A vision-based approach to collision prediction at traffic intersections

Stefan Atev, Hemanth Arumugam, Osama Masoud, Ravi Janardan, Nikolaos P Papanikolopoulos

Research output: Contribution to journalArticle

93 Citations (Scopus)

Abstract

Monitoring traffic intersections in real time and predicting possible collisions is an important first step towards building an early collision-warning system. We present a vision-based system addressing this problem and describe the practical adaptations necessary to achieve real-time performance. Innovative low-overhead collision-prediction algorithms (such as the one using the time-as-axis paradigm) are presented. The proposed system was able to perform successfully in real time on videos of quarter-video graphics array (VGA) (320 × 240) resolution under various weather conditions. The errors in target position and dimension estimates in a test video sequence are quantified and several experimental results are presented.

Original languageEnglish (US)
Pages (from-to)416-423
Number of pages8
JournalIEEE Transactions on Intelligent Transportation Systems
Volume6
Issue number4
DOIs
StatePublished - Dec 1 2005

Fingerprint

Alarm systems
Monitoring

Keywords

  • Collision prediction
  • Machine vision
  • Real-time systems
  • Tracking
  • Traffic control (transportation)

Cite this

A vision-based approach to collision prediction at traffic intersections. / Atev, Stefan; Arumugam, Hemanth; Masoud, Osama; Janardan, Ravi; Papanikolopoulos, Nikolaos P.

In: IEEE Transactions on Intelligent Transportation Systems, Vol. 6, No. 4, 01.12.2005, p. 416-423.

Research output: Contribution to journalArticle

@article{8be96165d27e41cc9880862b542d2cdd,
title = "A vision-based approach to collision prediction at traffic intersections",
abstract = "Monitoring traffic intersections in real time and predicting possible collisions is an important first step towards building an early collision-warning system. We present a vision-based system addressing this problem and describe the practical adaptations necessary to achieve real-time performance. Innovative low-overhead collision-prediction algorithms (such as the one using the time-as-axis paradigm) are presented. The proposed system was able to perform successfully in real time on videos of quarter-video graphics array (VGA) (320 × 240) resolution under various weather conditions. The errors in target position and dimension estimates in a test video sequence are quantified and several experimental results are presented.",
keywords = "Collision prediction, Machine vision, Real-time systems, Tracking, Traffic control (transportation)",
author = "Stefan Atev and Hemanth Arumugam and Osama Masoud and Ravi Janardan and Papanikolopoulos, {Nikolaos P}",
year = "2005",
month = "12",
day = "1",
doi = "10.1109/TITS.2005.858786",
language = "English (US)",
volume = "6",
pages = "416--423",
journal = "IEEE Intelligent Transportation Systems Magazine",
issn = "1524-9050",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "4",

}

TY - JOUR

T1 - A vision-based approach to collision prediction at traffic intersections

AU - Atev, Stefan

AU - Arumugam, Hemanth

AU - Masoud, Osama

AU - Janardan, Ravi

AU - Papanikolopoulos, Nikolaos P

PY - 2005/12/1

Y1 - 2005/12/1

N2 - Monitoring traffic intersections in real time and predicting possible collisions is an important first step towards building an early collision-warning system. We present a vision-based system addressing this problem and describe the practical adaptations necessary to achieve real-time performance. Innovative low-overhead collision-prediction algorithms (such as the one using the time-as-axis paradigm) are presented. The proposed system was able to perform successfully in real time on videos of quarter-video graphics array (VGA) (320 × 240) resolution under various weather conditions. The errors in target position and dimension estimates in a test video sequence are quantified and several experimental results are presented.

AB - Monitoring traffic intersections in real time and predicting possible collisions is an important first step towards building an early collision-warning system. We present a vision-based system addressing this problem and describe the practical adaptations necessary to achieve real-time performance. Innovative low-overhead collision-prediction algorithms (such as the one using the time-as-axis paradigm) are presented. The proposed system was able to perform successfully in real time on videos of quarter-video graphics array (VGA) (320 × 240) resolution under various weather conditions. The errors in target position and dimension estimates in a test video sequence are quantified and several experimental results are presented.

KW - Collision prediction

KW - Machine vision

KW - Real-time systems

KW - Tracking

KW - Traffic control (transportation)

UR - http://www.scopus.com/inward/record.url?scp=29544443376&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=29544443376&partnerID=8YFLogxK

U2 - 10.1109/TITS.2005.858786

DO - 10.1109/TITS.2005.858786

M3 - Article

VL - 6

SP - 416

EP - 423

JO - IEEE Intelligent Transportation Systems Magazine

JF - IEEE Intelligent Transportation Systems Magazine

SN - 1524-9050

IS - 4

ER -