Vision based obstacle detection for all-terrain robots

Dissertação apresentada na Faculdade de Ciências e Tecnologia da Universidade Nova de Lisboa para obtenção do grau de Mestre em Engenharia Electrotécnica e de Computadores

ErasmusApp: A Location-Based Collaborative System for Erasmus Students

This paper reports on the design and development of an Android-based context-aware system to support Erasmus students during their mobility in Porto. It enables: (i) guest users to create, rate and store personal points of interest (POI) in a private, local on board database; and (ii) authenticated users to upload and share POI as well as get and rate recommended POI from the shared central database. The system is a distributed client / server application. The server interacts with a central database that maintains the user profiles and the shared POI organized by category and rating. The Android GUI application works both as a standalone application and as a client module. In standalone mode, guest users have access to generic info, a map-based interface and a local database to store and retrieve personal POI. Upon successful authentication, users can, additionally, share POI as well as get and rate recommendations sorted by category, rating and distance-to-user.

A questão visual na oftalmologia pediátrica da região de Lisboa

RESUMO: Na parte inicial incluem-se algumas notas sucintas com base no panorama científico,histórico e cultural da visão considerada segundo três abordagens - o olho (o olho humano na especificidade da sua posição filogenética, elemento anátomo-funcional básico do sistema visual ao qual o cérebro pertence), os olhos (unidades gémeas essenciais do rosto na sua actividade consensual e conjugada da binocularidade), o olhar (carregado de expressão psicológica e o seu efeito sobre o observador, sinal para o comportamento e criador de sentimentos, sedimentado em obras de arte e em formas de superstição dos povos). Segue-se a apresentação de um estudo descritivo transversal, como contribuição para o conhecimento do estado de saúde visual da população infantil da região de Lisboa e determinar factores que o influenciam. Entre Outubro de 2005 e Agosto de 2006 examinaram-se 649 crianças com idade inferior a 10 anos da Consulta de Oftalmologia Pediátrica dos Serviços de Assistência Médico-Social do Sindicato dos Bancários do Sul e Ilhas (SAMS). Colheram-se dados respeitantes a mais de 250 variáveis primárias que cobriram a maior parte dos itens do exame oftalmológico habitual. Na análise dos dados teve-se especialmente em conta a idade, com um papel decisivo nas principais fases de desenvolvimento do sistema visual. No caso das crianças de 6 a 7 anos de idade põem-se lado a lado resultados dos SAMS e das Escolas. A profusão de dados numéricos ditou a necessidade da determinação frequente da significância estatística dos resultados de subgrupos. Alguns resultados do estudo, na sua maioria do grupo SAMS: Crianças de 6-7 anos, 71,1% (SAMS) e 91,5% (Escolas) não tinham sido examinadas com menos de 4 anos. Frequência global de alterações miópicas 9,4%, de alterações hipermetrópicas 25,3%, umas e outras com variações acentuadas com a idade. Estrabismo convergente 3,9%. Ambliopia 2,6% (13/491 crianças >=4 anos de idade), mais frequente no sexo feminino, naquelas que tiveram a sua 1ª observação depois dos 4 anos e em que os pais não aderiam à terapêutica prescrita. Objectivos específicos ocuparam-se da acuidade visual e da refracção ocular. O estudo comparativo da refractometria automática sem e com cicloplegia permitiu evidenciar que o teste da acuidade visual é insuficiente, por si só, para fazer o diagnóstico correcto. A análise dos antecedentes familiares oftalmológicos demonstrou a importância do seu conhecimento e pôs em evidência, entre outras, as seguintes relações: 10 pag1.qxp 27-11-2001 18:28 Page 10 Índice Geral 11 Crianças com antecedentes de alterações miópicas têm maior frequência de diagnóstico de alterações miópicas e de refracção negativa, uma taxa mais elevada de correspondência quantitativa diagnóstico/refracção nas alterações miópicas. Estas crianças também têm, em geral, características inversas no que diz respeito a alterações hipermetrópicas. Crianças com antecedentes de alterações hipermetrópicas têm maior frequência de diagnóstico de alterações hipermetrópicas. Crianças com antecedentes de estrabismo têm maior frequência de diagnóstico de estrabismo convergente manifesto e de esodesvios no seu todo. Crianças com antecedentes familiares de astigmatismo têm maior frequência de diagnóstico de astigmatismo. Traçam-se alguns perfis oftalmológicos infantis que permitem apreciar de forma sinóptica um conjunto de parâmetros da saúde da visão. Os dados colhidos sobre a aderência dos pais à terapêutica prescrita e sobre a atitude em relação ao uso de óculos assim como os dados sobre o comportamento da criança na sala de aula e dificuldades de aprendizagem foram em geral escassos para permitirem tirar conclusões, embora mostrem indícios a investigar futuramente. Paralelamente ortoptistas e enfermeiras efectuaram um rastreio escolar da acuidade visual <0,8 e de alterações da motilidade ocular extrínseca que abrangeu 520 alunos do 1º ano do 1º ciclo do ensino básico (2005/2006) das escolas públicas da cidade de Lisboa. 101 destas crianças foram observadas no consultório da autora, umas referidas a partir do rastreio, outras como controlo deste. Quanto à acuidade visual o valor preditivo do teste negativo foi de 91% mas o do teste positivo de apenas 67% (33% de falsos positivos, consequentemente uma alta taxa de sobrerreferenciação). A qualidade do rastreio efectuado por ortoptistas foi inferior à do efectuado por enfermeiras. O rastreio não teve qualidade aceitável. Foi feito um inquérito a médicos e enfermeiros de centros de saúde sobre conhecimentos, atitudes e práticas em relação com os cuidados de oftalmologia pediátrica. Discutem-se os resultados, tiram-se conclusões e fazem-se recomendações susceptíveis de contribuir para uma melhor saúde visual das crianças. ABSTRACT: Firstly some brief remarks are made based on the scientific, historical and cultural panorama of the human vision with regard to three approaches: the eye (the human eye in its specific filogenetic place, fundamental anatomofunctional element of the visual system in interaction with the brain), the eyes (essential twin units of the face with their consensual and conjugated binocular activity), the gaze (psychologicaly overloaded, a means to express oneself and to influence the observer, a guide to other persons' behaviour, consolidated in works of art and in people's traditional superstitious believes and ways of thinking). A report is made on a cross-sectional descriptive study whose goal is to contribute to the knowledge of the level of visual health of children in the Lisbon Region and to identify factors which determine it. Between October 2005 and August 2006 649 children under 10 years were observed at the pediatric ophthalmologic consultation in the SAMS (Serviços de Assistência Médico-Social do Sindicato dos Bancários do Sul e Ilhas). Data were collected concerning more than 250 primary variables covering most itens of the usual ophthalmological examination. Special attention was paid to children's age since it plays a crucial role in main stages of visual system development. In the case of children age 6 to 7 SAMS and school results are often put side by side. On account of the great number of numerical data it was often necessary to look at the degree of statistical significancy of differencies between subgroups. Some of the study's results (mostly SAMS): Children age 6 to 7 - 71,1% (SAMS) and 91,5% (Schools) had not an ophthalmologic examination before 4 years old. Total frequency of myopic disorders 9,4%, of hypermetropic disorders 25,3%, both showing great differences between age groups; convergent strabismus 3,9%; amblyopia 2,6% (13/491 children over 3 years old), more frequent among little girls, in those with 1st examination after 4 years old and in those whose parents didn´t complied to the therapy ordered for the child. Specific objectives dealt with visual acuity and ocular refraction. The comparison of automatic refractometry without and with cycloplegy showed that visual acuity testing is often not enough for a correct diagnosis. Eye disorders in the family history proved to be a very important information. Analysis of corresponding data disclosed a lot of relationships among others: 12 pag1.qxp 27-11-2001 18:28 Page 12 Índice Geral 13 Children with a family history of myopic disorders have more frequently a diagnosis of myopic disorders and a negative refraction, a higher rate of quantitative diagnosis/refraction matching concerning myopic disorders. Those children have in general inverse characteristics regarding hypermetropic disorders. Children with a family history of hypermetropic disorders have more frequently a diagnosis of hypermetropic disorders. Children with a family history of strabismus have more frequently a diagnosis of manifest convergent strabismus and all forms of esodeviations. Children with a family history of astigmatism have more frequently a diagnosis of astigmatism. Ophthalmologic profiles are drawn allowing to take into account in a synoptic way a set of visual health parameters. Data on parents' compliance with therapy ordered for the child, and attitudes regarding child's glass wearing, as well as data on child's behaviour in the classroom and learning difficulties were as a rule too few to allow conclusions but still need more studies in the future. Orthoptists and nurses performed in the same study period a screening of visual acuity <0,8 and of ocular motility disorders addressed to children of 1srt degree of public schools (term 2005/2006) in the town of Lisbon. 520 of such children were screened. 101 of them were examined by the author in her medical office; some were refered, the others taken as a control. Regarding visual acuity the predictive value of a negative test was 91% but the predictive value of a positive test was only 67% (33% of false positive results, consequently a too high rate of overreferal). Performed by orthoptists screening quality was inferior in comparison with screening done by nurses. On the whole this screening had not the required quality. A survey on physicians' and nurses' knowledge, attitudes and practices related to pediatric ophthalmologic care was carried out in health centers. Results are discussed, conclusions drawn. Some suggestions are made aiming at a better children's visual health.

Robot visual localization through local feature fusion: an evaluation of multiple classifiers combination approaches

In the last decade, local image features have been widely used in robot visual localization. In order to assess image similarity, a strategy exploiting these features compares raw descriptors extracted from the current image with those in the models of places. This paper addresses the ensuing step in this process, where a combining function must be used to aggregate results and assign each place a score. Casting the problem in the multiple classifier systems framework, in this paper we compare several candidate combiners with respect to their performance in the visual localization task. For this evaluation, we selected the most popular methods in the class of non-trained combiners, namely the sum rule and product rule. A deeper insight into the potential of these combiners is provided through a discriminativity analysis involving the algebraic rules and two extensions of these methods: the threshold, as well as the weighted modifications. In addition, a voting method, previously used in robot visual localization, is assessed. Furthermore, we address the process of constructing a model of the environment by describing how the model granularity impacts upon performance. All combiners are tested on a visual localization task, carried out on a public dataset. It is experimentally demonstrated that the sum rule extensions globally achieve the best performance, confirming the general agreement on the robustness of this rule in other classification problems. The voting method, whilst competitive with the product rule in its standard form, is shown to be outperformed by its modified versions.

Vision based trail detection for all-terrain robots

Dissertação apresentada na Faculdade de Ciências e Tecnologia da Universidade Nova de Lisboa para obtenção do grau de Mestre em Engenharia Electrotécnica e de Computadores

Utilização de técnicas de análise fotogramétricas em quebra-mares de taludes

Dissertação de Natureza Científica elaborada no Laboratório Nacional de Engenharia Civil (LNEC) para obtenção do grau de mestre em Engenharia Civil na Área de Especialização de Hidráulica no âmbito do protocolo de cooperação entre o ISEL e o LNEC

FPGA-based architecture for hyperspectral unmixing

This paper proposes an FPGA-based architecture for onboard hyperspectral unmixing. This method based on the Vertex Component Analysis (VCA) has several advantages, namely it is unsupervised, fully automatic, and it works without dimensionality reduction (DR) pre-processing step. The architecture has been designed for a low cost Xilinx Zynq board with a Zynq-7020 SoC FPGA based on the Artix-7 FPGA programmable logic and tested using real hyperspectral datasets. Experimental results indicate that the proposed implementation can achieve real-time processing, while maintaining the methods accuracy, which indicate the potential of the proposed platform to implement high-performance, low cost embedded systems.

Parallel GPU architecture for hyperspectral unmixing based on augmented Lagrangian method

Hyperspectral imaging has become one of the main topics in remote sensing applications, which comprise hundreds of spectral bands at different (almost contiguous) wavelength channels over the same area generating large data volumes comprising several GBs per flight. This high spectral resolution can be used for object detection and for discriminate between different objects based on their spectral characteristics. One of the main problems involved in hyperspectral analysis is the presence of mixed pixels, which arise when the spacial resolution of the sensor is not able to separate spectrally distinct materials. Spectral unmixing is one of the most important task for hyperspectral data exploitation. However, the unmixing algorithms can be computationally very expensive, and even high power consuming, which compromises the use in applications under on-board constraints. In recent years, graphics processing units (GPUs) have evolved into highly parallel and programmable systems. Specifically, several hyperspectral imaging algorithms have shown to be able to benefit from this hardware taking advantage of the extremely high floating-point processing performance, compact size, huge memory bandwidth, and relatively low cost of these units, which make them appealing for onboard data processing. In this paper, we propose a parallel implementation of an augmented Lagragian based method for unsupervised hyperspectral linear unmixing on GPUs using CUDA. The method called simplex identification via split augmented Lagrangian (SISAL) aims to identify the endmembers of a scene, i.e., is able to unmix hyperspectral data sets in which the pure pixel assumption is violated. The efficient implementation of SISAL method presented in this work exploits the GPU architecture at low level, using shared memory and coalesced accesses to memory.

Vertex component analysis GPU-based implementation for hyperspectral unmixing

Endmember extraction (EE) is a fundamental and crucial task in hyperspectral unmixing. Among other methods vertex component analysis ( VCA) has become a very popular and useful tool to unmix hyperspectral data. VCA is a geometrical based method that extracts endmember signatures from large hyperspectral datasets without the use of any a priori knowledge about the constituent spectra. Many Hyperspectral imagery applications require a response in real time or near-real time. Thus, to met this requirement this paper proposes a parallel implementation of VCA developed for graphics processing units. The impact on the complexity and on the accuracy of the proposed parallel implementation of VCA is examined using both simulated and real hyperspectral datasets.

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.