BEST FIT MODELS TEST FOR THE VIRTUAL CHANNEL IN DISTRIBUTED VIDEO CODING

Abstract

Wyner-Ziv (WZ) video coding – a particular case of distributed video coding (DVC) – is a new video coding paradigm based on two major Information Theory results: the Slepian-Wolf and Wyner-Ziv theorems. Most of the solutions available in the literature, model the correlation noise between the original frame and the so-called side information by virtual channel. However most of the DVC solutions in the literature assume Laplacian distribution as noise virtual channel model, in this study we perform three goodness-of-fit tests, the Kolmogorov-Smirnov test and the Chi-Square test and log-Likelihood test to study the nature of the virtual channel. The results show that a mixture of 3 (or 4) mixture Gaussian model can best describe this virtual channel.

Keywords

• Distributed video coding
• Virtual channel model
• KS test
• Chi-square test
• Log-likelihood ratio test