Drastic Anomaly Detection in Video Using Motion Direction Statistics

Chang LIU; Guijin WANG; Wenxin NING; Xinggang LIN

doi:10.1587/transinf.E94.D.1700

Drastic Anomaly Detection in Video Using Motion Direction Statistics

Chang LIU, Guijin WANG, Wenxin NING, Xinggang LIN

Full Text Views

0

Share
Cite this

Summary :

A novel approach for detecting anomaly in visual surveillance system is proposed in this paper. It is composed of three parts: (a) a dense motion field and motion statistics method, (b) motion directional PCA for feature dimensionality reduction, (c) an improved one-class SVM for one-class classification. Experiments demonstrate the effectiveness of the proposed algorithm in detecting abnormal events in surveillance video, while keeping a low false alarm rate. Our scheme works well in complicated situations that common tracking or detection modules cannot handle.

Publication: IEICE TRANSACTIONS on Information Vol.E94-D No.8 pp.1700-1707

Publication Date: 2011/08/01

Publicized

Online ISSN: 1745-1361

DOI: 10.1587/transinf.E94.D.1700

Type of Manuscript: PAPER

Category: Image Recognition, Computer Vision

Cite this

Copy

Chang LIU, Guijin WANG, Wenxin NING, Xinggang LIN, "Drastic Anomaly Detection in Video Using Motion Direction Statistics" in IEICE TRANSACTIONS on Information, vol. E94-D, no. 8, pp. 1700-1707, August 2011, doi: 10.1587/transinf.E94.D.1700.
Abstract: A novel approach for detecting anomaly in visual surveillance system is proposed in this paper. It is composed of three parts: (a) a dense motion field and motion statistics method, (b) motion directional PCA for feature dimensionality reduction, (c) an improved one-class SVM for one-class classification. Experiments demonstrate the effectiveness of the proposed algorithm in detecting abnormal events in surveillance video, while keeping a low false alarm rate. Our scheme works well in complicated situations that common tracking or detection modules cannot handle.
URL: https://globals.ieice.org/en_transactions/information/10.1587/transinf.E94.D.1700/_p

Copy

@ARTICLE{e94-d_8_1700,
author={Chang LIU, Guijin WANG, Wenxin NING, Xinggang LIN, },
journal={IEICE TRANSACTIONS on Information},
title={Drastic Anomaly Detection in Video Using Motion Direction Statistics},
year={2011},
volume={E94-D},
number={8},
pages={1700-1707},
abstract={A novel approach for detecting anomaly in visual surveillance system is proposed in this paper. It is composed of three parts: (a) a dense motion field and motion statistics method, (b) motion directional PCA for feature dimensionality reduction, (c) an improved one-class SVM for one-class classification. Experiments demonstrate the effectiveness of the proposed algorithm in detecting abnormal events in surveillance video, while keeping a low false alarm rate. Our scheme works well in complicated situations that common tracking or detection modules cannot handle.},
keywords={},
doi={10.1587/transinf.E94.D.1700},
ISSN={1745-1361},
month={August},}

Copy

TY - JOUR
TI - Drastic Anomaly Detection in Video Using Motion Direction Statistics
T2 - IEICE TRANSACTIONS on Information
SP - 1700
EP - 1707
AU - Chang LIU
AU - Guijin WANG
AU - Wenxin NING
AU - Xinggang LIN
PY - 2011
DO - 10.1587/transinf.E94.D.1700
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E94-D
IS - 8
JA - IEICE TRANSACTIONS on Information
Y1 - August 2011
AB - A novel approach for detecting anomaly in visual surveillance system is proposed in this paper. It is composed of three parts: (a) a dense motion field and motion statistics method, (b) motion directional PCA for feature dimensionality reduction, (c) an improved one-class SVM for one-class classification. Experiments demonstrate the effectiveness of the proposed algorithm in detecting abnormal events in surveillance video, while keeping a low false alarm rate. Our scheme works well in complicated situations that common tracking or detection modules cannot handle.
ER -