Practical real-time system for object counting based on optical flow

Jacky Baltes, Amirhossein Hosseinmemar, Joshua Jung, Soroush Sadeghnejad, John Anderson

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper describes a simple and effective system for counting the number of objects that move through a region of interest. In this work, I focus on the problem of counting the number of people that are entering or leaving an event. I design a pedestrian counting system that uses a dense optical flow field to calculate the integral of the optical flow in a video sequence. The only parameter used in the system is the the estimated integral flow for a single person. This parameter can be easily calculated from a short training sequence. Empirical evaluations show that the system is able to provide accurate estimates even for complex sequences in real-time. The described system won 2nd place in the pedestrian counting computer vision competition at the IEA-AIE 2014 conference.

Original languageEnglish
Title of host publicationRobot Intelligence Technology and Applications 3 - Edition of the Selected Papers from the 3rd International Conference on Robot Intelligence Technology and Applications
EditorsWeimin Yang, Hyun Myung, Jong-Hwan Kim, Peter Sincak, Jun Jo
PublisherSpringer Verlag
Pages299-306
Number of pages8
ISBN (Print)9783319168401
DOIs
Publication statusPublished - 2015 Jan 1
Event3rd International Conference on Robot Intelligence Technology and Applications, RiTA 2014 - Beijing, China
Duration: 2014 Nov 62014 Nov 8

Publication series

NameAdvances in Intelligent Systems and Computing
Volume345
ISSN (Print)2194-5357

Other

Other3rd International Conference on Robot Intelligence Technology and Applications, RiTA 2014
CountryChina
CityBeijing
Period14/11/614/11/8

Fingerprint

Optical flows
Real time systems
Computer vision
Flow fields

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Computer Science(all)

Cite this

Baltes, J., Hosseinmemar, A., Jung, J., Sadeghnejad, S., & Anderson, J. (2015). Practical real-time system for object counting based on optical flow. In W. Yang, H. Myung, J-H. Kim, P. Sincak, & J. Jo (Eds.), Robot Intelligence Technology and Applications 3 - Edition of the Selected Papers from the 3rd International Conference on Robot Intelligence Technology and Applications (pp. 299-306). (Advances in Intelligent Systems and Computing; Vol. 345). Springer Verlag. https://doi.org/10.1007/978-3-319-16841-8_28

Practical real-time system for object counting based on optical flow. / Baltes, Jacky; Hosseinmemar, Amirhossein; Jung, Joshua; Sadeghnejad, Soroush; Anderson, John.

Robot Intelligence Technology and Applications 3 - Edition of the Selected Papers from the 3rd International Conference on Robot Intelligence Technology and Applications. ed. / Weimin Yang; Hyun Myung; Jong-Hwan Kim; Peter Sincak; Jun Jo. Springer Verlag, 2015. p. 299-306 (Advances in Intelligent Systems and Computing; Vol. 345).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Baltes, J, Hosseinmemar, A, Jung, J, Sadeghnejad, S & Anderson, J 2015, Practical real-time system for object counting based on optical flow. in W Yang, H Myung, J-H Kim, P Sincak & J Jo (eds), Robot Intelligence Technology and Applications 3 - Edition of the Selected Papers from the 3rd International Conference on Robot Intelligence Technology and Applications. Advances in Intelligent Systems and Computing, vol. 345, Springer Verlag, pp. 299-306, 3rd International Conference on Robot Intelligence Technology and Applications, RiTA 2014, Beijing, China, 14/11/6. https://doi.org/10.1007/978-3-319-16841-8_28
Baltes J, Hosseinmemar A, Jung J, Sadeghnejad S, Anderson J. Practical real-time system for object counting based on optical flow. In Yang W, Myung H, Kim J-H, Sincak P, Jo J, editors, Robot Intelligence Technology and Applications 3 - Edition of the Selected Papers from the 3rd International Conference on Robot Intelligence Technology and Applications. Springer Verlag. 2015. p. 299-306. (Advances in Intelligent Systems and Computing). https://doi.org/10.1007/978-3-319-16841-8_28
Baltes, Jacky ; Hosseinmemar, Amirhossein ; Jung, Joshua ; Sadeghnejad, Soroush ; Anderson, John. / Practical real-time system for object counting based on optical flow. Robot Intelligence Technology and Applications 3 - Edition of the Selected Papers from the 3rd International Conference on Robot Intelligence Technology and Applications. editor / Weimin Yang ; Hyun Myung ; Jong-Hwan Kim ; Peter Sincak ; Jun Jo. Springer Verlag, 2015. pp. 299-306 (Advances in Intelligent Systems and Computing).
@inproceedings{27e9fa217bc340bf9f06ba922109612b,
title = "Practical real-time system for object counting based on optical flow",
abstract = "This paper describes a simple and effective system for counting the number of objects that move through a region of interest. In this work, I focus on the problem of counting the number of people that are entering or leaving an event. I design a pedestrian counting system that uses a dense optical flow field to calculate the integral of the optical flow in a video sequence. The only parameter used in the system is the the estimated integral flow for a single person. This parameter can be easily calculated from a short training sequence. Empirical evaluations show that the system is able to provide accurate estimates even for complex sequences in real-time. The described system won 2nd place in the pedestrian counting computer vision competition at the IEA-AIE 2014 conference.",
author = "Jacky Baltes and Amirhossein Hosseinmemar and Joshua Jung and Soroush Sadeghnejad and John Anderson",
year = "2015",
month = "1",
day = "1",
doi = "10.1007/978-3-319-16841-8_28",
language = "English",
isbn = "9783319168401",
series = "Advances in Intelligent Systems and Computing",
publisher = "Springer Verlag",
pages = "299--306",
editor = "Weimin Yang and Hyun Myung and Jong-Hwan Kim and Peter Sincak and Jun Jo",
booktitle = "Robot Intelligence Technology and Applications 3 - Edition of the Selected Papers from the 3rd International Conference on Robot Intelligence Technology and Applications",

}

TY - GEN

T1 - Practical real-time system for object counting based on optical flow

AU - Baltes, Jacky

AU - Hosseinmemar, Amirhossein

AU - Jung, Joshua

AU - Sadeghnejad, Soroush

AU - Anderson, John

PY - 2015/1/1

Y1 - 2015/1/1

N2 - This paper describes a simple and effective system for counting the number of objects that move through a region of interest. In this work, I focus on the problem of counting the number of people that are entering or leaving an event. I design a pedestrian counting system that uses a dense optical flow field to calculate the integral of the optical flow in a video sequence. The only parameter used in the system is the the estimated integral flow for a single person. This parameter can be easily calculated from a short training sequence. Empirical evaluations show that the system is able to provide accurate estimates even for complex sequences in real-time. The described system won 2nd place in the pedestrian counting computer vision competition at the IEA-AIE 2014 conference.

AB - This paper describes a simple and effective system for counting the number of objects that move through a region of interest. In this work, I focus on the problem of counting the number of people that are entering or leaving an event. I design a pedestrian counting system that uses a dense optical flow field to calculate the integral of the optical flow in a video sequence. The only parameter used in the system is the the estimated integral flow for a single person. This parameter can be easily calculated from a short training sequence. Empirical evaluations show that the system is able to provide accurate estimates even for complex sequences in real-time. The described system won 2nd place in the pedestrian counting computer vision competition at the IEA-AIE 2014 conference.

UR - http://www.scopus.com/inward/record.url?scp=84942645436&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84942645436&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-16841-8_28

DO - 10.1007/978-3-319-16841-8_28

M3 - Conference contribution

AN - SCOPUS:84942645436

SN - 9783319168401

T3 - Advances in Intelligent Systems and Computing

SP - 299

EP - 306

BT - Robot Intelligence Technology and Applications 3 - Edition of the Selected Papers from the 3rd International Conference on Robot Intelligence Technology and Applications

A2 - Yang, Weimin

A2 - Myung, Hyun

A2 - Kim, Jong-Hwan

A2 - Sincak, Peter

A2 - Jo, Jun

PB - Springer Verlag

ER -