Hyperspectral Data Classification Using Extended Extinction Profiles

dc.creatorGhamisi
dc.creatorPedram; Souza
dc.creatorRoberto; Benediktsson
dc.creatorJon Atli; Rittner
dc.creatorLeticia; Lotufo
dc.creatorRoberto; Zhu
dc.creatorXiao Xiang
dc.date2016
dc.datenov
dc.date2017-11-13T13:22:34Z
dc.date2017-11-13T13:22:34Z
dc.date.accessioned2018-03-29T05:55:19Z
dc.date.available2018-03-29T05:55:19Z
dc.identifierIeee Geoscience And Remote Sensing Letters. Ieee-inst Electrical Electronics Engineers Inc, v. 13, p. 1641 - 1645, 2016.
dc.identifier1545-598X
dc.identifier1558-0571
dc.identifierWOS:000386255600011
dc.identifier10.1109/LGRS.2016.2600244
dc.identifierhttp://ieeexplore.ieee.org/document/7551242/
dc.identifierhttp://repositorio.unicamp.br/jspui/handle/REPOSIP/327914
dc.identifier.urihttp://repositorioslatinoamericanos.uchile.cl/handle/2250/1364939
dc.descriptionFundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)
dc.descriptionConselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)
dc.descriptionThis letter proposes a new approach for the spectral-spatial classification of hyperspectral images, which is based on a novel extrema-oriented connected filtering technique, entitled as extended extinction profiles. The proposed approach progressively simplifies the first informative features extracted from hyperspectral data considering different attributes. Then, the classification approach is applied on two well-known hyperspectral data sets, i.e., Pavia University and Indian Pines, and compared with one of the most powerful filtering approaches in the literature, i.e., extended attribute profiles. Results indicate that the proposed approach is able to efficiently extract spatial information for the classification of hyperspectral images automatically and swiftly. In addition, an array-based node-oriented max-tree representation was carried out to efficiently implement the proposed approach.
dc.description13
dc.description11
dc.description1641
dc.description1645
dc.descriptionAlexander von Humboldt Fellowship for Postdoctoral Researchers
dc.descriptionHelmholtz Young Investigators Group "SiPEO" - Fundacao de Amparo a Pesquisa do Estado de Sao Paulo [VH-NG-1018, 2013/23514-0, 2015/12127-0, 2013/07559-3]
dc.descriptionCNPq [311228/2014-3]
dc.descriptionFundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)
dc.descriptionConselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)
dc.languageEnglish
dc.publisherIEEE-Inst Electrical Electronics Engineers Inc
dc.publisherPiscataway
dc.relationIEEE Geoscience and Remote Sensing Letters
dc.rightsfechado
dc.sourceWOS
dc.subjectExtended Multiextinction Profile (emep)
dc.subjectHyper-spectral Data Classification
dc.subjectRandom Forests (rfs)
dc.subjectSupport Vector Machines (svms)
dc.titleHyperspectral Data Classification Using Extended Extinction Profiles
dc.typeArtículos de revistas


Este ítem pertenece a la siguiente institución