Deep learning has been widely used in automatic target recognition (ATR) for synthetic aperture radar (SAR) recently. However, most of the studies are based on the network structure in optical images and lack full consideration of the inherent characteristics of SAR targets, which limits the improvement of recognition accuracy and makes poor generalization ability. In addition, due to the black-box characteristics, it is difficult to effectively interpret SAR ATR results. To conquer these problems, we propose an electromagnetic scattering feature (ESF) module embedded network based on attributed scattering center (ASC) model to incorporate the SAR targets’ characteristics into the deep learning framework. First, a novel convolutional neural network (CNN)-based algorithm for extracting ASC parameters is proposed, which makes the network focus on target features under the guidance of physical model. Then, the ESF module is designed based on a well-trained ASC parameters extractor to inject the learned target features into the classification network for more robust and interpretable results. Besides, two structures are proposed combined with the ESF module for single-view and multiview SAR target classification, which further illustrates the portability of the module. Experiments on the Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset show the validity of the proposed CNN-based ASC extractor and the ESF module embedded classification network. Compared with ordinary networks, our method can achieve higher classification accuracy under complex conditions, which reflects the better generalization performance of the algorithm. Furthermore, through visualization analysis of the classification results, we show the interpretability of the network combined with the electromagnetic scattering characteristics.

Machine learning methods for synthetic aperture radar (SAR) image automatic target recognition (ATR) can be divided into two main types: traditional methods and deep learning methods. The deep learning methods can learn the high-dimensional features of the target directly, and usually obtain high target recognition accuracy. However, they lack full consideration of SAR targets’ inherent characteristics resulting in poor generalization and interpretation ability. Compared with the deep learning methods, traditional methods can get more interpretable and stable results with model-based features. In order to take full advantage of these two kinds of methods, we propose target part attention network based on the attributed scattering center (ASC) model to integrate the electromagnetic characteristics with the deep learning framework. Firstly, considering the importance of scattering structure for SAR ATR, we design a target part model based on ASC model. Then, a novel part attention module based on Scaled Dot-Product Attention mechanism is proposed, which directly associates the features of target parts with the classification results. Finally, we give the derivation method of the importance of each part, which is of great significance for practical application and the interpretation of SAR ATR. Experiments on the MSTAR data set demonstrate the effectiveness of the proposed part attention network. Compared with existing studies, it can achieve higher and more robust classification accuracy under different complex conditions. Furthermore, combined with the importance of parts, we constructed two effective interpretable analysis methods for deep learning network classification results.

The realistic false targets caused by interrupted sampling repeater jamming (ISRJ) can mask the real target, leading to the failure of radar target detection. In this letter, a method based on jointly designing complementary sequences and receiving filters under the signal-to-noise ratio loss constraint is proposed to suppress ISRJ. A gradient-based nonlinear programming solver and the Lagrange multiplier method are used to optimize the sequences and filters alternately. Numerical results show that the proposed method can generate sequences and receiving filters with good correlation properties and anti-ISRJ performance.

Sequence set design with good correlation properties and Doppler tolerance has been a classic and important problem in many multi-channel systems, including but not limited to the multiple-input multiple-output and simultaneous polarimetric radar systems. In this paper, we first consider the problem of jointly designing Doppler resilient unimodular sequences and receiving filters to minimize the metric weighted integrated sidelobe level (WISL), which can be used to construct sequence set with "thumbtack" co-channel and zero cross-channel ambiguity functions. To control the signal-to-noise ratio (SNR) loss caused by the mismatched filter, a peak constraint function is added into the objective function based on the penalty function method. An algorithm based on the alternatively iterative scheme and general majorization-minimization method is developed to tackle the constrained joint design problem. Moreover, the proposed algorithm is then extended to optimize the l_p -norm of sidelobes of ambiguity functions, which gives a way to optimize the weighted peak sidelobe level (WPSL) metric. Due to the use of the fast Fourier transform (FFT) algorithm and a general acceleration scheme, the proposed algorithm can be realized efficiently. A number of simulations are provided to demonstrate the excellent performance of the proposed sequence set synthesis algorithms. Besides, an application of using the designed Doppler resilient sequence set on the simultaneous polarimetric radar to detect multiple moving targets in strong clutter scene is given via simulation, which further verifies the practicability of the proposed algorithm.

Simultaneous polarimetric radars can measure the polarization scattering matrix (PSM) of moving targets within one pulse. The key point is the orthogonal waveform design to reduce the interference caused by the simultaneous transmission and reception. Meanwhile, to ensure the measurement accuracy of moving targets, the Doppler tolerance of the transmitted waveforms is also important. In this article, first, a matched filter (MF) at the receiver is considered and a unified framework with a newly proposed objective function to design Doppler resilient sequences under several constraints is described. The proposed objective function contains the widely used peak sidelobe level (PSL) and the integrated sidelobe level (ISL) as special cases. Meanwhile, a series of constraint conditions, including the unimodular constraint, the uncertainty modulus constraint, and the PAR constraint, is considered. Thereafter, a mismatched filter is considered for further improving the correlation properties and a similar framework for designing the optimal receiving filter at the expense of a controllable signal-to-noise ratio (SNR) loss is proposed. Numerical results are presented to verify the performance of the proposed methods. The designed sequence pair is also implemented on a fully polarimetric system to measure the PSM of a canonical target in the anechoic chamber, and the effectiveness of the proposed framework is verified by using the simultaneous polarimetric radar. It is predicted that the framework has the potential to be applied for other multichannel systems.

The ambiguity function (AF), which is used to evaluate the range and Doppler resolutions, plays an important role in radar systems. In this article, we consider the problems of jointly designing unimodular sequence and receiving filters, and also unimodular complementary sequences and corresponding receiving filters with desired AF shapes. The design problems are formulated as the minimization of the weighted integrated sidelobe level (WISL) and the minimization of the complementary integrated sidelobe level (CISL), respectively, under the constraint of the signal-to-noise ratio (SNR) loss. Algorithms based on the alternately iterative minimization method and the majorization-minimization method are developed to tackle the optimization problems. Numerical results are demonstrated to show the superior performance of the proposed algorithms in terms of the achieved objective and running time in comparison with the state-of-the-art algorithms. Meanwhile, the excellent capability of the designed sequences to detect multiple moving targets under the strong clutter is evaluated via simulations. Moreover, the designed sequences are also implemented on an indoor hardware system, and their performance is verified.