Maintenance of blind background model for robust object detection

研究成果: ジャーナルへの寄稿記事

1 引用 (Scopus)

抄録

An adaptive background model plays an important role for object detection in a scene which includes illumination changes. An updating process of the background model is utilized to improve the robustness against illumination changes. However, the process sometimes causes a false-negative problem when a moving object stops in an observed scene. A paused object will be gradually trained as the background since the observed pixel value is directly used for the model update. In addition, the original background model hidden by the paused object cannot be updated. If the illumination changes behind the paused object, a false-positive problem will be caused when the object restarts to move. In this paper, we propose 1) a method to inhibit background training to avoid the falsenegative problem, and 2) a method to update an original background region occluded by a paused object to avoid the false-positive problem. We have used a probabilistic approach and a predictive approach of the background model to solve these problems. The great contribution of this paper is that we can keep paused objects from being trained by modeling the original background hidden by them. And also, our approach has an ability to adapt to various illumination changes. Our experimental results show that the proposed method can detect stopped objects robustly, and in addition, it is also robust for illumination changes and as efficient as the state-of-the-art method.

元の言語英語
ページ(範囲)148-159
ページ数12
ジャーナルIPSJ Transactions on Computer Vision and Applications
3
DOI
出版物ステータス出版済み - 12 1 2011

Fingerprint

Lighting
Pixels
Object detection

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition

これを引用

Maintenance of blind background model for robust object detection. / Shimada, Atsushi; Yoshinaga, Satoshi; Taniguchi, Rin-Ichiro.

:: IPSJ Transactions on Computer Vision and Applications, 巻 3, 01.12.2011, p. 148-159.

研究成果: ジャーナルへの寄稿記事

@article{915481e66233415099cf0cb201c6fa6a,
title = "Maintenance of blind background model for robust object detection",
abstract = "An adaptive background model plays an important role for object detection in a scene which includes illumination changes. An updating process of the background model is utilized to improve the robustness against illumination changes. However, the process sometimes causes a false-negative problem when a moving object stops in an observed scene. A paused object will be gradually trained as the background since the observed pixel value is directly used for the model update. In addition, the original background model hidden by the paused object cannot be updated. If the illumination changes behind the paused object, a false-positive problem will be caused when the object restarts to move. In this paper, we propose 1) a method to inhibit background training to avoid the falsenegative problem, and 2) a method to update an original background region occluded by a paused object to avoid the false-positive problem. We have used a probabilistic approach and a predictive approach of the background model to solve these problems. The great contribution of this paper is that we can keep paused objects from being trained by modeling the original background hidden by them. And also, our approach has an ability to adapt to various illumination changes. Our experimental results show that the proposed method can detect stopped objects robustly, and in addition, it is also robust for illumination changes and as efficient as the state-of-the-art method.",
author = "Atsushi Shimada and Satoshi Yoshinaga and Rin-Ichiro Taniguchi",
year = "2011",
month = "12",
day = "1",
doi = "10.2197/ipsjtcva.3.148",
language = "English",
volume = "3",
pages = "148--159",
journal = "IPSJ Transactions on Computer Vision and Applications",
issn = "1882-6695",
publisher = "Information Processing Society of Japan",

}

TY - JOUR

T1 - Maintenance of blind background model for robust object detection

AU - Shimada, Atsushi

AU - Yoshinaga, Satoshi

AU - Taniguchi, Rin-Ichiro

PY - 2011/12/1

Y1 - 2011/12/1

N2 - An adaptive background model plays an important role for object detection in a scene which includes illumination changes. An updating process of the background model is utilized to improve the robustness against illumination changes. However, the process sometimes causes a false-negative problem when a moving object stops in an observed scene. A paused object will be gradually trained as the background since the observed pixel value is directly used for the model update. In addition, the original background model hidden by the paused object cannot be updated. If the illumination changes behind the paused object, a false-positive problem will be caused when the object restarts to move. In this paper, we propose 1) a method to inhibit background training to avoid the falsenegative problem, and 2) a method to update an original background region occluded by a paused object to avoid the false-positive problem. We have used a probabilistic approach and a predictive approach of the background model to solve these problems. The great contribution of this paper is that we can keep paused objects from being trained by modeling the original background hidden by them. And also, our approach has an ability to adapt to various illumination changes. Our experimental results show that the proposed method can detect stopped objects robustly, and in addition, it is also robust for illumination changes and as efficient as the state-of-the-art method.

AB - An adaptive background model plays an important role for object detection in a scene which includes illumination changes. An updating process of the background model is utilized to improve the robustness against illumination changes. However, the process sometimes causes a false-negative problem when a moving object stops in an observed scene. A paused object will be gradually trained as the background since the observed pixel value is directly used for the model update. In addition, the original background model hidden by the paused object cannot be updated. If the illumination changes behind the paused object, a false-positive problem will be caused when the object restarts to move. In this paper, we propose 1) a method to inhibit background training to avoid the falsenegative problem, and 2) a method to update an original background region occluded by a paused object to avoid the false-positive problem. We have used a probabilistic approach and a predictive approach of the background model to solve these problems. The great contribution of this paper is that we can keep paused objects from being trained by modeling the original background hidden by them. And also, our approach has an ability to adapt to various illumination changes. Our experimental results show that the proposed method can detect stopped objects robustly, and in addition, it is also robust for illumination changes and as efficient as the state-of-the-art method.

UR - http://www.scopus.com/inward/record.url?scp=84855407272&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84855407272&partnerID=8YFLogxK

U2 - 10.2197/ipsjtcva.3.148

DO - 10.2197/ipsjtcva.3.148

M3 - Article

VL - 3

SP - 148

EP - 159

JO - IPSJ Transactions on Computer Vision and Applications

JF - IPSJ Transactions on Computer Vision and Applications

SN - 1882-6695

ER -