Correcting rural building annotations in OpenStreetMap using convolutional neural networks

John E. Vargas-Muñoz, Sylvain Lobry, Alexandre X. Falcão, Devis Tuia

Research output: Contribution to journalArticleAcademicpeer-review

1 Citation (Scopus)

Abstract

Rural building mapping is paramount to support demographic studies and plan actions in response to crisis that affect those areas. Rural building annotations exist in OpenStreetMap (OSM), but their quality and quantity are not sufficient for training models that can create accurate rural building maps. The problems with these annotations essentially fall into three categories: (i) most commonly, many annotations are geometrically misaligned with the updated imagery; (ii) some annotations do not correspond to buildings in the images (they are misannotations or the buildings have been destroyed); and (iii) some annotations are missing for buildings in the images (the buildings were never annotated or were built between subsequent image acquisitions). First, we propose a method based on Markov Random Field (MRF) to align the buildings with their annotations. The method maximizes the correlation between annotations and a building probability map while enforcing that nearby buildings have similar alignment vectors. Second, the annotations with no evidence in the building probability map are removed. Third, we present a method to detect non-annotated buildings with predefined shapes and add their annotation. The proposed methodology shows considerable improvement in accuracy of the OSM annotations for two regions of Tanzania and Zimbabwe, being more accurate than state-of-the-art baselines.
LanguageEnglish
Pages283-293
JournalISPRS Journal of Photogrammetry and Remote Sensing
Volume147
DOIs
Publication statusPublished - Jan 2019

Fingerprint

annotations
Neural networks
action plan
imagery
methodology
Image acquisition
method
Zimbabwe
Tanzania
acquisition

Cite this

@article{114ce066961244e1baa2d26b1cc0b124,
title = "Correcting rural building annotations in OpenStreetMap using convolutional neural networks",
abstract = "Rural building mapping is paramount to support demographic studies and plan actions in response to crisis that affect those areas. Rural building annotations exist in OpenStreetMap (OSM), but their quality and quantity are not sufficient for training models that can create accurate rural building maps. The problems with these annotations essentially fall into three categories: (i) most commonly, many annotations are geometrically misaligned with the updated imagery; (ii) some annotations do not correspond to buildings in the images (they are misannotations or the buildings have been destroyed); and (iii) some annotations are missing for buildings in the images (the buildings were never annotated or were built between subsequent image acquisitions). First, we propose a method based on Markov Random Field (MRF) to align the buildings with their annotations. The method maximizes the correlation between annotations and a building probability map while enforcing that nearby buildings have similar alignment vectors. Second, the annotations with no evidence in the building probability map are removed. Third, we present a method to detect non-annotated buildings with predefined shapes and add their annotation. The proposed methodology shows considerable improvement in accuracy of the OSM annotations for two regions of Tanzania and Zimbabwe, being more accurate than state-of-the-art baselines.",
author = "Vargas-Mu{\~n}oz, {John E.} and Sylvain Lobry and Falc{\~a}o, {Alexandre X.} and Devis Tuia",
year = "2019",
month = "1",
doi = "10.1016/j.isprsjprs.2018.11.010",
language = "English",
volume = "147",
pages = "283--293",
journal = "ISPRS Journal of Photogrammetry and Remote Sensing",
issn = "0924-2716",
publisher = "Elsevier",

}

Correcting rural building annotations in OpenStreetMap using convolutional neural networks. / Vargas-Muñoz, John E.; Lobry, Sylvain; Falcão, Alexandre X.; Tuia, Devis.

In: ISPRS Journal of Photogrammetry and Remote Sensing, Vol. 147, 01.2019, p. 283-293.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - Correcting rural building annotations in OpenStreetMap using convolutional neural networks

AU - Vargas-Muñoz, John E.

AU - Lobry, Sylvain

AU - Falcão, Alexandre X.

AU - Tuia, Devis

PY - 2019/1

Y1 - 2019/1

N2 - Rural building mapping is paramount to support demographic studies and plan actions in response to crisis that affect those areas. Rural building annotations exist in OpenStreetMap (OSM), but their quality and quantity are not sufficient for training models that can create accurate rural building maps. The problems with these annotations essentially fall into three categories: (i) most commonly, many annotations are geometrically misaligned with the updated imagery; (ii) some annotations do not correspond to buildings in the images (they are misannotations or the buildings have been destroyed); and (iii) some annotations are missing for buildings in the images (the buildings were never annotated or were built between subsequent image acquisitions). First, we propose a method based on Markov Random Field (MRF) to align the buildings with their annotations. The method maximizes the correlation between annotations and a building probability map while enforcing that nearby buildings have similar alignment vectors. Second, the annotations with no evidence in the building probability map are removed. Third, we present a method to detect non-annotated buildings with predefined shapes and add their annotation. The proposed methodology shows considerable improvement in accuracy of the OSM annotations for two regions of Tanzania and Zimbabwe, being more accurate than state-of-the-art baselines.

AB - Rural building mapping is paramount to support demographic studies and plan actions in response to crisis that affect those areas. Rural building annotations exist in OpenStreetMap (OSM), but their quality and quantity are not sufficient for training models that can create accurate rural building maps. The problems with these annotations essentially fall into three categories: (i) most commonly, many annotations are geometrically misaligned with the updated imagery; (ii) some annotations do not correspond to buildings in the images (they are misannotations or the buildings have been destroyed); and (iii) some annotations are missing for buildings in the images (the buildings were never annotated or were built between subsequent image acquisitions). First, we propose a method based on Markov Random Field (MRF) to align the buildings with their annotations. The method maximizes the correlation between annotations and a building probability map while enforcing that nearby buildings have similar alignment vectors. Second, the annotations with no evidence in the building probability map are removed. Third, we present a method to detect non-annotated buildings with predefined shapes and add their annotation. The proposed methodology shows considerable improvement in accuracy of the OSM annotations for two regions of Tanzania and Zimbabwe, being more accurate than state-of-the-art baselines.

U2 - 10.1016/j.isprsjprs.2018.11.010

DO - 10.1016/j.isprsjprs.2018.11.010

M3 - Article

VL - 147

SP - 283

EP - 293

JO - ISPRS Journal of Photogrammetry and Remote Sensing

T2 - ISPRS Journal of Photogrammetry and Remote Sensing

JF - ISPRS Journal of Photogrammetry and Remote Sensing

SN - 0924-2716

ER -