Robots are widely used in domestic and commercial applications. These applications typically involve robots built for a specific the task, thus leading to efficiency in task completion. However, with the increase in completion efficiency comes an increase in the time required for completion of the whole system. Specific tasks create the need for many different robots, all with differing capabilities, causing an increase in development cost and time needed. This raises the issue of whether using an off the shelf system with minor modifications can accurately perform the same tasks. If so, more time can be spent on refining the process leading to completion of the task, resulting in less time spent developing the robot. Consequently, less cost in the life cycle of the system leads to less cost for the end user, thus allowing robots to be used for more applications. This thesis explores using a commercially available robot, Acroname Inc.'s Garcia, to perform mapping and localization tasks. As the robot travels it gathers data about the environment. This data is processed in Matlab and the result of the algorithm is a map. In the creation of the map, mathematical morphology is explored as a means to reduce noise. When the robot has located a corner, Matlab provides the robot with a position estimate correction. This correction allows the robot to better estimate its location resulting in a more accurate map. As the results of this thesis illustrate, with very minor modifications, the robot is capable of accurately performing mapping and localization tasks. The results demonstrate that an off the shelf system is capable of accurately performing tasks for which it was not specifically designed. / Master of Science

No description available.

One of the main problems in image analysis is a comparison of different shapes in images. It is often desirable to determine the extent to which one shape differs from another. This is usually a difficult task because shapes vary in size, length, contrast, texture, orientation, etc. Shapes can be described using sets of points, crisp of fuzzy. Hence, distance functions between sets have been used for comparing different shapes. Mathematical morphology is a non-linear theory related to the shape or morphology of features in the image, and morphological operators are defined by the interaction between an image and a small set called a structuring element. Although morphological operators have been extensively used to differentiate shapes by their size, it is not an easy task to differentiate shapes with respect to other features such as contrast or orientation. One approach for differentiation on these type of features is to use data-dependent structuring elements. In this thesis, we investigate the usefulness of various distance functions for: (i) shape registration and recognition; and (ii) construction of adaptive structuring elements and functions. We examine existing distance functions between sets, and propose a new one, called the Complement weighted sum of minimal distances, where the contribution of each point to the distance function is determined by the position of the point within the set. The usefulness of the new distance function is shown for different image registration and shape recognition problems. Furthermore, we extend the new distance function to fuzzy sets and show its applicability to classification of fuzzy objects. We propose two different types of adaptive structuring elements from the salience map of the edge strength: (i) the shape of a structuring element is predefined, and its size is determined from the salience map; (ii) the shape and size of a structuring element are dependent on the salience map. Using this salience map, we also define adaptive structuring functions. We also present the applicability of adaptive mathematical morphology to image regularization. The connection between adaptive mathematical morphology and Lasry-Lions regularization of non-smooth functions provides an elegant tool for image regularization.

O objetivo deste trabalho é apresentar uma técnica automática baseada em morfologia matemática para medida de sinal em imagens de cDNA desenvolvida no BIOINFO,em parceria com o Instituto Ludwig de Pesquisa contra o Câncer. A tecnologia de lâminas de cDNA é um processo baseado em hibridização que possibilita observar a concentração relativa de mRNA de amostras de tecidos analisando a luminosidade de sinais fluorescentes ou radioativos. Hibridização é o processo bioquímico onde duas fitas de ácido nucleico com seqüências complementares se combinam. A técnica apresentada permite o cálculo da expressão gênica com alto grau de automação, podendo o usuário corrigir com facilidade eventuais erros de segmentação. O usuário interage com o programa apenas para selecionar as imagens e inserir os dados de geometria da lâmina. A estratégia de solução usada tem três fases: gradeamento dos blocos, gradeamento dos spots e segmentação dos spots. Todas as fases utilizam filtros morfológicos e as fases de gradeamento possuem um passo final de correção baseado nos dados de geometria da lâmina o que aumenta a robustez do processo, que funciona bem mesmo em imagens ruidosas. / The objective of this work is to present the automated technique for measuring signal from cDNA images developed in BIOINFO, associated with the Ludwig Institute for Cancer Research. Microarray technology is a hybridization based process that makes possible to quantify the relative abundance of mRNA in two tissue samples analysing the luminosity of fluorescent or radioactive signals. Hybridization is a biochemical process where a strand of nucleic acid matches up its counterpart. The developed technique permits the calculation of gene expression with a high level of automation. Besides that, the user can easily correct eventual segmentation mistakes. The user interacts with the program only to select the images and to set the slide geometry parameters. The solution strategy has three main steps: subarray griding, spots gridding and spots detection. All the steps use morphological filters, and the two gridding steps have a final correction substep based on the slide geometry, increasing the process robustness, that works well even in noisy images.

O objetivo deste trabalho é apresentar uma técnica automática baseada em morfologia matemática para medida de sinal em imagens de cDNA desenvolvida no BIOINFO,em parceria com o Instituto Ludwig de Pesquisa contra o Câncer. A tecnologia de lâminas de cDNA é um processo baseado em hibridização que possibilita observar a concentração relativa de mRNA de amostras de tecidos analisando a luminosidade de sinais fluorescentes ou radioativos. Hibridização é o processo bioquímico onde duas fitas de ácido nucleico com seqüências complementares se combinam. A técnica apresentada permite o cálculo da expressão gênica com alto grau de automação, podendo o usuário corrigir com facilidade eventuais erros de segmentação. O usuário interage com o programa apenas para selecionar as imagens e inserir os dados de geometria da lâmina. A estratégia de solução usada tem três fases: gradeamento dos blocos, gradeamento dos spots e segmentação dos spots. Todas as fases utilizam filtros morfológicos e as fases de gradeamento possuem um passo final de correção baseado nos dados de geometria da lâmina o que aumenta a robustez do processo, que funciona bem mesmo em imagens ruidosas. / The objective of this work is to present the automated technique for measuring signal from cDNA images developed in BIOINFO, associated with the Ludwig Institute for Cancer Research. Microarray technology is a hybridization based process that makes possible to quantify the relative abundance of mRNA in two tissue samples analysing the luminosity of fluorescent or radioactive signals. Hybridization is a biochemical process where a strand of nucleic acid matches up its counterpart. The developed technique permits the calculation of gene expression with a high level of automation. Besides that, the user can easily correct eventual segmentation mistakes. The user interacts with the program only to select the images and to set the slide geometry parameters. The solution strategy has three main steps: subarray griding, spots gridding and spots detection. All the steps use morphological filters, and the two gridding steps have a final correction substep based on the slide geometry, increasing the process robustness, that works well even in noisy images.

This work presents a novel technique for 2D human motion capture using a single non calibrated camera. The user's five extremities (head, hands and feet) are extracted, labelled and tracked after silhouette segmentation. As they are the minimal number of points that can be used in order to enable whole body gestural interaction, we will henceforth refer to these features as crucial points. The crucial point candidates are defined as the local maxima of the geodesic distance with respect to the center of gravity of the actor region which lie on the silhouette boundary. In order to disambiguate the selected crucial points into head, left and right foot, left and right hand classes, we propose a Bayesian method that combines a prior human model and the intensities of the tracked crucial points. Due to its low computational complexity, the system can run at real-time paces on standard Personal Computers, with an average error rate range between 2% and 7% in realistic situations, depending on the context and segmentation quality.

This thesis presents advances in reduced-order modeling based on proper orthogonal decomposition (POD) for single and two-phase flows. Reduced-order models (ROMs) are generated for two-phase gas-solid flows. A multiphase numerical flow solver, MFIX, is used to generate a database of solution snapshots for proper orthogonal decomposition. Time-independent basis functions are extracted using POD from the data, and the governing equations of the MFIX are projected onto the basis functions to generate the multiphase POD-based ROMs. Reduced-order models are constructed to simulate multiphase two-dimensional non-isothermal flow and isothermal flow particle kinetics and three-dimensional isothermal flow. These reduced-order models are applied to three reference cases. The results of this investigation show that the two-dimensional reduced-order models are capable of producing qualitatively accurate results with less than 5 percent error with at least an order of magnitude reduction of computational costs. The three-dimensional ROM shows improvements in computational costs. This thesis also presents an algorithm based on mathematical morphology used to extract discontinuities present in quasi-steady and unsteady flows for POD basis augmentation. Both MFIX and a Reynolds Average Navier-Stokes (RANS) flow solver, UNS3D, are used to generate solution databases for feature extraction. The algorithm is applied to bubbling uidized beds, transonic airfoils, and turbomachinery seals. The results of this investigation show that all of the important features are extracted without loss in accuracy.

L'intervention coronarienne percutanée (ICP) est réalisée en utilisant l'imagerie radiographique en temps réel dans une suite interventionnelle. La modélisation de ces procédures ICP pour aider le praticien implique la compréhension des différentes phases de la procédure ICP, par la machine d’intervention, qui peut être utilisées pour optimiser la dose de rayons X et l'agent de contraste. Pour atteindre cet objectif, l’une des tâches importantes consiste à segmenter différents outils d’intervention dans les flux d’images fluoroscopiques et à en déduire des informations sémantiques. L’arbre des composants, un puissant outil morphologique mathématique, constitue la base des méthodes de segmentation proposées. Nous présentons ce travail en deux parties: 1) la segmentation du cathéter vide à faible contraste, et 2) la segmentation de la pointe du guide et le suivi de la détection du vaisseau d’intervention. Nous présentons une nouvelle méthode de segmentation basée sur l’espace à plusieurs échelles pour détecter des objets faiblement contrastés comme un cathéter vide. Pour la dernière partie, nous présentons la segmentation de la pointe du guide avec le filtrage basé sur l’arbre de composants et proposons un algorithme pour suivre sémantiquement la pointe segmentée pour déterminer le vaisseau d’intervention / Percutaneous coronary intervention (PCI) is performed using real-time radiographic imaging in an interventional suite. Modeling these ICP procedures to help the practitioner involves understanding the different phases of the ICP procedure, by the interventional machine, which can be used to optimize the X-ray dose and the contrast agent. One of the important tasks in achieving this goal is to segment different interventional tools into the flow of fluoroscopic images and to derive semantic information from them. The component tree, a powerful mathematical morphological tool, forms the basis of the proposed segmentation methods. We present this work in two parts: 1) the segmentation of the low-contrast empty catheter, and 2) the segmentation of the tip of the guide and the monitoring of the detection of the intervention vessel. We present a new multi-scale space-based segmentation method for detecting low-contrast objects such as an empty catheter. For the last part, we present the segmentation of the tip of the guide with filtering based on the component tree and propose an algorithm to semantically follow the segmented tip to determine the intervention vessel

Orientador: Roberto de Alencar Lotufo / Dissertação (mestrado) - Universidade Estadual de Campinas, Faculdade de Engenharia Eletrica e de Computação / Made available in DSpace on 2018-08-15T23:43:15Z (GMT). No. of bitstreams: 1 Korbes_Andre_M.pdf: 12082047 bytes, checksum: 8ff8c998c80a0436fe3a83560ac2e6eb (MD5) Previous issue date: 2010 / Resumo: A transformada watershed é uma técnica morfológica de segmentação de imagens inspirada na divisão de superfícies em bacias hidrográficas, tendo diversas formas de definição e de algoritmos. Este trabalho realiza uma análise sistemática da literatura de catorze destes algoritmos. Foram consideradas as principais abordagens existentes desde a introdução do primeiro algoritmo rápido por Vincent e Soille em 1991, até os trabalhos de Cousty et al. em 2009. Para melhor compreensão da área, as definições de transformada watershed são revisitadas, provendo o conjunto de soluções formais possíveis e esperadas dos algoritmos. Na análise destes algoritmos é fornecido pseudocódigo com notação uniformizada e uma implementação operacional Python permitindo abstrair detalhes de programação. Além disto, três algoritmos foram corrigidos para melhor aderência a definição e especificação. Também são identificadas propriedades tais como o comportamento de varredura dos pixels, uso de estratégias em particular, uso de estruturas de dados, entre outras. A compilação das informações sobre os algoritmos permitiu generalizá-los e classificá-los baseado em paradigmas clássicos da computação, a saber a busca em largura e em profundidade. Ambos são embasados na ordem de visitação dos pixels utilizada, sendo a busca em largura semelhante a simulação de inundação enquanto a busca em profundidade simula gotas de água em uma superfície. Foram também realizados estudos comparativos entre as definições implementadas pelos algoritmos, entre as estratégias utilizadas para tratamento de problemas comuns, entre o desempenho obtido pelos programas Python, e de paralelismo e abordagens utilizadas neste último caso. Desta forma, produziu-se um panorama geral e atualizado dos algoritmos de transformada watershed / Abstract: The watershed transform is a morphological image segmentation technique inspired on the division of surfaces in catchment basins, with several forms of definition and algorithms. This work accomplishes a survey of the literature on fourteen of these algorithms. The main approaches since the introduction of the first fast algorithm by Vincent and Soille in 1991, until the work of Cousty et al. in 2009 has been considered. For better understanding of the subject, the watershed definitions are revisited, providing the set of formal solutions that are possible and expected from the algorithms. On the analysis of the algorithms it is supplied pseudocode with a uniform notation and a Python operational implementation allowing to abstract programming details. Aside, three algorithms were corrected for better adherence to definition and specification. Also some properties such as the scanning behaviour, use of particular strategies, and use of data structures, among others were identified. The compilation of information of the algorithms allowed to generalise and classify them based on classic paradigms of computing, namely breadth-first and depth-first search. Both are based on the visiting order of the pixels, with the breadth-first similar to a flooding simulation while the depth-first simulates drops of water on a surface / Mestrado / Engenharia de Computação / Mestre em Engenharia Elétrica

A morfologia matemática é o estudo da forma utilizando as ferramentas da teoria de conjuntos e representa uma área extremamente importante em análise de imagens. Suas operações básicas são a dilatação e a erosão, e através destas é possível realizar outras operações mais complexas. A morfologia matemática fornece ferramentas poderosas para a realização de análise de imagens em baixo nível e tem encontrado aplicações em diversas áreas, tais como: visão robótica, inspeção visual, medicina, análise de textura, entre outras. Muitas destas aplicações requerem processamento em tempo real, e para sua execução de forma eficiente freqüentemente é utilizado hardware dedicado. A análise de imagens em baixo nível geralmente envolve computações repetidas sobre estruturas grandes de dados. Assim, o paralelismo parece ser um atributo necessário de um sistema de hardware capaz de executar eficientemente estas tarefas. As ferramentas da morfologia matemática são bem adequadas à implementação em arquiteturas pipeline. A necessidade de sistemas capazes de realizar o processamento de imagens digitais em tempo real, com o menor custo e tempo de desenvolvimento, tem sido suprida pela tecnologia de dispositivos de lógica programável complexa. Assim, neste trabalho foi projetada e implementada uma arquitetura pipeline dedicada para dilatação e erosão de imagens binárias em tempo real utilizando dispositivos lógicos programáveis de alta capacidade. Esta arquitetura é capaz de processar imagens binárias de 512 x 512 pixels. Os estágios desta arquitetura são flexíveis, permitindo a reprogramação da forma e do tamanho dos elementos estruturantes utilizados nas operações morfológicas. A arquitetura desenvolvida apresentou um desempenho satisfatório, demonstrando ser uma alternativa viável e eficiente. / Mathematical morphology is a very important image analysis area that uses set theory tools to study shapes. The basic operations in mathematical morphology are dilation and erosion, these can be used for more complex operations. Mathematical morphology has powerful tools for low level image processing and has been used in a wide range of applications such as robotic vision, visual inspection, medicine and texture analysis. Low level image processing requires repetitive processing over large data structures, dedicated parallel computing hardware is often used. Complex field programmable logic devices (CPLDs) have increasingly been used for the fast development of real time image processing systems. In this work we present a pipeline architecture for real time erosion and dilation operations, the architecture was developed using high density programmable logic devices. The developed architecture can process 512 x 512 pixels binary images, and has flexible stages that can be reprogrammed according to the shape and size of the structuring elements used in the morphological operations. Tests performed using the architecture demonstrated its good performance and that it is a good and efficient alternative for dedicated morphological image processing operations.