Cette thèse présente une étude pour l'interprétation automatique d'images en milieu urbain. Nous proposons une application permettant de reconnaître différents monuments au sein d'images représentant des scènes complexes. La problématique principale est ici de différencier l'information locale extraite des points d'intérêt du bâtiment recherché parmi tous les points extraits de l'image. En effet, la particularité d'une image en milieu urbain vient de la nature publique de la scène. L'objet que l'on cherche à identifier est au milieu de divers autres objets pouvant interférer avec ce dernier. Nous présentons dans une première partie un état de l'art des méthodes de reconnaissance d’images en se concentrant sur l'utilisation de points d'intérêts locaux ainsi que des bases de données pouvant être employées lors des phases d'expérimentation. Nous retenons au final le modèle de sac de mots (BOW) appliqué aux descripteurs locaux SIFT (Scale-Invariant Feature Transform). Dans un second temps nous proposons une approche de classification des données locales faisant intervenir le modèle de machine à vecteurs de support (SVM). L'intérêt présenté dans cette approche proposée est le faible nombre de données requises lors de la phase d'entraînement des modèles. Différentes stratégies d'entraînement et de classification sont exposées ici. Une troisième partie suggère l'ajout d'une correction géométrique de la classification obtenue précédemment. Nous obtenons ainsi une classification non seulement de l'information locale mais aussi visuelle permettant ainsi une cohérence géométrique de la distribution des points d'intérêt. Enfin, un dernier chapitre présente les résultats expérimentaux obtenus, notamment sur des bâtiments de Paris et d'Oxford / This thesis presents a study for an automatic interpretation of urban images. We propose an application for the retrieval of different landmarks in images representing complex scenes. The main issue here is to differentiate the local information extracted from the key-points of the desired building from all the points extracted within the entire image. Indeed, an urban area image is specific by the public nature of the scene depicted. The object sought to be identified is fused within various other objects that can interfere. First of all, we present a state of the art about image recognition and retrieval methods focusing on local points of interest. Databases that can be used during the phases of experimentation are also exposed in a second chapter. We finally retain the Bag of Words modèle applied to local SIFT descriptors. In a second part, we propose a local data classification approach involving the Support Vector Machine model. The interest shown with this proposed approach is the low number of data required during the training phase of the models. Different training and classification strategies are also discussed. A third step suggests the addition of a geometric correction on the classification obtained previously. We thus obtain a classification not only for the local information but also for the visual information allowing thereby a geometric consistency of the points of interest. Finally, a last chapter presents the experimental results obtained, in particular involving images of buildings in Paris and Oxford

This thesis presents an ethnographic account of the everyday meanings and processes associated with the idea of ‘community’ within the London neighbourhood of Kilburn. In policy and popular discourse, community is cast both as somehow able to unite people across difference, and as under threat from the proliferation of difference, which is seen as impeding mutual understanding, cooperation and belonging. Within scholarly writing, ‘community’ is often challenged as too archaic, too rigid or too ambiguous a concept to provide sufficient analytical leverage or to work as a normative ideal. Against this background, my PhD takes a look the neighbourhood of Kilburn, where amidst significant diversity, tropes of community are still widely used. I investigate how residents imagine various forms of community in relation to diversity, as well as the connections and discontinuities between these various imaginings. I draw on 16 months of ethnographic fieldwork, following over a dozen community projects and groups, tracing informal local networks and getting to know residents individually. My ethnography ranges from community cafes, to religious youth groups, to urban ‘gangs’, to government-led urban regeneration projects. Despite the variation in how different individuals imagined ‘community’, there was a shared view of community as a space which facilitated the bridging of difference and the construction of shared moral projects. These spaces did not exist sui generis. Rather they were opened up through the balancing of two traits: fixity and fluidity. Fixity involved defining community in terms of a clearly identifiable and familiar set of boundary markers, which serve to give it an ‘objective’ existence. Fluidity involved suspending this attempt to define community in terms of the familiar, once people were involved, in order to allow for new, shared understandings and values to emerge. The first two chapters unpack this balancing of fixity and fluidity. Chapter 1, traces inclusion and exclusion in a range of community projects, and Chapter 2 looks at tropes of race and ethnicity, examining how such ideas might be treated as simultaneously fixed and fluid. . The two chapters unpack the transformational power of community. Chapter 3 looks at a community centre for young Muslims, as well as at a local community radio station, and argues that community spaces have the potential to foster an ethic of continual openness to difference. Chapter 4 looks at a group of ‘street youth’ and their diverse views of success, and argues that community can act as a collective repository of future potential, allowing community members to transform their ethical trajectory within their own lives. The final two chapters look at contestations over community. Chapter 5 looks at clashing uses of public spaces and argues that such spaces are often read in highly fixed ways, and as lacking the potential for community-like negotiations. Chapter 6 looks at local regeneration projects and contrasts the ways in which community is valued locally, to the ways in which it is valued by state and market actors. The thesis concludes by emphasizing the necessarily plural, dynamic, contested and grounded nature of the idea of community described here.