DocumentCode :
1495573
Title :
Adaptive selection of model histograms in block-based background subtraction
Author :
Kim, Heonhwan ; Ku, Bon Woo ; Han, David K. ; Kang, Sook-Yang ; Ko, Hanseok
Author_Institution :
Sch. of Electr. Eng., Korea Univ., Seoul, South Korea
Volume :
48
Issue :
8
fYear :
2012
Firstpage :
434
Lastpage :
435
Abstract :
An adaptive block-based background modelling technique is proposed whereby the optimal number of model histograms is selected. The dynamic nature of a background tends to vary the pool of model histograms when capturing all possible scenes. Proposed is a novel method that recursively estimates the model weights, thereby continuously adjusting the number of histograms to robustly capture only the essence of intended objects. The proposed algorithm shows improved and reliable segmentation performance in various environments, including dynamic backgrounds with moving objects and repetitive variation of the pixel value.
Keywords :
image motion analysis; image segmentation; recursive estimation; adaptive block-based background modelling technique; adaptive selection; block-based background subtraction; model histograms; model weights; recursive estimation; reliable segmentation performance;
fLanguage :
English
Journal_Title :
Electronics Letters
Publisher :
iet
ISSN :
0013-5194
Type :
jour
DOI :
10.1049/el.2011.4068
Filename :
6183705
Link To Document :
بازگشت