Advanced image processing techniques for detection and quantification of drusen

Dissertation presented to obtain the degree of Doctor of Philosophy in Electrical Engineering, speciality on Perceptional Systems, by the Universidade Nova de Lisboa, Faculty of Sciences and Technology

Vertex component analysis: a geometric-based approach to unmix hyperspectral data

Hyperspectral remote sensing exploits the electromagnetic scattering patterns of the different materials at specific wavelengths [2, 3]. Hyperspectral sensors have been developed to sample the scattered portion of the electromagnetic spectrum extending from the visible region through the near-infrared and mid-infrared, in hundreds of narrow contiguous bands [4, 5]. The number and variety of potential civilian and military applications of hyperspectral remote sensing is enormous [6, 7]. Very often, the resolution cell corresponding to a single pixel in an image contains several substances (endmembers) [4]. In this situation, the scattered energy is a mixing of the endmember spectra. A challenging task underlying many hyperspectral imagery applications is then decomposing a mixed pixel into a collection of reflectance spectra, called endmember signatures, and the corresponding abundance fractions [8–10]. Depending on the mixing scales at each pixel, the observed mixture is either linear or nonlinear [11, 12]. Linear mixing model holds approximately when the mixing scale is macroscopic [13] and there is negligible interaction among distinct endmembers [3, 14]. If, however, the mixing scale is microscopic (or intimate mixtures) [15, 16] and the incident solar radiation is scattered by the scene through multiple bounces involving several endmembers [17], the linear model is no longer accurate. Linear spectral unmixing has been intensively researched in the last years [9, 10, 12, 18–21]. It considers that a mixed pixel is a linear combination of endmember signatures weighted by the correspondent abundance fractions. Under this model, and assuming that the number of substances and their reflectance spectra are known, hyperspectral unmixing is a linear problem for which many solutions have been proposed (e.g., maximum likelihood estimation [8], spectral signature matching [22], spectral angle mapper [23], subspace projection methods [24,25], and constrained least squares [26]). In most cases, the number of substances and their reflectances are not known and, then, hyperspectral unmixing falls into the class of blind source separation problems [27]. Independent component analysis (ICA) has recently been proposed as a tool to blindly unmix hyperspectral data [28–31]. ICA is based on the assumption of mutually independent sources (abundance fractions), which is not the case of hyperspectral data, since the sum of abundance fractions is constant, implying statistical dependence among them. This dependence compromises ICA applicability to hyperspectral images as shown in Refs. [21, 32]. In fact, ICA finds the endmember signatures by multiplying the spectral vectors with an unmixing matrix, which minimizes the mutual information among sources. If sources are independent, ICA provides the correct unmixing, since the minimum of the mutual information is obtained only when sources are independent. This is no longer true for dependent abundance fractions. Nevertheless, some endmembers may be approximately unmixed. These aspects are addressed in Ref. [33]. Under the linear mixing model, the observations from a scene are in a simplex whose vertices correspond to the endmembers. Several approaches [34–36] have exploited this geometric feature of hyperspectral mixtures [35]. Minimum volume transform (MVT) algorithm [36] determines the simplex of minimum volume containing the data. The method presented in Ref. [37] is also of MVT type but, by introducing the notion of bundles, it takes into account the endmember variability usually present in hyperspectral mixtures. The MVT type approaches are complex from the computational point of view. Usually, these algorithms find in the first place the convex hull defined by the observed data and then fit a minimum volume simplex to it. For example, the gift wrapping algorithm [38] computes the convex hull of n data points in a d-dimensional space with a computational complexity of O(nbd=2cþ1), where bxc is the highest integer lower or equal than x and n is the number of samples. The complexity of the method presented in Ref. [37] is even higher, since the temperature of the simulated annealing algorithm used shall follow a log( ) law [39] to assure convergence (in probability) to the desired solution. Aiming at a lower computational complexity, some algorithms such as the pixel purity index (PPI) [35] and the N-FINDR [40] still find the minimum volume simplex containing the data cloud, but they assume the presence of at least one pure pixel of each endmember in the data. This is a strong requisite that may not hold in some data sets. In any case, these algorithms find the set of most pure pixels in the data. PPI algorithm uses the minimum noise fraction (MNF) [41] as a preprocessing step to reduce dimensionality and to improve the signal-to-noise ratio (SNR). The algorithm then projects every spectral vector onto skewers (large number of random vectors) [35, 42,43]. The points corresponding to extremes, for each skewer direction, are stored. A cumulative account records the number of times each pixel (i.e., a given spectral vector) is found to be an extreme. The pixels with the highest scores are the purest ones. N-FINDR algorithm [40] is based on the fact that in p spectral dimensions, the p-volume defined by a simplex formed by the purest pixels is larger than any other volume defined by any other combination of pixels. This algorithm finds the set of pixels defining the largest volume by inflating a simplex inside the data. ORA SIS [44, 45] is a hyperspectral framework developed by the U.S. Naval Research Laboratory consisting of several algorithms organized in six modules: exemplar selector, adaptative learner, demixer, knowledge base or spectral library, and spatial postrocessor. The first step consists in flat-fielding the spectra. Next, the exemplar selection module is used to select spectral vectors that best represent the smaller convex cone containing the data. The other pixels are rejected when the spectral angle distance (SAD) is less than a given thresh old. The procedure finds the basis for a subspace of a lower dimension using a modified Gram–Schmidt orthogonalizati on. The selected vectors are then projected onto this subspace and a simplex is found by an MV T pro cess. ORA SIS is oriented to real-time target detection from uncrewed air vehicles using hyperspectral data [46]. In this chapter we develop a new algorithm to unmix linear mixtures of endmember spectra. First, the algorithm determines the number of endmembers and the signal subspace using a newly developed concept [47, 48]. Second, the algorithm extracts the most pure pixels present in the data. Unlike other methods, this algorithm is completely automatic and unsupervised. To estimate the number of endmembers and the signal subspace in hyperspectral linear mixtures, the proposed scheme begins by estimating sign al and noise correlation matrices. The latter is based on multiple regression theory. The signal subspace is then identified by selectin g the set of signal eigenvalue s that best represents the data, in the least-square sense [48,49 ], we note, however, that VCA works with projected and with unprojected data. The extraction of the end members exploits two facts: (1) the endmembers are the vertices of a simplex and (2) the affine transformation of a simplex is also a simplex. As PPI and N-FIND R algorithms, VCA also assumes the presence of pure pixels in the data. The algorithm iteratively projects data on to a direction orthogonal to the subspace spanned by the endmembers already determined. The new end member signature corresponds to the extreme of the projection. The algorithm iterates until all end members are exhausted. VCA performs much better than PPI and better than or comparable to N-FI NDR; yet it has a computational complexity between on e and two orders of magnitude lower than N-FINDR. The chapter is structure d as follows. Section 19.2 describes the fundamentals of the proposed method. Section 19.3 and Section 19.4 evaluate the proposed algorithm using simulated and real data, respectively. Section 19.5 presents some concluding remarks.

Identidade visual corporativa enquanto recurso estratégico na competitividade entre organizações em Portugal

Dissertação apresentada à Escola Superior de Comunicação Social como parte dos requisitos para obtenção de grau de mestre em Publicidade e Marketing.

Vision based context categorization for all-terrain robot

Dissertation presented at the Faculdade de Ciências e Tecnologia da Universidade Nova de Lisboa to obtain the Master degree in Electrical and Computer Engineering.

Automated image tagging through tag propagation

Trabalho apresentado no âmbito do Mestrado em Engenharia Informática, como requisito parcial Para obtenção do grau de Mestre em Engenharia Informática

Análise de Capacidade Processo Inspeção Visual

Este trabalho foi realizado no âmbito do Mestrado em Engenharia Mecânica, especialização em Gestão Industrial, do Instituto Superior de Engenharia do Porto. O estudo foi desenvolvido na Continental Mabor – Indústria de Pneus S.A., sendo analisado o processo de Inspeção Visual dos pneus. Face à atual conjuntura de mercado, as empresas devem estar munidas de dados detalhados e precisos relativos aos seus processos produtivos. A Capacidade instalada apresenta-secomo um parâmetro determinante na medida em que condiciona diretamente a resposta a solicitações de clientes. Esta é fortemente influenciada pelo Layout fabril, pelo que a otimização do mesmo é fundamental numa perspetiva de ganho de Capacidade produtiva. O relatório iniciou-se com a determinação do Tempo Previsto da operação segundo o referencial REFA. Seguidamente quantificaram-se as atuais perturbações através de auditorias ao processo. Deste modo obteve-se uma Capacidade instalada de 59380 pneus/dia. A análise das perturbações desenvolveu-se a partir de um diagrama causa-efeito, no qual foram identificadas diversas potenciais causas, classificadas posteriormente por uma equipa experiente e conhecedora do processo. Assim, conhecidas as perturbações de maior impacto, foi apresentada uma solução de Layout que visou a sua minimização. O ganho estimado, em termos de Capacidade, após a implementação da solução proposta é de 3000 pneus/dia. Este ganho de 5% é significativo na medida em que é obtido sem a necessidade de aquisição de novos equipamentos nem de área fabril adicional. É expectável que esta implementação proporcione ainda melhorias no processo produtivo subsequente - Uniformidade, especificamente na alimentação do mesmo. A quantificação desta melhoria, na sequência deste trabalho, apresenta-se como uma oportunidade de estudo futuro.

Study of behavioural and neural bases of visuo-spatial working memory with an fMRI paradigm based on an n-back task

The goal of this study was to propose a new functional magnetic resonance imaging (fMRI) paradigm using a language-free adaptation of a 2-back working memory task to avoid cultural and educational bias. We additionally provide an index of the validity of the proposed paradigm and test whether the experimental task discriminates the behavioural performances of healthy participants from those of individuals with working memory deficits. Ten healthy participants and nine patients presenting working memory (WM) deficits due to acquired brain injury (ABI) performed the developed task. To inspect whether the paradigm activates brain areas typically involved in visual working memory (VWM), brain activation of the healthy participants was assessed with fMRIs. To examine the task's capacity to discriminate behavioural data, performances of the healthy participants in the task were compared with those of ABI patients. Data were analysed with GLM-based random effects procedures and t-tests. We found an increase of the BOLD signal in the specialized areas of VWM. Concerning behavioural performances, healthy participants showed the predicted pattern of more hits, less omissions and a tendency for fewer false alarms, more self-corrected responses, and faster reaction times, when compared with subjects presenting WM impairments. The results suggest that this task activates brain areas involved in VWM and discriminates behavioural performances of clinical and non-clinical groups. It can thus be used as a research methodology for behavioural and neuroimaging studies of VWM in block-design paradigms.

Development of paper-based color test-strip for drug detection in aquatic environment: Application to oxytetracycline

The wide use of antibiotics in aquaculture has led to the emergence of resistant microbial species. It should be avoided/minimized by controlling the amount of drug employed in fish farming. For this purpose, the present work proposes test-strip papers aiming at the detection/semi-quantitative determination of organic drugs by visual comparison of color changes, in a similar analytical procedure to that of pH monitoring by universal pH paper. This is done by establishing suitable chemical changes upon cellulose, attributing the paper the ability to react with the organic drug and to produce a color change. Quantitative data is also enabled by taking a picture and applying a suitable mathematical treatment to the color coordinates given by the HSL system used by windows. As proof of concept, this approach was applied to oxytetracycline (OXY), one of the antibiotics frequently used in aquaculture. A bottom-up modification of paper was established, starting by the reaction of the glucose moieties on the paper with 3-triethoxysilylpropylamine (APTES). The so-formed amine layer allowed binding to a metal ion by coordination chemistry, while the metal ion reacted after with the drug to produce a colored compound. The most suitable metals to carry out such modification were selected by bulk studies, and the several stages of the paper modification were optimized to produce an intense color change against the concentration of the drug. The paper strips were applied to the analysis of spiked environmental water, allowing a quantitative determination for OXY concentrations as low as 30 ng/mL. In general, this work provided a simple, method to screen and discriminate tetracycline drugs, in aquaculture, being a promising tool for local, quick and cheap monitoring of drugs.

Protein–polyphenol interaction on silica beads for astringency tests based on eye, photography or reflectance detection modes

Astringency is an organoleptic property of beverages and food products resulting mainly from the interaction of salivary proteins with dietary polyphenols. It is of great importance to consumers, but the only effective way of measuring it involves trained sensorial panellists, providing subjective and expensive responses. Concurrent chemical evaluations try to screen food astringency, by means of polyphenol and protein precipitation procedures, but these are far from the real human astringency sensation where not all polyphenol–protein interactions lead to the occurrence of precipitate. Here, a novel chemical approach that tries to mimic protein–polyphenol interactions in the mouth is presented to evaluate astringency. A protein, acting as a salivary protein, is attached to a solid support to which the polyphenol binds (just as happens when drinking wine), with subsequent colour alteration that is fully independent from the occurrence of precipitate. Employing this simple concept, Bovine Serum Albumin (BSA) was selected as the model salivary protein and used to cover the surface of silica beads. Tannic Acid (TA), employed as the model polyphenol, was allowed to interact with the BSA on the silica support and its adsorption to the protein was detected by reaction with Fe(III) and subsequent colour development. Quantitative data of TA in the samples were extracted by colorimetric or reflectance studies over the solid materials. The analysis was done by taking a regular picture with a digital camera, opening the image file in common software and extracting the colour coordinates from HSL (Hue, Saturation, Lightness) and RGB (Red, Green, Blue) colour model systems; linear ranges were observed from 10.6 to 106.0 μmol L−1. The latter was based on the Kubelka–Munk response, showing a linear gain with concentrations from 0.3 to 10.5 μmol L−1. In either of these two approaches, semi-quantitative estimation of TA was enabled by direct eye comparison. The correlation between the levels of adsorbed TA and the astringency of beverages was tested by using the assay to check the astringency of wines and comparing these to the response of sensorial panellists. Results of the two methods correlated well. The proposed sensor has significant potential as a robust tool for the quantitative/semi-quantitative evaluation of astringency in wine.

O treino da perceção visual e da consciência fonológica como promotor da fluência da leitura num aluno do 2º ciclo do ensino básico

Aprender a ler é um dos maiores desafios que as crianças enfrentam quando entram para a escola. A dificuldade no domínio do código alfabético, nos níveis da consciência fonológica e a falta de fluência na leitura são fatores que interferem em larga escala na aprendizagem global dos alunos. Habilitar um aluno para a prática da leitura é um estímulo que tem vindo a dar origem a várias investigações e intervenções no campo da educação. Este projeto descreve dois programas de treino: “Programa de treino da percepção Visual” e “Programa de promoção do desenvolvimento da consciência fonológica”, num aluno do 2º ciclo do ensino básico com dificuldade de fluência na leitura, ao longo de quinze aulas de 90 minutos. No que respeita aos resultados do primeiro estudo, que teve por base o “Programa de treino da percepção visual”, não foram encontradas diferenças relevantes quanto ao seu efeito na fluência da leitura do aluno. No entanto, no segundo estudo, que se centrou na aplicação do “Programa de promoção do desenvolvimento da consciência fonológica” em complemento com o “Programa de treino da percepção visual”, mostrou que o aluno ficou mais fluente na leitura diminuindo o número de erros de precisão (substituições, omissões, inversões, adições e erros complexos). Assim, sugere-se uma monotorização sistemática das aprendizagens dos alunos para que as intervenções possam ser cada vez mais precoces e direcionadas para as suas necessidades.

Decentralized Target Tracking based on Multi-Robot Cooperative Triangulation

Target tracking with bearing-only sensors is a challenging problem when the target moves dynamically in complex scenarios. Besides the partial observability of such sensors, they have limited field of views, occlusions can occur, etc. In those cases, cooperative approaches with multiple tracking robots are interesting, but the different sources of uncertain information need to be considered appropriately in order to achieve better estimates. Even though there exist probabilistic filters that can estimate the position of a target dealing with incertainties, bearing-only measurements bring usually additional problems with initialization and data association. In this paper, we propose a multi-robot triangulation method with a dynamic baseline that can triangulate bearing-only measurements in a probabilistic manner to produce 3D observations. This method is combined with a decentralized stochastic filter and used to tackle those initialization and data association issues. The approach is validated with simulations and field experiments where a team of aerial and ground robots with cameras track a dynamic target.

Application of Visual-Inertial SLAM for 3D Mapping of Underground Environments

The underground scenarios are one of the most challenging environments for accurate and precise 3d mapping where hostile conditions like absence of Global Positioning Systems, extreme lighting variations and geometrically smooth surfaces may be expected. So far, the state-of-the-art methods in underground modelling remain restricted to environments in which pronounced geometric features are abundant. This limitation is a consequence of the scan matching algorithms used to solve the localization and registration problems. This paper contributes to the expansion of the modelling capabilities to structures characterized by uniform geometry and smooth surfaces, as is the case of road and train tunnels. To achieve that, we combine some state of the art techniques from mobile robotics, and propose a method for 6DOF platform positioning in such scenarios, that is latter used for the environment modelling. A visual monocular Simultaneous Localization and Mapping (MonoSLAM) approach based on the Extended Kalman Filter (EKF), complemented by the introduction of inertial measurements in the prediction step, allows our system to localize himself over long distances, using exclusively sensors carried on board a mobile platform. By feeding the Extended Kalman Filter with inertial data we were able to overcome the major problem related with MonoSLAM implementations, known as scale factor ambiguity. Despite extreme lighting variations, reliable visual features were extracted through the SIFT algorithm, and inserted directly in the EKF mechanism according to the Inverse Depth Parametrization. Through the 1-Point RANSAC (Random Sample Consensus) wrong frame-to-frame feature matches were rejected. The developed method was tested based on a dataset acquired inside a road tunnel and the navigation results compared with a ground truth obtained by post-processing a high grade Inertial Navigation System and L1/L2 RTK-GPS measurements acquired outside the tunnel. Results from the localization strategy are presented and analyzed.

Combining sparse and dense methods in 6D Visual Odometry

13th International Conference on Autonomous Robot Systems (Robotica), 2013, Lisboa

6D Visual Odometry with Dense Probabilistic Egomotion Estimation

Proceedings of the International Conference on Computer Vision Theory and Applications, 361-365, 2013, Barcelona, Spain

Real-Time Visual Ground-Truth System for Indoor Robotic Applications

The robotics community is concerned with the ability to infer and compare the results from researchers in areas such as vision perception and multi-robot cooperative behavior. To accomplish that task, this paper proposes a real-time indoor visual ground truth system capable of providing accuracy with at least more magnitude than the precision of the algorithm to be evaluated. A multi-camera architecture is proposed under the ROS (Robot Operating System) framework to estimate the 3D position of objects and the implementation and results were contextualized to the Robocup Middle Size League scenario.