Comparative performance of convolutional neural network, weighted and conventional support vector machine and random forest for classifying tree species using hyperspectral and photogrammetric data

Registro completo de metadados
MetadadosDescriçãoIdioma
Autor(es): dc.contributorNational Institute for Space Research (INPE)-
Autor(es): dc.contributorSanta Catarina State University (UDESC)-
Autor(es): dc.contributorPontifical Catholic University of Rio de Janeiro (PUC)-
Autor(es): dc.contributorResearch and Innovation Centre-
Autor(es): dc.contributorUniversidade Estadual Paulista (Unesp)-
Autor(es): dc.creatorSothe, C.-
Autor(es): dc.creatorDe Almeida, C. M.-
Autor(es): dc.creatorSchimalski, M. B.-
Autor(es): dc.creatorLa Rosa, L. E.C.-
Autor(es): dc.creatorCastro, J. D.B.-
Autor(es): dc.creatorFeitosa, R. Q.-
Autor(es): dc.creatorDalponte, M.-
Autor(es): dc.creatorLima, C. L.-
Autor(es): dc.creatorLiesenberg, V.-
Autor(es): dc.creatorMiyoshi, G. T. [UNESP]-
Autor(es): dc.creatorTommaselli, A. M.G. [UNESP]-
Data de aceite: dc.date.accessioned2022-02-22T00:29:03Z-
Data de disponibilização: dc.date.available2022-02-22T00:29:03Z-
Data de envio: dc.date.issued2020-12-11-
Data de envio: dc.date.issued2020-12-11-
Data de envio: dc.date.issued2020-04-02-
Fonte completa do material: dc.identifierhttp://dx.doi.org/10.1080/15481603.2020.1712102-
Fonte completa do material: dc.identifierhttp://hdl.handle.net/11449/200003-
Fonte: dc.identifier.urihttp://educapes.capes.gov.br/handle/11449/200003-
Descrição: dc.descriptionThe classification of tree species can significantly benefit from high spatial and spectral information acquired by unmanned aerial vehicles (UAVs) associated with advanced classification methods. This study investigated the following topics concerning the classification of 16 tree species in two subtropical forest fragments of Southern Brazil: i) the potential integration of UAV-borne hyperspectral images with 3D information derived from their photogrammetric point cloud (PPC); ii) the performance of two machine learning methods (support vector machine–SVM and random forest–RF) when employing different datasets at a pixel and individual tree crown (ITC) levels; iii) the potential of two methods for dealing with the imbalanced sample set problem: a new weighted SVM (wSVM) approach, which attributes different weights to each sample and class, and a deep learning classifier (convolutional neural network–CNN), associated with a previous step to balance the sample set; and finally, iv) the potential of this last classifier for tree species classification as compared to the above mentioned machine learning methods. Results showed that the inclusion of the PPC features to the hyperspectral data provided a great accuracy increase in tree species classification results when conventional machine learning methods were applied, between 13 and 17% depending on the classifier and the study area characteristics. When using the PPC features and the canopy height model (CHM), associated with the majority vote (MV) rule, the SVM, wSVM and RF classifiers reached accuracies similar to the CNN, which outperformed these classifiers for both areas when considering the pixel-based classifications (overall accuracy of 84.4% in Area 1, and 74.95% in Area 2). The CNN was between 22% and 26% more accurate than the SVM and RF when only the hyperspectral bands were employed. The wSVM provided a slight increase in accuracy not only for some lesser represented classes, but also some major classes in Area 2. While conventional machine learning methods are faster, they demonstrated to be less stable to changes in datasets, depending on prior segmentation and hand-engineered features to reach similar accuracies to those attained by the CNN. To date, CNNs have been barely explored for the classification of tree species, and CNN-based classifications in the literature have not dealt with hyperspectral data specifically focusing on tropical environments. This paper thus presents innovative strategies for classifying tree species in subtropical forest areas at a refined legend level, integrating UAV-borne 2D hyperspectral and 3D photogrammetric data and relying on both deep and conventional machine learning approaches.-
Descrição: dc.descriptionFundação de Amparo à Pesquisa e Inovação do Estado de Santa Catarina-
Descrição: dc.descriptionConselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)-
Descrição: dc.descriptionCoordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)-
Descrição: dc.descriptionDivision of Remote Sensing National Institute for Space Research (INPE)-
Descrição: dc.descriptionDepartment of Forest Engineering Santa Catarina State University (UDESC)-
Descrição: dc.descriptionDepartment of Electrical Engineering Pontifical Catholic University of Rio de Janeiro (PUC)-
Descrição: dc.descriptionDepartment of Sustainable Agro-Ecosystems and Bioresources Research and Innovation Centre-
Descrição: dc.descriptionDepartment of Geography Santa Catarina State University (UDESC)-
Descrição: dc.descriptionDepartment of Cartography São Paulo State University (UNESP)-
Descrição: dc.descriptionDepartment of Cartography São Paulo State University (UNESP)-
Descrição: dc.descriptionFundação de Amparo à Pesquisa e Inovação do Estado de Santa Catarina: 2017TR1762-
Descrição: dc.descriptionCNPq: 313887/2018-7-
Descrição: dc.descriptionCAPES: 88882.330700/2018-01-
Formato: dc.format369-394-
Idioma: dc.languageen-
Relação: dc.relationGIScience and Remote Sensing-
???dc.source???: dc.sourceScopus-
Palavras-chave: dc.subjectdeep learning-
Palavras-chave: dc.subjectimbalanced sample set-
Palavras-chave: dc.subjectindividual tree crown-
Palavras-chave: dc.subjectTropical diversity-
Palavras-chave: dc.subjectunmanned aerial vehicle-
Título: dc.titleComparative performance of convolutional neural network, weighted and conventional support vector machine and random forest for classifying tree species using hyperspectral and photogrammetric data-
Tipo de arquivo: dc.typelivro digital-
Aparece nas coleções:Repositório Institucional - Unesp

Não existem arquivos associados a este item.