Pairwise alignment between point clouds is an important task in building 3D maps of indoor environments with partial information. The combination of 2D local features with depth information provided by RGB-D cameras are often used to improve such alignment. However, under varying lighting or low visual texture, indoor pairwise frame registration with sparse 2D local features is not a particularly robust method. In these conditions, features are hard to detect, thus leading to misalignment between consecutive pairs of frames. The use of 3D local features can be a solution as such features come from the 3D points themselves and are resistant to variations in visual texture and illumination. Because varying conditions in real indoor scenes are unavoidable, we propose a new framework to improve the pairwise frame alignment using an adaptive combination of sparse 2D and 3D features based on both the levels of geometric structure and visual texture contained in each scene. Experiments with datasets including unrestricted RGB-D camera motion and natural changes in illumination show that the proposed framework convincingly outperforms methods using 2D or 3D features separately, as reflected in better level of alignment accuracy. / O alinhamento entre pares de nuvens de pontos é uma tarefa importante na construção de mapas de ambientes em 3D. A combinação de características locais 2D com informação de profundidade fornecida por câmeras RGB-D são frequentemente utilizadas para melhorar tais alinhamentos. No entanto, em ambientes internos com baixa iluminação ou pouca textura visual o método usando somente características locais 2D não é particularmente robusto. Nessas condições, as características 2D são difíceis de serem detectadas, conduzindo a um desalinhamento entre pares de quadros consecutivos. A utilização de características 3D locais pode ser uma solução uma vez que tais características são extraídas diretamente de pontos 3D e são resistentes a variações na textura visual e na iluminação. Como situações de variações em cenas reais em ambientes internos são inevitáveis, essa tese apresenta um novo sistema desenvolvido com o objetivo de melhorar o alinhamento entre pares de quadros usando uma combinação adaptativa de características esparsas 2D e 3D. Tal combinação está baseada nos níveis de estrutura geométrica e de textura visual contidos em cada cena. Esse sistema foi testado com conjuntos de dados RGB-D, incluindo vídeos com movimentos irrestritos da câmera e mudanças naturais na iluminação. Os resultados experimentais mostram que a nossa proposta supera aqueles métodos que usam características 2D ou 3D separadamente, obtendo uma melhora da precisão no alinhamento de cenas em ambientes internos reais.

Mapas topologicamente ordenados sÃo tÃcnicas de representaÃÃo de dados baseadas em reduÃÃo de dimensionalidade com a propriedade especial de preservaÃÃo da vizinhanÃa espacial entre os protÃtipos no espaÃo dos dados e entre suas respectivas posiÃÃes no espaÃo de saÃda. Com base nesta propriedade, mapas topologicamente ordenados sÃo aplicados principalmente em agrupamento, quantizaÃÃo vetorial ou reduÃÃo de dimensionalidade e visualizaÃÃo de dados. Esta tese propÃe uma nova classificaÃÃo para os algoritmos de formaÃÃo de mapas topologicamente ordenados baseada no mecanismo de correlaÃÃo entre os espaÃos de entrada e de saÃda, e descreve um novo algoritmo, baseado em computaÃÃo evolucionÃria, denominado EvSOM, para a formaÃÃo de mapas topologicamente ordenado. As principais propriedades do novo algoritmo sÃo a sua flexibilidade para ponderaÃÃo pelo usuÃrio da importÃncia relativa das propriedades de quantizaÃÃo vetorial e de preservaÃÃo de topologia no mapa final, alÃm de boa rejeiÃÃo a outliers quando comparado ao algoritmo SOM de Kohonen. O trabalho desenvolve uma avaliaÃÃo empÃrica destas propriedades. O EvSOM Ã um algoritmo hÃbrido, neural-evolucionÃrio, biologicamente inspirado, que se utiliza de conceitos de redes neurais competitivas, computaÃÃo evolucionÃria, otimizaÃÃo e aproximaÃÃo iterativa. Para validar sua viabilidade de aplicaÃÃo, o EvSOM Ã estendido e especializado para a soluÃÃo de dois problemas bÃsicos relevantes em processamento de imagens e visÃo computacional, quais sejam, o problema de registro de imagens mÃdicas e o problema de rastreamento visual de objetos em vÃdeo. O algoritmo apresentou desempenho satisfatÃrio nas duas aplicaÃÃes. / Topologically ordered maps are data representation techniques based on dimensionality reduction with the special property of preserving the neighborhood between the data prototypes lying in the data space and their positions on to the output space. Based on this property, topologically ordered maps are applied mainly in clustering projected, vector quantization or dimensionality reduction and data visualization. This thesis proposes a new classification for the existing algorithms devoted to the formation of topologically ordered maps, which is based on the mechanism of correlation between the input and output spaces, and describes a new algorithm based on evolutionary computation, called EvSOM, for the topologically ordered maps formation. The main properties of the new algorithm are its flexibility for consideration by the user of the relative importance of the properties of vector quantization and topology preservation of the final map, and good outliers rejection when compared to the Kohonen SOM algorithm. The work provides an empirical evaluation of these properties. The EvSOM is a hybrid , neural-evolutionary, biologically inspired algorithm, which uses concepts of competitive neural networks, evolutionary computing, optimization and iterative approximation approximation. To validate its application feasibility, EvSOM is extended and specialized to solve two relevant basic problems in image processing and computer vision, namely, the medical image registration problem and the visual tracking of objects in video problem. The algorithm exhibits satisfactory performance in both aplications.

A análise da retina permite o diagnostico de muitas patologias relacionadas ao olho humano. A qualidade da imagem e um fator importante já que o médico normalmente examina os pequenos vasos da retina e a sua coloração. O equipamento normalmente utilizado para a visualização da retina e o retinógrafo digital, que utiliza sensor colorido com filtro de Bayer e luz (flash) branca. No entanto, esse filtro causa perda na resolução espacial, uma vez que e necessário um processo de interpolação matemática para a formação da imagem. Com o objetivo de melhorar a qualidade da imagem da retina, um retinógrafo com câmera CCD monocromática de alta resolução foi desenvolvido. Nele, as imagens coloridas são geradas pela combinação dos canais monocromáticos R (vermelho), G (verde) e B (azul), adquiridos com o chaveamento da iluminação do olho com LED vermelho, verde e azul, respectivamente. Entretanto, o pequeno período entre os flashes pode causar desalinhamento entre os canais devido a pequenos movimentos do olho. Assim, este trabalho apresenta uma técnica de registro de imagens, baseado em correlação de fase no domínio da frequência, para realizar precisamente o alinhamento dos canais RGB no processo de geração de imagens coloridas da retina. A validação do método foi realizada com um olho mecânico (phantom) para a geração de 50 imagens desalinhadas que foram corrigidas pelo método proposto e comparadas com as imagens alinhadas obtidas como referência (ground-truth). Os resultados mostraram que retinógrafo com câmera monocromática e o método de registro proposto nesse trabalho podem produzir imagens coloridas da retina com alta resolução espacial, sem a perda de qualidade intrínseca às câmeras CCD coloridas que utilizam o filtro de Bayer. / The analysis of retina allows the diagnostics of several pathologies related to the human eye. Image quality is an important factor since the physician often examines the small vessels of the retina and its color. The device usually used to observe the retina is the fundus camera, which uses color sensor with Bayer filter and white light. However, this filter causes loss of spatial resolution, since it is necessary a mathematical interpolation process to create the final image. Aiming at improving the retina image quality, a fundus camera with monochromatic CCD camera was developed. In this device, color images are generated by combining the monochromatic channels R (red), G (green) and B (blue), which were acquired by switching the eye illumination with red, green and blue light, respectively. However, the short period between the flashes may cause misalignment among the channels because of the small movements of the eye. Thus, this work presents an image registration technique based on phase correlation in the frequency domain, for accurately aligning the RGB channels on the process of generating retina color images. Validation of the method was performed by using a mechanical eye (phantom) for generating 50 misaligned images, which were aligned by the proposed method and compared to the aligned images obtained as references (ground-truth). Results showed that the fundus camera with monochromatic camera and the method proposed in this work can produce high spatial resolution images without the loss of quality intrinsic to color CCD cameras that uses Bayer filter.

Brown adipose tissue (BAT) is the main tissue involved in non-shivering heat production. A greater understanding of BAT could possibly lead to new ways of prevention and treatment of obesity and type 2 diabetes. The increasing prevalence of these conditions and the problems they cause society and individuals make the study of the subject important. An ongoing study performed at the Turku University Hospital uses images acquired using PET/MRI with 18F-FDG as the tracer. Scans are performed on sedentary and athlete subjects during normal room temperature and during cold stimulation. Sedentary subjects then undergo scanning during cold stimulation again after a six weeks long exercise training intervention. This degree project used images from this study. The objective of this degree project was to examine methods to automatically and objectively quantify parameters relevant for activation of BAT in combined PET/MRI data. A secondary goal was to create images showing glucose uptake changes in subjects from images taken at different times. Parameters were quantified in adipose tissue directly without registration (image matching), and for neck scans also after registration. Results for the first three subjects who have completed the study are presented. Larger registration errors were encountered near moving organs and in regions with less information. The creation of images showing changes in glucose uptake seem to be working well for the neck scans, and somewhat well for other sub-volumes. These images can be useful for identification of BAT. Examples of these images are shown in the report.

La fusion d’images TDM de phase artérielles et veineuses est cruciale afin d’assurer une meilleure planification chirurgicale. Cependant, le recalage non-rigide d’images abdominales est encore un challenge à cause de la respiration qui fait glisser les viscères abdominaux le long de la paroi abdominale, créant ainsi un champ de déformation discontinu. L’objectif de cette thèse est de fournir un outil de recalage précis pour les images TDM multi-phases de l’abdomen.Comme la zone de glissement dans l’abdomen est difficile à segmenter, nous avons d’abord implémenté deux outils de segmentation interactifs permettant une délinéation en 10 minutes de la paroi abdominale et du diaphragme. Pour intégrer ces zones de glissement comme a priori, nous réalisons le recalage sur de nouvelles images dans lesquelles la paroi abdominale et les viscères thoraciques ont été enlevés. Les évaluations sur des données de patient ont montré que notre approche fournit une précision d’environ 1 mm. / The fusion of arterial and venous phase CT images of the entire abdominal viscera is critical for a better diagnosis, surgi-cal planning and treatment, since these two phase images contain complementary information. However, non-rigid regis-tration of abdominal images is still a big challenge due to the breathing motion, which causes sliding motion between the abdominal viscera and the abdo-thoracic wall. The purpose of this thesis is to provide an accurate registration method for abdominal viscera between venous and arterial phase CT images.In order to remove the sliding motion effect, we decide to separate the image into big motion and less motion regions, and perform the registration on new images where abdo-thoracic wall and thoracic viscera are removed. The segmentation of these sliding interfaces is completed with our fast interactive tools within 10 minitues. Two state-of-the-art non-rigid registration algorithms are then applied on these new images and compared to registration obtained with original images. The evaluation using four abdominal organs (liver, kidney, spleen) and several vessel bifurcations shows that our approach provides a much higher accuracy within 1 mm.

The goal of the thesis is to find general nonlinear geometric transformation, which compensates irregular deformation of images, so that they could be registered. In the introductory part, necessary mathematical tools are stated, especially convolution, correlation and Fourier transform. In the next part, method of phase correlation is stated, followed by algorithms used for finding the geometric transformation. Those algorithms are implemented in computer program, that is included.

Les travaux présentés dans ce manuscrit s’inscrivent dans le contexte de l’inspection automatisée d’assemblages mécaniques aéronautiques par vision artificielle. Il s’agit de décider si l’assemblage mécanique a été correctement réalisé (assemblage conforme). Les travaux ont été menés dans le cadre de deux projets industriels. Le projet CAAMVis d’une part, dans lequel le capteur d’inspection est constitué d’une double tête stéréoscopique portée par un robot, le projet Lynx© d’autre part, dans lequel le capteur d’inspection est une caméra Pan/Tilt/Zoom (vision monoculaire). Ces deux projets ont pour point commun la volonté d’exploiter au mieux le modèle CAO de l’assemblage (qui fournit l’état de référence souhaité) dans la tâche d’inspection qui est basée sur l’analyse de l’image ou des images 2D fournies par le capteur. La méthode développée consiste à comparer une image 2D acquise par le capteur (désignée par « image réelle ») avec une image 2D synthétique, générée à partir du modèle CAO. Les images réelles et synthétiques sont segmentées puis décomposées en un ensemble de primitives 2D. Ces primitives sont ensuite appariées, en exploitant des concepts de la théorie de graphes, notamment l’utilisation d’un graphe biparti pour s’assurer du respect de la contrainte d’unicité dans le processus d’appariement. Le résultat de l’appariement permet de statuer sur la conformité ou la non-conformité de l’assemblage. L’approche proposée a été validée à la fois sur des données de simulation et sur des données réelles acquises dans le cadre des projets sus-cités. / The work presented in this manuscript deals with automated inspection of aeronautical mechanical parts using computer vision. The goal is to decide whether a mechanical assembly has been assembled correctly i.e. if it is compliant with the specifications. This work was conducted within two industrial projects. On one hand the CAAMVis project, in which the inspection sensor consists of a dual stereoscopic head (stereovision) carried by a robot, on the other hand the Lynx© project, in which the inspection sensor is a single Pan/Tilt/Zoom camera (monocular vision). These two projects share the common objective of exploiting as much as possible the CAD model of the assembly (which provides the desired reference state) in the inspection task which is based on the analysis of the 2D images provided by the sensor. The proposed method consists in comparing a 2D image acquired by the sensor (referred to as "real image") with a synthetic 2D image generated from the CAD model. The real and synthetic images are segmented and then decomposed into a set of 2D primitives. These primitives are then matched by exploiting concepts from the graph theory, namely the use of a bipartite graph to guarantee the respect of the uniqueness constraint required in such a matching process. The matching result allows to decide whether the assembly has been assembled correctly or not. The proposed approach was validated on both simulation data and real data acquired within the above-mentioned projects.

This thesis covers the development of a series of new methods and the application of adaptive filter theory which are combined to produce a generalised adaptive filter system which may be used to perform such tasks as pattern recognition. Firstly, the relevant background adaptive filter theory is discussed in Chapter 1 and methods and results which are important to the rest of the thesis are derived or referenced. Chapter 2 of this thesis covers the development of a new adaptive algorithm which is designed to give faster convergence than the LMS algorithm but unlike the Recursive Least Squares family of algorithms it does not require storage of a matrix with n2 elements, where n is the number of filter taps. In Chapter 3 a new extension of the LMS adaptive notch filter is derived and applied which gives an adaptive notch filter the ability to lock and track signals of varying pitch without sacrificing notch depth. This application of the LMS filter is of interest as it demonstrates a time varying filter solution to a stationary problem. The LMS filter is next extended to the multidimensional case which allows the application of LMS filters to image processing. The multidimensional filter is then applied to the problem of image registration and this new application of the LMS filter is shown to have significant advantages over current image registration methods. A consideration of the multidimensional LMS filter as a template matcher and pattern recogniser is given. In Chapter 5 a brief review of statistical pattern recognition is given, and in Chapter 6 a review of relevant connectionist models. In Chapter 7 the generalised adaptive filter is derived. This is an adaptive filter with the ability to model non-linear input-output relationships. The Volterra functional analysis of non-linear systems is given and this is combined with adaptive filter methods to give a generalised non-linear adaptive digital filter. This filter is then considered as a linear adaptive filter operating in a non-linearly extended vector space. This new filter is shown to have desirable properties as a pattern recognition system. The performance and properties of the new filter is compared with current connectionist models and results demonstrated in Chapter 8. In Chapter 9 further mathematical analysis of the networks leads to suggested methods to greatly reduce network complexity for a given problem by choosing suitable pattern classification indices and allowing it to define its own internal structure. In Chapter 10 robustness of the network to imperfections in its implementation is considered. Chapter 11 finishes the thesis with some conclusions and suggestions for future work.

The primary goal of this dissertation is to develop point-based rigid and non-rigid image registration methods that have better accuracy than existing methods. We first present point-based PoIRe, which provides the framework for point-based global rigid registrations. It allows a choice of different search strategies including (a) branch-and-bound, (b) probabilistic hill-climbing, and (c) a novel hybrid method that takes advantage of the best characteristics of the other two methods. We use a robust similarity measure that is insensitive to noise, which is often introduced during feature extraction. We show the robustness of PoIRe using it to register images obtained with an electronic portal imaging device (EPID), which have large amounts of scatter and low contrast. To evaluate PoIRe we used (a) simulated images and (b) images with fiducial markers; PoIRe was extensively tested with 2D EPID images and images generated by 3D Computer Tomography (CT) and Magnetic Resonance (MR) images. PoIRe was also evaluated using benchmark data sets from the blind retrospective evaluation project (RIRE). We show that PoIRe is better than existing methods such as Iterative Closest Point (ICP) and methods based on mutual information. We also present a novel point-based local non-rigid shape registration algorithm. We extend the robust similarity measure used in PoIRe to non-rigid registrations adapting it to a free form deformation (FFD) model and making it robust to local minima, which is a drawback common to existing non-rigid point-based methods. For non-rigid registrations we show that it performs better than existing methods and that is less sensitive to starting conditions. We test our non-rigid registration method using available benchmark data sets for shape registration. Finally, we also explore the extraction of features invariant to changes in perspective and illumination, and explore how they can help improve the accuracy of multi-modal registration. For multimodal registration of EPID-DRR images we present a method based on a local descriptor defined by a vector of complex responses to a circular Gabor filter.

Tato práce se zabývá zpracováním snímků Slunce pořízených kosmickou sondou SDO na různých vlnových délkách a vizualizací výskytu třikrát ionizovaného uhlíku C IV jejich vhodným složením. V práci jsou uvedeny základní informace o Slunci a jeho atmosféře, dále je shrnuta potřebná teorie a možné postupy vizualizace, které jsou následně vyhodnoceny a porovnány. Součástí je i vytvořený program pro snadnou tvorbu snímků vizualizujících uhlík C IV.