Development of a tracking-based system for automated traffic data collection for roundabouts

Hai Dinh, Hua Tang

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Traffic data collection is essential for performance assessment, safety improvement and road planning. While automated traffic data collection for highways is relatively mature, that for roundabouts is more challenging due to more complex traffic scenes, data specifications and vehicle behavior. In this paper, the authors propose an automated traffic data collection system dedicated to roundabout scenes. The proposed system has mainly four steps of processing. First, camera calibration is performed for roundabout traffic scenes with a novel circle-based calibration algorithm. Second, the system uses enhanced Mixture of Gaussian algorithm with shaking removal for video segmentation, which can tolerate repeated camera displacements and background movements. Then, Kalman filtering, Kernel-based tracking and overlap-based optimization are employed to track vehicles while they are occluded and to derive the complete vehicle trajectories. The resulting vehicle trajectory of each individual vehicle gives the position, size, shape and speed of the vehicle at each time moment. Finally, a data mining algorithm is used to automatically extract the interested traffic data from the vehicle trajectories. The overall traffic data collection system has been implemented in software and runs on regular PC. The total processing time for a 3-hour video is currently 6 h. The automated traffic data collection system can significantly reduce cost and improve efficiency compared to manual data collection. The extracted traffic data have been compared to accurate manual measurements for 29 videos recorded on 29 different days, and an accuracy of more than 90% has been achieved.

Original languageEnglish (US)
Pages (from-to)12-23
Number of pages12
JournalJournal of Modern Transportation
Volume25
Issue number1
DOIs
StatePublished - Mar 1 2017

Fingerprint

traffic
Trajectories
video
Cameras
Calibration
Processing
Data mining
performance assessment
PC
Specifications
Planning
road
efficiency
planning
Costs
costs

Keywords

  • Intelligent transport systems
  • Roundabout
  • Traffic data collection
  • Vehicle tracking
  • Vision-based systems

Cite this

Development of a tracking-based system for automated traffic data collection for roundabouts. / Dinh, Hai; Tang, Hua.

In: Journal of Modern Transportation, Vol. 25, No. 1, 01.03.2017, p. 12-23.

Research output: Contribution to journalArticle

@article{557f6110feb849bfb0b635826c76f249,
title = "Development of a tracking-based system for automated traffic data collection for roundabouts",
abstract = "Traffic data collection is essential for performance assessment, safety improvement and road planning. While automated traffic data collection for highways is relatively mature, that for roundabouts is more challenging due to more complex traffic scenes, data specifications and vehicle behavior. In this paper, the authors propose an automated traffic data collection system dedicated to roundabout scenes. The proposed system has mainly four steps of processing. First, camera calibration is performed for roundabout traffic scenes with a novel circle-based calibration algorithm. Second, the system uses enhanced Mixture of Gaussian algorithm with shaking removal for video segmentation, which can tolerate repeated camera displacements and background movements. Then, Kalman filtering, Kernel-based tracking and overlap-based optimization are employed to track vehicles while they are occluded and to derive the complete vehicle trajectories. The resulting vehicle trajectory of each individual vehicle gives the position, size, shape and speed of the vehicle at each time moment. Finally, a data mining algorithm is used to automatically extract the interested traffic data from the vehicle trajectories. The overall traffic data collection system has been implemented in software and runs on regular PC. The total processing time for a 3-hour video is currently 6 h. The automated traffic data collection system can significantly reduce cost and improve efficiency compared to manual data collection. The extracted traffic data have been compared to accurate manual measurements for 29 videos recorded on 29 different days, and an accuracy of more than 90{\%} has been achieved.",
keywords = "Intelligent transport systems, Roundabout, Traffic data collection, Vehicle tracking, Vision-based systems",
author = "Hai Dinh and Hua Tang",
year = "2017",
month = "3",
day = "1",
doi = "10.1007/s40534-017-0124-z",
language = "English (US)",
volume = "25",
pages = "12--23",
journal = "Journal of Modern Transportation",
issn = "2095-087X",
publisher = "Southwest Jiaotong University",
number = "1",

}

TY - JOUR

T1 - Development of a tracking-based system for automated traffic data collection for roundabouts

AU - Dinh, Hai

AU - Tang, Hua

PY - 2017/3/1

Y1 - 2017/3/1

N2 - Traffic data collection is essential for performance assessment, safety improvement and road planning. While automated traffic data collection for highways is relatively mature, that for roundabouts is more challenging due to more complex traffic scenes, data specifications and vehicle behavior. In this paper, the authors propose an automated traffic data collection system dedicated to roundabout scenes. The proposed system has mainly four steps of processing. First, camera calibration is performed for roundabout traffic scenes with a novel circle-based calibration algorithm. Second, the system uses enhanced Mixture of Gaussian algorithm with shaking removal for video segmentation, which can tolerate repeated camera displacements and background movements. Then, Kalman filtering, Kernel-based tracking and overlap-based optimization are employed to track vehicles while they are occluded and to derive the complete vehicle trajectories. The resulting vehicle trajectory of each individual vehicle gives the position, size, shape and speed of the vehicle at each time moment. Finally, a data mining algorithm is used to automatically extract the interested traffic data from the vehicle trajectories. The overall traffic data collection system has been implemented in software and runs on regular PC. The total processing time for a 3-hour video is currently 6 h. The automated traffic data collection system can significantly reduce cost and improve efficiency compared to manual data collection. The extracted traffic data have been compared to accurate manual measurements for 29 videos recorded on 29 different days, and an accuracy of more than 90% has been achieved.

AB - Traffic data collection is essential for performance assessment, safety improvement and road planning. While automated traffic data collection for highways is relatively mature, that for roundabouts is more challenging due to more complex traffic scenes, data specifications and vehicle behavior. In this paper, the authors propose an automated traffic data collection system dedicated to roundabout scenes. The proposed system has mainly four steps of processing. First, camera calibration is performed for roundabout traffic scenes with a novel circle-based calibration algorithm. Second, the system uses enhanced Mixture of Gaussian algorithm with shaking removal for video segmentation, which can tolerate repeated camera displacements and background movements. Then, Kalman filtering, Kernel-based tracking and overlap-based optimization are employed to track vehicles while they are occluded and to derive the complete vehicle trajectories. The resulting vehicle trajectory of each individual vehicle gives the position, size, shape and speed of the vehicle at each time moment. Finally, a data mining algorithm is used to automatically extract the interested traffic data from the vehicle trajectories. The overall traffic data collection system has been implemented in software and runs on regular PC. The total processing time for a 3-hour video is currently 6 h. The automated traffic data collection system can significantly reduce cost and improve efficiency compared to manual data collection. The extracted traffic data have been compared to accurate manual measurements for 29 videos recorded on 29 different days, and an accuracy of more than 90% has been achieved.

KW - Intelligent transport systems

KW - Roundabout

KW - Traffic data collection

KW - Vehicle tracking

KW - Vision-based systems

UR - http://www.scopus.com/inward/record.url?scp=85015726864&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85015726864&partnerID=8YFLogxK

U2 - 10.1007/s40534-017-0124-z

DO - 10.1007/s40534-017-0124-z

M3 - Article

VL - 25

SP - 12

EP - 23

JO - Journal of Modern Transportation

JF - Journal of Modern Transportation

SN - 2095-087X

IS - 1

ER -