Home > Research > Publications & Outputs > Automatic object detection based on adaptive ba...

Research

Associated organisational unit

Electronic data

Links

Keywords

View graph of relations

Automatic object detection based on adaptive background subtraction using symmetric alpha stable distribution

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review

Published

Standard

Automatic object detection based on adaptive background subtraction using symmetric alpha stable distribution. / Bhaskar, H.; Mihaylova, L.; Maskell, S.
Target Tracking and Data Fusion: Algorithms and Applications, 2008 IET Seminar on. 2008. p. 197 - 203 .

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review

Harvard

Bhaskar, H, Mihaylova, L & Maskell, S 2008, Automatic object detection based on adaptive background subtraction using symmetric alpha stable distribution. in Target Tracking and Data Fusion: Algorithms and Applications, 2008 IET Seminar on. pp. 197 - 203 , The Institution of Engineering and Technology Seminar on Target Tracking and Data Fusion: Algorithms and Applications, Birmingham, UK, 15/04/08. <http://www.theiet.org/target>

APA

Bhaskar, H., Mihaylova, L., & Maskell, S. (2008). Automatic object detection based on adaptive background subtraction using symmetric alpha stable distribution. In Target Tracking and Data Fusion: Algorithms and Applications, 2008 IET Seminar on (pp. 197 - 203 ) http://www.theiet.org/target

Vancouver

Bhaskar H, Mihaylova L, Maskell S. Automatic object detection based on adaptive background subtraction using symmetric alpha stable distribution. In Target Tracking and Data Fusion: Algorithms and Applications, 2008 IET Seminar on. 2008. p. 197 - 203

Author

Bhaskar, H. ; Mihaylova, L. ; Maskell, S. / Automatic object detection based on adaptive background subtraction using symmetric alpha stable distribution. Target Tracking and Data Fusion: Algorithms and Applications, 2008 IET Seminar on. 2008. pp. 197 - 203

Bibtex

@inproceedings{659d0d69b27643e3bd3ad38ba2279b8c,
title = "Automatic object detection based on adaptive background subtraction using symmetric alpha stable distribution",
abstract = "Automatic detection of objects is critical to video tracking systems. One of the simplest techniques for detection is background subtraction (BS). BS refers to the process of segmenting moving regions from image sequences. The BS process involves building a model of the background and extracting regions of the foreground (moving objects). In this paper, we propose an extended cluster BS (CBS) technique based on symmetric alpha stable (SAS) distributions. The developed method functions at cluster-level as against the traditional pixel-level BS methods. An iterative self-adaptive mechanism is presented that allows automated learning of the distribution of the model parameters. The results for the CBS S{\textregistered}S algorithm on real video sequences show improvement compared with a CBS using a Gaussian mixture model.",
keywords = "automatic object detection, tracking, background subtraction, alpha stable distribution, video sequences DCS-publications-id, inproc-562, DCS-publications-credits, dsp-fa, DCS-publications-personnel-id, 121, 132",
author = "H. Bhaskar and L. Mihaylova and S. Maskell",
note = "pp. 197-203 Printed by the Institution of Engineering and Technology, London, ISBN 9780863419102 ISSN 0537-9989 Reference PES08273; The Institution of Engineering and Technology Seminar on Target Tracking and Data Fusion: Algorithms and Applications ; Conference date: 15-04-2008 Through 16-04-2008",
year = "2008",
month = apr,
day = "15",
language = "English",
isbn = "978-0-86341-910-2",
pages = "197 -- 203 ",
booktitle = "Target Tracking and Data Fusion: Algorithms and Applications, 2008 IET Seminar on",

}

RIS

TY - GEN

T1 - Automatic object detection based on adaptive background subtraction using symmetric alpha stable distribution

AU - Bhaskar, H.

AU - Mihaylova, L.

AU - Maskell, S.

N1 - pp. 197-203 Printed by the Institution of Engineering and Technology, London, ISBN 9780863419102 ISSN 0537-9989 Reference PES08273

PY - 2008/4/15

Y1 - 2008/4/15

N2 - Automatic detection of objects is critical to video tracking systems. One of the simplest techniques for detection is background subtraction (BS). BS refers to the process of segmenting moving regions from image sequences. The BS process involves building a model of the background and extracting regions of the foreground (moving objects). In this paper, we propose an extended cluster BS (CBS) technique based on symmetric alpha stable (SAS) distributions. The developed method functions at cluster-level as against the traditional pixel-level BS methods. An iterative self-adaptive mechanism is presented that allows automated learning of the distribution of the model parameters. The results for the CBS S®S algorithm on real video sequences show improvement compared with a CBS using a Gaussian mixture model.

AB - Automatic detection of objects is critical to video tracking systems. One of the simplest techniques for detection is background subtraction (BS). BS refers to the process of segmenting moving regions from image sequences. The BS process involves building a model of the background and extracting regions of the foreground (moving objects). In this paper, we propose an extended cluster BS (CBS) technique based on symmetric alpha stable (SAS) distributions. The developed method functions at cluster-level as against the traditional pixel-level BS methods. An iterative self-adaptive mechanism is presented that allows automated learning of the distribution of the model parameters. The results for the CBS S®S algorithm on real video sequences show improvement compared with a CBS using a Gaussian mixture model.

KW - automatic object detection

KW - tracking

KW - background subtraction

KW - alpha stable distribution

KW - video sequences DCS-publications-id

KW - inproc-562

KW - DCS-publications-credits

KW - dsp-fa

KW - DCS-publications-personnel-id

KW - 121

KW - 132

M3 - Conference contribution/Paper

SN - 978-0-86341-910-2

SP - 197

EP - 203

BT - Target Tracking and Data Fusion: Algorithms and Applications, 2008 IET Seminar on

T2 - The Institution of Engineering and Technology Seminar on Target Tracking and Data Fusion: Algorithms and Applications

Y2 - 15 April 2008 through 16 April 2008

ER -