Présentée pour obtenir le grade de docteur de l'École Nationale Supérieure des Télécommunications Spécialité: Signal et Images

From the advent of human civilization on our planet to modern urbanization, road networks have not only provided a means for transportation of logistics but have also helped us to cross cultural boundaries. The properties of road networks vary considerably from one geographical environment to another. The networks pertaining in a satellite image can therefore be used to classify and retrieve such environments. In this work, we have de ned several such environments, and classi ed them using geometrical and topological features computed from the road networks occurring in them. Due to certain limitations of these extraction methods there was a relative failure of network extraction in some urban regions containing narrow and dense road structures. This loss of information was circumvented by segmenting the urban regions and computing a second set of geometrical and topological features from them. The small images forming our database were extracted from images acquired from the SPOT5 satellite with 5m resolution (each image of size 512x512 pixels). The set of geometrical and topological features computed from the road networks and urban regions are used to classify the pre-de ned geographical classes. In order to avoid the burden of feature dimensionality and reduce the classi cation performance, feature selection was performed using Fisher Linear Discriminant (FLD) analysis and an one-vs-rest linear Support Vector Machine (SVM) classi cation was performed on the selected feature set. The impact of spatial resolution and size of images on the feature set have been explored in this work. We took a closer look at the e ect of spatial resolution and size of images on the discriminative power of the feature set to classify the images belonging to the pre-de ned geographical classes. Tests were performed with feature selection by FLD and one-vs-rest linear SVM classi cation on a database with images of 10m resolution. Another test was performed with feature selection by FLD and one-vs-rest linear SVM classi cation on a database with 5m resolution images each of size 256x256 pixels. With the above mentioned approaches, we developed a novel method to classify large satellite images with patches of images each of size 512x512 extracted from them acquired by SPOT5 satellite of 5m resolution. There has been a large amount of work dedicated to the classi cation of large satellite images at pixel level rather than considering image patches of di erent sizes. Classi cation of image patches of di erent sizes from a large satellite image is a novel idea in the sense that the patches considered contain signi cant coverage of a particular type of geographical environment. Road networks and urban region features were computed from these image patches extracted from the large image. A one-vs-rest Gaussian kernel SVM classi cation method was used to classify this large image. The classi cation labels the image patches with the one having the maximum geographical coverage of the area associated in the large image. The large image was mapped into a "region matrix", where each element of the matrix corresponds to a geographical class. In certain cases, this pa st el -0 00 06 27 5, v er si on 1 19 A ug 2 01 0