A hyper-trellis based turbo decoder for Wyner-Ziv video coding

Abstract

A new approach to design video coding schemes for wireless video applications has emerged recently. Schemes using this approach are based on the principle of distributed source coding, and they exploit the correlation in the frames of the video sequence at the decoder. One such scheme models the correlation between frames as a Laplacian channel, and uses a turbo code to correct errors occurring in this pseudo-channel. Existing implementations use a sub-optimal approximation to compute the channel likelihoods in the BCJR algorithm in the turbo decoder. To resolve this sub-optimality, we propose applying the BCJR algorithm on a trellis-structure with parallel transitions. This trellis structure is called a hyper-trellis. The BCJR maximum a posteriori algorithm is modified to use the hyper-trellis, and computation of the channel-likelihoods are shown to be optimal on the hyper-trellis. Simulation results show that the hyper-trellis approach can yield a 5 dB improvement in peak signal-to-noise ratio.