A análise de texturas tem atraído um crescente interesse em visão computacional devido a sua importância na caracterização de imagens. Basicamente, as pesquisas em texturas podem ser divididas em duas categorias: texturas estáticas e texturas dinâmicas. As texturas estáticas são caracterizadas por variações de intensidades que formam um determinado padrão repetido espacialmente na imagem. Por outro lado, as texturas dinâmicas são padrões de texturas presentes em uma sequência de imagens. Embora muitas pesquisas tenham sido realizadas, essa área ainda se encontra aberta a estudos, principalmente em texturas dinâmicas por se tratar de um assunto recente e pouco explorado. Este trabalho tem como objetivo o desenvolvimento de pesquisas que abrangem ambos os tipos de texturas nos âmbitos teórico e prático. Em texturas estáticas, foram propostos dois métodos: (i) baseado em caminhadas determinísticas parcialmente auto-repulsivas e dimensão fractal - (ii) baseado em atividade em redes direcionadas. Em texturas dinâmicas, as caminhadas determinísticas parcialmente auto-repulsivas foram estendidas para sequências de imagens e obtiveram resultados interessantes em reconhecimento e segmentação. Os métodos propostos foram aplicados em problemas da biologia e nanotecnologia, apresentando resultados interessantes para o desenvolvimento de ambas as áreas. / Texture analysis has attracted an increasing interest in computer vision due to its importance in describing images. Basically, research on textures can be divided into two categories: static and dynamic textures. Static textures are characterized by intensity variations which form a pattern repeated in the image spatially. On the other hand, dynamic textures are patterns of textures present in a sequence of images. Although many studies have been carried out, this area is still open to study, especially in dynamic textures since it is a recent and little-explored subject. This study aims to develop research covering both types of textures in theoretical and practical fields. In static textures, two methods were proposed: (i) based on deterministic partially self-avoiding walks and fractal dimension - (ii) based on activity in directed networks. In dynamic textures, deterministic partially self-avoiding walks were extended to sequences of images and obtained interesting results in recognition and segmentation. The proposed methods were applied to problems of biology and nanotechnology, presenting interesting results in the development of both areas.

A análise de texturas tem atraído um crescente interesse em visão computacional devido a sua importância na caracterização de imagens. Basicamente, as pesquisas em texturas podem ser divididas em duas categorias: texturas estáticas e texturas dinâmicas. As texturas estáticas são caracterizadas por variações de intensidades que formam um determinado padrão repetido espacialmente na imagem. Por outro lado, as texturas dinâmicas são padrões de texturas presentes em uma sequência de imagens. Embora muitas pesquisas tenham sido realizadas, essa área ainda se encontra aberta a estudos, principalmente em texturas dinâmicas por se tratar de um assunto recente e pouco explorado. Este trabalho tem como objetivo o desenvolvimento de pesquisas que abrangem ambos os tipos de texturas nos âmbitos teórico e prático. Em texturas estáticas, foram propostos dois métodos: (i) baseado em caminhadas determinísticas parcialmente auto-repulsivas e dimensão fractal - (ii) baseado em atividade em redes direcionadas. Em texturas dinâmicas, as caminhadas determinísticas parcialmente auto-repulsivas foram estendidas para sequências de imagens e obtiveram resultados interessantes em reconhecimento e segmentação. Os métodos propostos foram aplicados em problemas da biologia e nanotecnologia, apresentando resultados interessantes para o desenvolvimento de ambas as áreas. / Texture analysis has attracted an increasing interest in computer vision due to its importance in describing images. Basically, research on textures can be divided into two categories: static and dynamic textures. Static textures are characterized by intensity variations which form a pattern repeated in the image spatially. On the other hand, dynamic textures are patterns of textures present in a sequence of images. Although many studies have been carried out, this area is still open to study, especially in dynamic textures since it is a recent and little-explored subject. This study aims to develop research covering both types of textures in theoretical and practical fields. In static textures, two methods were proposed: (i) based on deterministic partially self-avoiding walks and fractal dimension - (ii) based on activity in directed networks. In dynamic textures, deterministic partially self-avoiding walks were extended to sequences of images and obtained interesting results in recognition and segmentation. The proposed methods were applied to problems of biology and nanotechnology, presenting interesting results in the development of both areas.

De nombreuses applications de la vision par ordinateur requièrent la détection, la localisation et le suivi de régions ou d’objets d’intérêt dans une image ou une séquence d’images. De nombreux modèles d’attention visuelle, inspirés de la vision humaine, qui détectent de manière automatique les régions d’intérêt dans une image ou une vidéo, ont récemment été développés et utilisés avec succès dans différentes applications. Néanmoins, la plupart des approches existantes sont limitées à l’analyse de scènes statiques et très peu de méthodes exploitent la nature temporelle des séquences d’images.L'objectif principal de ce travail de thèse est donc l'étude de modèles d'attention visuelle pour l'analyse de scènes dynamiques complexes. Une carte de saliance est habituellement obtenue par la fusion d'une carte statitque (saliance spatiale dans une image) d'une part, et d'une carte dynamique (salience temporelle entre une série d'image) d'autre part. Dans notre travail, nous modélisons les changements dynamiques par un opérateur de texture LBP-TOP (Local Binary Patterns) et nous utilisons l'information couleur pour l'aspect spatial.Les deux cartes de saliances sont calculées en utilisant une formulation discriminante inspirée du système visuel humain, et fuionnées de manière appropriée en une carte de saliance spatio-temporelle.De nombreuses expériences avec des bases de données publiques, montrent que notre approche obteint des résulats meilleurs ou comparables avec les approches de la littérature. / Visual saliency is an important research topic in the field of computer vision due to its numerouspossible applications. It helps to focus on regions of interest instead of processingthe whole image or video data. Detecting visual saliency in still images has been widelyaddressed in literature with several formulations. However, visual saliency detection invideos has attracted little attention, and is a more challenging task due to additional temporalinformation. Indeed, a video contains strong spatio-temporal correlation betweenthe regions of consecutive frames, and, furthermore, motion of foreground objects dramaticallychanges the importance of the objects in a scene. The main objective of thethesis is to develop a spatio-temporal saliency method that works well for complex dynamicscenes.A spatio-temporal saliency map is usually obtained by the fusion of a static saliency mapand a dynamic saliency map. In our work, we model the dynamic textures in a dynamicscene with Local Binary Patterns (LBP-TOP) to compute the dynamic saliency map, andwe use color features to compute the static saliency map. Both saliency maps are computedusing a bio-inspired mechanism of Human Visual System (HVS) with a discriminantformulation known as center surround saliency, and are fused in a proper way.The proposed models have been extensively evaluated with diverse publicly availabledatasets which contain several videos of dynamic scenes. The evaluation is performed intwo parts. First, the method in locating interesting foreground objects in complex scene.Secondly, we evaluate our model on the task of predicting human observers fixations.The proposed method is also compared against state-of-the art methods, and the resultsshow that the proposed approach achieves competitive results.In this thesis we also evaluate the performance of different fusion techniques, because fusionplays a critical role in the accuracy of the spatio-temporal saliency map. We evaluatethe performances of different fusion techniques on a large and diverse complex datasetand the results show that a fusion method must be selected depending on the characteristics,in terms of color and motion contrasts, of a sequence. Overall, fusion techniqueswhich take the best of each saliency map (static and dynamic) in the final spatio-temporalmap achieve best results.

Nous nous intéresserons dans cette thèse à l'étude et la caractérisation des Textures Dynamiques (TDs), avec comme application visée l'indexation dans de grandes bases de vidéos. Ce thème de recherche étant émergent, nous proposons une définition des TDs, une taxonomie de celles-ci, ainsi qu'un état de l'art. La classe de TD la plus représentative est décrite par un modèle formel qui considère les TDs comme la superposition d'ondes porteuses et de phénomènes locaux. La construction d'outils d'analyse spatio-temporelle adaptés aux TDs est notre principale contribution. D'une part, nous montrons que la transformée en curvelets 2D+T est pertinente pour la représentation de l'onde porteuse. D'autre part, dans un objectif de décomposition des séquences vidéos, nous proposons d'utiliser l'approche par Analyse en Composantes Morphologiques. Notre contribution consiste en l'apport et l'étude de nouvelles stratégies de seuillage. Ces méthodes sont testées sur plusieurs applications: segmentation spatio-temporelle, décomposition de TDs, estimation du mouvement global d'une TD, ... Nous avons de plus montré que l'Analyse en Composantes Morphologiques et les approches multi-échelles donnent des résultats significatifs pour la recherche par le contenu et l'indexation de Textures Dynamiques de la base de données DynTex. Cette thèse constitue ainsi un premier pas vers l'indexation automatique de textures dynamiques dans des séquences d'images, et ouvre la voie à de nombreux développements sur ce sujet nouveau. Enfin, le caractère générique des approches proposées permet d'envisager leurs applications dans un cadre plus large mettant en jeu par exemple des données 3D. / This report is focused on the study and the characterization of Dynamic Textures (DTs), with the aim of video indexing in large databases. This research topic being new and emerging, we propose a taxonomy, a definition of DTs and a state of the art. The most representative DT class is described by a model that considers DTs as the superposition of several wavefronts and local oscillating phenomena. The design of spatio-temporal analysis tools adapted to DT is our main contribution. We first show that the 2D+T curvelet transform is relevant for representing wavefronts. In order to analyse and better understand the DTs, we propose in a second step to adapt the Morphological Component Analysis approach using new thresholding strategies. These methods are tested on several applications: decomposition of DTs, spatio-temporal segmentation, global motion estimation of a DT, ... We have shown that Morphological Component Analysis and multi-scale approaches enable significant results for content-based retrieval applications and dynamic texture indexing on the DynTex database. This thesis constitutes a first step towards automatic indexing of DTs in image sequences and opens the way for many new developments in this topic. Moreover, the proposed approaches are generic and could be applied in a broader context, for instance the processing of 3D data.