Hyperspectral Images
Mostrando 1-12 de 13 artigos, teses e dissertações.
-
1. Sparse Estimation of the Precision Matrix and Plug-In Principle in Linear Discriminant Analysis for Hyperspectral Image Classification
ABSTRACT In this paper, a new method for supervised classification of hyperspectral images is proposed for the case in which the size of the training sample is small. It consists of replacing in the Mahalanobis distance the maximum likelihood estimator of the precision matrix by a sparse estimator. The method is compared with two other existing versions of L
Trends in Computational and Applied Mathematics. Publicado em: 2022
-
2. CLASS-BASED AFFINITY PROPAGATION FOR HYPERSPECTRAL IMAGE DIMENSIONALITY REDUCTION AND IMPROVEMENT OF MAXIMUM LIKELIHOOD CLASSIFICATION ACCURACY
Resumo Este artigo investiga um método de classificação alternativo que integra o algoritmo de clusterização propagação de afinidade baseado nas classes (PAC) e o Classificador Máxima Verossimilhança (MAXVER) com a finalidade de superar as limitações do MAXVER na classificação de dados de alta dimensionalidade e, assim, melhorar a sua acurácia.
Bol. Ciênc. Geod.. Publicado em: 18/04/2019
-
3. Use of Infrared Spectroscopy and Near Infrared Hyperspectral Images to Evaluate Effects of Different Chemical Agents on PET Bottle Surface
PET - poly (ethylene terephthalate) - bottle surfaces were exposed to chemical agents and evaluated with middle infrared spectroscopy (MIR) and near infrared hyperspectral imaging (HSI-NIR). Images (928-2.524 nm) were acquired at different times from bottle surfaces exposed to alkaline, acidic and ethanolic media. Savitzky-Golay smoothing (2nd order polynomi
Mat. Res.. Publicado em: 09/08/2018
-
4. CLASSIFICAÇÃO DE FASES EM IMAGENS HIPERESPECTRAIS DE RAIOS X CARACTERÍSTICOS PELO MÉTODO DE AGRUPAMENTO POR DESLOCAMENTO PARA A MÉDIA / PHASE CLASSIFICATION IN CHARACTERISTIC X-RAYS HYPERSPECTRAL IMAGES BY MEAN SHIFT CLUSTERING METHOD
No presente trabalho será introduzido o algoritmo de Agrupamento por Deslocamento para a Média (ADM) como uma alternativa para executar a classificação de fases em materiais a partir de imagens hiperspectrais de mapas raios X característicos. Ao contrário de outras técnicas estatísticas multivariadas, tal como Análise de Componentes Principais (ACP)
IBICT - Instituto Brasileiro de Informação em Ciência e Tecnologia. Publicado em: 23/01/2012
-
5. Desenvolvimento de um algoritmo para identificação e correção de spikes em espectroscopia Raman de imagem
Raman imaging spectroscopy is a highly useful analytical tool that provides spatial and spectral information on a sample. However, CCD detectors used in dispersive instruments present the drawback of being sensitive to cosmic rays, giving rise to spikes in Raman spectra. Spikes influence variance structures and must be removed prior to the use of multivariat
Química Nova. Publicado em: 2012
-
6. Investigação do uso de imagens de sensor de sensoriamento remoto hiperespectral e com alta resolução espacial no monitoramento da condição de uso de pavimentos rodoviários. / Investigation of use hyperspectral and high spatial resolution images from remote sensing in pavement surface condition monitoring.
Segundo a Agência Nacional de Transportes Terrestres (ANTT) em seu Anuário Estatístico dos Transportes Terrestres AETT (2008), o Brasil em todo o seu território possui 211.678 quilômetros de rodovias pavimentadas. O valor de serventia do pavimento diminui com o passar do tempo por dois fatores principais: o tráfego e as intempéries (BERNUCCI et al., 2
Publicado em: 2010
-
7. Estudo da composição e distribuição da alteração hidrotermal do Cerro Aguas Calientes, Salta, Argentina a partir de imagens do sensor ASTER
The conception of the ASTER sensor by the end of the 1990s brought new benefit to the mapping of hydrothermal alteration zones, initiating a promising phase in remote sensing of earthly resources. Recent studies utilizing this sensor for mineralogical mapping have proved its effectiveness. This study tested the hyperspectral classification in ASTER multispec
Publicado em: 2009
-
8. Study of Cerrado physiognomies with Hyperion-EO-1 data / Estudo de fitofisionomias de Cerrado com dados do sensor Hyperion-EO-1
The study of the Brazilian savanna physiognomies (Cerrado) using remote sensing data is still a challenge due to floristic and structural diversity, variation in phenological response to precipitation, relationships with other biomes in the transition zones, and to fire and resultant effects. Because of these factors, some physiognomies are not separable in
Publicado em: 2009
-
9. Biblioteca espectral: determinação de espectros de referência para a classificação de tipos de água das áreas alagáveis da Amazônia / Spectral library: references for water types classification in Amazon wetlands
The advent of orbital hyperspectral sensors increased the possibility of assessing water properties in complex inland waters, such as that of Amazon wetlands. The current methods for water properties assessment are based upon empirical and semi-analytical models. An alternative to those methods is to build a water spectral library as reference to classify di
Publicado em: 2009
-
10. Hydrothermal alteration of the Cerro La Mina gold prospect, Los Menucos, Patagonia Argentina : geology, remote sensing and stable isotopes / Alteração hidrotermal do prospecto aurifero Cerro La Mina, Los Menucos, Patagonia Argentina : geologia , sensoriamento remoto e isotopos estaveis
The epithermal Cerro La Mina prospect, located in the Los Menucos region, Patagonia Argentina, is currently being explored for epithermal precious-metal mineralization. Triassic hydrothermal activity produced intense alteration of rhyolites, andesites, ignimbrites, and tuffs of the Middle- to Late Triassic Los Menucos Group, in the Somún Curá massif. The u
Publicado em: 2007
-
11. Study of amazon floodplain water composition using hyperion/EO-1 and field reflectance data for the comprehension of temporal variability of optically active constituents / Estudo da composição das águas da planície amazônica por meio de dados de reflectância do sensor hyperion/EO-1 e de espectrômetro de campo visando a compreensão da variação temporal dos seus constituintes opticamente ativos
Two methodological approaches were evaluated to study the reflectance of optically active constituents using hyperspectral imagery of EO-1 Hyperion orbital sensor: a) Linear Spectral Mixture Model; and b) derivative analysis. Two Hyperion images acquired over an area located upstream of the confluence between the Amazon and the Tapajós rivers were analysed,
Publicado em: 2006
-
12. Caracterização e mapeamento da vegetação da região da Floresta Nacional de Tapajós através de dados óticos, de radar e inventários florestais / Vegetation characterization and mapping of Tapajós national forest region through optico, radar and forest inventory data
The Tapajós National Forest (FNT) has been observed by several remote sensor types, for many years. As one of the main study sites of the Large Scale Biosphere-Atmosphere Experiment in Amazonia (LBA) project, the FNT has been object of several remote sensing campaigns. However, the papers that have tried to integrate the information originating from the mul
Publicado em: 2003