<?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/3PSMFN8</identifier>
		<repository>sid.inpe.br/marte2/2017/10.27.16.22</repository>
		<lastupdate>2017:10.27.16.22.11 dpi.inpe.br/marte2/2013/05.17.15.03.06 banon</lastupdate>
		<metadatarepository>sid.inpe.br/marte2/2017/10.27.16.22.11</metadatarepository>
		<metadatalastupdate>2018:06.06.03.12.15 dpi.inpe.br/marte2/2013/05.17.15.03.06 administrator {D 2017}</metadatalastupdate>
		<isbn>978-85-17-00088-1</isbn>
		<label>60161</label>
		<citationkey>SantosOlLiViRaSa:2017:MéAlCl</citationkey>
		<title>Método alternativo de classificação de imagens orbitais para o mapeamento do uso/cobertura da terra nas bacias dos rios Pardo e Salinas - MG</title>
		<format>Internet</format>
		<year>2017</year>
		<secondarytype>PRE CN</secondarytype>
		<numberoffiles>1</numberoffiles>
		<size>1584 KiB</size>
		<author>Santos, Ronaldo Medeiros,</author>
		<author>Oliveira, Isaac Alves,</author>
		<author>Lima, Vinícius Orlandi Barbosa,</author>
		<author>Vicente, Marcelo Rossi,</author>
		<author>Ramalho, Antônio Henrique Cordeiro,</author>
		<author>Santos, Tarley Aparecido,</author>
		<electronicmailaddress>ronaldo.medeiros@ifnmg.edu.br</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>7436-7443</pages>
		<booktitle>Anais</booktitle>
		<organization>Instituto Nacional de Pesquisas Espaciais (INPE)</organization>
		<transferableflag>1</transferableflag>
		<abstract>Land use / land cover mapping is a basic prerequisite for the development of a wide variety os studies and environmental actions planning, such as territorial management, rational exploitation of natural resources, environmental conservation and urban and agricultural planning. However, obtaining accurate results is still a challenge, because both the characteristics of the sensors, that generate the orbital images, and the different formulations of the classifiers may not be adequate to the natural complexity of the studied area, such as the northern region of Minas Gerais, characterized by strong fragmentation of the landscape. Therefore, the objective of the present work was to propose and evaluate an alternative classification method, based on decision tree algorithm, for the land use/cover mapping in the Pardo and Salinas rivers basins, in the northern region of Minas Gerais State. The methodology comprised the development of an alternative automatic decision tree classifier, considering spectral and non-spectral information, and the evaluation of its performance; individually and compared to the result obtained through classic automatic classifiers. 12 land use/cover classes were identified and the alternative method proposed was presented satisfactory and superior performance to that obtained by the application of the classical Battacharya (region) and maximum likelihoo (pixel-by-pixel) classifiers.</abstract>
		<area>SRE</area>
		<type>Processamento de imagens</type>
		<language>pt</language>
		<targetfile>60161.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 1</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/marte2/2017/10.27.16.22</url>
	</metadata>
</metadatalist>