Fine-grained landuse characterization using ground-based pictures: a deep learning solution based on globally available data

Research output: Contribution to journalArticleAcademicpeer-review

2 Citations (Scopus)

Abstract

We study the problem of landuse characterization at the urban-object level using deep learning algorithms. Traditionally, this task is performed by surveys or manual photo interpretation, which are expensive and difficult to update regularly. We seek to characterize usages at the single object level and to differentiate classes such as educational institutes, hospitals and religious places by visual cues contained in side-view pictures from Google Street View (GSV). These pictures provide geo-referenced information not only about the material composition of the objects but also about their actual usage, which otherwise is difficult to capture using other classical sources of data such as aerial imagery. Since the GSV database is regularly updated, this allows to consequently update the landuse maps, at lower costs than those of authoritative surveys. Because every urban-object is imaged from a number of viewpoints with street-level pictures, we propose a deep-learning based architecture that accepts arbitrary number of GSV pictures to predict the fine-grained landuse classes at the object level. These classes are taken from OpenStreetMap. A quantitative evaluation of the area of Île-de-France, France shows that our model outperforms other deep learning-based methods, making it a suitable alternative to manual landuse characterization.
LanguageEnglish
Number of pages20
JournalInternational Journal of Geographical Information Science
DOIs
Publication statusE-pub ahead of print - 18 Nov 2018

Fingerprint

learning
search engine
visual cue
France
imagery
Learning algorithms
Antennas
cost
Deep learning
Chemical analysis
interpretation
Costs
costs
evaluation
hospital
material
method
geo-referenced information

Cite this

@article{ff09df1a24ba4a4d94b835cac10b79bd,
title = "Fine-grained landuse characterization using ground-based pictures: a deep learning solution based on globally available data",
abstract = "We study the problem of landuse characterization at the urban-object level using deep learning algorithms. Traditionally, this task is performed by surveys or manual photo interpretation, which are expensive and difficult to update regularly. We seek to characterize usages at the single object level and to differentiate classes such as educational institutes, hospitals and religious places by visual cues contained in side-view pictures from Google Street View (GSV). These pictures provide geo-referenced information not only about the material composition of the objects but also about their actual usage, which otherwise is difficult to capture using other classical sources of data such as aerial imagery. Since the GSV database is regularly updated, this allows to consequently update the landuse maps, at lower costs than those of authoritative surveys. Because every urban-object is imaged from a number of viewpoints with street-level pictures, we propose a deep-learning based architecture that accepts arbitrary number of GSV pictures to predict the fine-grained landuse classes at the object level. These classes are taken from OpenStreetMap. A quantitative evaluation of the area of {\^I}le-de-France, France shows that our model outperforms other deep learning-based methods, making it a suitable alternative to manual landuse characterization.",
author = "Shivangi Srivastava and {Vargas Mu{\~n}oz}, {John E.} and Sylvain Lobry and Devis Tuia",
year = "2018",
month = "11",
day = "18",
doi = "10.1080/13658816.2018.1542698",
language = "English",
journal = "International Journal of Geographical Information Science",
issn = "1365-8816",
publisher = "Taylor & Francis",

}

TY - JOUR

T1 - Fine-grained landuse characterization using ground-based pictures: a deep learning solution based on globally available data

AU - Srivastava, Shivangi

AU - Vargas Muñoz, John E.

AU - Lobry, Sylvain

AU - Tuia, Devis

PY - 2018/11/18

Y1 - 2018/11/18

N2 - We study the problem of landuse characterization at the urban-object level using deep learning algorithms. Traditionally, this task is performed by surveys or manual photo interpretation, which are expensive and difficult to update regularly. We seek to characterize usages at the single object level and to differentiate classes such as educational institutes, hospitals and religious places by visual cues contained in side-view pictures from Google Street View (GSV). These pictures provide geo-referenced information not only about the material composition of the objects but also about their actual usage, which otherwise is difficult to capture using other classical sources of data such as aerial imagery. Since the GSV database is regularly updated, this allows to consequently update the landuse maps, at lower costs than those of authoritative surveys. Because every urban-object is imaged from a number of viewpoints with street-level pictures, we propose a deep-learning based architecture that accepts arbitrary number of GSV pictures to predict the fine-grained landuse classes at the object level. These classes are taken from OpenStreetMap. A quantitative evaluation of the area of Île-de-France, France shows that our model outperforms other deep learning-based methods, making it a suitable alternative to manual landuse characterization.

AB - We study the problem of landuse characterization at the urban-object level using deep learning algorithms. Traditionally, this task is performed by surveys or manual photo interpretation, which are expensive and difficult to update regularly. We seek to characterize usages at the single object level and to differentiate classes such as educational institutes, hospitals and religious places by visual cues contained in side-view pictures from Google Street View (GSV). These pictures provide geo-referenced information not only about the material composition of the objects but also about their actual usage, which otherwise is difficult to capture using other classical sources of data such as aerial imagery. Since the GSV database is regularly updated, this allows to consequently update the landuse maps, at lower costs than those of authoritative surveys. Because every urban-object is imaged from a number of viewpoints with street-level pictures, we propose a deep-learning based architecture that accepts arbitrary number of GSV pictures to predict the fine-grained landuse classes at the object level. These classes are taken from OpenStreetMap. A quantitative evaluation of the area of Île-de-France, France shows that our model outperforms other deep learning-based methods, making it a suitable alternative to manual landuse characterization.

U2 - 10.1080/13658816.2018.1542698

DO - 10.1080/13658816.2018.1542698

M3 - Article

JO - International Journal of Geographical Information Science

T2 - International Journal of Geographical Information Science

JF - International Journal of Geographical Information Science

SN - 1365-8816

ER -