Use este identificador para citar ou linkar para este item: http://www.alice.cnptia.embrapa.br/alice/handle/doc/1034915
Registro completo de metadados
Campo DCValorIdioma
dc.contributor.authorSCHULTZ, B.pt_BR
dc.contributor.authorIMMITZER, M.pt_BR
dc.contributor.authorFORMAGGIO, A. R.pt_BR
dc.contributor.authorSANCHES, I. D. A.pt_BR
dc.contributor.authorLUIZ, A. J. B.pt_BR
dc.contributor.authorATZBERGER, C.pt_BR
dc.date.accessioned2016-01-25T11:11:11Zpt_BR
dc.date.available2016-01-25T11:11:11Zpt_BR
dc.date.created2016-01-25pt_BR
dc.date.issued2015pt_BR
dc.identifier.citationRemote Sensing, Basel, v. 7, n. 11, p. 14482-14508, 2015.pt_BR
dc.identifier.isbnhttp://dx.doi.org/10.3390/rs71114482pt_BR
dc.identifier.urihttp://www.alice.cnptia.embrapa.br/alice/handle/doc/1034915pt_BR
dc.descriptionAbstract: Only well-chosen segmentation parameters ensure optimum results of object-based image analysis (OBIA). Manually defining suitable parameter sets can be a time-consuming approach, not necessarily leading to optimum results; the subjectivity of the manual approach is also obvious. For this reason, in supervised segmentation as proposed by Stefanski et al. (2013) one integrates the segmentation and classification tasks. The segmentation is optimized directly with respect to the subsequent classification. In this contribution, we build on this work and developed a fully autonomous workflow for supervised object-based classification, combining image segmentation and random forest (RF) classification. Starting from a fixed set of randomly selected and manually interpreted training samples, suitable segmentation parameters are automatically identified. A sub-tropical study site located in São Paulo State (Brazil) was used to evaluate the proposed approach. Two multi-temporal Landsat 8 image mosaics were used as input (from August 2013 and January 2014) together with training samples from field visits and VHR (RapidEye) photo-interpretation. Using four test sites of 15 × 15 km2 with manually interpreted crops as independent validation samples, we demonstrate that the approach leads to robust classification results. On these samples (pixel wise, n ? 1 million) an overall accuracy (OA) of 80% could be reached while classifying five classes: sugarcane, soybean, cassava, peanut and others. We found that the overall accuracy obtained from the four test sites was only marginally lower compared to the out-of-bag OA obtained from the training samples. Amongst the five classes, sugarcane and soybean were classified best, while cassava and peanut were often misclassified due to similarity in the spatio-temporal feature space and high within-class variabilities. Interestingly, misclassified pixels were in most cases correctly identified through the RF classification margin, which is produced as a by-product to the classification map.pt_BR
dc.language.isoengeng
dc.rightsopenAccesseng
dc.subjectMapeamento agrícolapt_BR
dc.subjectSegmentação multirresoluçãopt_BR
dc.subjectOBIApt_BR
dc.subjectCrop mappingpt_BR
dc.subjectMulti-resolution segmentationpt_BR
dc.subjectOLIpt_BR
dc.subjectRandom forestpt_BR
dc.titleSelf-guided segmentation and classification of multi-temporal landsat 8 images for crop type mapping in southeastern Brazil.pt_BR
dc.typeArtigo de periódicopt_BR
dc.date.updated2016-01-25T11:11:11Zpt_BR
dc.subject.thesagroSensoriamento remotopt_BR
dc.subject.nalthesaurusRemote sensingpt_BR
dc.subject.nalthesaurusBrazilpt_BR
riaa.ainfo.id1034915pt_BR
riaa.ainfo.lastupdate2016-01-25pt_BR
dc.contributor.institutionBRUNO SCHULTZ, INPE; MARCUS IMMITZER, University of Natural Resources and Life Sciences, Viena; ANTONIO ROBERTO FORMAGGIO, INPE; IEDA DEL'ARCO SANCHES, INPE; ALFREDO JOSE BARRETO LUIZ, CNPMA; CLEMENT ATZBERGER, University of Natural Resources and Life Sciences, Viena.pt_BR
Aparece nas coleções:Artigo em periódico indexado (CNPMA)

Arquivos associados a este item:
Arquivo Descrição TamanhoFormato 
2015AP38.pdf5.67 MBAdobe PDFThumbnail
Visualizar/Abrir
Mostrar registro simples do item Visualizar estatísticas

FacebookTwitterDeliciousLinkedInGoogle BookmarksMySpace