Applying Data Mining Techniques in a Wyner-Ziv to H.264 Video Transcoder

This paper proposes an improved Wyner-Ziv to H.264 transcoder for supporting mobile-to-mobile video communications. In this framework, both transmitter and receptor should employ video encoders and decoders of low complexity. Taking advantage of both paradigms, in terms of low complexity algorithms, a suitable solution consists in transcoding from Wyner-Ziv to H.264. In order to reduce this process this paper proposes an algorithm which is based on the hypothesis that macroblock coding mode decisions in H.264 video have a high correlation with the distribution of the side information residual in Wyner-Ziv video. The proposed algorithm, which is based on data mining techniques, selects one sub-set of the several coding modes in H.264. Simulation results show that the proposed transcoder reduces the inter prediction complexity in H.264 by up to 53%, while maintaining coding efficiency.