Classification of urban structural types (UST) using multiple data sources and spatial priors

Abstract

Remote sensing and geographic information science offer many possibilities in terms of availability of diverse data. Some products like land cover layers or digital elevation models can be extracted from imagery and enable the realization of 3D city models. Starting from these morphological and geographical sources, an approach is proposed to extract information about urban structure types (UST), i.e. types of urban habitat at the neighborhoodscale. We propose an effective processing chain to describe UST : from the different data sources, we extract spectral and spatial indices and use them as features in a machine learning process to classify these urban structural types using support vector machine classication (SVM). Moreover, Markov Random Fields (MRF) are used to take into account the spatial distribution of the classe and increase the spatial consistency. This study focuses on the city of Munich and uses as different data sources the land cover data, the 3D city model, spectral images from LandSat TM 8 and OpenStreetMap (OSM) vector data to characterize UST. The main hypothesis is that we can discriminate among urban structural types by using land cover information, spectral properties and 3D structure: in other words, that an industrial area will not have the same structure nor the same properties as a residential or an agricultural area. The proposed processing chain enables to predict with a precision of 70% the 11 UST. This opens possibilities to describe the urban footprint of the city, to detect the key areas for urban planification and to better understand the city dynamics.