Digitization and characterization of urban spaces are essential components as we move to an ever-growing ’always connected’ world. Accurate analysis of such digital urban spaces has become more important as we continue to get spatial and social context-aware feedback and recommendations in our daily activities. Modeling and reconstruction of urban environments have thus gained unprecedented importance in the last few years. Such analysis typically spans multiple disciplines, such as computer graphics, and computer vision as well as architecture, geoscience, and remote sensing. Reconstructing an urban environment usually requires an entire pipeline consisting of different tasks. In such a pipeline, data analysis plays a strong role in acquiring meaningful insights from the raw data. This dissertation primarily focuses on the analysis of various forms of urban data and proposes a set of techniques to extract useful information, which is then used for different applications. The first part of this dissertation presents a semi-automatic framework to analyze facade images to recover individual windows along with their functional configurations such as open or (partially) closed states. The main advantage of recovering both the repetition patterns of windows and their individual deformation parameters is to produce a factored facade representation. Such a factored representation enables a range of applications including interactive facade images, improved multi-view stereo reconstruction, facade-level change detection, and novel image editing possibilities. The second part of this dissertation demonstrates the importance of a layout configuration on its performance. As a specific application scenario, I investigate the interior layout of warehouses wherein the goal is to assign items to their storage locations while reducing flow congestion and enhancing the speed of order picking processes. The third part of the dissertation proposes a method to classify cities based on their functional behavior. Commonly used computational approaches concentrate on geometric descriptors, for both images and laser scans. Instead, I analyze street networks, both their topology (i.e., connectivity) and geometry (i.e., layout), in an attempt to understand the factors that play dominant roles in determining the characteristic of cities. A set of street network descriptors is proposed to capture the essence of city layouts and used, in a supervised setting, to classify and categorize various cities across the world. Each part of the dissertation shows the utility of the proposed methods through describing a variety of applications on different examples.

Depuis quelques années, avec l'émergence de larges bases d'images comme Google Street View, la capacité à traiter massivement et automatiquement des données, souvent très contaminées par les faux positifs et massivement ambiguës, devient un enjeu stratégique notamment pour la gestion de patrimoine et le diagnostic de l'état de façades de bâtiment. Sur le plan scientifique, ce souci est propre à faire avancer l'état de l'art dans des problèmes fondamentaux de vision par ordinateur. Notamment, nous traitons dans cette thèse les problèmes suivants: la mise en correspondance robuste, algorithmiquement efficace de caractéristiques visuelles et l'analyse d'images de façades par grammaire. L'enjeu est de développer des méthodes qui doivent également être adaptées à des problèmes de grande échelle. Tout d'abord, nous proposons une formalisation mathématique de la cohérence géométrique qui joue un rôle essentiel pour une mise en correspondance robuste de caractéristiques visuelles. A partir de cette formalisation, nous en dérivons un algorithme de mise en correspondance qui est algorithmiquement efficace, précise et robuste aux données fortement contaminées et massivement ambiguës. Expérimentalement, l'algorithme proposé se révèle bien adapté à des problèmes de mise en correspondance d'objets déformés, et à des problèmes de mise en correspondance précise à grande échelle pour la calibration de caméras. En s'appuyant sur notre algorithme de mise en correspondance, nous en dérivons ensuite une méthode de recherche d'éléments répétés, comme les fenêtres. Celle-ci s'avère expérimentalement très efficace et robuste face à des conditions difficiles comme la grande variabilité photométrique des éléments répétés et les occlusions. De plus, elle fait également peu d'hallucinations. Enfin, nous proposons des contributions méthodologiques qui exploitent efficacement les résultats de détections d'éléments répétés pour l'analyse de façades par grammaire, qui devient substantiellement plus précise et robuste / For a few years, with the emergence of large image database such as Google Street View, designing efficient, scalable, robust and accurate strategies have now become a critical issue to process very large data, which are also massively contaminated by false positives and massively ambiguous. Indeed, this is of particular interest for property management and diagnosing the health of building fac{c}ades. Scientifically speaking, this issue puts into question the current state-of-the-art methods in fundamental computer vision problems. More particularly, we address the following problems: (1) robust and scalable feature correspondence and (2) façade image parsing. First, we propose a mathematical formalization of the geometry consistency which plays a key role for a robust feature correspondence. From such a formalization, we derive a novel match propagation method. Our method is experimentally shown to be robust, efficient, scalable and accurate for highly contaminated and massively ambiguous sets of correspondences. Our experiments show that our method performs well in deformable object matching and large-scale and accurate matching problem instances arising in camera calibration. We build a novel repetitive pattern search upon our feature correspondence method. Our pattern search method is shown to be effective for accurate window localization and robust to the potentially great appearance variability of repeated patterns and occlusions. Furthermore, our pattern search method makes very few hallucinations. Finally, we propose methodological contributions that exploit our repeated pattern detection results, which results in a substantially more robust and more accurate façade image parsing