基于自学习稀疏先验的三维SAR成像方法

3D SAR Imaging Method Based on Learned Sparse Prior

合成孔径雷达三维成像技术(3D SAR)能通过孔径维度扩展实现三维成像能力,但数据维度大、系统实现难、成像分辨率低。压缩感知稀疏重构技术在简化3D SAR系统、提升成像质量等方面展现出巨大潜力,但面临计算复杂度高、参数设置困难、弱稀疏场景适应差等新问题,制约了其实际应用。针对上述问题,该文结合卷积神经网络的特征学习及迭代算法的深度展开理论,提出了基于自学习稀疏先验的3D SAR成像方法。首先,探讨了常规3D SAR稀疏成像中矩阵向量线性表征模型的局限性,引入成像算子提升成像算法处理效率。其次,讨论了迭代算法映射网络的深度展开模型和实现方式,包括网络拓扑结构设计、算法参数的优化约束及网络的训练方法。最后,通过仿真数据和地面实验,证明了所提方法在提升成像精度的同时,其运行时间较传统稀疏成像算法降低一个数量级。

The development of 3D Synthetic Aperture Radar(SAR)imaging is currently hampered by issues such as high data dimension,high system complexity,and low imaging processing efficiency.Sparse SAR imaging has grown in importance as a research branch in SAR imaging due to the high potential of sparse signal processing techniques based on Compressed Sensing(CS)to show high potential in reducing system complexity and improving imaging quality.However,traditional sparse imaging methods are still constrained by high computational complexity,nontrivial parameter tuning,and poor adaptability to weakly sparse scenes.To address these issues,we propose a new 3D SAR imaging method based on learned sparse priors inspired by the deep unfolding concept.First,the limitations of the matrix-vector linear representation model are discussed,and an imaging operator is introduced to improve the algorithm’s imaging efficiency.Furthermore,this research focuses on algorithm network details,such as network topology design,the problem of complex-valued propagations,optimization constraints of algorithm parameters,and network training details.Finally,through simulations and measured experiments,it is proved that the proposed method can improve the imaging accuracy while reducing the running time by more than one order of magnitude compared with the conventional sparse imaging algorithms.