Classification of urban structural types with multisource data and structured models

Arnaud Poncet Montanges; Gabriele Moser; Hannes Taubenböck; Michael Wurm; Devis Tuia

doi:10.1109/JURSE.2015.7120489

Classification of urban structural types with multisource data and structured models

Arnaud Poncet Montanges, Gabriele Moser, Hannes Taubenböck, Michael Wurm, Devis Tuia

Research output: Chapter in Book/Report/Conference proceeding › Conference paper

16 Citations (Scopus)

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).

Original language	English
Title of host publication	2015 Joint Urban Remote Sensing Event, JURSE 2015
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Print)	9781479966523
DOIs	https://doi.org/10.1109/JURSE.2015.7120489
Publication status	Published - 9 Jun 2015
Externally published	Yes
Event	2015 Joint Urban Remote Sensing Event, JURSE 2015 - Lausanne, Switzerland Duration: 30 Mar 2015 → 1 Apr 2015

Publication series

Name	2015 Joint Urban Remote Sensing Event, JURSE 2015

Conference

Conference	2015 Joint Urban Remote Sensing Event, JURSE 2015
Country	Switzerland
City	Lausanne
Period	30/03/15 → 1/04/15

Access to Document

10.1109/JURSE.2015.7120489

Fingerprint Dive into the research topics of 'Classification of urban structural types with multisource data and structured models'. Together they form a unique fingerprint.

Cite this

Montanges, A. P., Moser, G., Taubenböck, H., Wurm, M., & Tuia, D. (2015). Classification of urban structural types with multisource data and structured models. In 2015 Joint Urban Remote Sensing Event, JURSE 2015 [7120489] (2015 Joint Urban Remote Sensing Event, JURSE 2015). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/JURSE.2015.7120489

@inproceedings{2f25f8bdf11a43b48301dc42034a2292,

title = "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).",

author = "Montanges, {Arnaud Poncet} and Gabriele Moser and Hannes Taubenb{\"o}ck and Michael Wurm and Devis Tuia",

year = "2015",

month = jun,

day = "9",

doi = "10.1109/JURSE.2015.7120489",

language = "English",

isbn = "9781479966523",

series = "2015 Joint Urban Remote Sensing Event, JURSE 2015",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2015 Joint Urban Remote Sensing Event, JURSE 2015",

note = "2015 Joint Urban Remote Sensing Event, JURSE 2015 ; Conference date: 30-03-2015 Through 01-04-2015",

}

Montanges, AP, Moser, G, Taubenböck, H, Wurm, M & Tuia, D 2015, Classification of urban structural types with multisource data and structured models. in 2015 Joint Urban Remote Sensing Event, JURSE 2015., 7120489, 2015 Joint Urban Remote Sensing Event, JURSE 2015, Institute of Electrical and Electronics Engineers Inc., 2015 Joint Urban Remote Sensing Event, JURSE 2015, Lausanne, Switzerland, 30/03/15. https://doi.org/10.1109/JURSE.2015.7120489

Classification of urban structural types with multisource data and structured models. / Montanges, Arnaud Poncet; Moser, Gabriele; Taubenböck, Hannes; Wurm, Michael; Tuia, Devis.

2015 Joint Urban Remote Sensing Event, JURSE 2015. Institute of Electrical and Electronics Engineers Inc., 2015. 7120489 (2015 Joint Urban Remote Sensing Event, JURSE 2015).

Research output: Chapter in Book/Report/Conference proceeding › Conference paper

TY - GEN

T1 - Classification of urban structural types with multisource data and structured models

AU - Montanges, Arnaud Poncet

AU - Moser, Gabriele

AU - Taubenböck, Hannes

AU - Wurm, Michael

AU - Tuia, Devis

PY - 2015/6/9

Y1 - 2015/6/9

N2 - 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).

AB - 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).

U2 - 10.1109/JURSE.2015.7120489

DO - 10.1109/JURSE.2015.7120489

M3 - Conference paper

AN - SCOPUS:84938826532

SN - 9781479966523

T3 - 2015 Joint Urban Remote Sensing Event, JURSE 2015

BT - 2015 Joint Urban Remote Sensing Event, JURSE 2015

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2015 Joint Urban Remote Sensing Event, JURSE 2015

Y2 - 30 March 2015 through 1 April 2015

ER -