Learning traffic patterns at intersections by spectral clustering of motion trajectories

Stefan Atev, Osama Masoud, Nikos Papanikolopoulos

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

62 Scopus citations

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

Publication series

NameIEEE International Conference on Intelligent Robots and Systems

Other

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

Fingerprint Dive into the research topics of 'Learning traffic patterns at intersections by spectral clustering of motion trajectories'. Together they form a unique fingerprint.

Cite this