A novel approach for detecting intersections from GPS traces

Xingzhe Xie, Wenzhi Liao, Hamid Aghajan, Peter Veelaert, Wilfried Philips, Ji WU (Editor), Yaqiu JIN (Editor), Jiancheng SHI (Editor)

Research output: Contribution to conferencePaper

1 Citation (Scopus)

Abstract

Intersection detection is a critical aspect for both route planning and path optimization. In literature, intersections are detected mostly using the road users’ turning behaviors. This paper proposes to detect intersections using its definition of connecting at least 3 roads. We first detect the Longest Common Sub-Sequences (LCSS) between each pair of GPS traces using dynamic programming approach. Second, we partition the longest nonconsecutive subsequences into consecutive substrings. The starting and ending points of each common substring are connecting points where two GPS traces split to different directions after they share a series of common locations. At last, we estimate Kernel Density (KD) of the connecting points and find the local maximums on the density map as intersections. Experimental results show better performance of the proposed method.

Conference

Conference2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS)
Abbreviated titleIGARSS 2016
CountryChina
CityBeijing
Period10/07/1615/07/16

Fingerprint

intersections
GPS
road
roads
dynamic programming
planning
partitions
routes
optimization
estimates
method
route planning
detection

Keywords

  • LCSS
  • GPS traces
  • KDE
  • intersection detection
  • road map inference
  • global positioning system

Cite this

Xie, X., Liao, W., Aghajan, H., Veelaert, P., Philips, W., WU, J. (Ed.), ... SHI, J. (Ed.) (2016). A novel approach for detecting intersections from GPS traces. 1816-1819. Paper presented at 2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Beijing, China. https://doi.org/10.1109/IGARSS.2016.7729466
Xie, Xingzhe ; Liao, Wenzhi ; Aghajan, Hamid ; Veelaert, Peter ; Philips, Wilfried ; WU, Ji (Editor) ; JIN, Yaqiu (Editor) ; SHI, Jiancheng (Editor). / A novel approach for detecting intersections from GPS traces. Paper presented at 2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Beijing, China.4 p.
@conference{fc1ae0f65f3c44929109aad5dcd33547,
title = "A novel approach for detecting intersections from GPS traces",
abstract = "Intersection detection is a critical aspect for both route planning and path optimization. In literature, intersections are detected mostly using the road users’ turning behaviors. This paper proposes to detect intersections using its definition of connecting at least 3 roads. We first detect the Longest Common Sub-Sequences (LCSS) between each pair of GPS traces using dynamic programming approach. Second, we partition the longest nonconsecutive subsequences into consecutive substrings. The starting and ending points of each common substring are connecting points where two GPS traces split to different directions after they share a series of common locations. At last, we estimate Kernel Density (KD) of the connecting points and find the local maximums on the density map as intersections. Experimental results show better performance of the proposed method.",
keywords = "LCSS, GPS traces, KDE, intersection detection, road map inference, global positioning system",
author = "Xingzhe Xie and Wenzhi Liao and Hamid Aghajan and Peter Veelaert and Wilfried Philips and Ji WU and Yaqiu JIN and Jiancheng SHI",
year = "2016",
month = "11",
day = "3",
doi = "10.1109/IGARSS.2016.7729466",
language = "English",
pages = "1816--1819",
note = "2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), IGARSS 2016 ; Conference date: 10-07-2016 Through 15-07-2016",

}

Xie, X, Liao, W, Aghajan, H, Veelaert, P, Philips, W, WU, J (ed.), JIN, Y (ed.) & SHI, J (ed.) 2016, 'A novel approach for detecting intersections from GPS traces' Paper presented at 2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Beijing, China, 10/07/16 - 15/07/16, pp. 1816-1819. https://doi.org/10.1109/IGARSS.2016.7729466

A novel approach for detecting intersections from GPS traces. / Xie, Xingzhe; Liao, Wenzhi; Aghajan, Hamid; Veelaert, Peter; Philips, Wilfried; WU, Ji (Editor); JIN, Yaqiu (Editor); SHI, Jiancheng (Editor).

2016. 1816-1819 Paper presented at 2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Beijing, China.

Research output: Contribution to conferencePaper

TY - CONF

T1 - A novel approach for detecting intersections from GPS traces

AU - Xie, Xingzhe

AU - Liao, Wenzhi

AU - Aghajan, Hamid

AU - Veelaert, Peter

AU - Philips, Wilfried

A2 - WU, Ji

A2 - JIN, Yaqiu

A2 - SHI, Jiancheng

PY - 2016/11/3

Y1 - 2016/11/3

N2 - Intersection detection is a critical aspect for both route planning and path optimization. In literature, intersections are detected mostly using the road users’ turning behaviors. This paper proposes to detect intersections using its definition of connecting at least 3 roads. We first detect the Longest Common Sub-Sequences (LCSS) between each pair of GPS traces using dynamic programming approach. Second, we partition the longest nonconsecutive subsequences into consecutive substrings. The starting and ending points of each common substring are connecting points where two GPS traces split to different directions after they share a series of common locations. At last, we estimate Kernel Density (KD) of the connecting points and find the local maximums on the density map as intersections. Experimental results show better performance of the proposed method.

AB - Intersection detection is a critical aspect for both route planning and path optimization. In literature, intersections are detected mostly using the road users’ turning behaviors. This paper proposes to detect intersections using its definition of connecting at least 3 roads. We first detect the Longest Common Sub-Sequences (LCSS) between each pair of GPS traces using dynamic programming approach. Second, we partition the longest nonconsecutive subsequences into consecutive substrings. The starting and ending points of each common substring are connecting points where two GPS traces split to different directions after they share a series of common locations. At last, we estimate Kernel Density (KD) of the connecting points and find the local maximums on the density map as intersections. Experimental results show better performance of the proposed method.

KW - LCSS

KW - GPS traces

KW - KDE

KW - intersection detection

KW - road map inference

KW - global positioning system

UR - http://hdl.handle.net/1854/LU-7181929

U2 - 10.1109/IGARSS.2016.7729466

DO - 10.1109/IGARSS.2016.7729466

M3 - Paper

SP - 1816

EP - 1819

ER -

Xie X, Liao W, Aghajan H, Veelaert P, Philips W, WU J, (ed.) et al. A novel approach for detecting intersections from GPS traces. 2016. Paper presented at 2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Beijing, China. https://doi.org/10.1109/IGARSS.2016.7729466