You are on page 1of 18

Exploratory analysis of OpenStreetMap for land

use classification

Jacinto Estima and Marco Painho


Jacinto.estima@gmail.com; painho@isegi.unl.pt
www.isegi.unl.pt

2nd International Workshop on Crowdsourced and Volunteered Geographic Information (GEOCROWD) 2013
21st International Conference on Advances in Geographic Information Systems (ACM SIGSPATIAL GIS 2013)
November 5 - 8, 2013 — Orlando, Florida, USA

05-11-2013 Nome e/ou Título e/ou Outros 1


Agenda
• Introduction
• Objective
• Related work:
– Volunteered Geographic Information
– VGI Initiatives (examples)
– Research using VGI
• Material and Methods
• Results and Discussion
• Conclusions

GEOCROWD 2013 • ACM SIGSPATIAL GIS 2013 2


05-11-2013 November 5 - 8, 2013 — Orlando, Florida, USA
Introduction
• VGI has become exponentially available over the web in the last
years
• An inventory made by Elwood in 2009 identified 99 VGI initiatives
running
• Research has already been conducted in some areas:
– emergency response
– Navigation
– Land Use/Cover validation
– etc.
• To our best knowledge, no study using OSM in the production of
Land Use/Cover databases exists

GEOCROWD 2013 • ACM SIGSPATIAL GIS 2013 3


05-11-2013 November 5 - 8, 2013 — Orlando, Florida, USA
Objective
• Objective:
– Conduct an exploratory analysis of the OSM database for land
use/cover production, using Corine Land Cover (CLC) as
reference data
• Contributions:
– Establish a tentative to relate both nomenclatures
– Evaluate the quality of OSM land use classification over
continental Portugal taking CLC as reference data, to assess if it
can be used as ground truth for LULC validation in the future

GEOCROWD 2013 • ACM SIGSPATIAL GIS 2013 4


05-11-2013 November 5 - 8, 2013 — Orlando, Florida, USA
Volunteered Geographic Information
• “Spatial” type of User Generated Content (UGC) contributed by
volunteers
• Has been exponentially growing since 2005:
– Evolution of important technologies (Web 2.0, GPS, etc.)
– Willingness of private citizens to contribute
• 70% of the initiatives counted by Elwood started after 2005 (when
Google Maps was launched)
• Issues:
– heterogeneity, absence of formal structures and quality control
procedures, absence of metadata
• Advantages:
– Quantity, temporal coverage, and the local knowledge of its contributors

GEOCROWD 2013 • ACM SIGSPATIAL GIS 2013 5


05-11-2013 November 5 - 8, 2013 — Orlando, Florida, USA
VGI initiatives (examples)
• HD Traffic TM from TomTom (real-time traffic data)
• OpenStreetMap (OSM) (aims to provide free geographic data for
free to anyone)
• Wikimapia (based in Google Maps)
• Flickr (Kisilevich downloaded a total of 86,314,466 geotagged
photos in 2010)
• Map Tube (“Place to put maps”)
• “Did you feel it” (USGS initiative for earthquake mapping)
• Etc.

GEOCROWD 2013 • ACM SIGSPATIAL GIS 2013 6


05-11-2013 November 5 - 8, 2013 — Orlando, Florida, USA
Research using VGI
• Fritz et al. developed a plattform that uses a global network of volunteers to
help improving the quality of global land cover maps
• Leung and Newsam (2010) conducted some experiments to automatically
derive maps of what-is-where from large collections of georeferenced
photos (they achieved around 75% of classification accuracy)
• Estima and Painho (2013) explored the possibility of using Flickr photos as
a source of truth data to help in the accuracy assessment phase of land
use/cover production
• OSM:
– Over et al. (2010) studied, for the first time, the possibility of generating
interactive 3D City Models based on free geo-data available from OSM, and
public domain height information provided by the Shuttle Radar Topography
Mission
– Al-Bakri and Fairbairn (2012) used OSM and Ordnance Survey (OS) to give one
step towards the integration of geospatial datasets from varied sources (focus on
semantic and structural similarities)
GEOCROWD 2013 • ACM SIGSPATIAL GIS 2013 7
05-11-2013 November 5 - 8, 2013 — Orlando, Florida, USA
Study area and Datasets (1)
• Study area
– The study area is Continental Portugal
– The land cover is mainly composed by agricultural and forest
areas (around 95%)
• Datasets
– OSM database (only polygon datasets were used to quantify
areas):
• Buildings, Landuse and Natural Areas datasets
– Corine Land Cover (CLC) database for the CLC2006 inventory -
version 16 (04/2012) – vector format
– Portuguese official administrative boundaries database - “Carta
Administrativa Oficial de Portugal” (CAOP) – vector format
GEOCROWD 2013 • ACM SIGSPATIAL GIS 2013 8
05-11-2013 November 5 - 8, 2013 — Orlando, Florida, USA
a) b
)
c)

Study area and Datasets (2)


• CLC nomenclature
• OSM nomenclature available from http://
wiki.openstreetmap.org/wiki/Map_Features

• Assumptions:
– We assume the time difference between CLC and OSM
databases (2006 for CLC and 2013 for OSM) would not
represent a major issue, Considering a yearly average change
value of land cover in Europe of 0.23%

GEOCROWD 2013 • ACM SIGSPATIAL GIS 2013 9


05-11-2013 November 5 - 8, 2013 — Orlando, Florida, USA
Methods
1. Analysis of OSM datasets (nomenclature and area of
coverage)
2. Analysis and establishment of a relationship between
the nomenclatures (OSM and CLC)
3. Analysis of the coverage of each OSM class using CLC
level 1 as reference
4. Analysis of the matching degree between related
classes
5. Analysis of the OSM spatial distribution

GEOCROWD 2013 • ACM SIGSPATIAL GIS 2013 10


05-11-2013 November 5 - 8, 2013 — Orlando, Florida, USA
1. Analysis of OSM datasets
Areas of coverage of OSM datasets Existing classification differences (overlapping areas)
Dataset Area (Ha) Country Natural areas Landuse Buildings Area
coverage (%) dataset dataset dataset (Ha)
Natural areas 140006.95 1.57% Forest Military None 5.24
Landuse 144350.23 1.62% Residential Reservoir_cover 0.02
Buildings 7057.61 0.08% Recreation_ground Hospital 0.25
Total 3.27% Park Commercial None 0.01
Overlapping areas - 0.03% Residential Museum 0.39
Total 3.24% Cafe 0.05
Chapel 0.01
Church 0.00
House 0.03
Library 0.03
Museum 0.08
Public 0.02
Public_building 0.37
Restaurant 0.03
Roof 0.01
Theatre 0.03
Toilets 0.00
Yes 0.01

GEOCROWD 2013 • ACM SIGSPATIAL GIS 2013 11


05-11-2013 November 5 - 8, 2013 — Orlando, Florida, USA
2. OSM and CLC relationship nomenclatures
CLC classes
OSM classes
Level 3 Level 2 Level 1
Landuse dataset
Abutters 111-112-121 11-12 1
Allotments 242 24 2
Basin 512 51 5
Beach 331 33 3
Brownfield 133 13 1
Cemetery 111-112 11 1
Commercial 121 12 1
Conservation 313-312-311 31 3
Construction 133 13 1
Farm 222-231-241-242 22-23-24 2
Farmland 222-231-241-242 22-23-24 2
Farmyard 222-231-241-242 22-23-24 2
Field ? ? ?
Garages 122 12 1
Garden 142 14 1
Grass 231-321 23-32 2-3
GEOCROWD 2013 • ACM SIGSPATIAL GIS 2013 12
05-11-2013 November 5 - 8, 2013 — Orlando, Florida, USA
3. Coverage analysis of OSM datasets
1. Gave to each OSM class got its correspondent CLC level1
2. Dissolve by CLC level1 class
3. Removed overlapping areas (not deducted) – 1.39% of the total OSM area

Coverage areas from CLC level 1 and OSM


Area from CLC Area from OSM Class coverage
CLC classes
(Ha) (Ha) (%)
unclassified --- 7036.75 ---
1 309716.89 62407.48 20.15
2 4199177.27 34309.93 0.82
3 4259642.22 98536.62 2.31
4 28777.11 64.59 0.22
5 110906.66 82621.61 74.50
GEOCROWD 2013 • ACM SIGSPATIAL GIS 2013 13
05-11-2013 November 5 - 8, 2013 — Orlando, Florida, USA
4. Matching degree between classes (areas)
Confusion matrix of CLC vs. OSM classifications

Classification accuracy
Classification
Class
accuracy (%)
1 84.3%
2 46.6%
3 83.5%
4 1.2%
5 99.5%
Global 76.7%
GEOCROWD 2013 • ACM SIGSPATIAL GIS 2013 14
05-11-2013 November 5 - 8, 2013 — Orlando, Florida, USA
5. OSM spatial distribution
Spatial distribution of
OSM classified areas
over continental
Portugal

Distribution of classes’
coverage areas by
continental
Portuguese districts
GEOCROWD 2013 • ACM SIGSPATIAL GIS 2013 15
05-11-2013 November 5 - 8, 2013 — Orlando, Florida, USA
Conclusions
• Tentative to relate OSM and CLC
• Determined the accuracy of classification of OSM
polygon features based on CLC level 1 classes
• Analyzed OSM spatial distribution
• Results show that might be worth to study OSM with the
more detailed CLC levels 1 and 2
• Classification accuracy of 76.7% (23.3% need further
investigation):
– Not all the classes have similar accuracy
– We believe that it might be used, for instance, as another source
of ground truth data in the validation process of LULC databases
GEOCROWD 2013 • ACM SIGSPATIAL GIS 2013 16
05-11-2013 November 5 - 8, 2013 — Orlando, Florida, USA
Conclusions (2)
• Further investigation needed:
– Correspondence between OSM and the 3 levels of CLC
– Ways to avoid “not_known” class and classes without
description
– The cause of discrepancies between both classifications (errors
or just different views?)
– Understand the real effect of conflicting overlapping areas
(1.39%) (level of contributors trust to decide which one is
correct?)

GEOCROWD 2013 • ACM SIGSPATIAL GIS 2013 17


05-11-2013 November 5 - 8, 2013 — Orlando, Florida, USA
Thank you for your attention

Jacinto Estima and Marco Painho


Jacinto.estima@gmail.com; painho@isegi.unl.pt
www.isegi.unl.pt

2nd International Workshop on Crowdsourced and Volunteered Geographic Information (GEOCROWD) 2013
21st International Conference on Advances in Geographic Information Systems (ACM SIGSPATIAL GIS 2013)
November 5 - 8, 2013 — Orlando, Florida, USA

05-11-2013 Nome e/ou Título e/ou Outros 18

You might also like