Fusing Complementary Operators to Enhance Foreground/Background Segmentation

Al-Mazeed, Ahmad H., Nixon, Mark S. and Gunn, Steve R., (2003) Fusing Complementary Operators to Enhance Foreground/Background Segmentation Harvey, Richard and Bagham, J. Andrew (eds.) At British Machine Vision Conference 2003. , pp. 501-510.


[img] PDF almazeed_bmvc2003.pdf - Other
Download (1MB)


Foreground/background segmentation is an active research area for moving object analysis. We combine two probabilistic approaches one of which estimates foreground/background probabilistic density and the other uses prior knowledge to decompose the colour space. The observed performance advantages are associated with the fusion of operators with completely different basis. Tests on outdoor and indoor sequences confirm the efficacy of this approach. The new algorithms can successfully identify and remove shadows and highlights with improved moving-object segmentation. A particular advantage of our evaluation is that it is the first approach that compares foreground/ background labelling with results obtained from labelling by broadcast techniques.

Item Type: Conference or Workshop Item (Paper)
Additional Information: Event Dates: 2003
Venue - Dates: British Machine Vision Conference 2003, 2003-01-01
Keywords: Motion Segmentation, Mixture Models, Foregraound/ Background Labelling, Gait
Organisations: Electronic & Software Systems, Southampton Wireless Group
ePrint ID: 258445
Date :
Date Event
Date Deposited: 20 Nov 2003
Last Modified: 17 Apr 2017 22:43
Further Information:Google Scholar
URI: http://eprints.soton.ac.uk/id/eprint/258445

Actions (login required)

View Item View Item