umu.sePublikationer
Ändra sökning
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
OSM POI Analyzer: A Platform for Assessing Position of POIs in OpenStreetMap
Dept. of Infrastructure Engineering, University of Melbourne, Parkville, Australia.ORCID-id: 0000-0002-2395-3184
Dept. of Infrastructure Engineering, University of Melbourne, Parkville, Australia.ORCID-id: 0000-0002-4256-3173
Dept. of Infrastructure Engineering, University of Melbourne, Parkville, Australia.
Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.ORCID-id: 0000-0001-5629-0981
2017 (Engelska)Ingår i: ISPRS Geospatial Week 2017 / [ed] D. Li, J. Gong, B. Yang, H. Wu, L. Wu, Z. Gui, X. Cheng, H. Wu, S. Li, R. Lindenbergh, J. Boehm, M. Rutzinger, W. Yao, M. Weinmann, Z. Kang, K. Khoshelham, M. Peter, L. Díaz-Vilariño, W. Shi, B. Lu, H. Abdulmuttalib, M. R. Delavar, T. Balz, B. Osmanoglu, F. Rocca, U. Sörgel, J. Zhang, P. Li, S. Du, L. Zhao, X. Lin, K. Qin, C. Kang, X. Li, C. Chen, R. Li, G. Qiao, H. Wu, and C. Heipke, 2017, Vol. XLII-2/W7, s. 497-504Konferensbidrag, Publicerat paper (Refereegranskat)
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.

Ort, förlag, år, upplaga, sidor
2017. Vol. XLII-2/W7, s. 497-504
Serie
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences (ISPRS Archives), ISSN 1682-1750, E-ISSN 2194-9034 ; XLII-2/W7
Nyckelord [en]
OpenStreetMap, Spatial Data Quality, Co-existence analysis, Co-location Pattern, Spatial Association Rule, POI
Nationell ämneskategori
Datavetenskap (datalogi) Annan data- och informationsvetenskap Multidisciplinär geovetenskap
Forskningsämne
data- och systemvetenskap
Identifikatorer
URN: urn:nbn:se:umu:diva-142170DOI: 10.5194/isprs-archives-XLII-2-W7-497-2017OAI: oai:DiVA.org:umu-142170DiVA, id: diva2:1160005
Konferens
ISPRS Geospatial Week 2017, 18–22 September 2017, Wuhan, China
Tillgänglig från: 2017-11-24 Skapad: 2017-11-24 Senast uppdaterad: 2018-11-12Bibliografiskt granskad

Open Access i DiVA

fulltext(1107 kB)89 nedladdningar
Filinformation
Filnamn FULLTEXT01.pdfFilstorlek 1107 kBChecksumma SHA-512
2248cc25499fa0b7fbe99c26e1e0204eee9a79666805b07a17f07f20f27565ceaf1d21389e6c7dfb26ba97cdeda95d069dbdffabdb24d6b539d21640b4c46c08
Typ fulltextMimetyp application/pdf

Övriga länkar

Förlagets fulltext

Personposter BETA

Richter, Kai-Florian

Sök vidare i DiVA

Av författaren/redaktören
Kashian, AlirezaRajabifard, AbbasRichter, Kai-Florian
Av organisationen
Institutionen för datavetenskap
Datavetenskap (datalogi)Annan data- och informationsvetenskapMultidisciplinär geovetenskap

Sök vidare utanför DiVA

GoogleGoogle Scholar
Totalt: 89 nedladdningar
Antalet nedladdningar är summan av nedladdningar för alla fulltexter. Det kan inkludera t.ex tidigare versioner som nu inte längre är tillgängliga.

doi
urn-nbn

Altmetricpoäng

doi
urn-nbn
Totalt: 374 träffar
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf