Ghent University Academic Bibliography

Advanced

Road intersection detection through finding common sub-tracks between pairwise GNSS traces

Xingzhe Xie and Wilfried Philips UGent (2017) ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION. 6.
abstract
This paper proposes a novel approach to detect road intersections from GNSS traces. Different from the existing methods of detecting intersections directly from the road users’ turning behaviors, the proposed method detects intersections indirectly from common sub-tracks shared by different traces. We first compute the local distance matrix for each pair of traces. Second, we apply image processing techniques to find all “sub-paths” in the matrix, which represents good alignment between local common sub-tracks. Lastly, we identify the intersections from the endpoints of the common sub-tracks through Kernel Density Estimation (KDE). Experimental results show that the proposed method outperforms the traditional turning point-based methods in terms of the F-score, and our previous connecting point-based method in terms of computational efficiency.
Please use this url to cite or link to this publication:
author
organization
year
type
journalArticle (original)
publication status
in press
keyword
intersection detection, road map inference, image processing, KDE, GNSS traces
journal title
ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION
volume
6
article number
311
pages
14 pages
publisher
MDPI
Web of Science type
Article
ISSN
2220-9964
DOI
10.3390/ijgi6100311
language
English
UGent publication?
yes
classification
A1
id
8534665
handle
http://hdl.handle.net/1854/LU-8534665
alternative location
http://www.mdpi.com/2220-9964/6/10/311
date created
2017-10-18 11:19:51
date last changed
2017-10-20 11:15:52
@article{8534665,
  abstract     = {This paper proposes a novel approach to detect road intersections from GNSS traces.
Different from the existing methods of detecting intersections directly from the road users{\textquoteright} turning
behaviors, the proposed method detects intersections indirectly from common sub-tracks shared
by different traces. We first compute the local distance matrix for each pair of traces. Second, we apply
image processing techniques to find all {\textquotedblleft}sub-paths{\textquotedblright} in the matrix, which represents good alignment
between local common sub-tracks. Lastly, we identify the intersections from the endpoints of the
common sub-tracks through Kernel Density Estimation (KDE). Experimental results show that the
proposed method outperforms the traditional turning point-based methods in terms of the F-score,
and our previous connecting point-based method in terms of computational efficiency.},
  articleno    = {311},
  author       = {Xie, Xingzhe and Philips, Wilfried},
  issn         = {2220-9964},
  journal      = {ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION},
  keyword      = {intersection detection,road map inference,image processing,KDE,GNSS traces},
  language     = {eng},
  pages        = {14},
  publisher    = {MDPI},
  title        = {Road intersection detection through finding common sub-tracks between pairwise GNSS traces},
  url          = {http://dx.doi.org/10.3390/ijgi6100311},
  volume       = {6},
  year         = {2017},
}

Chicago
Xie, Xingzhe, and Wilfried Philips. 2017. “Road Intersection Detection Through Finding Common Sub-tracks Between Pairwise GNSS Traces.” Isprs International Journal of Geo-information 6.
APA
Xie, X., & Philips, W. (2017). Road intersection detection through finding common sub-tracks between pairwise GNSS traces. ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION, 6.
Vancouver
1.
Xie X, Philips W. Road intersection detection through finding common sub-tracks between pairwise GNSS traces. ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION. MDPI; 2017;6.
MLA
Xie, Xingzhe, and Wilfried Philips. “Road Intersection Detection Through Finding Common Sub-tracks Between Pairwise GNSS Traces.” ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION 6 (2017): n. pag. Print.