ISEL - Eng. Elect. Tel. Comp. - Comunicações
Permanent URI for this collection
Browse
Browsing ISEL - Eng. Elect. Tel. Comp. - Comunicações by Issue Date
Now showing 1 - 10 of 455
Results Per Page
Sort Options
- Estimação de superfícies tridimensionais com modelos activosPublication . Nascimento, Jose; Marques, Jorge SalvadorEsta comunicação aborda a estimação da superfície de objectos a partir de um conjunto de pontos tridimensionais usando modelos activos. Propõe-se, uma extensão da Classe Unificada desenvolvida por Abrantes e Marques. A superfície é discretizada usando dois tipos de redes: redes de malha rectangular e redes Simplex. A Classe Unificada baseia-se no cálculo dos centróides dos dados na vizinhança de amostras pré-definidas da superfície deformável. Os pontos da superfície são atraídos na direcção dos centróides. O artigo revê os conceitos básicos de modelamento activo de superfícies, a Classe Unificada e as redes Simplex. Os modelos descritos são testados usando dados sintéticos e reais obtidos a partir de imagens ecográficas e de ressonância magnética.
- Estimation of 3D shapes using active surface modelsPublication . Nascimento, Jose; Marques, Jorge S.This paper addresses the estimation of surfaces from a set of 3D points using the unified framework described in [1]. This framework proposes the use of competitive learning for curve estimation, i.e., a set of points is defined on a deformable curve and they all compete to represent the available data. This paper extends the use of the unified framework to surface estimation. It o shown that competitive learning performes better than snakes, improving the model performance in the presence of concavities and allowing to desciminate close surfaces. The proposed model is evaluated in this paper using syntheticdata and medical images (MRI and ultrasound images).
- An algoritmh for the estimation of 3D surfaces using competitive learningPublication . Nascimento, Jose; Marques, Jorge SalvadorThis paper addresses the estimation of object boundaries from a set of 3D points. An extension of the constrained clustering algorithm developed by Abrantes and Marques in the context of edge linking is presented. The object surface is approximated using rectangular meshes and simplex nets. Centroid-based forces are used for attracting the model nodes towards the data, using competitive learning methods. It is shown that competitive learning improves the model performance in the presence of concavities and allows to discriminate close surfaces. The proposed model is evaluated using synthetic data and medical images (MRI and ultrasound images).
- Laser scanned photodiodes (LSP) for image sensingPublication . Vieira, Manuela; Fernandes, Miguel; Louro, Paula; Schwarz, R.; Schubert, M.An optimized ZnO:Al/a-pin SixCl1-x:H/Al configuration for the laser scanned photodiode (LSP) imaging detector is proposed. The LSP utilizes light induced depletion layers as detector and a laser beam for readout. The effect of the sensing element structure, cell configuration and light source flux are investigated and correlated with the sensor output characteristics. Experimental data reveal that the large optical gap and the low conductivity of the doped a-SixC1-x:H layers are responsible by an induced inversion layer at the illuminated interfaces which blocks the carrier collection. These insulator-like layers act as MIS gates preventing image smearing. The physical background of the LSP is discussed.
- Automatic tracking of multiple pedestrians with group formation and occlusionsPublication . Jorge, Pedro; Abrantes, Arnaldo; Marques, Jorge S.This work addresses the problem of automatic track ing of pedestrians observed by a fixed camera in out door scenes. Tracking isolated pedestrians is not a difficult task. The challenge arises when the track ing system has to deal with temporary occlusions and groups of pedestrians. In both cases it is not possi ble to track each pedestrian during the whole video sequence. However, the system should be able to rec ognize each pedestrian as soon as he/she becomes vis ible and isolated from the group. This paper presents methods to tackle these difficulties. The proposed sys tem is based on a hierarchical approach which allows the application of the same methods for tracking iso lated pedestrians and groups.
- Classificação não-supervisionada de dados hiperespectrais usando análise em componentes independentesPublication . Nascimento, Jose; Bioucas-Dias, José M.No passado recente foram desenvolvidas v árias t écnicas para classi ca ção de dados hiperspectrais. Uma abordagem tí pica consiste em considerar que cada pixel e uma mistura linear das reflectancias espectrais dos elementos presentes na c élula de resolu ção, adicionada de ru ído. Para classifi car e estimar os elementos presentes numa imagem hiperespectral, v ários problemas se colocam: Dimensionalidade dos dados, desconhecimento dos elementos presentes e a variabilidade da reflectância destes. Recentemente foi proposta a An álise em Componentes Independentes,para separa ção de misturas lineares. Nesta comunica ção apresenta-se uma metodologia baseada na An álise em Componentes Independentes para detec ção dos elementos presentes em imagens hiperespectrais e estima ção das suas quantidades. Apresentam-se resultados desta metodologia com dados simulados e com dados hiperespectrais reais, ilustrando a potencialidade da t écnica.
- Fast unsupervised technique for extraction of endmembers spectra from hyperspectral dataPublication . Nascimento, Jose; Bioucas-Dias, José M.One of the most challenging task underlying many hyperspectral imagery applications is the linear unmixing. The key to linear unmixing is to find the set of reference substances, also called endmembers, that are representative of a given scene. This paper presents the vertex component analysis (VCA) a new method to unmix linear mixtures of hyperspectral sources. The algorithm is unsupervised and exploits a simple geometric fact: endmembers are vertices of a simplex. The algorithm complexity, measured in floating points operations, is O (n), where n is the sample size. The effectiveness of the proposed scheme is illustrated using simulated data.
- Vertex component analysis: a fast algorithm to extract endmembers spectra from hyperspectral dataPublication . Nascimento, Jose; Bioucas-Dias, José M.Linear spectral mixture analysis, or linear unmixing, has proven to be a useful tool in hyperspectral remote sensing applications. It aims at estimating the number of reference substances, also called endmembers, their spectral signature and abundance fractions, using only the observed data (mixed pixels). This paper presents new method that performs unsupervised endmember extraction from hyperspectral data. The algorithm exploits a simple geometric fact: endmembers are vertices of a simplex. The algorithm complexity, measured in floating points operations, is O(n), where n is the sample size. The effectiveness of the proposed scheme is illustrated using simulated data.
- Does Independent Component Analysis Play a Role in Unmixing Hyperspectral Data?Publication . Nascimento, Jose; Bioucas-Dias, José M.Independent Component Analysis (ICA) have recently been proposed as a tool to unmix hyperspectral data. ICA is founded on two assumptions: i) The observed data vector is a linear mixture of the sources (abundance fractions); ii) sources are independent. Concerning hyperspectral data, the first assumption is valid whenever the constituent substances are surface distributed. The second assumption, however, is violated, since the sum of abundance fractions associated to each pixel is constant due to physical constraints in the data acquisition process. Thus, sources cannot be independent. This paper gives evidence that ICA, at least in its canonical form, is not suited to unmix hyperspectral data. We arrive to this conclusion by minimizing the mutual information of simulated hyperspectral mixtures. The hyperspectral data model includes signature variability, abundance perturbation, sensor Point Spread Function (PSF), abundance constraint and electronic noise. Mutual information computation is based on fitting mixtures of Gaussians to the observed data.
- On independent component analysis applied to unmixing hyperspectral dataPublication . Nascimento, Jose; Bioucas-Dias, José M.One of the most challenging task underlying many hyperspectral imagery applications is the spectral unmixing, which decomposes a mixed pixel into a collection of reectance spectra, called endmember signatures, and their corresponding fractional abundances. Independent Component Analysis (ICA) have recently been proposed as a tool to unmix hyperspectral data. The basic goal of ICA is to nd a linear transformation to recover independent sources (abundance fractions) given only sensor observations that are unknown linear mixtures of the unobserved independent sources. In hyperspectral imagery the sum of abundance fractions associated to each pixel is constant due to physical constraints in the data acquisition process. Thus, sources cannot be independent. This paper address hyperspectral data source dependence and its impact on ICA performance. The study consider simulated and real data. In simulated scenarios hyperspectral observations are described by a generative model that takes into account the degradation mechanisms normally found in hyperspectral applications. We conclude that ICA does not unmix correctly all sources. This conclusion is based on the a study of the mutual information. Nevertheless, some sources might be well separated mainly if the number of sources is large and the signal-to-noise ratio (SNR) is high.