High-Resolution ISAR Imaging Based on 2-D Fast Sparse Bayesian Learning

We address the problem of high-resolution ISAR imaging in a Bayesian inference framework. Firstly, the probabilistic graphical model is constructed by imposing the sparsity-promoting Gamma-Gaussian prior to the distribution of scattering centers. In order to eliminate the issue of matrix inversion in conventional Sparse Bayesian Learning (SBL), a 2-D fast SBL is then proposed to improve the computational efficiency. Experimental results have demonstrated the effectiveness of the proposed method in sparse-aperture and low signal-to-noise ratio scenarios.