Sciweavers

Share
ICCV
2007
IEEE

Optimization and Learning for Registration of Moving Dynamic Textures

9 years 7 months ago
Optimization and Learning for Registration of Moving Dynamic Textures
We address the problem of registering a sequence of images in a moving dynamic texture video. This involves optimization with respect to camera motion, the average image, and the dynamic texture model. This problem is highly illposed and almost impossible to have good solutions without priors. In this paper, we introduce powerful priors for this problem, based on two simple observations: 1) registration should simplify the dynamic texture model while preserving all useful information. It motivates us to compute a prior for the dynamic texture by marginalizing over specific dynamics in the space of all stable auto-regressive sequences; 2) the statistics of derivative filter responses in the average image can be significantly changed by registration, and better registration should lead to a sharper average image. This offers us the prior of requiring the derivative distribution of the estimated average image to be close to that learned from the input image sequence. With these priors, a...
Junzhou Huang, Xiaolei Huang, Dimitris N. Metaxas
Added 14 Oct 2009
Updated 30 Oct 2009
Type Conference
Year 2007
Where ICCV
Authors Junzhou Huang, Xiaolei Huang, Dimitris N. Metaxas
Comments (0)
books