		<format>Internet</format>
		<year>2017</year>
		<secondarytype>PRE CN</secondarytype>
		<numberoffiles>1</numberoffiles>
		<size>2607 KiB</size>
		<author>Rodrigues, Mikael Timóteo,</author>
		<author>Rodrigues, Bruno Timóteo,</author>
		<author>Tagliarini, Felipe de Souza Nogueira,</author>
		<author>Cardoso, Lincoln Gehring,</author>
		<author>Campos, Sérgio,</author>
		<electronicmailaddress>mikaelgeo@gmail.com</electronicmailaddress>
		<editor>Gherardi, Douglas Francisco Marcolino,</editor>
		<editor>Aragão, Luiz Eduardo Oliveira e Cruz de,</editor>
		<e-mailaddress>daniela.seki@inpe.br</e-mailaddress>
		<conferencename>Simpósio Brasileiro de Sensoriamento Remoto, 18 (SBSR)</conferencename>
		<conferencelocation>Santos</conferencelocation>
		<date>28-31 maio 2017</date>
		<publisher>Instituto Nacional de Pesquisas Espaciais (INPE)</publisher>
		<publisheraddress>São José dos Campos</publisheraddress>
		<pages>2263-2270</pages>
		<booktitle>Anais</booktitle>
		<organization>Instituto Nacional de Pesquisas Espaciais (INPE)</organization>
		<transferableflag>1</transferableflag>
		<abstract>The main objective of this study is to investigate the performance of TerraView 4.2.2 and Idrisi Selva performing classification oversees through the spectral pattern on Landsat 5, associated with comparing the land use of the river Capivara watershed, inserted in the municipality of Botucatu, São Paulo, Brazil. The areas of supervised training were defined through seven land use classes, founded by the Manual Use of Technical IBGE Earth. In the region of Capivara watershed, they are practiced multiple types of management, which can be found planting crops from subsistence scale, through small and medium-sized farms, to major agro-industrial structures, thus providing a panorama of great complexity to mapped and subsequently patterned. An aggravating the methodology were the weed common in cultivated pastures and soils with various forms of culture, because they cause interference in the spectral pattern of land use classes, thus providing noise that changed the pure spectral response of crops inducing error digital classification. Post-classification also improved matrix realignment estimates for removal of pixel groups, reaching a higher order than 50% accuracy, increasing accuracy, allowing a lower inclusion of items of other classes, thus making it the best classification. Unlike the products derived from the supervised classification by maximum likelihood post classified with the majority filter, which after reclassification accuracy was high, presented fewer errors, as well as smoothing of classified maps.</abstract>
		<area>SRE</area>
		<type>Bacias hidrográficas</type>
		<language>pt</language>
		<targetfile>59441.pdf</targetfile>
		<usergroup>banon</usergroup>
		<visibility>shown</visibility>
		<mirrorrepository>urlib.net/www/2011/03.29.20.55</mirrorrepository>
		<nexthigherunit>8JMKD3MGP6W34M/3PMFNUS</nexthigherunit>
		<citingitemlist>sid.inpe.br/marte2/2017/09.25.14.55 4</citingitemlist>
		<hostcollection>dpi.inpe.br/marte2/2013/05.17.15.03.06</hostcollection>
		<username>banon</username>
		<lasthostcollection>dpi.inpe.br/marte2/2013/05.17.15.03.06</lasthostcollection>
		<url>http://marte2.sid.inpe.br/rep-/sid.inpe.br/marte2/2017/10.27.12.37.28</url>
	</metadata>
</metadatalist>