Dynamic control of adaptive mixture-of-Gaussians background model

Atsushi Shimada; Daisaku Arita; Rin Ichiro Taniguchi

doi:10.1109/AVSS.2006.44

Dynamic control of adaptive mixture-of-Gaussians background model

Atsushi Shimada, Daisaku Arita, Rin Ichiro Taniguchi

Real world robotics

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

85 Citations (Scopus)

Abstract

We propose a method for create a background model in non-stationary scenes. Each pixel has a dynamic Gaussian mixture model Our approach can automatically change the number of Gaussians in each pixel. The number of Gaussians increases when pixel values often change because of Illumination change, object moving and so on. On the other hand, when pixel values are constant in a while, some Gaussians are eliminated or integrated. This process helps reduce computational time. We conducted experiments to investigate the effectiveness of our approach.

Original language	English
Title of host publication	Proceedings - IEEE International Conference on Video and Signal Based Surveillance 2006, AVSS 2006
Publisher	IEEE Computer Society
Pages	5
Number of pages	1
ISBN (Print)	0769526888, 9780769526881
DOIs	https://doi.org/10.1109/AVSS.2006.44
Publication status	Published - 2006
Event	IEEE International Conference on Video and Signal Based Surveillance 2006, AVSS 2006 - Sydney, NSW, Australia Duration: Nov 22 2006 → Nov 24 2006

Publication series

Name	Proceedings - IEEE International Conference on Video and Signal Based Surveillance 2006, AVSS 2006

Other

Other	IEEE International Conference on Video and Signal Based Surveillance 2006, AVSS 2006
Country/Territory	Australia
City	Sydney, NSW
Period	11/22/06 → 11/24/06

All Science Journal Classification (ASJC) codes

Computer Vision and Pattern Recognition
Signal Processing
Electrical and Electronic Engineering

Access to Document

10.1109/AVSS.2006.44

Cite this

Shimada, A., Arita, D., & Taniguchi, R. I. (2006). Dynamic control of adaptive mixture-of-Gaussians background model. In Proceedings - IEEE International Conference on Video and Signal Based Surveillance 2006, AVSS 2006 (pp. 5). Article 4020664 (Proceedings - IEEE International Conference on Video and Signal Based Surveillance 2006, AVSS 2006). IEEE Computer Society. https://doi.org/10.1109/AVSS.2006.44

Dynamic control of adaptive mixture-of-Gaussians background model. / Shimada, Atsushi; Arita, Daisaku; Taniguchi, Rin Ichiro.
Proceedings - IEEE International Conference on Video and Signal Based Surveillance 2006, AVSS 2006. IEEE Computer Society, 2006. p. 5 4020664 (Proceedings - IEEE International Conference on Video and Signal Based Surveillance 2006, AVSS 2006).

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

Shimada, A, Arita, D & Taniguchi, RI 2006, Dynamic control of adaptive mixture-of-Gaussians background model. in Proceedings - IEEE International Conference on Video and Signal Based Surveillance 2006, AVSS 2006., 4020664, Proceedings - IEEE International Conference on Video and Signal Based Surveillance 2006, AVSS 2006, IEEE Computer Society, pp. 5, IEEE International Conference on Video and Signal Based Surveillance 2006, AVSS 2006, Sydney, NSW, Australia, 11/22/06. https://doi.org/10.1109/AVSS.2006.44

Shimada A, Arita D, Taniguchi RI. Dynamic control of adaptive mixture-of-Gaussians background model. In Proceedings - IEEE International Conference on Video and Signal Based Surveillance 2006, AVSS 2006. IEEE Computer Society. 2006. p. 5. 4020664. (Proceedings - IEEE International Conference on Video and Signal Based Surveillance 2006, AVSS 2006). doi: 10.1109/AVSS.2006.44

@inproceedings{4a5d5dfb8d554eac9b8a5da47c8bbf9d,

title = "Dynamic control of adaptive mixture-of-Gaussians background model",

abstract = "We propose a method for create a background model in non-stationary scenes. Each pixel has a dynamic Gaussian mixture model Our approach can automatically change the number of Gaussians in each pixel. The number of Gaussians increases when pixel values often change because of Illumination change, object moving and so on. On the other hand, when pixel values are constant in a while, some Gaussians are eliminated or integrated. This process helps reduce computational time. We conducted experiments to investigate the effectiveness of our approach.",

author = "Atsushi Shimada and Daisaku Arita and Taniguchi, {Rin Ichiro}",

year = "2006",

doi = "10.1109/AVSS.2006.44",

language = "English",

isbn = "0769526888",

series = "Proceedings - IEEE International Conference on Video and Signal Based Surveillance 2006, AVSS 2006",

publisher = "IEEE Computer Society",

pages = "5",

booktitle = "Proceedings - IEEE International Conference on Video and Signal Based Surveillance 2006, AVSS 2006",

address = "United States",

note = "IEEE International Conference on Video and Signal Based Surveillance 2006, AVSS 2006 ; Conference date: 22-11-2006 Through 24-11-2006",

}

TY - GEN

T1 - Dynamic control of adaptive mixture-of-Gaussians background model

AU - Shimada, Atsushi

AU - Arita, Daisaku

AU - Taniguchi, Rin Ichiro

PY - 2006

Y1 - 2006

N2 - We propose a method for create a background model in non-stationary scenes. Each pixel has a dynamic Gaussian mixture model Our approach can automatically change the number of Gaussians in each pixel. The number of Gaussians increases when pixel values often change because of Illumination change, object moving and so on. On the other hand, when pixel values are constant in a while, some Gaussians are eliminated or integrated. This process helps reduce computational time. We conducted experiments to investigate the effectiveness of our approach.

AB - We propose a method for create a background model in non-stationary scenes. Each pixel has a dynamic Gaussian mixture model Our approach can automatically change the number of Gaussians in each pixel. The number of Gaussians increases when pixel values often change because of Illumination change, object moving and so on. On the other hand, when pixel values are constant in a while, some Gaussians are eliminated or integrated. This process helps reduce computational time. We conducted experiments to investigate the effectiveness of our approach.

UR - http://www.scopus.com/inward/record.url?scp=34547274240&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34547274240&partnerID=8YFLogxK

U2 - 10.1109/AVSS.2006.44

DO - 10.1109/AVSS.2006.44

M3 - Conference contribution

AN - SCOPUS:34547274240

SN - 0769526888

SN - 9780769526881

T3 - Proceedings - IEEE International Conference on Video and Signal Based Surveillance 2006, AVSS 2006

SP - 5

BT - Proceedings - IEEE International Conference on Video and Signal Based Surveillance 2006, AVSS 2006

PB - IEEE Computer Society

T2 - IEEE International Conference on Video and Signal Based Surveillance 2006, AVSS 2006

Y2 - 22 November 2006 through 24 November 2006

ER -

Dynamic control of adaptive mixture-of-Gaussians background model

Abstract

Publication series

Other

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this