Dynamic Textures Modeling Using Temporal Mixing Coefficients Reduction

0439651 - ÚTIA 2015 RIV US eng C - Conference Paper (international conference)
Havlíček, Michal - Haindl, Michal - Filip, Jiří
Dynamic Textures Modeling Using Temporal Mixing Coefficients Reduction.
2014 International Workshop on Computational Intelligence for Multimedia Understanding (IWCIM). Los Alamitos, USA: IEEE Computer Society CPS, 2014. ISBN 978-1-4799-7971-4.
[International Workshop on Computational Intelligence for Multimedia Understanding 2014 (IWCIM). Paris (FR), 01.11.2014-02.11.2014]
R&D Projects: GA ČR(CZ) GA14-10911S; GA ČR(CZ) GA14-02652S
Institutional support: RVO:67985556
Keywords : Dynamic texture * texture analysis * texture synthesis * data compression
Subject RIV: BD - Theory of Information
http://library.utia.cas.cz/separaty/2014/RO/haindl-0439651.pdf

Real world materials often change their appearance over time. If these variations are spatially and temporally homogeneous then the material visual appearance can be represented by a dynamic texture which is a natural extension of classic texture concept including the time as an extra dimension. In this article we present possible way to handle multispectral dynamic textures based on a combination of input data eigen analysis and subsequent processing of temporal mixing coefficients. The proposed method exhibits overall good performance, offers extremely fast synthesis which is not restricted in temporal dimension and simultaneously enables to compress significantly the original measured visual data.
Permanent Link: http://hdl.handle.net/11104/0242972