Light Detection And Ranging (LiDAR), as well as many other applications and sensors, involve segmenting sparse sets of points (point clouds) for which point density is the only discriminating feature. The segmentation of these point clouds is challenging for several reasons, including the fact that the points are not associated with a regular grid. Moreover, the presence of noise, particularly impulsive noise with varying density, can make it difficult to obtain a good segmentation using traditional techniques, including the algorithms that had been developed to process LiDAR data. This dissertation introduces novel algorithms and frameworks based on statistical techniques and image analysis in order to segment and extract surfaces from sparse noisy point clouds. We introduce an adaptive method for mapping point clouds onto an image grid followed by a contour detection approach that is based on an enhanced version of region-based Active Contours Without Edges (ACWE). We also proposed a noise reduction method using Bayesian approach and incorporated it, along with other noise reduction approaches, into a joint framework that produces robust results. We combined the aforementioned techniques with a statistical surface refinement method to introduce a novel framework to detect ground and canopy surfaces in micropulse photon-counting LiDAR data. The algorithm is fully automatic and uses no prior elevation or geographic information to extract surfaces. Moreover, we propose a novel segmentation framework for noisy point clouds in the plane based on a Markov random field (MRF) optimization that we call Point Cloud Densitybased Segmentation (PCDS). We also developed a large synthetic dataset of in plane point clouds that includes either a set of randomly placed, sized and oriented primitive objects (circle, rectangle and triangle) or an arbitrary shape that forms a simple approximation for the LiDAR point clouds. The experiment performed on a large number of real LiDAR and synthetic point clouds showed that our proposed frameworks and algorithms outperforms the state-of-the-art algorithms in terms of segmentation accuracy and surface RMSE. / Ph. D. / The increasing concerns about the global warming have raised the interest about studying and understanding the global ecosystem components including the carbon cycle. The interaction between forests and earth atmosphere is one major component of the global carbon cycle. Thus, quantifying the global forest biomass is an important factor in studying carbon cycle and its dynamics. Therefore repeated large-scale estimates of forest biomass are critically important. LIDAR (Light Detection and Ranging) is a active remote sensing method that uses light in the form of a pulsed laser to measure ranges and distances based on the time-of-flight concept (similar to radar systems). LiDAR systems can generate precise, three-dimensional information about the shape of the Earth and its surface characteristics. Therefore, LiDAR remote sensing is much more suitable for forest studies than photogrammetry because of the laser’s ability to penetrate tree crowns allowing the system to find ground returns under dense canopies. This property allows us to estimate tree heights which is a major factor for estimating the forest biomass. In order to track forest biomass changes at the global scale, recurring high-altitude observations are needed. Satellite-based LiDAR systems can provide these observations, although no such systems are currently operational. The situation will change with the launch of NASAs ICESat-2, which is planned for July 2017. However, although LiDAR technology allows for rapid and inexpensive measurements over broad geographical areas, ICESat-2 will be equipped with a new sensor known as photon-counting micropulse LiDAR system. This new LiDAR technology is expected to produce measurements that include high levels of noise. The data produced by this sensor will be in the form of a cloud of points in which the signal points are expected to be much more dense than noise points. Analysis of data from the ICESat-2 satellite will therefore need to be robust with respect to noise, as well as fast and automatic because of the large quantity of data that will be generated. The problem of segmentation in point clouds is challenging for several reasons, including the fact that the points are not associated with a regular grid, as is the case with most image data. Moreover, the presence of noise particularly impulsive noise with varying density, can make it difficult to obtain a good segmentation using traditional techniques, including the algorithms that had been developed to process LiDAR data. This dissertation introduces novel algorithms and approaches based on statistical techniques and image analysis in order to segment sparse noisy point clouds to extract contours and surfaces in order to detect meaningful measurements and information.

Polarimetric Synthetic Aperture Radar (PolSAR) has been used for various remote sensing applications since more information could be obtained in multiple polarizations. The overall objective of this thesis is to investigate urban area information extraction from PolSAR data with the following specific objectives: (1) to exploit polarimetric scattering model-based decomposition methods for urban areas, (2) to investigate effective methods for man-made target detection, (3) to develop edge detection and superpixel generation methods, and (4) to investigate urban area classification and segmentation. Paper 1 proposes a new scattering coherency matrix to model the cross-polarized scattering component from urban areas, which adaptively considers the polarization orientation angles of buildings. Thus, the HV scattering components from forests and oriented urban areas can be modelled respectively. Paper 2 presents two urban area decompositions using this scattering model. After the decomposition, urban scattering components can be effectively extracted. Paper 3 presents an improved man-made target detection method for PolSAR data based on nonstationarity and asymmetry. Reflection asymmetry was incorporate into the azimuth nonstationarity extraction method to improve the man-made target detection accuracy, i.e., removing the natural areas and detecting the small targets. In Paper 4, the edge detection of PolSAR data was investigated using SIRV model and Gauss-shaped filter. This detector can locate the edge pixels accurately with fewer omissions. This could be useful for speckle noise reduction, superpixel generation and others. Paper 5 investigates an unsupervised classification method for PolSAR data in urban areas. The ortho and oriented buildings can be discriminated very well. Paper 6 proposes an adaptive superpixel generation method for PolSAR images. The algorithm produces compact superpixels that can well adhere to image boundaries in both natural and urban areas. / Polarimetriska Synthetic Aperture Radar (PolSAR) har använts för olika fjärranalystillämpningar för, eftersom mer information kan erhållas från multipolarisad data. Det övergripande syftet med denna avhandling är att undersöka informationshämtning över urbana områden från PolSAR data med följande särskilda mål: (1) att utnyttja polarimetrisk spridningsmodellbaserade nedbrytningsmetoder för stadsområden, (2) att undersöka effektiva metoder för upptäckt av konstgjorda objekt, (3) att utveckla metoder som kantavkänning och superpixel generation, och (4) för att undersöka klassificering och segmentering av stadsområden. Artikel 1 föreslår en ny spridnings-koherens matris för att modellera korspolariserade spridningskomponent från tätorter, som adaptivt utvärderar polariseringsorienteringsvinkel av byggnader. Artikel 2 presenterar nedbrytningstekniken över två urbana områden med hjälp av denna spridningsmodell. Efter nedbrytningen kunde urbana spridningskomponenter effektivt extraheras. Artikel 3 presenterar en förbättrad detekteringsmetod för konstgjorda mål med PolSAR data baserade på icke-stationaritet och asymmetri. integrerades reflektionsasymmetri i icke-stationaritetsmetoden för att förbättra noggrannheten i upptäckten av konstgjorda föremål, dvs. att ta bort naturområden och upptäcka de små föremålen. I artikel 4 undersöktes kantdetektering av PolSAR data med hjälp av SIRV modell och ett Gauss-formad filter. Denna detektor kan hitta kantpixlarna noggrant med mindre utelämnande. Detta skulle den vara användbar för reduktion av brus, superpixel generation och andra. Artikel 5 utforskar en oövervakad klassificeringsmetod av PolSAR data över stadsområden. Orto- och orienterade byggnader kan särskiljas mycket väl. Baserat på artikel 4 föreslår artikel 6 en adaptiv superpixel generationensmetod för PolSAR data. Algoritmen producerar kompakta superpixels som kan kommer att följa bildgränser i både naturliga och stadsområden. / <p>QC 20160607</p>

A representação de imagem baseada em superpixels tem se tornado indispensável na melhoria da eficiência em sistemas de Visão Computacional. Reconhecimento de objetos, segmentação, estimativa de profundidade e estimativa de modelo corporal são alguns importantes problemas nos quais superpixels podem ser aplicados. Porém, superpixels podem influenciar a qualidade dos resultados do sistema positiva ou negativamente, dependendo de quão bem eles respeitam as fronteiras dos objetos na imagem. Neste trabalho, é proposto um método iterativo para geração de superpixels, conhecido por IFT-SLIC, baseado em sequências de Transformadas Imagem-Floresta, começando com uma grade regular de sementes. Um procedimento de recomputação de pixels sementes é aplicado a cada iteração, gerando superpixels conexos com melhor aderência às bordas dos objetos presentes na imagem. Os superpixels obtidos via IFT-SLIC correspondem, estruturalmente, a árvores de espalhamento enraizadas nessas sementes, que naturalmente definem superpixels como regiões de pixels fortemente conexas. Comparadas ao Agrupamento Iterativo Linear Simples (SLIC), o IFT-SLIC considera os custos dos caminhos mínimos entre pixels e os centros dos agrupamentos, em vez de suas distâncias diretas. Funções de conexidade não monotonicamente incrementais são exploradas em neste método resultando em melhor desempenho. Estudos experimentais indicam resultados de extração de superpixels superiores pelo método proposto em comparação com o SLIC. Também é analisada a efetividade do IFT-SLIC, em termos de medidas de eficiência e acurácia, em uma aplicação de segmentação do céu em fotos de paisagens. Os resultados mostram que o IFT-SLIC é competitivo com os melhores métodos do estado da arte e superior a muitos outros, motivando seu desenvolvimento para diferentes aplicações. / Image representation based on superpixels has become indispensable for improving efficiency in Computer Vision systems. Object recognition, segmentation, depth estimation, and body model estimation are some important problems where superpixels can be applied. However, superpixels can influence the quality of the system results in a positive or negative manner, depending on how well they respect the object boundaries in the image. In this work, we propose an iterative method for superpixels generation, known as IFT-SLIC, which is based on sequences of Image Foresting Transforms, starting with a regular grid for seed sampling. A seed pixel recomputation procedure is applied per each iteration, generating connected superpixels with a better adherence to objects borders present in the image. The superpixels obtained by IFT-SLIC structurally correspond to spanning trees rooted at those seeds, that naturally define superpixels as regions of strongly connected pixels. Compared to Simple Linear Iterative Clustering (SLIC), IFT-SLIC considers minimum path costs between pixel and cluster centers rather than their direct distances. Non-monotonically increasing connectivity functions are explored in our IFT-SLIC approach leading to improved performance. Experimental results indicate better superpixel extraction by the proposed approach in comparation to that of SLIC. We also analyze the effectiveness of IFT-SLIC, according to efficiency, and accuracy on an application -- namely sky segmentation. The results show that IFT-SLIC can be competitive to the best state-of-the-art methods and superior to many others, which motivates it\'s further development for different applications.

A representação de imagem baseada em superpixels tem se tornado indispensável na melhoria da eficiência em sistemas de Visão Computacional. Reconhecimento de objetos, segmentação, estimativa de profundidade e estimativa de modelo corporal são alguns importantes problemas nos quais superpixels podem ser aplicados. Porém, superpixels podem influenciar a qualidade dos resultados do sistema positiva ou negativamente, dependendo de quão bem eles respeitam as fronteiras dos objetos na imagem. Neste trabalho, é proposto um método iterativo para geração de superpixels, conhecido por IFT-SLIC, baseado em sequências de Transformadas Imagem-Floresta, começando com uma grade regular de sementes. Um procedimento de recomputação de pixels sementes é aplicado a cada iteração, gerando superpixels conexos com melhor aderência às bordas dos objetos presentes na imagem. Os superpixels obtidos via IFT-SLIC correspondem, estruturalmente, a árvores de espalhamento enraizadas nessas sementes, que naturalmente definem superpixels como regiões de pixels fortemente conexas. Comparadas ao Agrupamento Iterativo Linear Simples (SLIC), o IFT-SLIC considera os custos dos caminhos mínimos entre pixels e os centros dos agrupamentos, em vez de suas distâncias diretas. Funções de conexidade não monotonicamente incrementais são exploradas em neste método resultando em melhor desempenho. Estudos experimentais indicam resultados de extração de superpixels superiores pelo método proposto em comparação com o SLIC. Também é analisada a efetividade do IFT-SLIC, em termos de medidas de eficiência e acurácia, em uma aplicação de segmentação do céu em fotos de paisagens. Os resultados mostram que o IFT-SLIC é competitivo com os melhores métodos do estado da arte e superior a muitos outros, motivando seu desenvolvimento para diferentes aplicações. / Image representation based on superpixels has become indispensable for improving efficiency in Computer Vision systems. Object recognition, segmentation, depth estimation, and body model estimation are some important problems where superpixels can be applied. However, superpixels can influence the quality of the system results in a positive or negative manner, depending on how well they respect the object boundaries in the image. In this work, we propose an iterative method for superpixels generation, known as IFT-SLIC, which is based on sequences of Image Foresting Transforms, starting with a regular grid for seed sampling. A seed pixel recomputation procedure is applied per each iteration, generating connected superpixels with a better adherence to objects borders present in the image. The superpixels obtained by IFT-SLIC structurally correspond to spanning trees rooted at those seeds, that naturally define superpixels as regions of strongly connected pixels. Compared to Simple Linear Iterative Clustering (SLIC), IFT-SLIC considers minimum path costs between pixel and cluster centers rather than their direct distances. Non-monotonically increasing connectivity functions are explored in our IFT-SLIC approach leading to improved performance. Experimental results indicate better superpixel extraction by the proposed approach in comparation to that of SLIC. We also analyze the effectiveness of IFT-SLIC, according to efficiency, and accuracy on an application -- namely sky segmentation. The results show that IFT-SLIC can be competitive to the best state-of-the-art methods and superior to many others, which motivates it\'s further development for different applications.

[pt] A segmentação de imagens com objetivo de determinar a forma de objetos é ainda um problema difícil. A separação de regiões que correspondem a objetos contidos na imagem geralmente leva em consideração propriedades de similaridade, proximidade e descontinuidade. A imagem a ser segmentada pode ser de diversas naturezas, como fotografias, imagens médicas e sísmicas. Podemos encontrar na literatura muitos métodos de segmentação propostos como possíveis soluções para diferentes problemas. Recentemente a técnica de superpixel tem sido utilizada como um passo inicial que reduz o tamanho da entrada do problema. Este trabalho propõe uma metodologia de segmentação de imagens fotográficas e de ultrassom que se baseia em variantes de superpixels. A metodologia proposta se adapta a natureza da imagem e a complexidade do problema utilizando diferentes medidas de similaridade e distância. O trabalho apresenta também resultados que buscam esclarecer o procedimento proposto e a escolha de seus parâmetros. / [en] Image segmentation for object modeling is a complex task that is still not well solved. The separation of the regions corresponding to each object in an image is based on proximity, similarity, and discontinuity of its boundaries. The image to be segmented can be of various natures, including photographs, medical and seismic images. We can find in literature many proposed segmentation methods used as solutions to different problems. Recently the superpixel technique has been used as an initial step that reduces the size of the problem input. This work proposes a methodology of segmentation of photographs and ultrasound images based on variants of superpixels. The proposed methodology adapts to the image s nature and to the problem s complexity using different measures of similarity and distance. This work also presents results that seek to clarify the proposed procedure and the choice of its parameters.

Dans le domaine de la vision par ordinateur, l’estimation de la structure d’une scène 3D à partir d’images 2D constitue un problème fondamental. Parmi les applications concernées par cette problématique, nous nous sommes intéressés dans le cadre de cette thèse à la modélisation d’un environnement urbain. Nous nous sommes intéressés à la reconstruction de scènes 3D à partir d’images monoculaires générées par un véhicule en mouvement. Ici, plusieurs défis se posent à travers les différentes étapes de la chaine de traitement inhérente à la reconstruction 3D. L’un de ces défis vient du fait de l’absence de zones suffisamment texturées dans certaines scènes urbaines, d’où une reconstruction 3D (un nuage de points 3D) trop éparse. De plus, du fait du mouvement du véhicule, d’une image à l’autre il n’y a pas toujours un recouvrement suffisant entre différentes vues consécutives d’une même scène. Dans ce contexte, et ce afin de lever les verrous ci-dessus mentionnés, nous proposons d’estimer, de reconstruire, la structure d’une scène 3D par morceaux en se basant sur une hypothèse de planéité. Nous proposons plusieurs améliorations à la chaine de traitement associée à la reconstruction 3D. D’abord, afin de structurer, de représenter, la scène sous la forme d’entités planes nous proposons une nouvelle méthode de reconstruction 3D, basée sur le regroupement de pixels similaires (superpixel segmentation), qui à travers une représentation multi-échelle pondérée fusionne les informations de couleur et de mouvement. Cette méthode est basée sur l’estimation de la probabilité de discontinuités locales aux frontières des régions calculées à partir du gradient (gradientbased boundary probability estimation). Afin de prendre en compte l’incertitude liée à l’estimation du mouvement, une pondération par morceaux est appliquée à chaque pixel en fonction de cette incertitude. Cette méthode génère des regroupements de pixels (superpixels) non contraints en termes de taille et de forme. Pour certaines applications, telle que la reconstruction 3D à partir d’une séquence d’images, des contraintes de taille sont nécessaires. Nous avons donc proposé une méthode qui intègre à l’algorithme SLIC (Simple Linear Iterative Clustering) l’information de mouvement. L’objectif étant d’obtenir une reconstruction 3D plus dense qui estime mieux la structure de la scène. Pour atteindre cet objectif, nous avons aussi introduit une nouvelle distance qui, en complément de l’information de mouvement et de données images, prend en compte la densité du nuage de points. Afin d’augmenter la densité du nuage de points utilisé pour reconstruire la structure de la scène sous la forme de surfaces planes, nous proposons une nouvelle approche qui mixte plusieurs méthodes d’appariement et une méthode de flot optique dense. Cette méthode est basée sur un système de pondération qui attribue un poids pré-calculé par apprentissage à chaque point reconstruit. L’objectif est de contrôler l’impact de ce système de pondération, autrement dit la qualité de la reconstruction, en fonction de la précision de la méthode d’appariement utilisée. Pour atteindre cet objectif, nous avons appliqué un processus des moindres carrés pondérés aux données reconstruites pondérées par les calculés par apprentissage, qui en complément de la segmentation par morceaux de la séquence d’images, permet une meilleure reconstruction de la structure de la scène sous la forme de surfaces planes. Nous avons également proposé un processus de gestion des discontinuités locales aux frontières de régions voisines dues à des occlusions (occlusion boundaries) qui favorise la coplanarité et la connectivité des régions connexes. L’ensemble des modèles proposés permet de générer une reconstruction 3D dense représentative à la réalité de la scène. La pertinence des modèles proposés a été étudiée et comparée à l’état de l’art. Plusieurs expérimentations ont été réalisées afin de démontrer, d’étayer, la validité de notre approche / In computer vision, the 3D structure estimation from 2D images remains a fundamental problem. One of the emergent applications is 3D urban modelling and mapping. Here, we are interested in street-level monocular 3D reconstruction from mobile vehicle. In this particular case, several challenges arise at different stages of the 3D reconstruction pipeline. Mainly, lacking textured areas in urban scenes produces low density reconstructed point cloud. Also, the continuous motion of the vehicle prevents having redundant views of the scene with short feature points lifetime. In this context, we adopt the piecewise planar 3D reconstruction where the planarity assumption overcomes the aforementioned challenges.In this thesis, we introduce several improvements to the 3D structure estimation pipeline. In particular, the planar piecewise scene representation and modelling. First, we propose a novel approach that aims at creating 3D geometry respecting superpixel segmentation, which is a gradient-based boundary probability estimation by fusing colour and flow information using weighted multi-layered model. A pixel-wise weighting is used in the fusion process which takes into account the uncertainty of the computed flow. This method produces non-constrained superpixels in terms of size and shape. For the applications that imply a constrained size superpixels, such as 3D reconstruction from an image sequence, we develop a flow based SLIC method to produce superpixels that are adapted to reconstructed points density for better planar structure fitting. This is achieved by the mean of new distance measure that takes into account an input density map, in addition to the flow and spatial information. To increase the density of the reconstructed point cloud used to performthe planar structure fitting, we propose a new approach that uses several matching methods and dense optical flow. A weighting scheme assigns a learned weight to each reconstructed point to control its impact to fitting the structure relative to the accuracy of the used matching method. Then, a weighted total least square model uses the reconstructed points and learned weights to fit a planar structure with the help of superpixel segmentation of the input image sequence. Moreover, themodel handles the occlusion boundaries between neighbouring scene patches to encourage connectivity and co-planarity to produce more realistic models. The final output is a complete dense visually appealing 3Dmodels. The validity of the proposed approaches has been substantiated by comprehensive experiments and comparisons with state-of-the-art methods

Superpixels are the results of an image oversegmentation. They are an established intermediate level image representation and used for various applications including object detection, 3d reconstruction and semantic segmentation. While there are various approaches to create such segmentations, there is a lack of knowledge about their properties. In particular, there are contradicting results published in the literature. This thesis identifies segmentation quality, stability, compactness and runtime to be important properties of superpixel segmentation algorithms. While for some of these properties there are established evaluation methodologies available, this is not the case for segmentation stability and compactness. Therefore, this thesis presents two novel metrics for their evaluation based on ground truth optical flow. These two metrics are used together with other novel and existing measures to create a standardized benchmark for superpixel algorithms. This benchmark is used for extensive comparison of available algorithms. The evaluation results motivate two novel segmentation algorithms that better balance trade-offs of existing algorithms: The proposed Preemptive SLIC algorithm incorporates a local preemption criterion in the established SLIC algorithm and saves about 80 % of the runtime. The proposed Compact Watershed algorithm combines Seeded Watershed segmentation with compactness constraints to create regularly shaped, compact superpixels at the even higher speed of the plain watershed transformation. Operating autonomous systems over the course of days, weeks or months, based on visual navigation, requires repeated recognition of places despite severe appearance changes as they are for example induced by illumination changes, day-night cycles, changing weather or seasons - a severe problem for existing methods. Therefore, the second part of this thesis presents two novel approaches that incorporate superpixel segmentations in place recognition in changing environments. The first novel approach is the learning of systematic appearance changes. Instead of matching images between, for example, summer and winter directly, an additional prediction step is proposed. Based on superpixel vocabularies, a predicted image is generated that shows, how the summer scene could look like in winter or vice versa. The presented results show that, if certain assumptions on the appearance changes and the available training data are met, existing holistic place recognition approaches can benefit from this additional prediction step. Holistic approaches to place recognition are known to fail in presence of viewpoint changes. Therefore, this thesis presents a new place recognition system based on local landmarks and Star-Hough. Star-Hough is a novel approach to incorporate the spatial arrangement of local image features in the computation of image similarities. It is based on star graph models and Hough voting and particularly suited for local features with low spatial precision and high outlier rates as they are expected in the presence of appearance changes. The novel landmarks are a combination of local region detectors and descriptors based on convolutional neural networks. This thesis presents and evaluates several new approaches to incorporate superpixel segmentations in local region detection. While the proposed system can be used with different types of local regions, in particular the combination with regions obtained from the novel multiscale superpixel grid shows to perform superior to the state of the art methods - a promising basis for practical applications.

Superpixels are the results of an image oversegmentation. They are an established intermediate level image representation and used for various applications including object detection, 3d reconstruction and semantic segmentation. While there are various approaches to create such segmentations, there is a lack of knowledge about their properties. In particular, there are contradicting results published in the literature. This thesis identifies segmentation quality, stability, compactness and runtime to be important properties of superpixel segmentation algorithms. While for some of these properties there are established evaluation methodologies available, this is not the case for segmentation stability and compactness. Therefore, this thesis presents two novel metrics for their evaluation based on ground truth optical flow. These two metrics are used together with other novel and existing measures to create a standardized benchmark for superpixel algorithms. This benchmark is used for extensive comparison of available algorithms. The evaluation results motivate two novel segmentation algorithms that better balance trade-offs of existing algorithms: The proposed Preemptive SLIC algorithm incorporates a local preemption criterion in the established SLIC algorithm and saves about 80 % of the runtime. The proposed Compact Watershed algorithm combines Seeded Watershed segmentation with compactness constraints to create regularly shaped, compact superpixels at the even higher speed of the plain watershed transformation. Operating autonomous systems over the course of days, weeks or months, based on visual navigation, requires repeated recognition of places despite severe appearance changes as they are for example induced by illumination changes, day-night cycles, changing weather or seasons - a severe problem for existing methods. Therefore, the second part of this thesis presents two novel approaches that incorporate superpixel segmentations in place recognition in changing environments. The first novel approach is the learning of systematic appearance changes. Instead of matching images between, for example, summer and winter directly, an additional prediction step is proposed. Based on superpixel vocabularies, a predicted image is generated that shows, how the summer scene could look like in winter or vice versa. The presented results show that, if certain assumptions on the appearance changes and the available training data are met, existing holistic place recognition approaches can benefit from this additional prediction step. Holistic approaches to place recognition are known to fail in presence of viewpoint changes. Therefore, this thesis presents a new place recognition system based on local landmarks and Star-Hough. Star-Hough is a novel approach to incorporate the spatial arrangement of local image features in the computation of image similarities. It is based on star graph models and Hough voting and particularly suited for local features with low spatial precision and high outlier rates as they are expected in the presence of appearance changes. The novel landmarks are a combination of local region detectors and descriptors based on convolutional neural networks. This thesis presents and evaluates several new approaches to incorporate superpixel segmentations in local region detection. While the proposed system can be used with different types of local regions, in particular the combination with regions obtained from the novel multiscale superpixel grid shows to perform superior to the state of the art methods - a promising basis for practical applications.

Cette thèse s’intéresse à diverses composantes du traitement et de l’analyse d’images par méthodes non locales. Ces méthodes sont basées sur la redondance d’information présente dans d’autres images, et utilisent des algorithmes de recherche de correspondance, généralement basés sur l’utilisation patchs, pour extraire et transférer de l’information depuis ces images d’exemples. Ces approches, largement utilisées par la communauté de vision par ordinateur, sont souvent limitées par le temps de calcul de l’algorithme de recherche, appliqué à chaque pixel, et par la nécessité d’effectuer un prétraitement ou un apprentissage pour utiliser de grandes bases de données.Pour pallier ces limites, nous proposons plusieurs méthodes générales, sans apprentissage,rapides, et qui peuvent être facilement adaptées à diverses applications de traitement et d’analyse d’images naturelles ou médicales. Nous introduisons un algorithme de recherche de correspondances permettant d’extraire rapidement des patchs d’une grande bibliothèque d’images 3D, que nous appliquons à la segmentation d’images médicales. Pour utiliser de façon similaire aux patchs,des présegmentations en superpixels réduisant le nombre d’éléments de l’image,nous présentons une nouvelle structure de voisinage de superpixels. Ce nouveau descripteur permet d’utiliser efficacement les superpixels dans des approches non locales. Nous proposons également une méthode de décomposition régulière et précise en superpixels. Nous montrons comment évaluer cette régularité de façon robuste, et que celle-ci est nécessaire pour obtenir de bonnes performances de recherche de correspondances basées sur les superpixels. / This thesis focuses on several aspects of image analysis and processing with non local methods. These methods are based on the redundancy of information that occurs in other images, and use matching algorithms, that are usually patch-based, to extract and transfer information from the example data. These approaches are widely used by the computer vision community, and are generally limited by the computational time of the matching algorithm, applied at the pixel scale, and by the necessity to perform preprocessing or learning steps to use large databases. To address these issues, we propose several general methods, without learning, fast, and that can be easily applied to different image analysis and processing applications on natural and medical images. We introduce a matching algorithm that enables to quickly extract patches from a large library of 3D images, that we apply to medical image segmentation. To use a presegmentation into superpixels that reduces the number of image elements, in a way that is similar to patches, we present a new superpixel neighborhood structure. This novel descriptor enables to efficiently use superpixels in non local approaches. We also introduce an accurate and regular superpixel decomposition method. We show how to evaluate this regularity in a robust manner, and that this property is necessary to obtain good superpixel-based matching performances.

In recent years, Polarimetric Synthetic Aperture Radar (PolSAR) has been one of the most important instruments for earth observation, and is increasingly used in various remote sensing applications. Statistical modelling and scattering analysis are two main ways for PolSAR data interpretation, and have been intensively investigated in the past two decades. Moreover, spatial analysis was applied in the analysis of PolSAR data and found to be beneficial to achieve more accurate interpretation results. This thesis focuses on extracting typical spatial information, i.e., edges and regions by exploring the statistical characteristics of PolSAR data. The existing spatial analysing methods are mainly based on the complex Wishart distribution, which well characterizes the inherent statistical features in homogeneous areas. However, the non-Gaussian models can give better representation of the PolSAR statistics, and therefore have the potential to improve the performance of spatial analysis, especially in heterogeneous areas. In addition, the traditional fixed-shape windows cannot accurately estimate the distribution parameter in some complicated areas, leading to the loss of the refined spatial details. Furthermore, many of the existing methods are not spatially adaptive so that the obtained results are promising in some areas whereas unsatisfactory in other areas. Therefore, this thesis is dedicated to extracting spatial information by applying the non-Gaussian statistical models and spatially adaptive strategies. The specific objectives of the thesis include: (1) to develop reliable edge detection method, (2) to develop spatially adaptive superpixel generation method, and (3) to investigate a new framework of region-based segmentation. Automatic edge detection plays a fundamental role in spatial analysis, whereas the performance of classical PolSAR edge detection methods is limited by the fixed-shape windows. Paper 1 investigates an enhanced edge detection method using the proposed directional span-driven adaptive (DSDA) window. The DSDA window has variable sizes and flexible shapes, and can overcome the limitation of fixed-shape windows by adaptively selecting homogeneous samples. The spherically invariant random vector (SIRV) product model is adopted to characterize the PolSAR data, and a span ratio is combined with the SIRV distance to highlight the dissimilarity measure. The experimental results demonstrated that the proposed method can detect not only the obvious edges, but also the tiny and inconspicuous edges in heterogeneous areas. Edge detection and region segmentation are two important aspects of spatial analysis. As to the region segmentation, paper 2 presents an adaptive PolSAR superpixel generation method based on the simple linear iterative clustering (SLIC) framework. In the k-means clustering procedure, multiple cues including polarimetric, spatial, and texture information are considered to measure the distance. Since the constant weighting factor which balances the spectral similarity and spatial proximity may cause over- or under-superpixel segmentation in different areas, the proposed method sets the factor adaptively based on the homogeneity analysis. Then, in heterogeneous areas, the spectral similarity is more significant than the spatial constraint, generating superpixels which better preserved local details and refined structures. Paper 3 investigates another PolSAR superpixel generation method, which is achieved from the global optimization aspect, using the entropy rate method. The distance between neighbouring pixels is calculated based on their corresponding DSDA regions. In addition, the SIRV distance and the Wishart distance are combined together. Therefore, the proposed method makes good use of the entropy rate framework, and also incorporates the merits of the SIRV distance and the Wishart distance. The superpixels are generated in a homogeneity-adaptive manner, resulting in smooth representation of the land covers in homogeneous areas, and well preserved details in heterogeneous areas. / <p>QC 20171123</p>