A Statistical Method for Counting Pedestrians in Crowded Environments

Gwang-Gook LEE; Whoi-Yul KIM

doi:10.1587/transinf.E94.D.1357

A Statistical Method for Counting Pedestrians in Crowded Environments

Gwang-Gook LEE, Whoi-Yul KIM

Full Text Views

0

Share
Cite this

Summary :

We propose a statistical method for counting pedestrians. Previous pedestrian counting methods are not applicable to highly crowded areas because they rely on the detection and tracking of individuals. The performance of detection-and-tracking methods are easily degraded for highly crowded scene in terms of both accuracy and computation time. The proposed method employs feature-based regression in the spatiotemporal domain to count pedestrians. The proposed method is accurate and requires less computation time, even for large crowds, because it does not include the detection and tracking of objects. Our test results from four hours of video sequence obtained from a highly crowded shopping mall, reveal that the proposed method is able to measure human traffic with an accuracy of 97.2% and requires only 14 ms per frame.

Publication: IEICE TRANSACTIONS on Information Vol.E94-D No.6 pp.1357-1361

Publication Date: 2011/06/01

Publicized

Online ISSN: 1745-1361

DOI: 10.1587/transinf.E94.D.1357

Type of Manuscript: LETTER

Category: Image Recognition, Computer Vision

Cite this

Copy

Gwang-Gook LEE, Whoi-Yul KIM, "A Statistical Method for Counting Pedestrians in Crowded Environments" in IEICE TRANSACTIONS on Information, vol. E94-D, no. 6, pp. 1357-1361, June 2011, doi: 10.1587/transinf.E94.D.1357.
Abstract: We propose a statistical method for counting pedestrians. Previous pedestrian counting methods are not applicable to highly crowded areas because they rely on the detection and tracking of individuals. The performance of detection-and-tracking methods are easily degraded for highly crowded scene in terms of both accuracy and computation time. The proposed method employs feature-based regression in the spatiotemporal domain to count pedestrians. The proposed method is accurate and requires less computation time, even for large crowds, because it does not include the detection and tracking of objects. Our test results from four hours of video sequence obtained from a highly crowded shopping mall, reveal that the proposed method is able to measure human traffic with an accuracy of 97.2% and requires only 14 ms per frame.
URL: https://globals.ieice.org/en_transactions/information/10.1587/transinf.E94.D.1357/_p

Copy

@ARTICLE{e94-d_6_1357,
author={Gwang-Gook LEE, Whoi-Yul KIM, },
journal={IEICE TRANSACTIONS on Information},
title={A Statistical Method for Counting Pedestrians in Crowded Environments},
year={2011},
volume={E94-D},
number={6},
pages={1357-1361},
abstract={We propose a statistical method for counting pedestrians. Previous pedestrian counting methods are not applicable to highly crowded areas because they rely on the detection and tracking of individuals. The performance of detection-and-tracking methods are easily degraded for highly crowded scene in terms of both accuracy and computation time. The proposed method employs feature-based regression in the spatiotemporal domain to count pedestrians. The proposed method is accurate and requires less computation time, even for large crowds, because it does not include the detection and tracking of objects. Our test results from four hours of video sequence obtained from a highly crowded shopping mall, reveal that the proposed method is able to measure human traffic with an accuracy of 97.2% and requires only 14 ms per frame.},
keywords={},
doi={10.1587/transinf.E94.D.1357},
ISSN={1745-1361},
month={June},}

Copy

TY - JOUR
TI - A Statistical Method for Counting Pedestrians in Crowded Environments
T2 - IEICE TRANSACTIONS on Information
SP - 1357
EP - 1361
AU - Gwang-Gook LEE
AU - Whoi-Yul KIM
PY - 2011
DO - 10.1587/transinf.E94.D.1357
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E94-D
IS - 6
JA - IEICE TRANSACTIONS on Information
Y1 - June 2011
AB - We propose a statistical method for counting pedestrians. Previous pedestrian counting methods are not applicable to highly crowded areas because they rely on the detection and tracking of individuals. The performance of detection-and-tracking methods are easily degraded for highly crowded scene in terms of both accuracy and computation time. The proposed method employs feature-based regression in the spatiotemporal domain to count pedestrians. The proposed method is accurate and requires less computation time, even for large crowds, because it does not include the detection and tracking of objects. Our test results from four hours of video sequence obtained from a highly crowded shopping mall, reveal that the proposed method is able to measure human traffic with an accuracy of 97.2% and requires only 14 ms per frame.
ER -