DocumentCode :
1302181
Title :
Information integration for accurate foreground segmentation in complex scenes
Author :
Shen, Jianbing ; Yang, Weiguo ; Lu, Zhi ; Liao, Qiumei
Author_Institution :
Dept. of Electron. Eng., Tsinghua Univ., Beijing, China
Volume :
6
Issue :
5
fYear :
2012
fDate :
7/1/2012 12:00:00 AM
Firstpage :
596
Lastpage :
605
Abstract :
The authors propose a hybrid framework that combines frame difference and background subtraction to integrate complementary sources of information for monocular video segmentation. This framework is modelled as an optimisation process of an energy function, which is established on a Markov random field (MRF) and optimised by Gibbs sampling. It provides a way to exploit different kinds of information obtained from frame difference and background subtraction. Central to the proposed method are two facts - that shape prior can be flexibly obtained from frame difference, and shadow removal can be integrated into the framework with a background texture model. The experiments show that this approach reliably and accurately performs on sequences that include different scenarios (indoors, outdoors) and also addresses several canonical segmentation problems, such as camouflage, foreground aperture and so forth.
Keywords :
Markov processes; image segmentation; image sequences; image texture; video signal processing; Gibbs sampling; MRF; Markov random field; background subtraction; background texture model; canonical segmentation problems; complex scenes; energy function optimisation process; foreground aperture; foreground segmentation; frame difference; information integration; monocular video segmentation; shadow removal; video sequences;
fLanguage :
English
Journal_Title :
Image Processing, IET
Publisher :
iet
ISSN :
1751-9659
Type :
jour
DOI :
10.1049/iet-ipr.2011.0383
Filename :
6315717
Link To Document :
بازگشت