• Refine Query
  • Source
  • Publication year
  • to
  • Language
  • 1
  • Tagged with
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • About
  • The Global ETD Search service is a free service for researchers to find electronic theses and dissertations. This service is provided by the Networked Digital Library of Theses and Dissertations.
    Our metadata is collected from universities around the world. If you manage a university/consortium/country archive and want to be added, details can be found on the NDLTD website.
1

Emergent tree species identification in highly diverse Brazilian Atlantic forest using hyperspectral images acquired with UAV /

Miyoshi, Gabriela Takahashi. January 2020 (has links)
Orientador: Nilton Nobuhiro Imai / Resumo: O objetivo desse doutorado é propor uma nova metodologia para identificar oito espécies arbóreas emergentes (i.e., que se sobressaem do dossel florestal), em diferentes idades e estágios de desenvolvimento e pertencentes à Mata Atlântica brasileira. Para tal, imagens hiperespectrais foram adquiridas em Julho/2017, em Junho/2018, e em Julho/2019 em um transecto localizado no fragmento florestal Ponte Branca, localizado a Oeste do Estado de São Paulo, onde a floresta é considerada estacional semidecidual e submontana. As imagens com resolução espacial de 10 cm foram adquiridas com câmara hiperespectral (500–900 nm) acoplada em veículo aéreo não tripulado (VANT ou UAV, do inglês Unmanned aerial vehicle) e, posteriormente corrigidas geometricamente e radiometricamente. Em seguida, as copas arbóreas individuais (ITCs, do inglês Individual tree crows) foram delineadas manualmente em cada conjunto de dados para serem utilizadas como referência para os experimentos. Dentre os experimentos realizados, destaca-se o uso do espectro normalizado para redução da variabilidade espectral intra-espécies, o uso da classificação baseada em regiões utilizando o algoritmo Random Forest e o uso de superpixexls para delineamento automático das ITCs em cada conjunto de imagens. Além disso, avaliou-se o uso dos superpixels multitemporais com diferentes atributos multitemporais (espectro normalizado, textura e índices de vegetação) e estruturais (derivados do modelo de altura das copas), sozinhos ou c... (Resumo completo, clicar acesso eletrônico abaixo) / Abstract: The objective of this doctoral dissertation is to propose a new methodology to identify eight emergent tree species (i.e., that stood out from the canopy) belonging to highly diverse Brazilian Atlantic forest and with different ages and development stages. To achieve the objective, hyperspectral images were acquired in July/2017, June/208, and July/2019 in a transect area located in the western part of São Paulo State. The area is in Ponte Branca ecological station, where the forest is classified as submontane semideciduous seasonal with different stages of succession. Images with a spatial resolution of 10 cm were acquired with a hyperspectral camera (500–900 nm) onboard unmanned aerial vehicle (UAV) and geometrically and radiometrically post-processed. In sequence, the individual tree crowns (ITCs) were manually delineated in each dataset to be used as reference in the experiments. From the performed experiments, it is highlighted the use of mean normalized spectra to reduce the within-species spectral variability, the use of region-based classification with the Random Forest algorithm, and the use of superpixels to automatically delineate the ITCs in each dataset. Additionally, the multitemporal superpixels with different multitemporal features (normalized spectra, texture and vegetation indexes) and structural features derived from the canopy height model, combined or not, were assessed to the tree species classification. The best result was achieved merging normalized sp... (Complete abstract click electronic access below) / Doutor

Page generated in 0.1158 seconds