The high-quality training data sets are often insufficient in synthetic aperture radar (SAR) automatic target recognition (ATR) applications. The generative adversarial network (GAN) provides a way for SAR data augmentation. It is necessary to ensure the diversity, similarity, and correct category of the generated images so that these images can be served as the supplementary data set. In this letter, the multiconstraint GAN (MCGAN) is proposed to generate high-quality multicategory SAR images. First, an encoder is used to learn the features of the real images to enhance the similarity. Then, the encoded features are mixed with noise and category labels as the input of the generator to improve the diversity and category correctness. The generated images will be sent to a pretrained classifier to ensure the correct category. Finally, the improved Wasserstein loss with the gradient penalty is extended to the model to further improve the diversity and similarity of the generated images. The MSTAR data set is used to validate the proposed method on generation. The quality evaluation and classification tests are performed on the generated images, and the results show that the MCGAN can provide high-quality images, which could assist in achieving good classification accuracy.

Barrage jamming technique with controllable jamming coverage against synthetic aperture radar (SAR) systems is of great importance in electronic countermeasures. However, it is still a difficulty for the jammer to accurately impose controllable two-dimensional (2-D) local jamming on the regions of interest (ROIs). In this respect, a new parameterized and large-dynamic-range precise controllable (PLDR-PC) jamming method has been proposed in this paper to assist in solving such problems. Based on the SAR imaging properties of linear frequency modulation (LFM) case, the range and azimuth modulation factors have been well designed to generate large dynamic controllable coverage of jamming signals with high 2-D processing gain. In such a context, the PLDR-PC technique can provide the optimal power allocation and considerably reduce the jamming power while still ensuring the satisfactory performance. The proposed PLDR-PC technique can improve the jamming efficiency and considerably reduce the exposure probability of the jammer. Moreover, to improve the barrage jamming performance, the parameter estimation error model is also established to determine the simple yet valid jamming strategy in practical implementations. Finally, extensive numerical simulations in comparison with the current jamming methods have been carried out to demonstrate the effectiveness and prospect of the PLDR-PC technique against airborne/spaceborne SAR systems.

The synthetic aperture radar automatic target recognition (SAR ATR) application based on the deep convolutional network often faces data scarcity. SAR image simulation based on electromagnetic and geometric calculations can provide a large amount of data that contains interpretable physical features, such as shadow and contour. However, there is a big difference between the simulated SAR image and the real image, and it is difficult to directly use it for data augmentation. This letter proposes the adversarial encoding network to extract the physical-related features, which can be understood as the common features between the simulated and real data. By designing the adversarial learning between an encoder and a discriminator, the encoder can extract real features from the simulated images. The encoded features are sent to a classifier to ensure the correct category information. A decoder is used to reconstruct the encoded features into the input image so that the encoded feature retains the image information as much as possible. Ablation experiments and comparative experiments are used to verify the ability of each module and the performance of the proposed method. The results show that the proposed model can achieve 98.55% accuracy, especially when the real data are insufficient for classification, which verifies that the proposed method is effective for data augmentation.

The Chinese first fully polarimetric space-borne synthetic aperture radar (SAR)-Gaofen-3 (GF-3) was launched in August 2016, which operates at the C-band and the resolution can reach 1 m. Polarimetric SAR calibration is a procedure that corrects the polarization distortion of a measured scattering matrix by referring to the scattering matrix of a known target. The present paper describes the principle, design, manufacture, and measurement results of a novel polarimetric active radar calibrator (PARC) designed for GF-3. A new design method for PARC was presented and two dual-polarized antennas with very high polarization purity were used. The internal calibration technique was introduced to ensure balance in the amplitude and phase, which ensures the precision of the PARC’s scattering matrices. The results we obtained through measurement in the microwave anechoic chamber and experiments in in-orbit calibration agree well with the theoretical predictions, and the novel PARC presented is proved to be well suited for polarization and radiometric calibration of GF-3.

The purpose of barrage jamming against the synthetic aperture radar (SAR) is to conceal the targets to be protected, but the jamming blocks on the regions of interest (ROIs) generated by the existing barrage jamming methods cannot fully destroy the structural information of the targets in the SAR images, resulting in jamming effects that need to be improved. Aiming at this deficiency, we analyze the relationship between the statistical characteristics of the jamming templates and the jamming effects using the structural similarity (SSIM), and design a multi-scale jamming template. The jamming blocks corresponding to this template can better disturb the structural information of the targets. In addition, in order to reduce the complexity of signal modulation and ensure a large effective jamming coverage, we propose a two-step jamming signal modulation method. Simulation experiments demonstrate the performances of the signal modulation method and the jamming effect of the multi-scale template.

Synthetic aperture radar (SAR) systems have the capacity for day-and-night and all-weather surveillance, which has become increasingly indispensable for military surveillance and global comprehensive environmental monitoring. With the development of the high-resolution SAR imaging technique, studies on SAR jamming have also received much interest. Traditional jamming methods are based on linear-frequency-modulated (LFM) signals, and this method can achieve high main-lobe jamming gain. However, its sidelobe jamming energy is very low. To solve this issue, a novel nonlinear frequency modulation (NLFM) waveform design method for SAR jamming is proposed in this paper. Compared with LFM waveforms, the designed waveforms have the same main-lobe jamming gain and very high sidelobes, which can significantly improve jamming performance. Moreover, detailed simulation experiments were carried out to verify the effectiveness of the newly proposed jamming scheme.