Case-based background modeling

Associative background database towards low-cost and high-performance change detection

Atsushi Shimada, Yosuke Nonaka, Hajime Nagahara, Rin-Ichiro Taniguchi

研究成果: ジャーナルへの寄稿記事

11 引用 (Scopus)

抄録

Background modeling and subtraction is an essential task in video surveillance applications. Many researchers have discussed about an improvement of performance of a background model, and a reduction of memory usage or computational cost. To adapt to background changes, a background model has been enhanced by introducing various information including a spatial consistency, a temporal tendency, etc. with a large memory allocation. Meanwhile, an approach to reduce a memory cost cannot provide better accuracy of a background subtraction. To tackle the trade-off problem, this paper proposes a novel framework named "case-based background modeling". The characteristics of the proposed method are (1) a background model is created, or removed when necessary, (2) case-by-case model sharing by some of the pixels, (3) pixel features are divided into two groups, one for model selection and the other for modeling. These approaches realize a low-cost and high accurate background model. The memory usage and the computational cost could be reduced by half of a traditional method and the accuracy was superior to the method.

元の言語英語
ページ(範囲)1121-1131
ページ数11
ジャーナルMachine Vision and Applications
25
発行部数5
DOI
出版物ステータス出版済み - 1 1 2014

Fingerprint

Costs
Data storage equipment
Pixels
Storage allocation (computer)

All Science Journal Classification (ASJC) codes

  • Software
  • Hardware and Architecture
  • Computer Vision and Pattern Recognition
  • Computer Science Applications

これを引用

Case-based background modeling : Associative background database towards low-cost and high-performance change detection. / Shimada, Atsushi; Nonaka, Yosuke; Nagahara, Hajime; Taniguchi, Rin-Ichiro.

:: Machine Vision and Applications, 巻 25, 番号 5, 01.01.2014, p. 1121-1131.

研究成果: ジャーナルへの寄稿記事

@article{8110fe7f3da34a1b8a651a8d46a5b4f4,
title = "Case-based background modeling: Associative background database towards low-cost and high-performance change detection",
abstract = "Background modeling and subtraction is an essential task in video surveillance applications. Many researchers have discussed about an improvement of performance of a background model, and a reduction of memory usage or computational cost. To adapt to background changes, a background model has been enhanced by introducing various information including a spatial consistency, a temporal tendency, etc. with a large memory allocation. Meanwhile, an approach to reduce a memory cost cannot provide better accuracy of a background subtraction. To tackle the trade-off problem, this paper proposes a novel framework named {"}case-based background modeling{"}. The characteristics of the proposed method are (1) a background model is created, or removed when necessary, (2) case-by-case model sharing by some of the pixels, (3) pixel features are divided into two groups, one for model selection and the other for modeling. These approaches realize a low-cost and high accurate background model. The memory usage and the computational cost could be reduced by half of a traditional method and the accuracy was superior to the method.",
author = "Atsushi Shimada and Yosuke Nonaka and Hajime Nagahara and Rin-Ichiro Taniguchi",
year = "2014",
month = "1",
day = "1",
doi = "10.1007/s00138-013-0563-4",
language = "English",
volume = "25",
pages = "1121--1131",
journal = "Machine Vision and Applications",
issn = "0932-8092",
publisher = "Springer Verlag",
number = "5",

}

TY - JOUR

T1 - Case-based background modeling

T2 - Associative background database towards low-cost and high-performance change detection

AU - Shimada, Atsushi

AU - Nonaka, Yosuke

AU - Nagahara, Hajime

AU - Taniguchi, Rin-Ichiro

PY - 2014/1/1

Y1 - 2014/1/1

N2 - Background modeling and subtraction is an essential task in video surveillance applications. Many researchers have discussed about an improvement of performance of a background model, and a reduction of memory usage or computational cost. To adapt to background changes, a background model has been enhanced by introducing various information including a spatial consistency, a temporal tendency, etc. with a large memory allocation. Meanwhile, an approach to reduce a memory cost cannot provide better accuracy of a background subtraction. To tackle the trade-off problem, this paper proposes a novel framework named "case-based background modeling". The characteristics of the proposed method are (1) a background model is created, or removed when necessary, (2) case-by-case model sharing by some of the pixels, (3) pixel features are divided into two groups, one for model selection and the other for modeling. These approaches realize a low-cost and high accurate background model. The memory usage and the computational cost could be reduced by half of a traditional method and the accuracy was superior to the method.

AB - Background modeling and subtraction is an essential task in video surveillance applications. Many researchers have discussed about an improvement of performance of a background model, and a reduction of memory usage or computational cost. To adapt to background changes, a background model has been enhanced by introducing various information including a spatial consistency, a temporal tendency, etc. with a large memory allocation. Meanwhile, an approach to reduce a memory cost cannot provide better accuracy of a background subtraction. To tackle the trade-off problem, this paper proposes a novel framework named "case-based background modeling". The characteristics of the proposed method are (1) a background model is created, or removed when necessary, (2) case-by-case model sharing by some of the pixels, (3) pixel features are divided into two groups, one for model selection and the other for modeling. These approaches realize a low-cost and high accurate background model. The memory usage and the computational cost could be reduced by half of a traditional method and the accuracy was superior to the method.

UR - http://www.scopus.com/inward/record.url?scp=84902117463&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84902117463&partnerID=8YFLogxK

U2 - 10.1007/s00138-013-0563-4

DO - 10.1007/s00138-013-0563-4

M3 - Article

VL - 25

SP - 1121

EP - 1131

JO - Machine Vision and Applications

JF - Machine Vision and Applications

SN - 0932-8092

IS - 5

ER -