Abstract

There is an increase in traffic volumes and, as such, a requirement for maximisation of the road capacity. It is crucial that there is awareness of the traffic volumes in order to make the right choices regarding road development. Video registrations and related software to video analysis to measure traffic volumes are increasingly used, but there is limited documentation on the reliability of these. This paper compares manual registrations, treated as ground truth, the hardware independent software RUBA and an on-the-shelf product. While the RUBA software, in general, had a reasonable precision on the direction parallel to the camera direction (8% and 3% deviations, respectively); it was less precise regarding transversal-driving vehicles (23% deviation). The on-the-shelf hardware had a significantly higher deviation regarding the two parallel directions, (35% and 67% deviations, respectively) and a reasonable deviation regarding transversal-driving vehicles (11% deviation). It indicates that on-the-shelf hardware might need further calibration in general.
Original languageEnglish
JournalITS World Congress
Volume6
Number of pages11
ISSNx000-0181
Publication statusPublished - 2018
Event25th ITS World Congress - Quality of Life - Bella Center, Copenhagen, Denmark
Duration: 17 Sep 201821 Sep 2018
https://itsworldcongress.com/

Conference

Conference25th ITS World Congress - Quality of Life
LocationBella Center
CountryDenmark
CityCopenhagen
Period17/09/201821/09/2018
Internet address

Fingerprint

Hardware
Cameras
Calibration

Bibliographical note

Paper presented in SP7 - Data and information

Keywords

  • Video detetion
  • Data quality
  • Traffic data
  • Transport data

Cite this

@inproceedings{6c02a53f96154f2ea77c47ba9c3ca954,
title = "Towards a ground truth of AADT on using video data and tracking software?",
abstract = "There is an increase in traffic volumes and, as such, a requirement for maximisation of the road capacity. It is crucial that there is awareness of the traffic volumes in order to make the right choices regarding road development. Video registrations and related software to video analysis to measure traffic volumes are increasingly used, but there is limited documentation on the reliability of these. This paper compares manual registrations, treated as ground truth, the hardware independent software RUBA and an on-the-shelf product. While the RUBA software, in general, had a reasonable precision on the direction parallel to the camera direction (8{\%} and 3{\%} deviations, respectively); it was less precise regarding transversal-driving vehicles (23{\%} deviation). The on-the-shelf hardware had a significantly higher deviation regarding the two parallel directions, (35{\%} and 67{\%} deviations, respectively) and a reasonable deviation regarding transversal-driving vehicles (11{\%} deviation). It indicates that on-the-shelf hardware might need further calibration in general.",
keywords = "Trafikdata, Videodetektering, Datakvalitet, Transport data, Video detetion, Data quality, Traffic data, Transport data",
author = "Rasmus {\O}hlenschl{\ae}ger and Lahrmann, {Harry Spaab{\ae}k} and Moeslund, {Thomas B.} and Bahnsen, {Chris Holmberg} and Niels Agerholm",
note = "Paper presented in SP7 - Data and information",
year = "2018",
language = "English",
volume = "6",
journal = "ITS World Congress",
issn = "x000-0181",

}

TY - GEN

T1 - Towards a ground truth of AADT on using video data and tracking software?

AU - Øhlenschlæger, Rasmus

AU - Lahrmann, Harry Spaabæk

AU - Moeslund, Thomas B.

AU - Bahnsen, Chris Holmberg

AU - Agerholm, Niels

N1 - Paper presented in SP7 - Data and information

PY - 2018

Y1 - 2018

N2 - There is an increase in traffic volumes and, as such, a requirement for maximisation of the road capacity. It is crucial that there is awareness of the traffic volumes in order to make the right choices regarding road development. Video registrations and related software to video analysis to measure traffic volumes are increasingly used, but there is limited documentation on the reliability of these. This paper compares manual registrations, treated as ground truth, the hardware independent software RUBA and an on-the-shelf product. While the RUBA software, in general, had a reasonable precision on the direction parallel to the camera direction (8% and 3% deviations, respectively); it was less precise regarding transversal-driving vehicles (23% deviation). The on-the-shelf hardware had a significantly higher deviation regarding the two parallel directions, (35% and 67% deviations, respectively) and a reasonable deviation regarding transversal-driving vehicles (11% deviation). It indicates that on-the-shelf hardware might need further calibration in general.

AB - There is an increase in traffic volumes and, as such, a requirement for maximisation of the road capacity. It is crucial that there is awareness of the traffic volumes in order to make the right choices regarding road development. Video registrations and related software to video analysis to measure traffic volumes are increasingly used, but there is limited documentation on the reliability of these. This paper compares manual registrations, treated as ground truth, the hardware independent software RUBA and an on-the-shelf product. While the RUBA software, in general, had a reasonable precision on the direction parallel to the camera direction (8% and 3% deviations, respectively); it was less precise regarding transversal-driving vehicles (23% deviation). The on-the-shelf hardware had a significantly higher deviation regarding the two parallel directions, (35% and 67% deviations, respectively) and a reasonable deviation regarding transversal-driving vehicles (11% deviation). It indicates that on-the-shelf hardware might need further calibration in general.

KW - Trafikdata

KW - Videodetektering

KW - Datakvalitet

KW - Transport data

KW - Video detetion

KW - Data quality

KW - Traffic data

KW - Transport data

M3 - Conference article in Journal

VL - 6

JO - ITS World Congress

JF - ITS World Congress

SN - x000-0181

ER -