Background modeling based on bidirectional analysis

Research output: Contribution to journalArticle

27 Citations (Scopus)

Abstract

Background modeling and subtraction is an essential task in video surveillance applications. Most traditional studies use information observed in past frames to create and update a background model. To adapt to background changes, the background model has been enhanced by introducing various forms of information including spatial consistency and temporal tendency. In this paper, we propose a new framework that leverages information from a future period. Our proposed approach realizes a low-cost and highly accurate background model. The proposed framework is called bidirectional background modeling, and performs background subtraction based on bidirectional analysis, i.e., analysis from past to present and analysis from future to present. Although a result will be output with some delay because information is taken from a future period, our proposed approach improves the accuracy by about 30% if only a 33-millisecond of delay is acceptable. Furthermore, the memory cost can be reduced by about 65% relative to typical background modeling.

Original languageEnglish
Article number6619102
Pages (from-to)1979-1986
Number of pages8
JournalUnknown Journal
DOIs
Publication statusPublished - 2013

Fingerprint

modeling
Information use
Costs
cost
Data storage equipment
analysis
video
surveillance

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition

Cite this

Background modeling based on bidirectional analysis. / Shimada, Atsushi; Nagahara, Hajime; Taniguchi, Rin-Ichiro.

In: Unknown Journal, 2013, p. 1979-1986.

Research output: Contribution to journalArticle

@article{8a2e492ebfaa411faa84318fa0c905a3,
title = "Background modeling based on bidirectional analysis",
abstract = "Background modeling and subtraction is an essential task in video surveillance applications. Most traditional studies use information observed in past frames to create and update a background model. To adapt to background changes, the background model has been enhanced by introducing various forms of information including spatial consistency and temporal tendency. In this paper, we propose a new framework that leverages information from a future period. Our proposed approach realizes a low-cost and highly accurate background model. The proposed framework is called bidirectional background modeling, and performs background subtraction based on bidirectional analysis, i.e., analysis from past to present and analysis from future to present. Although a result will be output with some delay because information is taken from a future period, our proposed approach improves the accuracy by about 30{\%} if only a 33-millisecond of delay is acceptable. Furthermore, the memory cost can be reduced by about 65{\%} relative to typical background modeling.",
author = "Atsushi Shimada and Hajime Nagahara and Rin-Ichiro Taniguchi",
year = "2013",
doi = "10.1109/CVPR.2013.258",
language = "English",
pages = "1979--1986",
journal = "Quaternary International",
issn = "1040-6182",
publisher = "Elsevier Limited",

}

TY - JOUR

T1 - Background modeling based on bidirectional analysis

AU - Shimada, Atsushi

AU - Nagahara, Hajime

AU - Taniguchi, Rin-Ichiro

PY - 2013

Y1 - 2013

N2 - Background modeling and subtraction is an essential task in video surveillance applications. Most traditional studies use information observed in past frames to create and update a background model. To adapt to background changes, the background model has been enhanced by introducing various forms of information including spatial consistency and temporal tendency. In this paper, we propose a new framework that leverages information from a future period. Our proposed approach realizes a low-cost and highly accurate background model. The proposed framework is called bidirectional background modeling, and performs background subtraction based on bidirectional analysis, i.e., analysis from past to present and analysis from future to present. Although a result will be output with some delay because information is taken from a future period, our proposed approach improves the accuracy by about 30% if only a 33-millisecond of delay is acceptable. Furthermore, the memory cost can be reduced by about 65% relative to typical background modeling.

AB - Background modeling and subtraction is an essential task in video surveillance applications. Most traditional studies use information observed in past frames to create and update a background model. To adapt to background changes, the background model has been enhanced by introducing various forms of information including spatial consistency and temporal tendency. In this paper, we propose a new framework that leverages information from a future period. Our proposed approach realizes a low-cost and highly accurate background model. The proposed framework is called bidirectional background modeling, and performs background subtraction based on bidirectional analysis, i.e., analysis from past to present and analysis from future to present. Although a result will be output with some delay because information is taken from a future period, our proposed approach improves the accuracy by about 30% if only a 33-millisecond of delay is acceptable. Furthermore, the memory cost can be reduced by about 65% relative to typical background modeling.

UR - http://www.scopus.com/inward/record.url?scp=84887334164&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84887334164&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2013.258

DO - 10.1109/CVPR.2013.258

M3 - Article

SP - 1979

EP - 1986

JO - Quaternary International

JF - Quaternary International

SN - 1040-6182

M1 - 6619102

ER -