Title :
Classification of urban structural types with multisource data and structured models
Author :
Montanges, Arnaud Poncet ; Moser, Gabriele ; Taubenbock, Hannes ; Wurm, Michael ; Tuia, Devis
Author_Institution :
EPFL, Lausanne, Switzerland
fDate :
March 30 2015-April 1 2015
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).
Keywords :
data models; feature extraction; geophysics computing; land use planning; pattern classification; remote sensing; solid modelling; support vector machines; 3D city model; SVM classifier; land use distribution; multimodal descriptor extraction; multisource data model; open access vector information; remote sensing data; spatial pattern; spatial relationship; structured prediction model; urban structural type classification; Buildings; Cities and towns; Markov processes; Remote sensing; Solid modeling; Support vector machines; Urban areas;
Conference_Titel :
Urban Remote Sensing Event (JURSE), 2015 Joint
Conference_Location :
Lausanne
DOI :
10.1109/JURSE.2015.7120489
