Robust Object Detection in Severe Imaging Conditions using Co-Occurrence Background Model

Liang, Dong; Kaneko, Shun'ichi; Hashimoto, Manabu et al.

International Journal of Optomechatronics, 2014, 8(1), 14-29

Permalink : https://hdl.handle.net/2115/57664

このアイテムのアクセス数:889件（2026-10-12 13:04 集計）

閲覧可能ファイル 

ファイル フォーマット サイズ 閲覧回数 説明
orIJO1 pdf 2.05 MB 1,211

論文情報

ファイル出力 EndNote Basic出力 Mendeley出力

アクセス権
open access
URI
https://hdl.handle.net/2115/57664
タイトル
Robust Object Detection in Severe Imaging Conditions using Co-Occurrence Background Model
著者
Liang, Dong ; Kaneko, Shun'ichi ; Hashimoto, Manabu ; Iwata, Kenji ; Zhao, Xinyue ; Satoh, Yutaka
著者名
Liang, Dong
e-Rad_Researcher
50134789
著者名
Kaneko, Shun'ichi
著者名
Hashimoto, Manabu
著者名
Iwata, Kenji
著者名
Zhao, Xinyue
著者名
Satoh, Yutaka
言語
英語
キーワード
background modeling
low-illumination
narrow dynamic range
object detection
underexposure
発行日
2014-01
出版者
Taylor & Francis
収録物名
International Journal of Optomechatronics
巻(号)
8(1)
ページ
14-29
抄録
In this study, a spatial-dependent background model for detecting objects is used in severe imaging conditions. It is robust in the cases of sudden illumination fluctuation and burst motion background. More importantly, it is quite sensitive under the cases of underexposure, low-illumination, and narrow dynamic range, all of which are very common phenomenon using a surveillance camera. The background model maintains statistical models in the form of multiple pixel pairs with few parameters. Experiments using several challenging datasets (Heavy Fog, PETS-2001, AIST-INDOOR, and a real surveillance application) confirm the robust performance in various imaging conditions.
資源タイプ
学術雑誌論文
出版タイプ
Accepted Manuscript
権利情報
This is an Accepted Manuscript of an article published by Taylor & Francis in International Journal of Optomechatronics on vol. 8, no. 1, 2014, available online: http://www.tandfonline.com/10.1080/15599612.2014.890686.
PISSN
1559-9612
EISSN
1559-9620
関連情報 (isVersionOf)
出版社版DOI
https://doi.org/10.1080/15599612.2014.890686