Details
| Original language | English |
|---|---|
| Article number | 4255 |
| Journal | Applied Sciences (Switzerland) |
| Volume | 9 |
| Issue number | 20 |
| Publication status | Published - 11 Oct 2019 |
Abstract
This work proposes a fast and straightforward method, called natural point correspondences (NaPoCo), for the extraction of road segment shapes from trajectories of vehicles. The algorithm can be expressed with 20 lines of code in Python and can be used as a baseline for further extensions or as a heuristic initialization for more complex algorithms. In this paper, we evaluate the performance of the proposed method. We show that (1) the order of the points in a trajectory can be used to cluster points among the trajectories for road segment shape extraction and (2) that preprocessing using polygonal approximation improves the results of the approach. Furthermore, we show based on "averaging GPS segments" competition results, that the algorithm despite its simplicity and low computational complexity achieves state-of-the-art performance on the challenge dataset, which is composed of data from several cities and countries.
Keywords
- Averaging, GPS, Road network, Segments, Trajectory
ASJC Scopus subject areas
- Materials Science(all)
- General Materials Science
- Physics and Astronomy(all)
- Instrumentation
- Engineering(all)
- General Engineering
- Chemical Engineering(all)
- Process Chemistry and Technology
- Computer Science(all)
- Computer Science Applications
- Chemical Engineering(all)
- Fluid Flow and Transfer Processes
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: Applied Sciences (Switzerland), Vol. 9, No. 20, 4255, 11.10.2019.
Research output: Contribution to journal › Article › Research › peer review
}
TY - JOUR
T1 - Estimating road segments using natural point correspondences of GPS trajectories
AU - Leichter, Artem
AU - Werner, Martin
N1 - Funding information: The publication of this article was funded by the Open Access fund of Leibniz Universität Hannover. This work was partially funded by the Federal Ministry of Education and Research, Germany (Bundesministerium für Bildung und Forschung, Förderkennzeichen 01IS17076). We gratefully acknowledge this support.
PY - 2019/10/11
Y1 - 2019/10/11
N2 - This work proposes a fast and straightforward method, called natural point correspondences (NaPoCo), for the extraction of road segment shapes from trajectories of vehicles. The algorithm can be expressed with 20 lines of code in Python and can be used as a baseline for further extensions or as a heuristic initialization for more complex algorithms. In this paper, we evaluate the performance of the proposed method. We show that (1) the order of the points in a trajectory can be used to cluster points among the trajectories for road segment shape extraction and (2) that preprocessing using polygonal approximation improves the results of the approach. Furthermore, we show based on "averaging GPS segments" competition results, that the algorithm despite its simplicity and low computational complexity achieves state-of-the-art performance on the challenge dataset, which is composed of data from several cities and countries.
AB - This work proposes a fast and straightforward method, called natural point correspondences (NaPoCo), for the extraction of road segment shapes from trajectories of vehicles. The algorithm can be expressed with 20 lines of code in Python and can be used as a baseline for further extensions or as a heuristic initialization for more complex algorithms. In this paper, we evaluate the performance of the proposed method. We show that (1) the order of the points in a trajectory can be used to cluster points among the trajectories for road segment shape extraction and (2) that preprocessing using polygonal approximation improves the results of the approach. Furthermore, we show based on "averaging GPS segments" competition results, that the algorithm despite its simplicity and low computational complexity achieves state-of-the-art performance on the challenge dataset, which is composed of data from several cities and countries.
KW - Averaging
KW - GPS
KW - Road network
KW - Segments
KW - Trajectory
UR - http://www.scopus.com/inward/record.url?scp=85074212626&partnerID=8YFLogxK
U2 - 10.15488/9273
DO - 10.15488/9273
M3 - Article
AN - SCOPUS:85074212626
VL - 9
JO - Applied Sciences (Switzerland)
JF - Applied Sciences (Switzerland)
SN - 2076-3417
IS - 20
M1 - 4255
ER -