A multitask recovery algorithm for block-sparse signals

The paper considers the problem of jointly reconstructing multiple block-sparse signals with block partition unknown. Based on the framework of block sparse Bayesian learning (BSBL), we develop a new multitask recovery algorithm, called the extension algorithm of multitask block sparse Bayesian learning (EMBSBL). In contrast to existing methods, EMBSBL exploits not only the statistical interrelationships of signals (i.e., a degree of overlap of nonzero elements´ positions among different signals), but also signals´ intra-block correlation, and does not need a priori information on block partition. Simulations corroborate the theoretical developments.