umu.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
OSM POI Analyzer: A Platform for Assessing Position of POIs in OpenStreetMap
the University of Melbourne. (Department of Infrastructure Engineering)ORCID iD: 0000-0002-2395-3184
the University of Melbourne. (Department of Infrastructure Engineering)ORCID iD: 0000-0002-4256-3173
the University of Melbourne. (Department of Infrastructure Engineering)
Umeå University, Faculty of Science and Technology, Department of Computing Science.ORCID iD: 0000-0001-5629-0981
2017 (English)Conference paper, Published paper (Refereed)
Abstract [en]

 In recent years, more and increased participation in Volunteered Geographical Information (VGI) projects provides enough data coverage for most places around the world for ordinary mapping and navigation purposes, however, the positional credibility of contributed data becomes more and more important to bring a long-term trust in VGI data. Today, it is hard to draw a definite traditional boundary between the authoritative map producers and the public map consumers and we observe that more and more volunteers are joining crowdsourcing activities for collecting geodata, which might result in higher rates of man-made mistakes in open map projects such as OpenStreetMap. While there are some methods for monitoring the accuracy and consistency of the created data, there is still a lack of advanced systems to automatically discover misplaced objects on the map. One feature type which is contributed daily to OSM is Point of Interest (POI). In order to understand how likely it is that a newly added POI represents a genuine real-world feature scientific means to calculate a probability of such a POI existing at that specific position is needed. This paper reports on a new analytic tool which dives into OSM data and finds co-existence patterns between one specific POI and its surrounding objects such as roads, parks and buildings. The platform uses a distance-based classification technique to find relationships among objects and tries to identify the high-frequency association patterns among each category of objects. Using such method, for each newly added POI, a probabilistic score would be generated, and the low scored POIs can be highlighted for editors for a manual check. The same scoring method can be used for existing registered POIs to check if they are located correctly. For a sample study, this paper reports on the evaluation of 800 pre-registered ATMs in Paris with associated scores to understand how outliers and fake entries could be detected automatically.

Place, publisher, year, edition, pages
2017. Vol. XLII-2/W7, p. 497-504
Series
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Keywords [en]
OpenStreetMap, Spatial Data Quality, Co-existence analysis, Co-location Pattern, Spatial Association Rule, POI
National Category
Computer Sciences Other Computer and Information Science Geosciences, Multidisciplinary
Research subject
Computer and Information Science
Identifiers
URN: urn:nbn:se:umu:diva-142170DOI: 10.5194/isprs-archives-XLII-2-W7-497-2017OAI: oai:DiVA.org:umu-142170DiVA, id: diva2:1160005
Conference
ISPRS Geospatial Week 2017
Available from: 2017-11-24 Created: 2017-11-24 Last updated: 2018-06-09

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full texthttps://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLII-2-W7/497/2017/

Authority records BETA

Kashian, AlirezaRajabifard, AbbasRichter, Kai-Florian

Search in DiVA

By author/editor
Kashian, AlirezaRajabifard, AbbasRichter, Kai-Florian
By organisation
Department of Computing Science
Computer SciencesOther Computer and Information ScienceGeosciences, Multidisciplinary

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 4 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf