Object detection based on spatiotemporal background models

Satoshi Yoshinaga, Atsushi Shimada, Hajime Nagahara, Rin Ichiro Taniguchi

研究成果: ジャーナルへの寄稿記事

26 引用 (Scopus)

抄録

We present a robust background model for object detection and its performance evaluation using the database of the Background Models Challenge (BMC). Background models should detect foreground objects robustly against background changes, such as "illumination changes" and "dynamic changes". In this paper, we propose two types of spatiotemporal background modeling frameworks that can adapt to illumination and dynamic changes in the background. Spatial information can be used to absorb the effects of illumination changes because they affect not only a target pixel but also its neighboring pixels. Additionally, temporal information is useful in handling the dynamic changes, which are observed repeatedly. To establish the spatiotemporal background model, our frameworks model an illumination invariant feature and a similarity of intensity changes among a set of pixels according to statistical models, respectively. Experimental results obtained for the BMC database show that our models can detect foreground objects robustly against background changes.

元の言語英語
ページ(範囲)84-91
ページ数8
ジャーナルComputer Vision and Image Understanding
122
DOI
出版物ステータス出版済み - 5 1 2014

Fingerprint

Lighting
Pixels
Object detection

All Science Journal Classification (ASJC) codes

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition

これを引用

Object detection based on spatiotemporal background models. / Yoshinaga, Satoshi; Shimada, Atsushi; Nagahara, Hajime; Taniguchi, Rin Ichiro.

:: Computer Vision and Image Understanding, 巻 122, 01.05.2014, p. 84-91.

研究成果: ジャーナルへの寄稿記事

@article{73d99ca03d53406d97c28138d9dba1b8,
title = "Object detection based on spatiotemporal background models",
abstract = "We present a robust background model for object detection and its performance evaluation using the database of the Background Models Challenge (BMC). Background models should detect foreground objects robustly against background changes, such as {"}illumination changes{"} and {"}dynamic changes{"}. In this paper, we propose two types of spatiotemporal background modeling frameworks that can adapt to illumination and dynamic changes in the background. Spatial information can be used to absorb the effects of illumination changes because they affect not only a target pixel but also its neighboring pixels. Additionally, temporal information is useful in handling the dynamic changes, which are observed repeatedly. To establish the spatiotemporal background model, our frameworks model an illumination invariant feature and a similarity of intensity changes among a set of pixels according to statistical models, respectively. Experimental results obtained for the BMC database show that our models can detect foreground objects robustly against background changes.",
author = "Satoshi Yoshinaga and Atsushi Shimada and Hajime Nagahara and Taniguchi, {Rin Ichiro}",
year = "2014",
month = "5",
day = "1",
doi = "10.1016/j.cviu.2013.10.015",
language = "English",
volume = "122",
pages = "84--91",
journal = "Computer Vision and Image Understanding",
issn = "1077-3142",
publisher = "Academic Press Inc.",

}

TY - JOUR

T1 - Object detection based on spatiotemporal background models

AU - Yoshinaga, Satoshi

AU - Shimada, Atsushi

AU - Nagahara, Hajime

AU - Taniguchi, Rin Ichiro

PY - 2014/5/1

Y1 - 2014/5/1

N2 - We present a robust background model for object detection and its performance evaluation using the database of the Background Models Challenge (BMC). Background models should detect foreground objects robustly against background changes, such as "illumination changes" and "dynamic changes". In this paper, we propose two types of spatiotemporal background modeling frameworks that can adapt to illumination and dynamic changes in the background. Spatial information can be used to absorb the effects of illumination changes because they affect not only a target pixel but also its neighboring pixels. Additionally, temporal information is useful in handling the dynamic changes, which are observed repeatedly. To establish the spatiotemporal background model, our frameworks model an illumination invariant feature and a similarity of intensity changes among a set of pixels according to statistical models, respectively. Experimental results obtained for the BMC database show that our models can detect foreground objects robustly against background changes.

AB - We present a robust background model for object detection and its performance evaluation using the database of the Background Models Challenge (BMC). Background models should detect foreground objects robustly against background changes, such as "illumination changes" and "dynamic changes". In this paper, we propose two types of spatiotemporal background modeling frameworks that can adapt to illumination and dynamic changes in the background. Spatial information can be used to absorb the effects of illumination changes because they affect not only a target pixel but also its neighboring pixels. Additionally, temporal information is useful in handling the dynamic changes, which are observed repeatedly. To establish the spatiotemporal background model, our frameworks model an illumination invariant feature and a similarity of intensity changes among a set of pixels according to statistical models, respectively. Experimental results obtained for the BMC database show that our models can detect foreground objects robustly against background changes.

UR - http://www.scopus.com/inward/record.url?scp=84898060004&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84898060004&partnerID=8YFLogxK

U2 - 10.1016/j.cviu.2013.10.015

DO - 10.1016/j.cviu.2013.10.015

M3 - Article

AN - SCOPUS:84898060004

VL - 122

SP - 84

EP - 91

JO - Computer Vision and Image Understanding

JF - Computer Vision and Image Understanding

SN - 1077-3142

ER -