Details
| Original language | English |
|---|---|
| Title of host publication | 17th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL GIS 2009 |
| Pages | 500-503 |
| Number of pages | 4 |
| Publication status | Published - 4 Nov 2009 |
| Event | 17th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL GIS 2009 - Seattle, United States Duration: 4 Nov 2009 → 6 Nov 2009 |
Publication series
| Name | GIS: Proceedings of the ACM International Symposium on Advances in Geographic Information Systems |
|---|
Abstract
Future driver assistance systems will require highly accurate positioning. One way to achieve this is by using on-board sensors to measure the relative location of landmarks for which the absolute coordinates are known. This paper investigates the use of mobile laser scanning for the fully automatic generation of such landmark maps. Starting from a 21.7 km scanned trajectory with a total of 70.7 million scanned points, we extract pole-like structures, such as signposts, traffic and street lights, and tree trunks. The location of all those structures then forms our landmark map to be used later by onboard systems for positioning. The focus of this paper is on the extraction and quality assessment of the features, including a description of different types of error sources and approaches to reduce false positives among the extracted poles.
Keywords
- Autonomous vehicles, Driver assistance systems, Feature extraction, Landmark based maps, Localization, Mobile laser scanning
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
17th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL GIS 2009. 2009. p. 500-503 (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 - Quality assessment of automatically generated feature maps for future driver assistance systems
AU - Hofmann, Sabine
AU - Brenner, Claus
PY - 2009/11/4
Y1 - 2009/11/4
N2 - Future driver assistance systems will require highly accurate positioning. One way to achieve this is by using on-board sensors to measure the relative location of landmarks for which the absolute coordinates are known. This paper investigates the use of mobile laser scanning for the fully automatic generation of such landmark maps. Starting from a 21.7 km scanned trajectory with a total of 70.7 million scanned points, we extract pole-like structures, such as signposts, traffic and street lights, and tree trunks. The location of all those structures then forms our landmark map to be used later by onboard systems for positioning. The focus of this paper is on the extraction and quality assessment of the features, including a description of different types of error sources and approaches to reduce false positives among the extracted poles.
AB - Future driver assistance systems will require highly accurate positioning. One way to achieve this is by using on-board sensors to measure the relative location of landmarks for which the absolute coordinates are known. This paper investigates the use of mobile laser scanning for the fully automatic generation of such landmark maps. Starting from a 21.7 km scanned trajectory with a total of 70.7 million scanned points, we extract pole-like structures, such as signposts, traffic and street lights, and tree trunks. The location of all those structures then forms our landmark map to be used later by onboard systems for positioning. The focus of this paper is on the extraction and quality assessment of the features, including a description of different types of error sources and approaches to reduce false positives among the extracted poles.
KW - Autonomous vehicles
KW - Driver assistance systems
KW - Feature extraction
KW - Landmark based maps
KW - Localization
KW - Mobile laser scanning
UR - http://www.scopus.com/inward/record.url?scp=74049139513&partnerID=8YFLogxK
U2 - 10.1145/1653771.1653854
DO - 10.1145/1653771.1653854
M3 - Conference contribution
AN - SCOPUS:74049139513
SN - 9781605586496
T3 - GIS: Proceedings of the ACM International Symposium on Advances in Geographic Information Systems
SP - 500
EP - 503
BT - 17th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL GIS 2009
T2 - 17th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL GIS 2009
Y2 - 4 November 2009 through 6 November 2009
ER -