Publication detail

Visual Analysis of Vehicle Trajectories for Determining Cross-Sectional Load Density

JURÁNEK, R. ŠPAŇHEL, J. SOCHOR, J. HEROUT, A. NOVÁK, J.

Original Title

Visual Analysis of Vehicle Trajectories for Determining Cross-Sectional Load Density

English Title

Visual Analysis of Vehicle Trajectories for Determining Cross-Sectional Load Density

Type

journal article in Scopus

Language

en

Original Abstract

The goal of this work was to analyze the behavior of drivers on third class roads with and without horizontal lane marking. The roads have low traffic volume, and therefore a conventional short-term study would not be able to provide enough data. We used recording devices for long-term (weeks) recording of the traffic and designed a system for analyzing the trajectories of the vehicles by means of computer vision. We collected a dataset at 6 distinct locations, containing 1 010 hours of day-time video. In this dataset, we tracked over 12 000 cars and analyzed their trajectories. The results show that the selected approach is functional and provides information that would be difficult to mine otherwise. After application of the horizontal markings, the drivers slowed down and shifted slightly towards the outer side of the curve.

English abstract

The goal of this work was to analyze the behavior of drivers on third class roads with and without horizontal lane marking. The roads have low traffic volume, and therefore a conventional short-term study would not be able to provide enough data. We used recording devices for long-term (weeks) recording of the traffic and designed a system for analyzing the trajectories of the vehicles by means of computer vision. We collected a dataset at 6 distinct locations, containing 1 010 hours of day-time video. In this dataset, we tracked over 12 000 cars and analyzed their trajectories. The results show that the selected approach is functional and provides information that would be difficult to mine otherwise. After application of the horizontal markings, the drivers slowed down and shifted slightly towards the outer side of the curve.

Keywords

Road Safety, Lane Marking, Trajectory Analysis, Computer Vision, Vehicle Tracking

Released

02.08.2019

Publisher

Palacky University

Location

NEUVEDEN

ISBN

1802-9876

Periodical

Transactions on Transport Sciences - online version

Year of study

10

Number

1

State

CZ

Pages from

50

Pages to

57

Pages count

8

URL

Documents

BibTex


@article{BUT159979,
  author="Roman {Juránek} and Jakub {Špaňhel} and Jakub {Sochor} and Adam {Herout}",
  title="Visual Analysis of Vehicle Trajectories for Determining Cross-Sectional Load Density",
  annote="The goal of this work was to analyze the behavior of drivers on third class roads
with and without horizontal lane marking. The roads have low traffic volume, and
therefore a conventional short-term study would not be able to provide enough
data. We used recording devices for long-term (weeks) recording of the traffic
and designed a system for analyzing the trajectories of the vehicles by means of
computer vision. We collected a dataset at 6 distinct locations, containing 1 010
hours of day-time video. In this dataset, we tracked over 12 000 cars and
analyzed their trajectories. The results show that the selected approach is
functional and provides information that would be difficult to mine otherwise.
After application of the horizontal markings, the drivers slowed down and shifted
slightly towards the outer side of the curve.",
  address="Palacky University",
  booktitle="Transactions on Transport Sciences",
  chapter="159979",
  doi="10.5507/tots.2019.002",
  edition="NEUVEDEN",
  howpublished="online",
  institution="Palacky University",
  number="1",
  volume="10",
  year="2019",
  month="august",
  pages="50--57",
  publisher="Palacky University",
  type="journal article in Scopus"
}