Classificador de máxima verossimilhança aplicado à identificação de espécies nativas na Floresta Amazônica.

Vista sencilla de ítem
dc.contributorLuiz Otávio Moras Filho, Universidade Federal de Lavras (Ufla)
dc.contributorEVANDRO ORFANO FIGUEIREDO, CPAF-AC
dc.contributorMarcos Antônio Isaac Júnior, Universidade Federal de Lavras (Ufla)
dc.contributorVanessa Cabral Costa de Barros, Universidade Federal de Lavras (Ufla)
dc.contributorMarcos Cicarini Hott, Universidade Federal de Lavras (Ufla)
dc.contributorLuís Antônio Coimbra Borges, Universidade Federal de Lavras (Ufla).
dc.creatorMORAS FILHO, L. O.
dc.creatorFIGUEIREDO, E. O.
dc.creatorISAAC JÚNIOR, M. A.
dc.creatorBARROS, V. C. C. de
dc.creatorHOTT, M. C.
dc.creatorBORGES, L. A. C.
dc.date2017-07-07T11:11:11Z
dc.date2017-07-07T11:11:11Z
dc.date2017-07-07
dc.date2017
dc.date2017-11-08T11:11:11Z
dc.date.accessioned2026-06-30T22:50:36Z
dc.descriptionAmong a variety of digital classification methods based on remote sensing images, the Maximum Likelihood (ML) is widely used in environmental studies, mainly for land cover and vegetation analysis. This study aimed to evaluate the effectiveness of supervised classification by ML technique in a forest management area of dense ombrophilous forest, using one RapidEye image. With this purpose, it was conducted the census of species over 30 cm in diameter at breast height and calculated the Cover Value Index (CVI), and selected the 20 species with the highest CVI as a parameter for classification in a Geographic Information System. 13 of the 20 species selected in the study area were not identified by the classification method, and among the seven identified species, two were underestimated and the others were overestimated. Both the maximum likelihood technique and the spatial resolution of the image used were not suitable for supervised classification of native vegetation, with Kappa index of 0.05 and global accuracy of 5.53%. Studies using spectral characterization in leaf level supported by higher or hyper spectral and spatial resolution images are recommended to increase the accuracy of classification.
dc.format6 p.
dc.identifierIn: SIMPÓSIO BRASILEIRO DE SENSORIAMENTO REMOTO, 18., 2017, Santos. Anais... Santos: Inpe, 2017.
dc.identifier978-85-11-00088-1
dc.identifierhttp://www.alice.cnptia.embrapa.br/alice/handle/doc/1072220
dc.identifier.urihttp://hdl.handle.net/123456789/369330
dc.languagepor
dc.rightsopenAccess
dc.subjectManejo florestal
dc.subjectMétodo de classificação digital
dc.subjectMaximum Likelihood
dc.subjectMáxima verossimilhança
dc.subjectRio Branco (AC)
dc.subjectAcre
dc.subjectAmazônia Ocidental
dc.subjectWestern Amazon
dc.subjectAmazonia Occidental
dc.subjectEspecies nativas
dc.subjectAnálisis estadístico
dc.subjectBosques tropicales
dc.subjectEstimación
dc.subjectIdentificación de plantas
dc.subjectSistemas de información geográfica
dc.subjectTeledetección
dc.subjectFloresta tropical
dc.subjectEspécie nativa
dc.subjectIdentificação
dc.subjectEstimativa
dc.subjectSensoriamento remoto
dc.subjectSistema de informação geográfica
dc.subjectAnálise estatística
dc.subjectMétodo estatístico
dc.subjectTropical forests
dc.subjectIndigenous species
dc.subjectPlant identification
dc.subjectEstimation
dc.subjectRemote sensing
dc.subjectGeographic information systems
dc.subjectStatistical analysis
dc.titleClassificador de máxima verossimilhança aplicado à identificação de espécies nativas na Floresta Amazônica.
dc.typeArtigo em anais e proceedings

Archivos

Colecciones

Embrapa Acre (CPAF-AC)