A carregar...
Projeto de investigação
Sem título
Financiador
Autores
Publicações
Unsupervised hyperspectral signal subspace identification
Publication . Nascimento, Jose; Bioucas-Dias, José M.
Hyperspectral imaging sensors provide image data containing both spectral and spatial information from the Earth surface. The huge data volumes produced by these sensors put stringent requirements on communications, storage, and processing.
This paper presents a method, termed hyperspectral signal subspace identification by minimum error (HySime), that infer the signal subspace and determines its dimensionality without any prior knowledge. The identification of this subspace enables a correct dimensionality reduction yielding gains in algorithm performance and complexity and in data storage. HySime method is unsupervised and fully-automatic, i.e., it does not depend on any tuning parameters. The effectiveness of the proposed method is illustrated using simulated data based on U.S.G.S. laboratory spectra and real hyperspectral data collected by the AVIRIS sensor over Cuprite, Nevada.
Hyperspectral signal subspace estimation
Publication . Nascimento, Jose; Bioucas-Dias, José M.
Given an hyperspectral image, the determination of the number of endmembers and the subspace where they live without any prior knowledge is crucial to the success of hyperspectral image analysis.
This paper introduces a new minimum mean squared error based approach to infer the signal subspace in hyperspectral imagery. The method, termed hyperspectral signal identification by minimum error (HySime), is eigendecomposition based and it does not depend on any tuning parameters. It first estimates the signal and noise correlation matrices and then selects the subset of eigenvalues that best represents the signal subspace in the least squared error sense. The effectiveness of the proposed method is illustrated using simulated data based on U.S.G.S. laboratory spectra and real hyperspectral data collected by the AVIRIS sensor over Cuprite, Nevada.
Unidades organizacionais
Descrição
Palavras-chave
Contribuidores
Financiadores
Entidade financiadora
Fundação para a Ciência e a Tecnologia
Programa de financiamento
Orçamento de Funcionamento/POSC
Número da atribuição
POSC/EEA-CPS/61271/2004