Unsupervised behaviour-specific dictionary learning for abnormal event detection

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

Standard

Unsupervised behaviour-specific dictionary learning for abnormal event detection. / Ren, Huamin; Liu, Weifeng; Olsen, Søren Ingvor; Escalera, Sergio; Moeslund, Thomas B.

Proceedings of the British Machine Vision Conference 2015. ed. / Xianghua Xie; Mark W. Jones; Gary K. L. Tam. BMVA, 2015. p. 28.1-28.13.

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

Harvard

Ren, H, Liu, W, Olsen, SI, Escalera, S & Moeslund, TB 2015, Unsupervised behaviour-specific dictionary learning for abnormal event detection. in X Xie, MW Jones & GKL Tam (eds), Proceedings of the British Machine Vision Conference 2015. BMVA, pp. 28.1-28.13, 26th British Machine Vision Conference, Swansea, United Kingdom, 07/09/2015. https://doi.org/10.5244/C.29.28

APA

Ren, H., Liu, W., Olsen, S. I., Escalera, S., & Moeslund, T. B. (2015). Unsupervised behaviour-specific dictionary learning for abnormal event detection. In X. Xie, M. W. Jones, & G. K. L. Tam (Eds.), Proceedings of the British Machine Vision Conference 2015 (pp. 28.1-28.13). BMVA. https://doi.org/10.5244/C.29.28

Vancouver

Ren H, Liu W, Olsen SI, Escalera S, Moeslund TB. Unsupervised behaviour-specific dictionary learning for abnormal event detection. In Xie X, Jones MW, Tam GKL, editors, Proceedings of the British Machine Vision Conference 2015. BMVA. 2015. p. 28.1-28.13 https://doi.org/10.5244/C.29.28

Author

Ren, Huamin ; Liu, Weifeng ; Olsen, Søren Ingvor ; Escalera, Sergio ; Moeslund, Thomas B. / Unsupervised behaviour-specific dictionary learning for abnormal event detection. Proceedings of the British Machine Vision Conference 2015. editor / Xianghua Xie ; Mark W. Jones ; Gary K. L. Tam. BMVA, 2015. pp. 28.1-28.13

Bibtex

@inproceedings{b8f15bfd92d94dc299e0536d3388603a,
title = "Unsupervised behaviour-specific dictionary learning for abnormal event detection",
abstract = "Abnormal event detection has been a challenge due to the lack of complete normalinformation in the training data and the volatility of the definitions of both normalityand abnormality. Recent research applying sparse representation has shown itseffectiveness in the expression of normal patterns. Despite progress in this area, the relationship of atoms within the dictionary is commonly neglected, thereafter anomalies which are detected based on reconstruction error could brings high false alarm - noise or infrequent normal visual features could be wrongly detected as anomalies, especially when the training data is only a small proportion of the surveillance data. Therefore, we propose behavior-specific dictionaries (BSD) through unsupervised learning, pursuing atoms from the same type of behavior to represent one behavior dictionary. To further improve the dictionary by introducing information from potential infrequent normal patterns, we refine the dictionary by searching {\textquoteleft}missed atoms{\textquoteright} that have compact coefficients. Experimental results show that our BSD algorithm outperforms state-of-the-art dictionaries in abnormal event detection on the public UCSD dataset. Moreover, BSD has less false alarms compared to state-of-the-art dictionaries especially when the training set is small, which is demonstrated on Anomaly Stairs dataset.",
keywords = "Faculty of Science, Image analysis, Machine learning, Computer Vision, Learning",
author = "Huamin Ren and Weifeng Liu and Olsen, {S{\o}ren Ingvor} and Sergio Escalera and Moeslund, {Thomas B.}",
year = "2015",
doi = "10.5244/C.29.28",
language = "English",
isbn = "1-901725-53-7",
pages = "28.1--28.13",
editor = "Xianghua Xie and Jones, {Mark W.} and Tam, {Gary K. L.}",
booktitle = "Proceedings of the British Machine Vision Conference 2015",
publisher = "BMVA",
note = "26th British Machine Vision Conference, BMVC 2015 ; Conference date: 07-09-2015 Through 10-09-2015",

}

RIS

TY - GEN

T1 - Unsupervised behaviour-specific dictionary learning for abnormal event detection

AU - Ren, Huamin

AU - Liu, Weifeng

AU - Olsen, Søren Ingvor

AU - Escalera, Sergio

AU - Moeslund, Thomas B.

N1 - Conference code: 26

PY - 2015

Y1 - 2015

N2 - Abnormal event detection has been a challenge due to the lack of complete normalinformation in the training data and the volatility of the definitions of both normalityand abnormality. Recent research applying sparse representation has shown itseffectiveness in the expression of normal patterns. Despite progress in this area, the relationship of atoms within the dictionary is commonly neglected, thereafter anomalies which are detected based on reconstruction error could brings high false alarm - noise or infrequent normal visual features could be wrongly detected as anomalies, especially when the training data is only a small proportion of the surveillance data. Therefore, we propose behavior-specific dictionaries (BSD) through unsupervised learning, pursuing atoms from the same type of behavior to represent one behavior dictionary. To further improve the dictionary by introducing information from potential infrequent normal patterns, we refine the dictionary by searching ‘missed atoms’ that have compact coefficients. Experimental results show that our BSD algorithm outperforms state-of-the-art dictionaries in abnormal event detection on the public UCSD dataset. Moreover, BSD has less false alarms compared to state-of-the-art dictionaries especially when the training set is small, which is demonstrated on Anomaly Stairs dataset.

AB - Abnormal event detection has been a challenge due to the lack of complete normalinformation in the training data and the volatility of the definitions of both normalityand abnormality. Recent research applying sparse representation has shown itseffectiveness in the expression of normal patterns. Despite progress in this area, the relationship of atoms within the dictionary is commonly neglected, thereafter anomalies which are detected based on reconstruction error could brings high false alarm - noise or infrequent normal visual features could be wrongly detected as anomalies, especially when the training data is only a small proportion of the surveillance data. Therefore, we propose behavior-specific dictionaries (BSD) through unsupervised learning, pursuing atoms from the same type of behavior to represent one behavior dictionary. To further improve the dictionary by introducing information from potential infrequent normal patterns, we refine the dictionary by searching ‘missed atoms’ that have compact coefficients. Experimental results show that our BSD algorithm outperforms state-of-the-art dictionaries in abnormal event detection on the public UCSD dataset. Moreover, BSD has less false alarms compared to state-of-the-art dictionaries especially when the training set is small, which is demonstrated on Anomaly Stairs dataset.

KW - Faculty of Science

KW - Image analysis

KW - Machine learning

KW - Computer Vision

KW - Learning

U2 - 10.5244/C.29.28

DO - 10.5244/C.29.28

M3 - Article in proceedings

SN - 1-901725-53-7

SP - 28.1-28.13

BT - Proceedings of the British Machine Vision Conference 2015

A2 - Xie, Xianghua

A2 - Jones, Mark W.

A2 - Tam, Gary K. L.

PB - BMVA

T2 - 26th British Machine Vision Conference

Y2 - 7 September 2015 through 10 September 2015

ER -

ID: 140751711