A novel deep learning method to identify single tree species in UAV-based hyperspectral images

Registro completo de metadados
MetadadosDescriçãoIdioma
Autor(es): dc.contributorUniversidade Estadual Paulista (Unesp)-
Autor(es): dc.contributorUniversidade Federal de Mato Grosso do Sul (UFMS)-
Autor(es): dc.contributorCidade Universitária-
Autor(es): dc.contributorNational Land Survey of Finland-
Autor(es): dc.creatorMiyoshi, Gabriela Takahashi [UNESP]-
Autor(es): dc.creatorArruda, Mauro dos Santos-
Autor(es): dc.creatorOsco, Lucas Prado-
Autor(es): dc.creatorJunior, José Marcato-
Autor(es): dc.creatorGonçalves, Diogo Nunes-
Autor(es): dc.creatorImai, Nilton Nobuhiro [UNESP]-
Autor(es): dc.creatorTommaselli, Antonio Maria Garcia [UNESP]-
Autor(es): dc.creatorHonkavaara, Eija-
Autor(es): dc.creatorGonçalves, Wesley Nunes-
Data de aceite: dc.date.accessioned2022-02-22T00:30:30Z-
Data de disponibilização: dc.date.available2022-02-22T00:30:30Z-
Data de envio: dc.date.issued2020-12-11-
Data de envio: dc.date.issued2020-12-11-
Data de envio: dc.date.issued2020-04-01-
Fonte completa do material: dc.identifierhttp://dx.doi.org/10.3390/RS12081294-
Fonte completa do material: dc.identifierhttp://hdl.handle.net/11449/200401-
Fonte: dc.identifier.urihttp://educapes.capes.gov.br/handle/11449/200401-
Descrição: dc.descriptionDeep neural networks are currently the focus of many remote sensing approaches related to forest management. Although they return satisfactory results in most tasks, some challenges related to hyperspectral data remain, like the curse of data dimensionality. In forested areas, another common problem is the highly-dense distribution of trees. In this paper, we propose a novel deep learning approach for hyperspectral imagery to identify single-tree species in highly-dense areas. We evaluated images with 25 spectral bands ranging from 506 to 820 nm taken over a semideciduous forest of the Brazilian Atlantic biome. We included in our network's architecture a band combination selection phase. This phase learns from multiple combinations between bands which contributed the most for the tree identification task. This is followed by a feature map extraction and a multi-stage model refinement of the confidence map to produce accurate results of a highly-dense target. Our method returned an f-measure, precision and recall values of 0.959, 0.973, and 0.945, respectively. The results were superior when compared with a principal component analysis (PCA) approach. Compared to other learning methods, ours estimate a combination of hyperspectral bands that most contribute to the mentioned task within the network's architecture. With this, the proposed method achieved state-of-the-art performance for detecting and geolocating individual tree-species in UAV-based hyperspectral images in a complex forest.-
Descrição: dc.descriptionGraduate Program in Cartographic Sciences São Paulo State University (UNESP)-
Descrição: dc.descriptionGraduate Program in Computer Sciences Faculty of Computer Science Federal University of Mato Grosso do Sul (UFMS), Av. Costa e Silva-
Descrição: dc.descriptionFaculty of Engineering and Architecture and Urbanism University ofWestern São Paulo (UNOESTE) Cidade Universitária, R. José Bongiovani-
Descrição: dc.descriptionFaculty of Engineering Architecture and Urbanism and Geography Federal University of Mato Grosso do Sul (UFMS), Av. Costa e Silva-
Descrição: dc.descriptionDepartment of Cartography São Paulo State University (UNESP)-
Descrição: dc.descriptionFinnish Geospatial Research Institute National Land Survey of Finland, Geodeetinrinne 2-
Descrição: dc.descriptionGraduate Program in Cartographic Sciences São Paulo State University (UNESP)-
Descrição: dc.descriptionDepartment of Cartography São Paulo State University (UNESP)-
Idioma: dc.languageen-
Relação: dc.relationRemote Sensing-
???dc.source???: dc.sourceScopus-
Palavras-chave: dc.subjectBand selection-
Palavras-chave: dc.subjectConvolutional neural network-
Palavras-chave: dc.subjectData-reduction-
Palavras-chave: dc.subjectHigh-density object-
Palavras-chave: dc.subjectTree species identification-
Título: dc.titleA novel deep learning method to identify single tree species in UAV-based hyperspectral images-
Tipo de arquivo: dc.typelivro digital-
Aparece nas coleções:Repositório Institucional - Unesp

Não existem arquivos associados a este item.