Multi-Resolution Illumination Compensation for foreground extraction

Author

Suau, Xavier ; Casas, Josep R. ; Ruiz-Hidalgo, Javier

Author_Institution

Signal Theor. & Commun. Dept., Tech. Univ. of Catalonia, Barcelona, Spain

fYear

2009

fDate

7-10 Nov. 2009

Firstpage

3225

Lastpage

3228

Abstract

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.

Keywords

Gaussian processes; feature extraction; image resolution; image sequences; lighting; video signal processing; background estimation; false foreground segmentation; foreground extraction; multiresolution illumination compensation; temporal statistical parameters; video sequences; Clouds; Gaussian processes; Layout; Lighting; Meteorology; Object detection; Pixel; Pollution; Video sequences; Video surveillance; Foreground Extraction; Illumination; Video Surveillance;

fLanguage

English

Publisher

ieee

Conference_Titel

Image Processing (ICIP), 2009 16th IEEE International Conference on

Conference_Location

Cairo

ISSN

1522-4880

Print_ISBN

978-1-4244-5653-6

Electronic_ISBN

1522-4880

Type

conf

DOI

10.1109/ICIP.2009.5414358

Filename

5414358