Spatio-temporal descriptor for abnormal human activity detection

Fam Boon Lung; Mohamed Hisham Jaward; Jussi Paavo Samuli Parkkinen

doi:10.1109/MVA.2015.7153233

Spatio-temporal descriptor for abnormal human activity detection

Fam Boon Lung, Mohamed Hisham Jaward, Jussi Paavo Samuli Parkkinen

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

6 Citations (Scopus)

Abstract

There has been an increased interest in the field of abnormal human activity detection to find a good descriptor with a lower computational cost. In this paper, we propose such a Spatio-Temporal Descriptor (STD) based on spatio-temporal features of an image sequence. Proposed descriptor is based on a texture map, known as Spatio-Temporal Texture Map (STTM) and is based on 3-dimensional Harris function. It is able to capture subtle variations in the spatio-temporal domain. Performance of the STD was illustrated with a mixture of Gaussian Hidden Markov Model (HMM) to show its potential for more complex modeling. Proposed algorithm was evaluated with UCSD dataset that has abnormal events that are not staged such as biker, skater, cart activities etc. Compared to other state of the art descriptors that are used with the same dataset, our proposed descriptor shows competitive performance with a lower computational cost.

Original language	English
Title of host publication	Proceedings of the 14th IAPR International Conference on Machine Vision Applications, MVA 2015
Editors	Norimichi Ukita, Eigo Segawa, Norichika Yui
Place of Publication	New Jersey USA
Publisher	IEEE, Institute of Electrical and Electronics Engineers
Pages	471 - 474
Number of pages	4
ISBN (Print)	9784901122146
DOIs	https://doi.org/10.1109/MVA.2015.7153233
Publication status	Published - 2015
Event	Machine Vision Applications 2015 - Tokyo Japan, Tokyo, Japan Duration: 18 May 2015 → 22 May 2015 Conference number: 14

Conference

Conference	Machine Vision Applications 2015
Abbreviated title	MVA
Country	Japan
City	Tokyo
Period	18/05/15 → 22/05/15
Other	14th IAPR International Conference on Machine Vision Applications, MVA 2015

Access to Document

10.1109/MVA.2015.7153233

Cite this

Lung, F. B., Jaward, M. H., & Parkkinen, J. P. S. (2015). Spatio-temporal descriptor for abnormal human activity detection. In N. Ukita, E. Segawa, & N. Yui (Eds.), Proceedings of the 14th IAPR International Conference on Machine Vision Applications, MVA 2015 (pp. 471 - 474). IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/MVA.2015.7153233

Lung, Fam Boon ; Jaward, Mohamed Hisham ; Parkkinen, Jussi Paavo Samuli. / Spatio-temporal descriptor for abnormal human activity detection. Proceedings of the 14th IAPR International Conference on Machine Vision Applications, MVA 2015. editor / Norimichi Ukita ; Eigo Segawa ; Norichika Yui. New Jersey USA : IEEE, Institute of Electrical and Electronics Engineers, 2015. pp. 471 - 474

@inproceedings{c89b872ffc444ed4837219ca21474929,

title = "Spatio-temporal descriptor for abnormal human activity detection",

abstract = "There has been an increased interest in the field of abnormal human activity detection to find a good descriptor with a lower computational cost. In this paper, we propose such a Spatio-Temporal Descriptor (STD) based on spatio-temporal features of an image sequence. Proposed descriptor is based on a texture map, known as Spatio-Temporal Texture Map (STTM) and is based on 3-dimensional Harris function. It is able to capture subtle variations in the spatio-temporal domain. Performance of the STD was illustrated with a mixture of Gaussian Hidden Markov Model (HMM) to show its potential for more complex modeling. Proposed algorithm was evaluated with UCSD dataset that has abnormal events that are not staged such as biker, skater, cart activities etc. Compared to other state of the art descriptors that are used with the same dataset, our proposed descriptor shows competitive performance with a lower computational cost.",

author = "Lung, {Fam Boon} and Jaward, {Mohamed Hisham} and Parkkinen, {Jussi Paavo Samuli}",

year = "2015",

doi = "10.1109/MVA.2015.7153233",

language = "English",

isbn = "9784901122146",

pages = "471 -- 474",

editor = "Norimichi Ukita and Eigo Segawa and Norichika Yui",

booktitle = "Proceedings of the 14th IAPR International Conference on Machine Vision Applications, MVA 2015",

publisher = "IEEE, Institute of Electrical and Electronics Engineers",

address = "United States of America",

note = "Machine Vision Applications 2015, MVA ; Conference date: 18-05-2015 Through 22-05-2015",

}

Lung, FB, Jaward, MH & Parkkinen, JPS 2015, Spatio-temporal descriptor for abnormal human activity detection. in N Ukita, E Segawa & N Yui (eds), Proceedings of the 14th IAPR International Conference on Machine Vision Applications, MVA 2015. IEEE, Institute of Electrical and Electronics Engineers, New Jersey USA, pp. 471 - 474, Machine Vision Applications 2015, Tokyo, Japan, 18/05/15. https://doi.org/10.1109/MVA.2015.7153233

Spatio-temporal descriptor for abnormal human activity detection. / Lung, Fam Boon; Jaward, Mohamed Hisham; Parkkinen, Jussi Paavo Samuli.

Proceedings of the 14th IAPR International Conference on Machine Vision Applications, MVA 2015. ed. / Norimichi Ukita; Eigo Segawa; Norichika Yui. New Jersey USA : IEEE, Institute of Electrical and Electronics Engineers, 2015. p. 471 - 474.

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

TY - GEN

T1 - Spatio-temporal descriptor for abnormal human activity detection

AU - Lung, Fam Boon

AU - Jaward, Mohamed Hisham

AU - Parkkinen, Jussi Paavo Samuli

N1 - Conference code: 14

PY - 2015

Y1 - 2015

N2 - There has been an increased interest in the field of abnormal human activity detection to find a good descriptor with a lower computational cost. In this paper, we propose such a Spatio-Temporal Descriptor (STD) based on spatio-temporal features of an image sequence. Proposed descriptor is based on a texture map, known as Spatio-Temporal Texture Map (STTM) and is based on 3-dimensional Harris function. It is able to capture subtle variations in the spatio-temporal domain. Performance of the STD was illustrated with a mixture of Gaussian Hidden Markov Model (HMM) to show its potential for more complex modeling. Proposed algorithm was evaluated with UCSD dataset that has abnormal events that are not staged such as biker, skater, cart activities etc. Compared to other state of the art descriptors that are used with the same dataset, our proposed descriptor shows competitive performance with a lower computational cost.

AB - There has been an increased interest in the field of abnormal human activity detection to find a good descriptor with a lower computational cost. In this paper, we propose such a Spatio-Temporal Descriptor (STD) based on spatio-temporal features of an image sequence. Proposed descriptor is based on a texture map, known as Spatio-Temporal Texture Map (STTM) and is based on 3-dimensional Harris function. It is able to capture subtle variations in the spatio-temporal domain. Performance of the STD was illustrated with a mixture of Gaussian Hidden Markov Model (HMM) to show its potential for more complex modeling. Proposed algorithm was evaluated with UCSD dataset that has abnormal events that are not staged such as biker, skater, cart activities etc. Compared to other state of the art descriptors that are used with the same dataset, our proposed descriptor shows competitive performance with a lower computational cost.

U2 - 10.1109/MVA.2015.7153233

DO - 10.1109/MVA.2015.7153233

M3 - Conference Paper

SN - 9784901122146

SP - 471

EP - 474

BT - Proceedings of the 14th IAPR International Conference on Machine Vision Applications, MVA 2015

A2 - Ukita, Norimichi

A2 - Segawa, Eigo

A2 - Yui, Norichika

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - New Jersey USA

T2 - Machine Vision Applications 2015

Y2 - 18 May 2015 through 22 May 2015

ER -