The Open UniversitySkip to content
 

Region-Based Shape Incorporation for Probabilistic Spatio-Temporal Video Object Segmentation

Ahmed, R.; Karmakar, G. C. and Dooley, L. S. (2006). Region-Based Shape Incorporation for Probabilistic Spatio-Temporal Video Object Segmentation. In: IEEE International Conference on Image Processing (ICIP’06), 8-11 Oct 2006, Atlanta.

URL: http://ieeexplore.ieee.org/search/wrapper.jsp?arnu...
DOI (Digital Object Identifier) Link: http://dx.doi.org/10.1109/ICIP.2006.312771
Google Scholar: Look up in Google Scholar

Abstract

Embedding generic shape information into probabilistic spatio-temporal video object segmentation is of pivotal importance to achieving better segmentation, since it provides valuable perceptual clues for humans in both distinguishing and recognising objects. Recently a probabilistic spatio-temporal video object segmentation algorithm incorporating shape information has been proposed, though since it is restricted to only pixel features, the probability of a pixel belonging to a certain cluster is directly correlated with its spatial location, which theoretically limits the segmentation performance of the technique. To address this problem, this paper proposes a new probabilistic spatio-temporal video object segmentation algorithm that incorporates generic shape information based on its region. Experimental results reveal a significant performance improvement in arbitrary-shaped video object segmentation compared with other contemporary methods for a variety of standard video test sequences

Item Type: Conference Item
ISSN: 1522-4880
Academic Unit/Department: Mathematics, Computing and Technology > Computing & Communications
Interdisciplinary Research Centre: Centre for Research in Computing (CRC)
Item ID: 10560
Depositing User: Laurence Dooley
Date Deposited: 10 Apr 2008
Last Modified: 02 Dec 2010 20:07
URI: http://oro.open.ac.uk/id/eprint/10560
Share this page:

Actions (login may be required)

View Item
Report issue / request change

Policies | Disclaimer

© The Open University   + 44 (0)870 333 4340   general-enquiries@open.ac.uk