Sparse Representation-Based ISAR Imaging Using Markov Random Fields

To encourage the continuity of the target scene, a novel sparse representation (SR)-based inverse synthetic aperture radar (ISAR) imaging algorithm is proposed by leveraging the Markov random fields (MRF). The ISAR imaging problem is reformulated in a Bayesian framework where correlated priors are used for the hidden variables to enforce the continuity of target scene. To further enforce the nonzero or zero scatterers to cluster in a spatial consistent manner, the MRF is used as the prior for the support of the target scene. To surmount the difficulty of calculating the posterior due to the imposed correlated priors and the MRF, variational Bayes expectation-maximization (VBEM) method is used to simultaneously approximate the posterior of the hidden variables and estimate the model parameters of the MRF. The convergence of the method is easily diagnosed by commonly used stopping criterion. Both the synthetic and the experimental results demonstrate that the proposed algorithm can achieve substantial improvements in terms of preserving the weak scatterers and removing noise components over other reported SR-based ISAR imaging algorithms.