A comprehensive and well-structured review on the application of deep learning (DL) based algorithms, such as convolutional neural networks (CNN) and long-short term memory (LSTM), in radar signal processing is given. The following DL application areas are covered: i) radar waveform and antenna array design; ii) passive or low probability of interception (LPI) radar waveform recognition; iii) automatic target recognition (ATR) based on high range resolution profiles (HRRPs), Doppler signatures, and synthetic aperture radar (SAR) images; and iv) radar jamming/clutter recognition and suppression. Although DL is unanimously praised as the ultimate solution to many bottleneck problems in most of existing works on similar topics, both the positive and the negative sides of stories about DL are checked in this work. Specifically, two limiting factors of the real-life performance of deep neural networks (DNNs), limited training samples and adversarial examples, are thoroughly examined. By investigating the relationship between the DL-based algorithms proposed in various papers and linking them together to form a full picture, this work serves as a valuable source for researchers who are seeking potential research opportunities in this promising research field.

The echo separation issue associated with different transmit antennas is the most technical challenge in realizing the Multiple-Input Multiple-Output (MIMO) Synthetic Aperture Radar (SAR) system. In this paper, a reconfigurable MIMO-SAR transmission scheme based on inter-pulse and intra-pulse joint phase modulation is proposed. The proposed scheme has many advantages. First, lots of monostatic waveforms can be directly employed in a MIMO-SAR system, which offers flexibility in waveform selection. Second, according to different MIMO-SAR applications, it is reconfigurable and can flexibly adjust the system Degree of Freedoms (DoFs) to accomplish echo separation, achieving the best system performance, which is the key for the multimodal operation of MIMO-SARs. Finally, due to the limited system resources in the real MIMO-SAR system, it is hard to separate echo in a single domain, and the proposed scheme jointly capitalizes DoFs of Doppler, time, and space domains to ensure the successful echo separation. In addition, detailed simulation experiments are carried out to verify the practicability and effectiveness of the newly proposed transceiver schemes.

Low probability of intercept (LPI) radar has played an important role in in modern radar systems due to its difficulty in being intercepted by non-cooperative interceptors. The modulation methods of LPI radar signals are becoming increasingly complex, causing some difficulties in accurately identifying radar signals in complex electromagnetic environments. To address this problem, we propose an automatic recognition framework for LPI radar modulated signals in complex multipath electromagnetic environments. Specifically, the radar time-domain signal is converted into a time-frequency distribution image through time-frequency analysis (TFA) technology, and then adaptive filtering is performed using Adaptive Network-based Fuzzy Inference System (ANFIS) in the preprocessing stage to enhance the time-frequency characteristics of the signal under low signal-to-noise ratios (SNRs). In the automatic recognition stage of radar signal, the inherent characteristics of time-frequency images (TFIs)of signals are extracted by exploiting deep learning, and a split-attention networks combined with a joint loss function is designed, namely ResNeSt. The experimental results show that compared with existing automatic modulation recognition (AMR) methods for radar signals, this framework has higher recognition accuracy in complex electromagnetic environments and exhibits robustness against superimposed multipath effects. When the SNR is as low as -12 dB, the average probability of accurately identifying 15 typical LPI radar signals is 94.93%.

The traditional method of constant false-alarm rate detection is based on the assumption of an echo statistical model. The target recognition accuracy rate and the high false-alarm rate under the background of sea clutter and other interferences are very low. Therefore, computer vision technology is widely discussed to improve the detection performance. However, the majority of studies have focused on the synthetic aperture radar because of its high resolution. For the defense radar, the detection performance is not satisfactory because of its low resolution. To this end, we herein propose a novel target detection method for the coastal defense radar based on faster region-based convolutional neural network (Faster R-CNN). The main processing steps are as follows: (1) the Faster R-CNN is selected as the sea-surface target detector because of its high target detection accuracy; (2) a modified Faster R-CNN based on the characteristics of sparsity and small target size in the data set is employed; and (3) soft non-maximum suppression is exploited to eliminate the possible overlapped detection boxes. Furthermore, detailed comparative experiments based on a real data set of coastal defense radar are performed. The mean average precision of the proposed method is improved by 10.86% compared with that of the original Faster R-CNN.

In order to more efficiently mine the features of polarimetric synthetic aperture radar (PolSAR) and establish a more appropriate classification model, this article proposes an improved convolutional autoencoder (ICAE) based on texture feature fusion (TFF-ICAE) for PolSAR terrain classification. First, TFF-ICAE specifically designs a multi-indicator squeeze-and-excitation (MI-SE) block and incorporates it into the CAE network. MI-SE can enhance the essential feature information while suppressing the interference information as much as possible, and it can effectively increase the between-class distance while reducing the within-class distance. Then, TFF-ICAE uses gray level co-occurrence matrix (GLCM) to capture the texture features, and it optimally fuses these texture features and the deep features extracted by ICAE to complete the multilevel feature fusion, elevating the feature representation completeness of the terrain. That is, TFF-ICAE effectively enhances the feature separation capability of different categories while greatly elevating the feature representation completeness. Experiments on the datasets of San Francisco, Oberpfaffenhofen, and Flevoland show that the proposed TFF-ICAE, respectively, achieves overall accuracies of 93.44%, 97.61%, and 97.78%, which are at least 0.92%, 1.52%, and 0.97% higher than other algorithms. Undoubtedly, the superiority of TFF-ICAE is verified on these datasets.

Range ambiguity is a technical challenge for current spaceborne synthetic aperture radar (SAR) systems. To this end, a novel range-azimuth joint modulation transmission scheme is proposed, and the corresponding imaging processing and performance analysis are detailed. Compared with the azimuth phase coding (APC) technique, this scheme fully exploits the sampling margins of the range and azimuth dimensions, resulting in the range ambiguities experiencing a double suppression effect. Starting from the range-azimuth joint modulation scheme, to obtain the best ambiguity suppression performance, the design of a nonlinear frequency modulation (NLFM) waveform with a continuous piecewise linear instantaneous frequency is formulated and tackled via a MATLAB optimization toolbox. The detailed simulation results based on LuTan-1 (LT-1) parameters illustrate that the proposed methodologies outperform the APC method and provide considerable ambiguity suppression.