Unsupervised Distance Learning for Plant Species Identification

Página do item simplificado
dc.citation.issue12
dc.citation.volume9
dc.contributor.authorAlmeida, Jurandy [UNIFESP]
dc.contributor.authorPedronette, Daniel C. G.
dc.contributor.authorAlberton, Bruna
dc.contributor.authorMorellato, Leonor Patricia C.
dc.contributor.authorTorres, Ricardo da S.
dc.coveragePiscataway
dc.date.accessioned2020-07-31T12:47:08Z
dc.date.available2020-07-31T12:47:08Z
dc.date.issued2016
dc.description.abstractPhenology is among the most trustworthy indicators of climate change effects on plants and animals. The recent application of repeated digital photographs to monitor vegetation phenology has provided accurate measures of plant life cycle changes over time. A fundamental requirement for phenology studies refers to the correct recognition of phenological patterns from plants by taking into account time series associated with their crowns. This paper presents a new similarity measure for identifying plants based on the use of an unsupervised distance learning scheme, instead of using traditional approaches based on pairwise similarities. We experimentally show that its use yields considerable improvements in time-series search tasks. In addition, we also demonstrate how the late fusion of different time series can improve the results on plant species identification. In some cases, significant gains were observed (up to +8.21% and +19.39% for mean average precision and precision at 10 scores, respectively) when compared with the use of time series in isolation.en
dc.description.affiliationFed Univ Sao Paulo UNIFESP, Inst Sci & Technol, BR-12247014 Sao Jose Dos Campos, Brazil
dc.description.affiliationSao Paulo State Univ UNESP, Dept Stat Appl Math & Computat, BR-13506900 Rio Claro, Brazil
dc.description.affiliationSao Paulo State Univ UNESP, Dept Bot, BR-13506900 Rio Claro, Brazil
dc.description.affiliationUniv Campinas UNICAMP, Inst Comp, BR-13083852 Campinas, SP, Brazil
dc.description.affiliationUnifespInstitute of Science and Technology, Universidade Federal de São Paulo (UNIFESP), São José dos Campos, Brazil
dc.description.sourceWeb of Science
dc.description.sponsorshipFundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP) e Microsoft Research Virtual Institute
dc.description.sponsorshipCoordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES) e Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)
dc.description.sponsorshipConselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)
dc.description.sponsorshipIDMicrosoft Research Virtual Institute E FAPESP: 2010/52113-5
dc.description.sponsorshipIDMicrosoft Research Virtual Institute e FAPESP: 2013/50169-1
dc.description.sponsorshipIDMicrosoft Research Virtual Institute e FAPESP: 2013/50155-0
dc.description.sponsorshipIDFAPESP: 2014/00215-0
dc.description.sponsorshipIDFAPESP: 2009/18438-7
dc.description.sponsorshipIDFAPESP: 2010/51307-0
dc.description.sponsorshipIDFAPESP: 2013/08645-0
dc.description.sponsorshipIDFAPESP: 2016/06441-7
dc.description.sponsorshipIDCNPq: 310761/2014-0
dc.description.sponsorshipIDCNPq: 306580/2012-8
dc.format.extent5325-5338
dc.identifierhttp://dx.doi.org/10.1109/JSTARS.2016.2608358
dc.identifier.citationIeee Journal Of Selected Topics In Applied Earth Observations And Remote Sensing. Piscataway, v. 9, n. 12, p. 5325-5338, 2016.
dc.identifier.doi10.1109/JSTARS.2016.2608358
dc.identifier.issn1939-1404
dc.identifier.urihttps://repositorio.unifesp.br/handle/11600/56607
dc.identifier.wosWOS:000391468100005
dc.language.isoeng
dc.publisherIeee-Inst Electrical Electronics Engineers Inc
dc.relation.ispartofIeee Journal Of Selected Topics In Applied Earth Observations And Remote Sensing
dc.rightsinfo:eu-repo/semantics/restrictedAccess
dc.subjectImage analysisen
dc.subjectplant identificationen
dc.subjectremote phenologyen
dc.subjecttime seriesen
dc.subjectunsupervised distance learningen
dc.titleUnsupervised Distance Learning for Plant Species Identificationen
dc.typeinfo:eu-repo/semantics/article
Arquivos
Coleções
ICT - Artigos