Classification of urban structural types with multisource data and structured models

Abstract

In this paper, we study the land use distribution of the city of Munich, Germany. We describe the city as a set of Urban Structural Types (UST) related to the type of spatial patterns occurring within regions composed of 200m side cells. To do so, we resort to a set of multimodal descriptors extracted from remote sensing data, a 3D city model and open access vector information. Based on these descriptors, we train a SVM classifier and apply two structured prediction models to enforce spatial relationships (Markov and Conditional Random fields).