Video-based monitoring of pedestrian movements at signalized intersections

Yegor Malinovskiy, Yao Jan Wu, Yinhai Wang

Research output: Research - peer-reviewArticle

  • 23 Citations

Abstract

Pedestrian and cyclist crossing characteristics are important for the design of urban intersections and signalized crossings. Parameters such as waiting time, crossing time, and arrival rate are key variables for describing pedestrian characteristics and improving crossing designs and signal timing plans. Manually collecting such data is often extremely labor intensive. Therefore, an automated computer-vision-based approach is introduced for collecting these parameters in real time with ordinary video cameras. Broadly defined pedestrian objects, including bicyclists and other nonmotorized modes, are extracted by means of the background subtraction technique and tracked through an inherent cost characteristic function in conjunction with an α-β-fllter. The waiting-zone concept introduced helps provide robust pedestrian tracking initialization and parameter extraction. The proposed approach is implemented in a pedestrian tracking (PedTrack) system by using Microsoft Visual C + +. Tested with real video data from three study sites, this system was proved to be effective and about 80% of pedestrian crossing events were successfully detected. PedTrack shows the potential to be a great data collection tool for nonmotorized object movements at intersections.

LanguageEnglish (US)
Pages11-17
Number of pages7
JournalTransportation Research Record
Issue number2073
DOIs
StatePublished - 2008
Externally publishedYes

Fingerprint

Monitoring
Crosswalks
Parameter extraction
Video cameras
Computer vision
Personnel
Costs

ASJC Scopus subject areas

  • Civil and Structural Engineering
  • Mechanical Engineering

Cite this

Video-based monitoring of pedestrian movements at signalized intersections. / Malinovskiy, Yegor; Wu, Yao Jan; Wang, Yinhai.

In: Transportation Research Record, No. 2073, 2008, p. 11-17.

Research output: Research - peer-reviewArticle

@article{24aea64ca5c4403a981cba8ba5a9da79,
title = "Video-based monitoring of pedestrian movements at signalized intersections",
abstract = "Pedestrian and cyclist crossing characteristics are important for the design of urban intersections and signalized crossings. Parameters such as waiting time, crossing time, and arrival rate are key variables for describing pedestrian characteristics and improving crossing designs and signal timing plans. Manually collecting such data is often extremely labor intensive. Therefore, an automated computer-vision-based approach is introduced for collecting these parameters in real time with ordinary video cameras. Broadly defined pedestrian objects, including bicyclists and other nonmotorized modes, are extracted by means of the background subtraction technique and tracked through an inherent cost characteristic function in conjunction with an α-β-fllter. The waiting-zone concept introduced helps provide robust pedestrian tracking initialization and parameter extraction. The proposed approach is implemented in a pedestrian tracking (PedTrack) system by using Microsoft Visual C + +. Tested with real video data from three study sites, this system was proved to be effective and about 80% of pedestrian crossing events were successfully detected. PedTrack shows the potential to be a great data collection tool for nonmotorized object movements at intersections.",
author = "Yegor Malinovskiy and Wu, {Yao Jan} and Yinhai Wang",
year = "2008",
doi = "10.3141/2073-02",
pages = "11--17",
journal = "Transportation Research Record",
issn = "0361-1981",
publisher = "US National Research Council",
number = "2073",

}

TY - JOUR

T1 - Video-based monitoring of pedestrian movements at signalized intersections

AU - Malinovskiy,Yegor

AU - Wu,Yao Jan

AU - Wang,Yinhai

PY - 2008

Y1 - 2008

N2 - Pedestrian and cyclist crossing characteristics are important for the design of urban intersections and signalized crossings. Parameters such as waiting time, crossing time, and arrival rate are key variables for describing pedestrian characteristics and improving crossing designs and signal timing plans. Manually collecting such data is often extremely labor intensive. Therefore, an automated computer-vision-based approach is introduced for collecting these parameters in real time with ordinary video cameras. Broadly defined pedestrian objects, including bicyclists and other nonmotorized modes, are extracted by means of the background subtraction technique and tracked through an inherent cost characteristic function in conjunction with an α-β-fllter. The waiting-zone concept introduced helps provide robust pedestrian tracking initialization and parameter extraction. The proposed approach is implemented in a pedestrian tracking (PedTrack) system by using Microsoft Visual C + +. Tested with real video data from three study sites, this system was proved to be effective and about 80% of pedestrian crossing events were successfully detected. PedTrack shows the potential to be a great data collection tool for nonmotorized object movements at intersections.

AB - Pedestrian and cyclist crossing characteristics are important for the design of urban intersections and signalized crossings. Parameters such as waiting time, crossing time, and arrival rate are key variables for describing pedestrian characteristics and improving crossing designs and signal timing plans. Manually collecting such data is often extremely labor intensive. Therefore, an automated computer-vision-based approach is introduced for collecting these parameters in real time with ordinary video cameras. Broadly defined pedestrian objects, including bicyclists and other nonmotorized modes, are extracted by means of the background subtraction technique and tracked through an inherent cost characteristic function in conjunction with an α-β-fllter. The waiting-zone concept introduced helps provide robust pedestrian tracking initialization and parameter extraction. The proposed approach is implemented in a pedestrian tracking (PedTrack) system by using Microsoft Visual C + +. Tested with real video data from three study sites, this system was proved to be effective and about 80% of pedestrian crossing events were successfully detected. PedTrack shows the potential to be a great data collection tool for nonmotorized object movements at intersections.

UR - http://www.scopus.com/inward/record.url?scp=61349107290&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=61349107290&partnerID=8YFLogxK

U2 - 10.3141/2073-02

DO - 10.3141/2073-02

M3 - Article

SP - 11

EP - 17

JO - Transportation Research Record

T2 - Transportation Research Record

JF - Transportation Research Record

SN - 0361-1981

IS - 2073

ER -