The magnitude sparse representation of compressed sensing SAR imaging

Compressed perception has been widely used in synthetic aperture radar (SAR) imaging due to its simplicity and efficiency. One of the prerequisites for using compressed perception theory is that the imaging scene can be sparsely represented. However, the SAR imaging scene may be complex and the whole scene may be filled with diffuse electromagnetic radiation. It is very difficult to directly perform sparse representation of a complex scene in this case. To address the above problems, this paper proposes a magnitude sparse representation method for sparse representation of complex scenes. In contrast to the problem of directly considering the sparse representation of a complex scene, in this paper, the magnitude and phase of the scene are treated separately, and only the scene magnitude is sparsely represented, so that the scene magnitude can be reconstructed and then the scene phase can be estimated accordingly. In the proposed framework, in addition to the sparse information in the magnitude, the real-valued information of the magnitude and the a priori information of the coefficient distribution in the sparse representation are also used, and the idea of one-bit is introduced to improve the noise immunity. Simulation experimental results show that the method can effectively improve the imaging quality.