<?xml version="1.0" encoding="ISO-8859-1"?>
<metadatalist>
	<metadata ReferenceType="Conference Proceedings">
		<site>mtc-m16c.sid.inpe.br 804</site>
		<holdercode>{isadg {BR SPINPE} ibi 8JMKD3MGPCW/3DT298S}</holdercode>
		<identifier>8JMKD3MGPDW34P/3Q5DLCB</identifier>
		<repository>sid.inpe.br/mtc-m16c/2017/12.01.19.18</repository>
		<lastupdate>2017:12.01.19.18.51 sid.inpe.br/mtc-m18@80/2008/03.17.15.17 simone</lastupdate>
		<metadatarepository>sid.inpe.br/mtc-m16c/2017/12.01.19.18.51</metadatarepository>
		<metadatalastupdate>2023:02.15.04.21.01 sid.inpe.br/mtc-m18@80/2008/03.17.15.17 administrator {D 2017}</metadatalastupdate>
		<issn>2179-4820</issn>
		<citationkey>ReisDutrEsca:2017:SiMuMu</citationkey>
		<title>Simultaneous multi-source and multi-temporal land cover classification using a Compound Maximum Likelihood classifier</title>
		<format>Pendrive, On-line.</format>
		<year>2017</year>
		<secondarytype>PRE CN</secondarytype>
		<numberoffiles>1</numberoffiles>
		<size>4899 KiB</size>
		<author>Reis, Mariane Souza,</author>
		<author>Dutra, Luciano Vieira,</author>
		<author>Escada, Maria Isabel Sobral,</author>
		<affiliation>Instituto Nacional de Pesquisas Espaciais (INPE)</affiliation>
		<affiliation>Instituto Nacional de Pesquisas Espaciais (INPE)</affiliation>
		<affiliation>Instituto Nacional de Pesquisas Espaciais (INPE)</affiliation>
		<editor>Davis Jr., Clodoveu A. (UFMG),</editor>
		<editor>Queiroz, Gilberto R. de (INPE),</editor>
		<e-mailaddress>lubia@dpi.inpe.br</e-mailaddress>
		<conferencename>Simpósio Brasileiro de Geoinformática, 18 (GEOINFO)</conferencename>
		<conferencelocation>Salvador</conferencelocation>
		<date>04-06 dez. 2017</date>
		<publisher>Instituto Nacional de Pesquisas Espaciais (INPE)</publisher>
		<publisheraddress>São José dos Campos</publisheraddress>
		<pages>74-85</pages>
		<booktitle>Anais</booktitle>
		<tertiarytype>Full papers</tertiarytype>
		<transferableflag>1</transferableflag>
		<abstract>The most widely used change detection method is to classify remote sensing images independently for each date, and stack them to form a class sequence vector. However, impossible transitions within the sequences might occur and errors might be accumulated. To solve this, we propose a novel al- gorithm called Compound Maximum Likelihood (CML), based on the Maximum Likelihood classifier (ML). In CML information from all images is used jointly by considering the a priori probability of each class sequence. The algorithm was tested for Synthetic Aperture Radar and optical images classification in a study area in Para &#769; state, within the Brazilian Amazon. CML presented either similar or very improved accuracy index values over ML land cover classifica- tions.</abstract>
		<area>SRE</area>
		<language>pt</language>
		<targetfile>8reis_escada.pdf</targetfile>
		<usergroup>lubia@dpi.inpe.br</usergroup>
		<visibility>shown</visibility>
		<documentstage>not transferred</documentstage>
		<mirrorrepository>dpi.inpe.br/banon-pc2@80/2006/07.04.20.21</mirrorrepository>
		<nexthigherunit>8JMKD3MGPDW34P/42T2QPE</nexthigherunit>
		<nexthigherunit>8JMKD3MGPDW34P/48F29JE</nexthigherunit>
		<citingitemlist>sid.inpe.br/mtc-m16c/2020/07.22.00.47 1</citingitemlist>
		<hostcollection>sid.inpe.br/mtc-m18@80/2008/03.17.15.17</hostcollection>
		<username>simone</username>
		<lasthostcollection>sid.inpe.br/mtc-m18@80/2008/03.17.15.17</lasthostcollection>
		<url>http://mtc-m16c.sid.inpe.br/rep-/sid.inpe.br/mtc-m16c/2017/12.01.19.18</url>
	</metadata>
</metadatalist>