Synthetic aperture radar (SAR) imaging has developed rapidly in recent years. Although the traditional sparse optimization imaging algorithm has achieved effective results, its shortcomings are slow imaging speed, large number of parameters, and high computational complexity. To solve the above problems, an end-to-end SAR deep learning imaging algorithm is proposed. Based on the existing SAR sparse imaging algorithm, the SAR imaging model is first rewritten to the SAR complex signal form based on the real-value model. Second, instead of arranging the two-dimensional echo data into a vector to continuously construct an observation matrix, the algorithm only derives the neural network imaging model based on the iteration soft threshold algorithm (ISTA) sparse algorithm in the two-dimensional data domain, and then reconstructs the observation scene through the superposition and expansion of the multi-layer network. Finally, through the experiment of simulation data and measured data of the three targets, it is verified that our algorithm is superior to the traditional sparse algorithm in terms of imaging quality, imaging time, and the number of parameters.

Vortex electromagnetic (EM) waves, with different orbital angular momentum (OAM) modes, have the ability to distinguish the azimuth of radar targets, and then the two-dimensional reconstruction of the targets can be achieved. However, the vortex EM wave imaging methods in published research have no ability to obtain the elevation of the targets, and thus, the three-dimensional spatial structure and richer feature information of the radar target cannot be obtained. Therefore, a three-dimensional imaging method of vortex EM waves with integer- and fractional-order OAM modes is proposed in this paper, which can realize a three-dimensional reconstruction of a radar target based on a uniform circular array (UCA) with two-step imaging. First, the vortex EM wave with integer- and fractional-order OAM modes is generated, and the echo model with different OAM mode types is established. Thereafter, the echo with integer order is processed to obtain the range-azimuth image by fast Fourier transform (FFT). Then, in order to realize the three-dimensional reconstruction, the echo with fractional order is processed by utilizing the butterfly operation and analyzing the characteristics of the fractional Bessel function. Moreover, the resolution and reconstruction precision of the azimuth and elevation are analyzed. Finally, the effectiveness of the proposed method is verified by simulation experiments.

In Synthetic aperture radar (SAR) recognition tasks, due to its special imaging principle, SAR images acquired from different viewpoints contain target features that may carry a large amount of information. These target features from different viewpoints enrich the training data and also improve the target recognition performance. However, considering the relative difficulty of acquiring SAR images and their fine annotations, if recognition is forced by fusion of multiview features when raw data is scarce, feature redundancy will be formed, which in turn will lead to a decrease in recognition accuracy. To remedy the above problem, a multiview inter-class dissimilarity feature fusion (MIDFF) network is proposed in this study. The proposed network can simultaneously input images of two classes, one of which is a multiview input used to extract features from the same target at different views, and the other is input from other classes, which we call Input-heterogeneous, used to extract heterogeneous features. Firstly, a method for rapidly generating sufficient training data for MIDFF is proposed, which generates training data by repeatedly combining images from different views and classes to ensure that a large number of training inputs are available even when raw SAR images are scarce. Secondly, a method of calculating and enhancing of inter-class dissimilarity (ICD) features is proposed to increase the inter-class distance and improve the inter-class separability. Then, the ICD and multiview features are fused to increase the features learned by the network and reduce feature redundancy. Finally, a multiview heterogeneous weighted loss function is proposed, which combines the calculation of inter-class similarity and heterogeneous loss. Through the gradual convergence of the loss function, the inter-class similarity decreases as the loss decreases, which further improves the target recognition performance. Experimental results on MSTAR and Civilian Vehicle SAR datasets show that our proposed method performs better than the state-of-the-art methods within sample scarcity conditions.

The vortex electromagnetic wave radar based on monostatic geometry can realize the imaging of a radar target in both range dimension and azimuth dimension by adjusting vortex electromagnetic wave modes, but it has no ability to distinguish the elevation of the radar target. To achieve three-dimensional imaging of the radar target, a three-dimensional imaging method of vortex electromagnetic wave based on bistatic geometry is proposed. The echo model of the target based on vortex electromagnetic wave in bistatic geometry is constructed firstly. The elevation resolution of the target is realized, and then the three-dimensional coordinate of the target is reconstructed. Moreover, the elevation resolution and the computational complexity of the proposed method are also analyzed. Simulation results demonstrate the effectiveness of the proposed method. The results also illustrate that the array element requirements and the computational complexity of presented algorithm are less than Multiple Signal Classification (MUSIC) algorithm.

A high-resolution three-dimensional (3D) image reconstruction method for a spinning target is proposed in this paper and the anisotropy is overcome by fusing different observation information acquired from the radar network. The proposed method will reconstruct the 3D scattering distribution, and the mapping of the reconstructed 3D image onto the imaging plane is identical to the two-dimensional (2D) imaging result. At first, the range compression and inverse radon transform is employed to produce the 2D image of the spinning target. In addition, the process of mapping the spinning target onto the imaging plane is analyzed and the mapping formulas which are to map the point onto the 2D image plane are derived. After the micro-Doppler signature about which every reconstructed point in 2D imaging result is extracted by the Radon transform, the extended Hough transform is adopted to calculate an important parameter about the micro-Doppler signature, and the 3D image reconstruction model for the spinning target is constructed based on the radar network. Finally, the algorithm for solving the reconstruction model is proposed and the 3D image of the spinning target is obtained. Some simulation results are given to illustrate the effectiveness of the proposed method, and results show that the mean square error (MSE) relatively holds a steady trend when the signal-to-noise ratio (SNR) is higher than −10 dB and the MSE of the reconstructed 3D target image is less than 0.15 when SNR is at the level of −10 dB.