On Stable Dynamic Background Generation Technique using Gaussian Mixture Models for Robust Object Detection

Mahfuzul Haque, Manzur Murshed, Manoranjan Paul

Research output: Book chapter/Published conference paperConference paper

26 Citations (Scopus)

Abstract

Gaussian mixture models (GMM) is used to represent the dynamic background in a surveillance video to detect the moving objects automatically. All the existing GMM based techniques inherently use the proportion by which a pixel is going to observe the background in any operating environment. In this paper we first show that such a proportion not only varies widely across different scenarios but also forbids using very fast learning rate. We then propose a dynamic background generation technique in conjunction with basic background subtraction which detected moving objects with improved stability and superior detection quality on a wide range of operating environments in two sets of benchmark surveillance sequences.
Original languageEnglish
Title of host publicationAVSS2008
Place of PublicationUSA
PublisherIEEE
Pages41-48
Number of pages8
ISBN (Electronic)9780769533414
DOIs
Publication statusPublished - 2008
EventIEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS) - Santa Fe, New Mexico
Duration: 01 Sep 200803 Sep 2008

Conference

ConferenceIEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)
Period01/09/0803/09/08

Fingerprint

Pixels
Object detection

Cite this

@inproceedings{d2d31c2b80a34502a501f99c714df74e,
title = "On Stable Dynamic Background Generation Technique using Gaussian Mixture Models for Robust Object Detection",
abstract = "Gaussian mixture models (GMM) is used to represent the dynamic background in a surveillance video to detect the moving objects automatically. All the existing GMM based techniques inherently use the proportion by which a pixel is going to observe the background in any operating environment. In this paper we first show that such a proportion not only varies widely across different scenarios but also forbids using very fast learning rate. We then propose a dynamic background generation technique in conjunction with basic background subtraction which detected moving objects with improved stability and superior detection quality on a wide range of operating environments in two sets of benchmark surveillance sequences.",
author = "Mahfuzul Haque and Manzur Murshed and Manoranjan Paul",
note = "Imported on 03 May 2017 - DigiTool details were: publisher = USA: IEEE, 2008. Event dates (773o) = 1-3 September, 2008; Parent title (773t) = IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS).",
year = "2008",
doi = "10.1109/AVSS.2008.12",
language = "English",
pages = "41--48",
booktitle = "AVSS2008",
publisher = "IEEE",

}

Haque, M, Murshed, M & Paul, M 2008, On Stable Dynamic Background Generation Technique using Gaussian Mixture Models for Robust Object Detection. in AVSS2008. IEEE, USA, pp. 41-48, IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), 01/09/08. https://doi.org/10.1109/AVSS.2008.12

On Stable Dynamic Background Generation Technique using Gaussian Mixture Models for Robust Object Detection. / Haque, Mahfuzul; Murshed, Manzur; Paul, Manoranjan.

AVSS2008. USA : IEEE, 2008. p. 41-48.

Research output: Book chapter/Published conference paperConference paper

TY - GEN

T1 - On Stable Dynamic Background Generation Technique using Gaussian Mixture Models for Robust Object Detection

AU - Haque, Mahfuzul

AU - Murshed, Manzur

AU - Paul, Manoranjan

N1 - Imported on 03 May 2017 - DigiTool details were: publisher = USA: IEEE, 2008. Event dates (773o) = 1-3 September, 2008; Parent title (773t) = IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS).

PY - 2008

Y1 - 2008

N2 - Gaussian mixture models (GMM) is used to represent the dynamic background in a surveillance video to detect the moving objects automatically. All the existing GMM based techniques inherently use the proportion by which a pixel is going to observe the background in any operating environment. In this paper we first show that such a proportion not only varies widely across different scenarios but also forbids using very fast learning rate. We then propose a dynamic background generation technique in conjunction with basic background subtraction which detected moving objects with improved stability and superior detection quality on a wide range of operating environments in two sets of benchmark surveillance sequences.

AB - Gaussian mixture models (GMM) is used to represent the dynamic background in a surveillance video to detect the moving objects automatically. All the existing GMM based techniques inherently use the proportion by which a pixel is going to observe the background in any operating environment. In this paper we first show that such a proportion not only varies widely across different scenarios but also forbids using very fast learning rate. We then propose a dynamic background generation technique in conjunction with basic background subtraction which detected moving objects with improved stability and superior detection quality on a wide range of operating environments in two sets of benchmark surveillance sequences.

U2 - 10.1109/AVSS.2008.12

DO - 10.1109/AVSS.2008.12

M3 - Conference paper

SP - 41

EP - 48

BT - AVSS2008

PB - IEEE

CY - USA

ER -