SiRCub, A Novel Approach to Recognize Agricultural Crops Using Supervised Classification

Página do item simplificado
dc.citation.issue4
dc.citation.volume8
dc.contributor.authorTomas, Jordi Creus
dc.contributor.authorFaria, Fabio Augusto [UNIFESP]
dc.contributor.authorDalla Mora Esquerdo, Julio Cesar
dc.contributor.authorCoutinho, Alexandre Camargo
dc.contributor.authorMedeiros, Claudia Bauzer
dc.coverageHershey
dc.date.accessioned2020-08-04T13:39:56Z
dc.date.available2020-08-04T13:39:56Z
dc.date.issued2017
dc.description.abstractThis paper presents a new approach to deal with agricultural crop recognition using SVM (Support Vector Machine), applied to time series of NDVI images. The presented method can be divided into two steps. First, the Timesat software package is used to extract a set of crop features from the NDVI time series. These features serve as descriptors that characterize each NDVI vegetation curve, i.e., the period comprised between sowing and harvesting dates. Then, it is used an SVM to learn the patterns that define each type of crop, and create a crop model that allows classifying new series. The authors present a set of experiments that show the effectiveness of this technique. They evaluated their algorithm with a collection of more than 3000 time series from the Brazilian State of Mato Grosso spanning 4 years (2009-2013). Such time series were annotated in the field by specialists from Embrapa (Brazilian Agricultural Research Corporation). This methodology is generic, and can be adapted to distinct regions and crop profiles.en
dc.description.affiliationUniv Estadual Campinas, Inst Comp, Campinas, SP, Brazil
dc.description.affiliationUniv Fed Sao Paulo, Inst Sci & Technol, Sao Jose Dos Campos, Brazil
dc.description.affiliationBrazilian Agr Res Corp, Embrapa Agr Informat, Campinas, SP, Brazil
dc.description.affiliationBrazilian Agr Res Corp, Embrapa Agr Informat, Campinas, SP, Brazil
dc.description.affiliationUniv Campinas Unicamp, Inst Comp, Campinas, SP, Brazil
dc.description.affiliationParis Dauphine Univ, Paris, France
dc.description.affiliationUnifespUniv Fed Sao Paulo, Inst Sci & Technol, Sao Jose Dos Campos, Brazil
dc.description.sourceWeb of Science
dc.description.sponsorshipFAPESP
dc.description.sponsorshipFAPESP/Cepid in Computational Engineering and Sciences
dc.description.sponsorshipINCT in Web Science
dc.description.sponsorshipCNPq Universal Project
dc.description.sponsorshipCNPq
dc.description.sponsorshipIDFAPESP: 2012/25169-5
dc.description.sponsorshipIDFAPESP: 2013/08293-7
dc.description.sponsorshipIDCNPq: 408919/2016-7
dc.format.extent20-36
dc.identifierhttp://dx.doi.org/10.4018/IJAEIS.2017100102
dc.identifier.citationInternational Journal Of Agricultural And Environmental Information Systems. Hershey, v. 8, n. 4, p. 20-36, 2017.
dc.identifier.doi10.4018/IJAEIS.2017100102
dc.identifier.issn1947-3192
dc.identifier.urihttps://repositorio.unifesp.br/handle/11600/57193
dc.identifier.wosWOS:000417449400002
dc.language.isoeng
dc.publisherIgi Global
dc.relation.ispartofInternational Journal Of Agricultural And Environmental Information Systems
dc.rightsinfo:eu-repo/semantics/restrictedAccess
dc.subjectCrop Classificationen
dc.subjectLULCen
dc.subjectMachine Learningen
dc.subjectNDVIen
dc.subjectRemote Sensingen
dc.subjectSVMen
dc.subjectTime Seriesen
dc.subjectTimesaten
dc.titleSiRCub, A Novel Approach to Recognize Agricultural Crops Using Supervised Classificationen
dc.typeinfo:eu-repo/semantics/article
Arquivos
Coleções
ICT - Artigos