MULTI-RESOLUTION ILLUMINATION COMPENSATION FOR FOREGROUND EXTRACTION

被引：1

作者：

Suau, Xavier ^{[1
]}

Casas, Josep R. ^{[1
]}

Ruiz-Hidalgo, Javier ^{[1
]}

机构：

[1] Tech Univ Catalonia, Signal Theory & Commun Dept, Barcelona 08034, Spain

来源：

2009 16TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, VOLS 1-6 | 2009年

关键词：

Illumination; Foreground Extraction; Video Surveillance;

D O I：

10.1109/ICIP.2009.5414358

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Illumination changes may lead to false foreground (FG) segmentation and tracking results. Most of the existing FG extraction algorithms obtain a background (BG) estimation from temporal statistical parameters. Such algorithms consider a quasi-static BG which does not change but slowly. Therefore, fast illumination changes are not taken into account by the BG estimator and they are considered as FG. The aim of the proposed algorithm is to reduce illumination effects in video sequences in order to improve foreground segmentation performances.

引用

页码：3225 / 3228

页数：4

共 7 条

[1]

AGARWAL V, 2003, 574 ECE, P1

[2] A variational framework for Retinex [J].

Kimmel, R ;

Elad, M ;

Shaked, D ;

Keshet, R ;

Sobel, I .

INTERNATIONAL JOURNAL OF COMPUTER VISION, 2003, 52 (01) :7-23

[3]

MATSUSHITA Y, 2005, COMP SOC C COMP VIS, V26, P1336

[4]

PORIKLI F, 2005, WORKSH MOT VID COMP, V2, P20

[5]

Stauffer C., 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149), P246, DOI 10.1109/CVPR.1999.784637

[6]

Weiss Y, 2001, EIGHTH IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION, VOL II, PROCEEDINGS, P68, DOI 10.1109/ICCV.2001.937606

[7]

Xu M., 2001, ILLUMINATION INVARIA

← 1 →