Crowd-Sourcing Approach of Building Ground Truth Database for Global Urban Area Mapping
1. Crowd-Sourcing Approach of
Building Ground Truth Database for
Global Urban Area Mapping
Hiroyuki Miyazaki1, Koki Iwao2, and Ryosuke Shibasaki1
1Center for Spatial Information Science, The University of Tokyo
2National Institute of Advanced Industrial Science and Technology
2. Needs on Global Urban Area Maps
• Satellite-based urban area map enables
– Monitoring without dependence on administrative district
– comparing urban forming internationally
– Disaster prevention & hazard assessment of broad areas
Monitoring urban expansion
Angel et al. (2005)
Grid-based population estimation
Bhaduri et al. (2002)
Consistent definition and representation
of urban area over countries and regions.
Consistent geographical unit across
countries and over time.
3. Sufficient ground truth data?
• IGBP Land Cover Validation Confidence Sites
(Muchoney et al., 1999)
– # of urban sites: 44 / 966
• Global Land Cover Ground Truth database (Tateishi,
2002)
– # of urban sites: 3 / 333 (Asia)
• Degree Confluence Project (Iwao et al., 2006)
– # of urban sites: 11 / 749 (Eurasia)
• Too scarce for mapping urban area globally
4. Campaigns of visual interpretations?
• To complete validating 55412 cities (> 1000 pop.) by visual
interpretations with achievable jobs for a person,
– have enough manpower and software licenses?
– associate thousands of file names and job assignments?
– send thousands of reference images to the operators?
– organize hundreds of spreadsheets from the operators?
– assures the data not to be leaked from the operators?
– frequent joins and leaves are flexibly possible?
Conveniences are varying by the person and by the time.
5. Crowd sourcing
• A method to create & collect massive data by an
undefined large group of people or community, the
“crowd”, over the Internet.
OpenStreetMap: tracing roads by GPS
and visual interpretation of photos
Geo-wiki: validating
disagreements of global land
cover maps using Google Earth
Degree Confluence Project:
posting ground information at
the integer lat-lon grids.
6. Web-based Geographical Information Systems
• Web Map Service (WMS)
– The web service for generating and transferring
map images through WWW.
– Standardized by Open Geospatial Consortium*
*an international organization of standardization of geographical data
• Web Feature Service (WFS)
– The web service for generating and transferring
map vector data through WWW.
– Standardized by Open Geospatial Consortium
• Expensive costs for the new software? No!
7. Power of FOSS4G
• FOSS4G: Free and Open Source Software for Geospatial
• MapServer
– A server software of WMS
• TinyOWS
– A server software of WFS
• PostgreSQL & PostGIS
– Relational database management system with geospatial
data extension
• Geographical Data Abstraction Library (GDAL)
– A library for interoperability of file formats
– Users don’t need to mind GeoTiff, Erdas, flat binary and
others.
8. System design & implementation
Satellite
image archive
(Thousands of
GeoTiffs)
Web
Mapping
Service
(MapServer)
User
interface
Reference images
of requested extent
Request for
reference images
with authentication
Web
Feature
Service
(TinyOWS)
Interpreted ground
information Ground truth
database
(PostgreSQL &
PostGIS)
Catalog
index
Record with
geometry
WWW
Display
Interpret
Crowd of the world
Securely protected
from the interpreters
and the Internet
Other map
service
Operator
9. An interface for trained GIS users
ASTER satellite
image archive
Request of the
reference image
Reference image
for the extent
Posting
interpreted data
with geometry
Ground truth
database
Quantum GIS: a free and open-source GIS software, which
enables intuitive geospatial operation like ArcGIS and other
commercial GIS software.
Google Maps window Delineate urban
and non-urban
boundary
10. Web-browser interface for non-experts
ASTER Global
Urban Area Map
Ground
assessment
database
DEMO
Coarse-resolution
urban area maps
(urban and built-up
class of MCD12Q1)
Requests
for maps &
reference
images
Google Maps Maps to be assessed
Overview Zoom-in Assessments
Posting the
assessment
11. Features of the system
• Securely restricted data access: administrator may easily
restrict accesses to the reference images by ways of
authentication commonly used within WWW. Frequent leave-
and-joins are flexibly durable.
• On-the-fly processing: no need for image composition,
merging & extracting for a specific extent, and converting
image format. MapServer will do those for every request of
reference images.
• Already organized: no need to manually re-organize the
database. TinyOWS and PostgreSQL records the posts with
systematic order.
• Extensibility: easily customizable interface for specific cases.
• Interoperability: friendly with other web mapping services
(e.g. overlaying with Google Maps, Microsoft Bing, and
OpenStreetMap)
12. Conclusion
• Proposed a method of building ground truth
database with a crowd sourcing approach.
• Developed a crowd-sourcing system for visual
interpretations over the Internet.
• Implemented the system with WMS & WFS of
FOSS4G (Free & Open Source Software for
Geospatial).
13. Future works
• Creating & collecting ground data of urban
area mapping by the system (under operation)
• Scientific evaluation of the developed data
(accuracy, precision, and etc.)
• Investigating psychological factors of the
motivations of the “crowd”
– Financial rewards, competitive game design, etc.