An approach to detect crowd panic behavior using flow-based feature

Yu Hao, Zhijie Xu, Jing Wang, Ying Liu, Jiulun Fan

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

7 Citations (Scopus)

Abstract

With the purpose of achieving automated detection of crowd abnormal behavior in public, this paper discusses the category of typical crowd and individual behaviors and their patterns. Popular image features for abnormal behavior detection are also introduced, including global flow based features such as optical flow, and local spatio-temporal based features such as Spatio-temporal Volume (STV). After reviewing some relative abnormal behavior detection algorithms, a brand-new approach to detect crowd panic behavior has been proposed based on optical flow features in this paper. During the experiments, all panic behaviors are successfully detected. In the end, the future work to improve current approach has been discussed.

Original languageEnglish
Title of host publication22nd International Conference on Automation and Computing
Subtitle of host publicationTackling the New Challenges in Automation and Computing
EditorsZhijie Xu, Jing Wang
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages462-466
Number of pages5
ISBN (Electronic)9781862181311
DOIs
Publication statusPublished - 24 Oct 2016
Event22nd International Conference on Automation and Computing - Colchester, United Kingdom
Duration: 7 Sep 20168 Sep 2016
Conference number: 22

Conference

Conference22nd International Conference on Automation and Computing
Abbreviated titleICAC 2016
CountryUnited Kingdom
CityColchester
Period7/09/168/09/16

Fingerprint

Optical flows
Optical Flow
Experiments
Experiment

Cite this

Hao, Y., Xu, Z., Wang, J., Liu, Y., & Fan, J. (2016). An approach to detect crowd panic behavior using flow-based feature. In Z. Xu, & J. Wang (Eds.), 22nd International Conference on Automation and Computing: Tackling the New Challenges in Automation and Computing (pp. 462-466). [7604963] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IConAC.2016.7604963
Hao, Yu ; Xu, Zhijie ; Wang, Jing ; Liu, Ying ; Fan, Jiulun. / An approach to detect crowd panic behavior using flow-based feature. 22nd International Conference on Automation and Computing: Tackling the New Challenges in Automation and Computing. editor / Zhijie Xu ; Jing Wang. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 462-466
@inproceedings{b6b5defda8684a6d8d29b29d98bbdf18,
title = "An approach to detect crowd panic behavior using flow-based feature",
abstract = "With the purpose of achieving automated detection of crowd abnormal behavior in public, this paper discusses the category of typical crowd and individual behaviors and their patterns. Popular image features for abnormal behavior detection are also introduced, including global flow based features such as optical flow, and local spatio-temporal based features such as Spatio-temporal Volume (STV). After reviewing some relative abnormal behavior detection algorithms, a brand-new approach to detect crowd panic behavior has been proposed based on optical flow features in this paper. During the experiments, all panic behaviors are successfully detected. In the end, the future work to improve current approach has been discussed.",
keywords = "behavior detection, optical flow, video processing",
author = "Yu Hao and Zhijie Xu and Jing Wang and Ying Liu and Jiulun Fan",
year = "2016",
month = "10",
day = "24",
doi = "10.1109/IConAC.2016.7604963",
language = "English",
pages = "462--466",
editor = "Zhijie Xu and Jing Wang",
booktitle = "22nd International Conference on Automation and Computing",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

Hao, Y, Xu, Z, Wang, J, Liu, Y & Fan, J 2016, An approach to detect crowd panic behavior using flow-based feature. in Z Xu & J Wang (eds), 22nd International Conference on Automation and Computing: Tackling the New Challenges in Automation and Computing., 7604963, Institute of Electrical and Electronics Engineers Inc., pp. 462-466, 22nd International Conference on Automation and Computing, Colchester, United Kingdom, 7/09/16. https://doi.org/10.1109/IConAC.2016.7604963

An approach to detect crowd panic behavior using flow-based feature. / Hao, Yu; Xu, Zhijie; Wang, Jing; Liu, Ying; Fan, Jiulun.

22nd International Conference on Automation and Computing: Tackling the New Challenges in Automation and Computing. ed. / Zhijie Xu; Jing Wang. Institute of Electrical and Electronics Engineers Inc., 2016. p. 462-466 7604963.

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

TY - GEN

T1 - An approach to detect crowd panic behavior using flow-based feature

AU - Hao, Yu

AU - Xu, Zhijie

AU - Wang, Jing

AU - Liu, Ying

AU - Fan, Jiulun

PY - 2016/10/24

Y1 - 2016/10/24

N2 - With the purpose of achieving automated detection of crowd abnormal behavior in public, this paper discusses the category of typical crowd and individual behaviors and their patterns. Popular image features for abnormal behavior detection are also introduced, including global flow based features such as optical flow, and local spatio-temporal based features such as Spatio-temporal Volume (STV). After reviewing some relative abnormal behavior detection algorithms, a brand-new approach to detect crowd panic behavior has been proposed based on optical flow features in this paper. During the experiments, all panic behaviors are successfully detected. In the end, the future work to improve current approach has been discussed.

AB - With the purpose of achieving automated detection of crowd abnormal behavior in public, this paper discusses the category of typical crowd and individual behaviors and their patterns. Popular image features for abnormal behavior detection are also introduced, including global flow based features such as optical flow, and local spatio-temporal based features such as Spatio-temporal Volume (STV). After reviewing some relative abnormal behavior detection algorithms, a brand-new approach to detect crowd panic behavior has been proposed based on optical flow features in this paper. During the experiments, all panic behaviors are successfully detected. In the end, the future work to improve current approach has been discussed.

KW - behavior detection

KW - optical flow

KW - video processing

UR - http://www.scopus.com/inward/record.url?scp=84999014701&partnerID=8YFLogxK

U2 - 10.1109/IConAC.2016.7604963

DO - 10.1109/IConAC.2016.7604963

M3 - Conference contribution

SP - 462

EP - 466

BT - 22nd International Conference on Automation and Computing

A2 - Xu, Zhijie

A2 - Wang, Jing

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Hao Y, Xu Z, Wang J, Liu Y, Fan J. An approach to detect crowd panic behavior using flow-based feature. In Xu Z, Wang J, editors, 22nd International Conference on Automation and Computing: Tackling the New Challenges in Automation and Computing. Institute of Electrical and Electronics Engineers Inc. 2016. p. 462-466. 7604963 https://doi.org/10.1109/IConAC.2016.7604963