DML
DML Sharif University of Technology
Motion Vector Recovery With Gaussian Process Regression
  May   2011       Bayesian estimation Error concealment Gaussian process regression Motion vector recovery
H. Asheri , A. Bayati , H.R. Rabiee and M.H. Rohban
In this paper, we propose a Gaussian Process Regression (GPR) framework for concealment of corrupted motion vectors in predictive video coding of packet video systems. The problem of estimating the lost motion vectors is modeled as a kernel construction problem in a Bayesian framework. First, to describe the similarity between the neighboring motion vectors, a kernel function is defined. Then the parameters of the kernel function is estimated as the coefficients of a linear Bayesian estimator. The experimental results verify the superiority of the proposed algorithm over the conventional and state of the art motion vector concealment methods. Moreover, noticeable improvements on both objective and subjective measures, on videos with heavy packet loss rates have been achieved.
Type
Conference
Publisher
IEEE
ISSN
1520-6149
ISBN
978-1-4577-0537-3
Accession
12118560
Pages
953-956
Location
Prague, Czech Republic