Video manifold modelling: finding the right parameter settings for anomaly detection

Hanhe Lin; Jeremiah D. Deng; Brendon J. Woodford

doi:10.1145/2425836.2425873

Video manifold modelling: finding the right parameter settings for anomaly detection

Hanhe Lin, Jeremiah D. Deng, Brendon J. Woodford

Computing

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Using video manifold to analyze video scenes and detect possible anomaly has become a popular research topic in recent years. While a number of attempts have been proposed and reported promising outcomes, there is currently a lack of understanding about the parameter setting for various components in the algorithmic framework. In this paper we look at some key parameters, particularly the dimension of the video manifold, the embedding dimension of the video trajectory, and explore the plausibility of setting these parameters automatically using outcome of spectral clustering and fractal dimension analysis. Experiments are conducted using a benchmark dataset and the results are promising.

Original language	English
Title of host publication	IVCNZ '12
Subtitle of host publication	Proceedings of the 27th Conference on Image and Vision Computing New Zealand
Editors	Brendan McCane, Steven Mills, Jeremiah Dreng
Place of Publication	New York, NY
Publisher	Association for Computing Machinery (ACM)
Pages	168-173
Number of pages	6
ISBN (Print)	978-1-4503-1473-2
DOIs	https://doi.org/10.1145/2425836.2425873
Publication status	Published - 26 Nov 2012
Event	27th Conference on Image and Vision Computing: New Zealand - Dunedin, New Zealand Duration: 26 Nov 2012 → 28 Nov 2012

Conference

Conference	27th Conference on Image and Vision Computing
Abbreviated title	IVCNZ 2012
Country/Territory	New Zealand
City	Dunedin
Period	26/11/12 → 28/11/12

Keywords

anomaly detection
manifold learning
trajectory embedding

ASJC Scopus subject areas

Software
Human-Computer Interaction
Computer Vision and Pattern Recognition
Computer Networks and Communications

Access to Document

10.1145/2425836.2425873

Cite this

@inproceedings{f7217dac2fea45618503ce0b35308257,

title = "Video manifold modelling: finding the right parameter settings for anomaly detection",

abstract = "Using video manifold to analyze video scenes and detect possible anomaly has become a popular research topic in recent years. While a number of attempts have been proposed and reported promising outcomes, there is currently a lack of understanding about the parameter setting for various components in the algorithmic framework. In this paper we look at some key parameters, particularly the dimension of the video manifold, the embedding dimension of the video trajectory, and explore the plausibility of setting these parameters automatically using outcome of spectral clustering and fractal dimension analysis. Experiments are conducted using a benchmark dataset and the results are promising.",

keywords = "anomaly detection, manifold learning, trajectory embedding",

author = "Hanhe Lin and Deng, {Jeremiah D.} and Woodford, {Brendon J.}",

year = "2012",

month = nov,

day = "26",

doi = "10.1145/2425836.2425873",

language = "English",

isbn = "978-1-4503-1473-2",

pages = "168--173",

editor = "Brendan McCane and Steven Mills and Jeremiah Dreng",

booktitle = "IVCNZ '12",

publisher = "Association for Computing Machinery (ACM)",

address = "United States",

}

Lin, H, Deng, JD & Woodford, BJ 2012, Video manifold modelling: finding the right parameter settings for anomaly detection. in B McCane, S Mills & J Dreng (eds), IVCNZ '12: Proceedings of the 27th Conference on Image and Vision Computing New Zealand. Association for Computing Machinery (ACM), New York, NY, pp. 168-173, 27th Conference on Image and Vision Computing, Dunedin, New Zealand, 26/11/12. https://doi.org/10.1145/2425836.2425873

Video manifold modelling: finding the right parameter settings for anomaly detection. / Lin, Hanhe; Deng, Jeremiah D.; Woodford, Brendon J.
IVCNZ '12: Proceedings of the 27th Conference on Image and Vision Computing New Zealand. ed. / Brendan McCane; Steven Mills; Jeremiah Dreng. New York, NY: Association for Computing Machinery (ACM), 2012. p. 168-173.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Video manifold modelling

T2 - 27th Conference on Image and Vision Computing

AU - Lin, Hanhe

AU - Deng, Jeremiah D.

AU - Woodford, Brendon J.

PY - 2012/11/26

Y1 - 2012/11/26

N2 - Using video manifold to analyze video scenes and detect possible anomaly has become a popular research topic in recent years. While a number of attempts have been proposed and reported promising outcomes, there is currently a lack of understanding about the parameter setting for various components in the algorithmic framework. In this paper we look at some key parameters, particularly the dimension of the video manifold, the embedding dimension of the video trajectory, and explore the plausibility of setting these parameters automatically using outcome of spectral clustering and fractal dimension analysis. Experiments are conducted using a benchmark dataset and the results are promising.

AB - Using video manifold to analyze video scenes and detect possible anomaly has become a popular research topic in recent years. While a number of attempts have been proposed and reported promising outcomes, there is currently a lack of understanding about the parameter setting for various components in the algorithmic framework. In this paper we look at some key parameters, particularly the dimension of the video manifold, the embedding dimension of the video trajectory, and explore the plausibility of setting these parameters automatically using outcome of spectral clustering and fractal dimension analysis. Experiments are conducted using a benchmark dataset and the results are promising.

KW - anomaly detection

KW - manifold learning

KW - trajectory embedding

UR - http://www.scopus.com/inward/record.url?scp=84873342986&partnerID=8YFLogxK

U2 - 10.1145/2425836.2425873

DO - 10.1145/2425836.2425873

M3 - Conference contribution

AN - SCOPUS:84873342986

SN - 978-1-4503-1473-2

SP - 168

EP - 173

BT - IVCNZ '12

A2 - McCane, Brendan

A2 - Mills, Steven

A2 - Dreng, Jeremiah

PB - Association for Computing Machinery (ACM)

CY - New York, NY

Y2 - 26 November 2012 through 28 November 2012

ER -

Video manifold modelling: finding the right parameter settings for anomaly detection

Abstract

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this