The Open UniversitySkip to content
 

Texture as pixel feature for video object segmentation

Ahmed, Rakib; Karmakar, Gour C. and Dooley, Laurence S. (2008). Texture as pixel feature for video object segmentation. Electronics Letters, 44(19) pp. 1126–1127.

Full text available as:
[img]
Preview
PDF (Not Set) - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
Download (153Kb)
DOI (Digital Object Identifier) Link: http://dx.doi.org/10.1049/el:20080407
Google Scholar: Look up in Google Scholar

Abstract

As texture represents one of the key perceptual attributes of any object, integrating textural information into existing video object segmentation frameworks affords the potential to achieve semantically improved performance. While object segmentation is fundamentally pixel-based classification, texture is normally defined for the entire image, which raises the question of how best to directly specify and characterise texture as a pixel feature. Introduced is a generic strategy for representing textural information so it can be seamlessly incorporated as a pixel feature into any video object segmentation paradigm. Both numerical and perceptual results upon various test sequences reveal considerable improvement in the object segmentation performance when textural information is embedded.

Item Type: Journal Article
ISSN: 0013-5194
Academic Unit/Department: Mathematics, Computing and Technology > Computing & Communications
Interdisciplinary Research Centre: Centre for Research in Computing (CRC)
Item ID: 11354
Depositing User: Laurence Dooley
Date Deposited: 30 Sep 2008 12:16
Last Modified: 25 Oct 2012 05:14
URI: http://oro.open.ac.uk/id/eprint/11354
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