Computer vision algorithms for intersection monitoring

Harini Veeraraghavan, Osama Masoud, Nikolaos P Papanikolopoulos

Research output: Contribution to journalArticle

134 Citations (Scopus)

Abstract

The goal of this project is to monitor activities at traffic intersections for detecting/predicting situations that may lead to accidents. Some of the key elements for robust intersection monitoring are camera calibration, motion tracking, incident detection, etc. In this paper, we consider the motion-tracking problem. A multilevel tracking approach using Kalman filter is presented for tracking vehicles and pedestrians at intersections. The approach combines low-level image-based blob tracking with high-level Kalman filtering for position and shape estimation. An intermediate occlusion-reasoning module serves the purpose of detecting occlusions and filtering relevant measurements. Motion segmentation is performed by using a mixture of Gaussian models which helps us achieve fairly reliable tracking in a variety of complex outdoor scenes. A visualization module is also presented. This module is very useful for visualizing the results of the tracker and serves as a platform for the incident detection module.

Original languageEnglish (US)
Pages (from-to)78-89
Number of pages12
JournalIEEE Transactions on Intelligent Transportation Systems
Volume4
Issue number2
DOIs
StatePublished - Jun 1 2003

Fingerprint

Computer vision
Monitoring
Kalman filters
Accidents
Visualization
Cameras
Calibration

Cite this

Computer vision algorithms for intersection monitoring. / Veeraraghavan, Harini; Masoud, Osama; Papanikolopoulos, Nikolaos P.

In: IEEE Transactions on Intelligent Transportation Systems, Vol. 4, No. 2, 01.06.2003, p. 78-89.

Research output: Contribution to journalArticle

@article{cc9352098c5c416e9bcb0888223eef03,
title = "Computer vision algorithms for intersection monitoring",
abstract = "The goal of this project is to monitor activities at traffic intersections for detecting/predicting situations that may lead to accidents. Some of the key elements for robust intersection monitoring are camera calibration, motion tracking, incident detection, etc. In this paper, we consider the motion-tracking problem. A multilevel tracking approach using Kalman filter is presented for tracking vehicles and pedestrians at intersections. The approach combines low-level image-based blob tracking with high-level Kalman filtering for position and shape estimation. An intermediate occlusion-reasoning module serves the purpose of detecting occlusions and filtering relevant measurements. Motion segmentation is performed by using a mixture of Gaussian models which helps us achieve fairly reliable tracking in a variety of complex outdoor scenes. A visualization module is also presented. This module is very useful for visualizing the results of the tracker and serves as a platform for the incident detection module.",
author = "Harini Veeraraghavan and Osama Masoud and Papanikolopoulos, {Nikolaos P}",
year = "2003",
month = "6",
day = "1",
doi = "10.1109/TITS.2003.821212",
language = "English (US)",
volume = "4",
pages = "78--89",
journal = "IEEE Intelligent Transportation Systems Magazine",
issn = "1524-9050",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "2",

}

TY - JOUR

T1 - Computer vision algorithms for intersection monitoring

AU - Veeraraghavan, Harini

AU - Masoud, Osama

AU - Papanikolopoulos, Nikolaos P

PY - 2003/6/1

Y1 - 2003/6/1

N2 - The goal of this project is to monitor activities at traffic intersections for detecting/predicting situations that may lead to accidents. Some of the key elements for robust intersection monitoring are camera calibration, motion tracking, incident detection, etc. In this paper, we consider the motion-tracking problem. A multilevel tracking approach using Kalman filter is presented for tracking vehicles and pedestrians at intersections. The approach combines low-level image-based blob tracking with high-level Kalman filtering for position and shape estimation. An intermediate occlusion-reasoning module serves the purpose of detecting occlusions and filtering relevant measurements. Motion segmentation is performed by using a mixture of Gaussian models which helps us achieve fairly reliable tracking in a variety of complex outdoor scenes. A visualization module is also presented. This module is very useful for visualizing the results of the tracker and serves as a platform for the incident detection module.

AB - The goal of this project is to monitor activities at traffic intersections for detecting/predicting situations that may lead to accidents. Some of the key elements for robust intersection monitoring are camera calibration, motion tracking, incident detection, etc. In this paper, we consider the motion-tracking problem. A multilevel tracking approach using Kalman filter is presented for tracking vehicles and pedestrians at intersections. The approach combines low-level image-based blob tracking with high-level Kalman filtering for position and shape estimation. An intermediate occlusion-reasoning module serves the purpose of detecting occlusions and filtering relevant measurements. Motion segmentation is performed by using a mixture of Gaussian models which helps us achieve fairly reliable tracking in a variety of complex outdoor scenes. A visualization module is also presented. This module is very useful for visualizing the results of the tracker and serves as a platform for the incident detection module.

UR - http://www.scopus.com/inward/record.url?scp=0742322397&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0742322397&partnerID=8YFLogxK

U2 - 10.1109/TITS.2003.821212

DO - 10.1109/TITS.2003.821212

M3 - Article

VL - 4

SP - 78

EP - 89

JO - IEEE Intelligent Transportation Systems Magazine

JF - IEEE Intelligent Transportation Systems Magazine

SN - 1524-9050

IS - 2

ER -