Modeling crowd motions for abnormal activity detection

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

10 Citations (Scopus)

Abstract

In this paper; we propose a novel crowd behavior representation method to detect abnormal behaviors in videos. An adaptive optical flow filtering method is proposed to utilize low-level optical flow informations. Furthermore, a simple framework is developed to detect and to localize abnormal crowd behavior using adaptive optical flow filtering result. The proposed method is more robust than other modeling methods in representing different behaviors. In this model, a normal behavior is presented by the general value. Some outliers in the temporal domain or spatial domain are presented by a higher value. Spatio-temporal cuboids are extracted from the filtering result to present the likelihood of anomaly in the frame. Experimental evaluations are performed on two public datasets with comparison to the provisos abnormal behavior detection methods in the literature. Experimental results show that the proposed methods outperform previous abnormal behavior detection techniques in the literature.

Original languageEnglish
Title of host publication11th IEEE International Conference on Advanced Video and Signal-Based Surveillance, AVSS 2014
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages325-330
Number of pages6
ISBN (Print)9781479948710
DOIs
Publication statusPublished - 2014 Jan 1
Event11th IEEE International Conference on Advanced Video and Signal-Based Surveillance, AVSS 2014 - Seoul, Korea, Republic of
Duration: 2014 Aug 262014 Aug 29

Other

Other11th IEEE International Conference on Advanced Video and Signal-Based Surveillance, AVSS 2014
CountryKorea, Republic of
CitySeoul
Period14/8/2614/8/29

Fingerprint

Optical flows

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Signal Processing

Cite this

Lee, D. G., Suk, H-I., & Lee, S. W. (2014). Modeling crowd motions for abnormal activity detection. In 11th IEEE International Conference on Advanced Video and Signal-Based Surveillance, AVSS 2014 (pp. 325-330). [6918689] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/AVSS.2014.6918689

Modeling crowd motions for abnormal activity detection. / Lee, Dong Gyu; Suk, Heung-Il; Lee, Seong Whan.

11th IEEE International Conference on Advanced Video and Signal-Based Surveillance, AVSS 2014. Institute of Electrical and Electronics Engineers Inc., 2014. p. 325-330 6918689.

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

Lee, DG, Suk, H-I & Lee, SW 2014, Modeling crowd motions for abnormal activity detection. in 11th IEEE International Conference on Advanced Video and Signal-Based Surveillance, AVSS 2014., 6918689, Institute of Electrical and Electronics Engineers Inc., pp. 325-330, 11th IEEE International Conference on Advanced Video and Signal-Based Surveillance, AVSS 2014, Seoul, Korea, Republic of, 14/8/26. https://doi.org/10.1109/AVSS.2014.6918689
Lee DG, Suk H-I, Lee SW. Modeling crowd motions for abnormal activity detection. In 11th IEEE International Conference on Advanced Video and Signal-Based Surveillance, AVSS 2014. Institute of Electrical and Electronics Engineers Inc. 2014. p. 325-330. 6918689 https://doi.org/10.1109/AVSS.2014.6918689
Lee, Dong Gyu ; Suk, Heung-Il ; Lee, Seong Whan. / Modeling crowd motions for abnormal activity detection. 11th IEEE International Conference on Advanced Video and Signal-Based Surveillance, AVSS 2014. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 325-330
@inproceedings{9da1d66957524c48b5c72b3d0adbaef0,
title = "Modeling crowd motions for abnormal activity detection",
abstract = "In this paper; we propose a novel crowd behavior representation method to detect abnormal behaviors in videos. An adaptive optical flow filtering method is proposed to utilize low-level optical flow informations. Furthermore, a simple framework is developed to detect and to localize abnormal crowd behavior using adaptive optical flow filtering result. The proposed method is more robust than other modeling methods in representing different behaviors. In this model, a normal behavior is presented by the general value. Some outliers in the temporal domain or spatial domain are presented by a higher value. Spatio-temporal cuboids are extracted from the filtering result to present the likelihood of anomaly in the frame. Experimental evaluations are performed on two public datasets with comparison to the provisos abnormal behavior detection methods in the literature. Experimental results show that the proposed methods outperform previous abnormal behavior detection techniques in the literature.",
author = "Lee, {Dong Gyu} and Heung-Il Suk and Lee, {Seong Whan}",
year = "2014",
month = "1",
day = "1",
doi = "10.1109/AVSS.2014.6918689",
language = "English",
isbn = "9781479948710",
pages = "325--330",
booktitle = "11th IEEE International Conference on Advanced Video and Signal-Based Surveillance, AVSS 2014",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Modeling crowd motions for abnormal activity detection

AU - Lee, Dong Gyu

AU - Suk, Heung-Il

AU - Lee, Seong Whan

PY - 2014/1/1

Y1 - 2014/1/1

N2 - In this paper; we propose a novel crowd behavior representation method to detect abnormal behaviors in videos. An adaptive optical flow filtering method is proposed to utilize low-level optical flow informations. Furthermore, a simple framework is developed to detect and to localize abnormal crowd behavior using adaptive optical flow filtering result. The proposed method is more robust than other modeling methods in representing different behaviors. In this model, a normal behavior is presented by the general value. Some outliers in the temporal domain or spatial domain are presented by a higher value. Spatio-temporal cuboids are extracted from the filtering result to present the likelihood of anomaly in the frame. Experimental evaluations are performed on two public datasets with comparison to the provisos abnormal behavior detection methods in the literature. Experimental results show that the proposed methods outperform previous abnormal behavior detection techniques in the literature.

AB - In this paper; we propose a novel crowd behavior representation method to detect abnormal behaviors in videos. An adaptive optical flow filtering method is proposed to utilize low-level optical flow informations. Furthermore, a simple framework is developed to detect and to localize abnormal crowd behavior using adaptive optical flow filtering result. The proposed method is more robust than other modeling methods in representing different behaviors. In this model, a normal behavior is presented by the general value. Some outliers in the temporal domain or spatial domain are presented by a higher value. Spatio-temporal cuboids are extracted from the filtering result to present the likelihood of anomaly in the frame. Experimental evaluations are performed on two public datasets with comparison to the provisos abnormal behavior detection methods in the literature. Experimental results show that the proposed methods outperform previous abnormal behavior detection techniques in the literature.

UR - http://www.scopus.com/inward/record.url?scp=84909951634&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84909951634&partnerID=8YFLogxK

U2 - 10.1109/AVSS.2014.6918689

DO - 10.1109/AVSS.2014.6918689

M3 - Conference contribution

AN - SCOPUS:84909951634

SN - 9781479948710

SP - 325

EP - 330

BT - 11th IEEE International Conference on Advanced Video and Signal-Based Surveillance, AVSS 2014

PB - Institute of Electrical and Electronics Engineers Inc.

ER -