Learning traffic patterns at intersections by spectral clustering of motion trajectories

Stefan Atev, Osama Masoud, Nikolaos P Papanikolopoulos

Research output: Chapter in Book/Report/Conference proceedingConference contribution

52 Citations (Scopus)

Abstract

We address the problem of automatically learning the layout of a traffic intersection from trajectories of vehicles obtained by a vision tracking system. We present a similarity measure which is suitable for use with spectral clustering in problems that emphasize spatial distinctions between vehicle trajectories. The robustness of the method to small perturbations and its sensitivity to the choice of parameters are evaluated using real-world data.

Original languageEnglish (US)
Title of host publication2006 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2006
Pages4851-4856
Number of pages6
DOIs
StatePublished - Dec 1 2006
Event2006 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2006 - Beijing, China
Duration: Oct 9 2006Oct 15 2006

Other

Other2006 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2006
CountryChina
CityBeijing
Period10/9/0610/15/06

Fingerprint

Trajectories

Cite this

Atev, S., Masoud, O., & Papanikolopoulos, N. P. (2006). Learning traffic patterns at intersections by spectral clustering of motion trajectories. In 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2006 (pp. 4851-4856). [4059186] https://doi.org/10.1109/IROS.2006.282362

Learning traffic patterns at intersections by spectral clustering of motion trajectories. / Atev, Stefan; Masoud, Osama; Papanikolopoulos, Nikolaos P.

2006 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2006. 2006. p. 4851-4856 4059186.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Atev, S, Masoud, O & Papanikolopoulos, NP 2006, Learning traffic patterns at intersections by spectral clustering of motion trajectories. in 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2006., 4059186, pp. 4851-4856, 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2006, Beijing, China, 10/9/06. https://doi.org/10.1109/IROS.2006.282362
Atev S, Masoud O, Papanikolopoulos NP. Learning traffic patterns at intersections by spectral clustering of motion trajectories. In 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2006. 2006. p. 4851-4856. 4059186 https://doi.org/10.1109/IROS.2006.282362
Atev, Stefan ; Masoud, Osama ; Papanikolopoulos, Nikolaos P. / Learning traffic patterns at intersections by spectral clustering of motion trajectories. 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2006. 2006. pp. 4851-4856
@inproceedings{a0ae989f7f434be48e30cfe5575beaaa,
title = "Learning traffic patterns at intersections by spectral clustering of motion trajectories",
abstract = "We address the problem of automatically learning the layout of a traffic intersection from trajectories of vehicles obtained by a vision tracking system. We present a similarity measure which is suitable for use with spectral clustering in problems that emphasize spatial distinctions between vehicle trajectories. The robustness of the method to small perturbations and its sensitivity to the choice of parameters are evaluated using real-world data.",
author = "Stefan Atev and Osama Masoud and Papanikolopoulos, {Nikolaos P}",
year = "2006",
month = "12",
day = "1",
doi = "10.1109/IROS.2006.282362",
language = "English (US)",
isbn = "142440259X",
pages = "4851--4856",
booktitle = "2006 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2006",

}

TY - GEN

T1 - Learning traffic patterns at intersections by spectral clustering of motion trajectories

AU - Atev, Stefan

AU - Masoud, Osama

AU - Papanikolopoulos, Nikolaos P

PY - 2006/12/1

Y1 - 2006/12/1

N2 - We address the problem of automatically learning the layout of a traffic intersection from trajectories of vehicles obtained by a vision tracking system. We present a similarity measure which is suitable for use with spectral clustering in problems that emphasize spatial distinctions between vehicle trajectories. The robustness of the method to small perturbations and its sensitivity to the choice of parameters are evaluated using real-world data.

AB - We address the problem of automatically learning the layout of a traffic intersection from trajectories of vehicles obtained by a vision tracking system. We present a similarity measure which is suitable for use with spectral clustering in problems that emphasize spatial distinctions between vehicle trajectories. The robustness of the method to small perturbations and its sensitivity to the choice of parameters are evaluated using real-world data.

UR - http://www.scopus.com/inward/record.url?scp=34250630167&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34250630167&partnerID=8YFLogxK

U2 - 10.1109/IROS.2006.282362

DO - 10.1109/IROS.2006.282362

M3 - Conference contribution

SN - 142440259X

SN - 9781424402595

SP - 4851

EP - 4856

BT - 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2006

ER -