Consistent Sparse Representation for Abnormal Event Detection
Summary :
Sparsity-based methods have been recently applied to abnormal event detection and have achieved impressive results. However, most such methods suffer from the problem of dimensionality curse; furthermore, they also take no consideration of the relationship among coefficient vectors. In this paper, we propose a novel method called consistent sparse representation (CSR) to overcome the drawbacks. We first reconstruct each feature in the space spanned by the clustering centers of training features so as to reduce the dimensionality of features and preserve the neighboring structure. Then, the consistent regularization is added to the sparse representation model, which explicitly considers the relationship of coefficient vectors. Our method is verified on two challenging databases (UCSD Ped1 database and Subway batabase), and the experimental results demonstrate that our method obtains better results than previous methods in abnormal event detection.
- Publication
- IEICE TRANSACTIONS on Information Vol.E98-D No.10 pp.1866-1870
- Publication Date
- 2015/10/01
- Publicized
- 2015/07/17
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.2015EDL8113
- Type of Manuscript
- LETTER
- Category
- Pattern Recognition
Authors
Zhong ZHANG
Tianjin Normal University
Shuang LIU
Tianjin Normal University
Zhiwei ZHANG
Purdue University
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Zhong ZHANG, Shuang LIU, Zhiwei ZHANG, "Consistent Sparse Representation for Abnormal Event Detection" in IEICE TRANSACTIONS on Information,
vol. E98-D, no. 10, pp. 1866-1870, October 2015, doi: 10.1587/transinf.2015EDL8113.
Abstract: Sparsity-based methods have been recently applied to abnormal event detection and have achieved impressive results. However, most such methods suffer from the problem of dimensionality curse; furthermore, they also take no consideration of the relationship among coefficient vectors. In this paper, we propose a novel method called consistent sparse representation (CSR) to overcome the drawbacks. We first reconstruct each feature in the space spanned by the clustering centers of training features so as to reduce the dimensionality of features and preserve the neighboring structure. Then, the consistent regularization is added to the sparse representation model, which explicitly considers the relationship of coefficient vectors. Our method is verified on two challenging databases (UCSD Ped1 database and Subway batabase), and the experimental results demonstrate that our method obtains better results than previous methods in abnormal event detection.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2015EDL8113/_p
Copy
@ARTICLE{e98-d_10_1866,
author={Zhong ZHANG, Shuang LIU, Zhiwei ZHANG, },
journal={IEICE TRANSACTIONS on Information},
title={Consistent Sparse Representation for Abnormal Event Detection},
year={2015},
volume={E98-D},
number={10},
pages={1866-1870},
abstract={Sparsity-based methods have been recently applied to abnormal event detection and have achieved impressive results. However, most such methods suffer from the problem of dimensionality curse; furthermore, they also take no consideration of the relationship among coefficient vectors. In this paper, we propose a novel method called consistent sparse representation (CSR) to overcome the drawbacks. We first reconstruct each feature in the space spanned by the clustering centers of training features so as to reduce the dimensionality of features and preserve the neighboring structure. Then, the consistent regularization is added to the sparse representation model, which explicitly considers the relationship of coefficient vectors. Our method is verified on two challenging databases (UCSD Ped1 database and Subway batabase), and the experimental results demonstrate that our method obtains better results than previous methods in abnormal event detection.},
keywords={},
doi={10.1587/transinf.2015EDL8113},
ISSN={1745-1361},
month={October},}
Copy
TY - JOUR
TI - Consistent Sparse Representation for Abnormal Event Detection
T2 - IEICE TRANSACTIONS on Information
SP - 1866
EP - 1870
AU - Zhong ZHANG
AU - Shuang LIU
AU - Zhiwei ZHANG
PY - 2015
DO - 10.1587/transinf.2015EDL8113
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E98-D
IS - 10
JA - IEICE TRANSACTIONS on Information
Y1 - October 2015
AB - Sparsity-based methods have been recently applied to abnormal event detection and have achieved impressive results. However, most such methods suffer from the problem of dimensionality curse; furthermore, they also take no consideration of the relationship among coefficient vectors. In this paper, we propose a novel method called consistent sparse representation (CSR) to overcome the drawbacks. We first reconstruct each feature in the space spanned by the clustering centers of training features so as to reduce the dimensionality of features and preserve the neighboring structure. Then, the consistent regularization is added to the sparse representation model, which explicitly considers the relationship of coefficient vectors. Our method is verified on two challenging databases (UCSD Ped1 database and Subway batabase), and the experimental results demonstrate that our method obtains better results than previous methods in abnormal event detection.
ER -
English
