Details
| Original language | English |
|---|---|
| Title of host publication | 18th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL GIS 2010 |
| Pages | 330-339 |
| Number of pages | 10 |
| Publication status | Published - 31 Dec 2010 |
| Event | 18th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL GIS 2010 - San Jose, CA, United States Duration: 2 Nov 2010 → 5 Nov 2010 |
Publication series
| Name | GIS: Proceedings of the ACM International Symposium on Advances in Geographic Information Systems |
|---|
Abstract
In recent times the amount of spatial data being collected by voluntary users, e.g. as part of the OpenStreetMap project, is rapidly increasing. Due to the fact, that everyone can participate in this social collaboration, the completeness and accuracy of the data is very heterogeneous. Although a object catalogue exists as part of the OSM project, users are not restricted which attributes they set and to which detail. Therefore the geometry of a feature is more reliable than its attributes. However, in order to use the data for analysis purposes, knowledge about the semantic contents is of importance. In our work, we propose an approach to classify spatial data solely based on geometric and topologic characteristics. We use both building outlines and road network information. In the first step, topology errors are fixed in order to create a consistent dataset. In the second step, we use unsupervised classification to separate buildings into clusters sharing the same characteristics. Including expert knowledge by visual inspection and interaction, some of these clusters are grouped together and semantically enriched. In the third step, we transfer the derived information from individual buildings to city blocks that are enclosed by edges of the road network. We evaluate our approach with test datasets from OSM and available authoritative datasets. Our results show, that enrichment of user-generated data is possible based on geometric and topologic feature characteristics.
Keywords
- Generalization, Settlement types, Spatial data mining
ASJC Scopus subject areas
- Earth and Planetary Sciences(all)
- Earth-Surface Processes
- Computer Science(all)
- Computer Science Applications
- Mathematics(all)
- Modelling and Simulation
- Computer Science(all)
- Computer Graphics and Computer-Aided Design
- Computer Science(all)
- Information Systems
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
18th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL GIS 2010. 2010. p. 330-339 (GIS: Proceedings of the ACM International Symposium on Advances in Geographic Information Systems).
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - Semi-automatic interpretation of buildings and settlement areas in user-generated spatial data
AU - Werder, Stefan
AU - Kieler, Birgit
AU - Sester, Monika
PY - 2010/12/31
Y1 - 2010/12/31
N2 - In recent times the amount of spatial data being collected by voluntary users, e.g. as part of the OpenStreetMap project, is rapidly increasing. Due to the fact, that everyone can participate in this social collaboration, the completeness and accuracy of the data is very heterogeneous. Although a object catalogue exists as part of the OSM project, users are not restricted which attributes they set and to which detail. Therefore the geometry of a feature is more reliable than its attributes. However, in order to use the data for analysis purposes, knowledge about the semantic contents is of importance. In our work, we propose an approach to classify spatial data solely based on geometric and topologic characteristics. We use both building outlines and road network information. In the first step, topology errors are fixed in order to create a consistent dataset. In the second step, we use unsupervised classification to separate buildings into clusters sharing the same characteristics. Including expert knowledge by visual inspection and interaction, some of these clusters are grouped together and semantically enriched. In the third step, we transfer the derived information from individual buildings to city blocks that are enclosed by edges of the road network. We evaluate our approach with test datasets from OSM and available authoritative datasets. Our results show, that enrichment of user-generated data is possible based on geometric and topologic feature characteristics.
AB - In recent times the amount of spatial data being collected by voluntary users, e.g. as part of the OpenStreetMap project, is rapidly increasing. Due to the fact, that everyone can participate in this social collaboration, the completeness and accuracy of the data is very heterogeneous. Although a object catalogue exists as part of the OSM project, users are not restricted which attributes they set and to which detail. Therefore the geometry of a feature is more reliable than its attributes. However, in order to use the data for analysis purposes, knowledge about the semantic contents is of importance. In our work, we propose an approach to classify spatial data solely based on geometric and topologic characteristics. We use both building outlines and road network information. In the first step, topology errors are fixed in order to create a consistent dataset. In the second step, we use unsupervised classification to separate buildings into clusters sharing the same characteristics. Including expert knowledge by visual inspection and interaction, some of these clusters are grouped together and semantically enriched. In the third step, we transfer the derived information from individual buildings to city blocks that are enclosed by edges of the road network. We evaluate our approach with test datasets from OSM and available authoritative datasets. Our results show, that enrichment of user-generated data is possible based on geometric and topologic feature characteristics.
KW - Generalization
KW - Settlement types
KW - Spatial data mining
UR - http://www.scopus.com/inward/record.url?scp=78650606927&partnerID=8YFLogxK
U2 - 10.1145/1869790.1869836
DO - 10.1145/1869790.1869836
M3 - Conference contribution
AN - SCOPUS:78650606927
SN - 9781450304283
T3 - GIS: Proceedings of the ACM International Symposium on Advances in Geographic Information Systems
SP - 330
EP - 339
BT - 18th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL GIS 2010
T2 - 18th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL GIS 2010
Y2 - 2 November 2010 through 5 November 2010
ER -