A novel product coding and decoding scheme for wireless image transmission

This paper presents a novel generic channel coding scheme for image transmission over wireless channels. The product code is constructed using one classical convolutional code in one direction and one recursive systematic code (RSC) in the other direction. At the receiving end, the data are alternatively decoded along the two directions. In each iteration, any correctly decoded data in one direction will be used to constrain the decoding along the other direction. The constrained Viterbi decoding algorithm is designed in such a way that the survival paths are forced to pass through the positions where the bits have already been correctly decoded. With such a constraint, we achieve a reduction of candidate paths for the maximum likelihood (ML) decoding as well as a speed up of convergence. Experimental results show that the proposed scheme is able to outperform all existing schemes under some random and bursty error channel conditions.