Adaptive Sensing Matrix Design For Greedy Algorithms In Mmv Compressive Sensing

Sensing matrix can be designed with low coherence with the measurement matrix to improve the sparse signal recovery performance of greedy algorithms. However, most of the sensing matrix design algorithms are computationally expensive due to large number of iterations. This paper proposes an iteration-free sensing matrix design algorithm for multiple measurement vectors (MMV) compressive sensing. Specifically, sensing matrix is designed in the sense of the local cumulative cross-coherence (LCCC) of the sensing matrix with respect to the measurement matrix when the number of MMV is sufficient and the sparse signals are of full rank. Experiment results verify the effectiveness of the proposed algorithm in terms of improving the sparse signal recovery performance of greedy algorithms.