A novel method for tracking and counting pedestrians in real-time using a single camera

Osama Masoud; Nikolaos P. Papanikolopoulos

doi:10.1109/25.950328

A novel method for tracking and counting pedestrians in real-time using a single camera

Osama Masoud, Nikolaos P. Papanikolopoulos

Computer Science and Engineering

Research output: Contribution to journal › Article › peer-review

204 Scopus citations

Abstract

This paper presents a real-time system for pedestrian tracking in sequences of grayscale images acquired by a stationary camera. The objective is to integrate this system with a traffic control application such as a pedestrian control scheme at intersections. The proposed approach can also be used to detect and track humans in front of vehicles. Furthermore, the proposed schemes can be employed for the detection of several diverse traffic objects of interest (vehicles, bicycles, etc.) The system outputs the spatio-temporal coordinates of each pedestrian during the period the pedestrian is in the scene. Processing is done at three levels: raw images, blobs, and pedestrians. Blob tracking is modeled as a graph optimization problem. Pedestrians are modeled as rectangular patches with a certain dynamic behavior. Kalman filtering is used to estimate pedestrian parameters. The system was implemented on a Datacube MaxVideo 20 equipped with a Datacube Max860 and was able to achieve a peak performance of over 30 frames per second. Experimental results based on indoor and outdoor scenes demonstrated the system's robustness under many difficult situations such as partial or full occlusions of pedestrians.

Original language	English (US)
Pages (from-to)	1267-1278
Number of pages	12
Journal	IEEE Transactions on Vehicular Technology
Volume	50
Issue number	5
DOIs	https://doi.org/10.1109/25.950328
State	Published - Sep 2001

Bibliographical note

Funding Information:
Manuscript received April 22, 1997; revised January 28, 2001. This work was supported by the Minnesota Department of Transportation through Contracts #71 789-72 983-169 and #71 789-72 447-159, the Center for Transportation Studies through Contract #USDOT/DTRS 93-G-0017-01, the National Science Foundation through Contracts #IRI-9 410 003 and #IRI-9502245, the Department of Energy (Sandia National Laboratories) through Contracts #AC-3752D and #AL-3021, and the McKnight Land-Grant Professorship Program at the University of Minnesota.

Funding Information:
Dr. Masoud is a recipient of the Research Contribution Award from the University of Minnesota, the Rosemount Instrumentation Award from Rosemount Inc., and the Matt Huber Award for Excellence in Transportation Research.

Keywords

Applications
Image sequence analysis
Intelligent transportation systems
Pedestrian control at intersections
Pedestrian tracking
Real-time tracking

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Publisher link

10.1109/25.950328

Find It

Find It at U of M Libraries

Cite this

@article{42deb93b49d049b7a4c2bbbca28e2391,

title = "A novel method for tracking and counting pedestrians in real-time using a single camera",

abstract = "This paper presents a real-time system for pedestrian tracking in sequences of grayscale images acquired by a stationary camera. The objective is to integrate this system with a traffic control application such as a pedestrian control scheme at intersections. The proposed approach can also be used to detect and track humans in front of vehicles. Furthermore, the proposed schemes can be employed for the detection of several diverse traffic objects of interest (vehicles, bicycles, etc.) The system outputs the spatio-temporal coordinates of each pedestrian during the period the pedestrian is in the scene. Processing is done at three levels: raw images, blobs, and pedestrians. Blob tracking is modeled as a graph optimization problem. Pedestrians are modeled as rectangular patches with a certain dynamic behavior. Kalman filtering is used to estimate pedestrian parameters. The system was implemented on a Datacube MaxVideo 20 equipped with a Datacube Max860 and was able to achieve a peak performance of over 30 frames per second. Experimental results based on indoor and outdoor scenes demonstrated the system's robustness under many difficult situations such as partial or full occlusions of pedestrians.",

keywords = "Applications, Image sequence analysis, Intelligent transportation systems, Pedestrian control at intersections, Pedestrian tracking, Real-time tracking",

author = "Osama Masoud and Papanikolopoulos, {Nikolaos P.}",

note = "Funding Information: Manuscript received April 22, 1997; revised January 28, 2001. This work was supported by the Minnesota Department of Transportation through Contracts #71 789-72 983-169 and #71 789-72 447-159, the Center for Transportation Studies through Contract #USDOT/DTRS 93-G-0017-01, the National Science Foundation through Contracts #IRI-9 410 003 and #IRI-9502245, the Department of Energy (Sandia National Laboratories) through Contracts #AC-3752D and #AL-3021, and the McKnight Land-Grant Professorship Program at the University of Minnesota. Funding Information: Dr. Masoud is a recipient of the Research Contribution Award from the University of Minnesota, the Rosemount Instrumentation Award from Rosemount Inc., and the Matt Huber Award for Excellence in Transportation Research.",

year = "2001",

month = sep,

doi = "10.1109/25.950328",

language = "English (US)",

volume = "50",

pages = "1267--1278",

journal = "IEEE Transactions on Vehicular Technology",

issn = "0018-9545",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "5",

}

TY - JOUR

T1 - A novel method for tracking and counting pedestrians in real-time using a single camera

AU - Masoud, Osama

AU - Papanikolopoulos, Nikolaos P.

N1 - Funding Information: Manuscript received April 22, 1997; revised January 28, 2001. This work was supported by the Minnesota Department of Transportation through Contracts #71 789-72 983-169 and #71 789-72 447-159, the Center for Transportation Studies through Contract #USDOT/DTRS 93-G-0017-01, the National Science Foundation through Contracts #IRI-9 410 003 and #IRI-9502245, the Department of Energy (Sandia National Laboratories) through Contracts #AC-3752D and #AL-3021, and the McKnight Land-Grant Professorship Program at the University of Minnesota. Funding Information: Dr. Masoud is a recipient of the Research Contribution Award from the University of Minnesota, the Rosemount Instrumentation Award from Rosemount Inc., and the Matt Huber Award for Excellence in Transportation Research.

PY - 2001/9

Y1 - 2001/9

N2 - This paper presents a real-time system for pedestrian tracking in sequences of grayscale images acquired by a stationary camera. The objective is to integrate this system with a traffic control application such as a pedestrian control scheme at intersections. The proposed approach can also be used to detect and track humans in front of vehicles. Furthermore, the proposed schemes can be employed for the detection of several diverse traffic objects of interest (vehicles, bicycles, etc.) The system outputs the spatio-temporal coordinates of each pedestrian during the period the pedestrian is in the scene. Processing is done at three levels: raw images, blobs, and pedestrians. Blob tracking is modeled as a graph optimization problem. Pedestrians are modeled as rectangular patches with a certain dynamic behavior. Kalman filtering is used to estimate pedestrian parameters. The system was implemented on a Datacube MaxVideo 20 equipped with a Datacube Max860 and was able to achieve a peak performance of over 30 frames per second. Experimental results based on indoor and outdoor scenes demonstrated the system's robustness under many difficult situations such as partial or full occlusions of pedestrians.

AB - This paper presents a real-time system for pedestrian tracking in sequences of grayscale images acquired by a stationary camera. The objective is to integrate this system with a traffic control application such as a pedestrian control scheme at intersections. The proposed approach can also be used to detect and track humans in front of vehicles. Furthermore, the proposed schemes can be employed for the detection of several diverse traffic objects of interest (vehicles, bicycles, etc.) The system outputs the spatio-temporal coordinates of each pedestrian during the period the pedestrian is in the scene. Processing is done at three levels: raw images, blobs, and pedestrians. Blob tracking is modeled as a graph optimization problem. Pedestrians are modeled as rectangular patches with a certain dynamic behavior. Kalman filtering is used to estimate pedestrian parameters. The system was implemented on a Datacube MaxVideo 20 equipped with a Datacube Max860 and was able to achieve a peak performance of over 30 frames per second. Experimental results based on indoor and outdoor scenes demonstrated the system's robustness under many difficult situations such as partial or full occlusions of pedestrians.

KW - Applications

KW - Image sequence analysis

KW - Intelligent transportation systems

KW - Pedestrian control at intersections

KW - Pedestrian tracking

KW - Real-time tracking

UR - http://www.scopus.com/inward/record.url?scp=0035440561&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0035440561&partnerID=8YFLogxK

U2 - 10.1109/25.950328

DO - 10.1109/25.950328

M3 - Article

AN - SCOPUS:0035440561

SN - 0018-9545

VL - 50

SP - 1267

EP - 1278

JO - IEEE Transactions on Vehicular Technology

JF - IEEE Transactions on Vehicular Technology

IS - 5

ER -

A novel method for tracking and counting pedestrians in real-time using a single camera

Abstract

Bibliographical note

Keywords

UN SDGs

Publisher link

Find It

Other files and links

Fingerprint

Cite this