Laplace prior based distributed compressive sensing

Abstract

Bayesian compressive sensing (BCS) utilizes the prior distribution of signal coefficients to reconstruct the original signal. The widely used prior is Laplace and Gaussian distributed. In this paper, we use the scene of L sets of signal sparse coefficients which are statistically related and take advantage of Laplace prior and statistically interrelationship among signals to propose the Laplace prior based distributed Bayesian compressive sensing. We provide the experiment result to demonstrating that the proposed method is an effective reconstruction algorithm and has a good performance.