Bistatic synthetic aperture radar (SAR) with spatially separated transmitter (TX) and receiver (RX) is advantageous over monostatic SAR systems in trajectory flexibility and antistealth/antijamming capability. On the other hand, since bistatic SAR imaging involves more technical complexities and incurs higher cost, the research in the field of bistatic automatic target recognition (ATR) has been mainly relying on simulated SAR imagery. Reckoning with the lack of supporting database in the public domain, the researchers at Nanjing University of Aeronautics and Astronautics (NUAA) constructed a proprietary bistatic SAR database featuring multiple types of representative military vehicles with the self-developed miniSAR system. Moreover, a multichannel multiview feature fusion network (MMFFN) is devised by incorporating the vision transformer (ViT). The simulation results show that the proposed MMFFN offers a classification accuracy improvement of 4.86%–16.63% over the baseline network (i.e., the plain ViT) in a series of experiments featuring small-to-large observation angle deviations between the training and test data.

Military operations often demand considerable concealment and raid capabilities, particularly at night or in adverse weather conditions. However, the use of synthetic aperture radar (SAR) technology provides early warning and target localization capabilities. While spaceborne or airborne SAR systems can capture expansive SAR scenes, they frequently encounter challenges in delivering timely and high-resolution data, thereby limiting their effectiveness in detecting small ground vehicle targets. To address this issue, our research has developed a low-cost, high-resolution, and real-time monostatic MiniSAR system for the effective detection of small targets, such as vehicles. Furthermore, to enhance the stealthiness of the MiniSAR, a bistatic MiniSAR system has been developed to accomplish detection tasks. Nevertheless, despite the utilization of MiniSAR systems for ground armored target detection, two primary challenges persist: the presence of highly ultracomplex scene interference making accurate target detection difficult; and poor real-time performance resulting in slow detection and tracking. To overcome these challenges, this article proposes a ground vehicle target recognition method based on an improved lightweight anchor-free detection network using monostatic/bistatic SAR images. The method initially leverages the inherent features of SAR targets for localization, embedding these features into SAR images, and then outputs detection results through the improved lightweight anchor-free network. We validate the effectiveness of this method on our self-constructed monostatic/bistatic SAR datasets and verify the algorithm’s robustness on publicly available ship datasets. Experimental results demonstrate that this method outperforms other representative methods in detecting SAR vehicle small targets, exhibiting higher detection accuracy and timeliness.

The majority of the existing deep-learning based SAR automatic target recognition (ATR) algorithms rely solely on the "appearance" of the SAR signatures for target classification, while ignoring the relationship between the objects of interest and their surroundings. In this work, we emphasize on enhancing the capability of SAR ATR algorithms in detecting and categorizing out-of-library (OOL) targets in open environment with context-based compositional learning. Rather than attempting to build a single do-it-all model, task-specific sub-models are chosen based on the natural selection mechanism, whose relationships are structured via logic flow based on context. To compensate for the SAR training data scarcity and the unequal distribution of classes, active learning, cross-domain transfer learning, and transductive learning are jointly exploited. Simulation results show that the proposed joint scene-target recognition framework could potentially solve the challenging problem of OOL target classification in complex mission scenarios.

Ground armored weapons have a high detection value in military operations. Satellite synthetic aperture radar (SAR) cannot accurately detect military targets with meter-level sizes limited by resolution of sensors. Airborne SAR have strict experimental conditions and cannot be applied in actual battlefield environments. MiniSAR sensors, which combine the advantages of submeter-level ultrahigh resolutions and flexible flight, play a crucial role in recognizing military targets. In this paper, various small military targets in real complex ground scenarios are detected with the MiniSAR of NUAA. However, there are still two difficulties. First, because of a limitation in the number of flight circles, the number of obtainable military target samples is not sufficient to adapt to the traditional deep learning methods that rely on a large number of image samples. Second, due to the imaging systems and different depression angle of MiniSAR, the SAR images of MiniSAR suffer from the same deformation challenge as the moving and stationary target acquisition and recognition (Mstar) with high depression angle. To address these two challenges, we propose a FASAR-Net framework based on few-shot learning with meta learning and adversarial domain learning, combined with the inherent scattering features of the SAR targets. Furthermore, we validate the reliability and accuracy of this algorithm on Mstar and our datasets, and the result of recognizing small SAR targets is compared with our algorithm and other classical algorithms. We conclude that the proposed algorithm has high accuracy in the recognition of the deformation small targets under the few sample condition.

In this article, a novel method for the moving target detection through multilevel spatial and channelwise attention network based on shallow feature channel module (MSCA-SFCM) is presented, and the circular spotlight (CSL) video synthetic aperture radar ground moving target indication (Video-SAR-GMTI) mode of the Nanjing University of Aeronautics and Astronautics miniature SAR (NUAA MiniSAR) system is introduced. However, due to the lack of moving target samples, MSCA-SFCM cannot be directly applied to the CSL Video-SAR-GMTI mode in the real system. To this end, this article proposes a training sample library construction scheme for moving targets of high verisimilitude. In this scheme, based on the radar system parameters, after the traversal of moving target parameters and SAR imaging, the scattering line characteristic of all possible moving targets under the current system parameters is simulated and then used for MSCA-SFCM network training. Afterward, the properly trained network can be used for moving target detection in real radar data. The effectiveness of the proposed method is verified by the NUAA MiniSAR system.

In recent years, convolutional neural networks (CNNs) have demonstrated significant potential for synthetic aperture radar (SAR) target recognition. SAR images possess a strong sense of granularity and contain texture features of varying scales, including speckle noise, dominant scatterers, and target contours, which are not typically considered in traditional CNN models. This article proposes two residual blocks, termed multibranch cross-channel attention (EMC2A) blocks, with multiscale receptive fields (RFs) based on a multibranch structure and designs an efficient isotopic architecture deep CNN (DCNN) called EMC2A-Net, whose structure is interpretable from a probability and mathematical statistics perspective. EMC2A blocks employ parallel dilated convolution with different dilation rates to effectively capture multiscale contextual features without significantly increasing the computational load. To further enhance the efficiency of multiscale feature fusion, this article presented a multiscale feature cross-channel attention module, known as the EMC2A module, which adopts a local multiscale feature interaction strategy without dimensionality reduction. This strategy adaptively adjusts the weights of each channel using efficient one-dimensional (1-D)-circular convolution and sigmoid function to guide attention at the global channel-wise level. Comparative results on the moving and stationary target acquisition and recognition (MSTAR) dataset demonstrate that EMC2A-Net outperforms the other available models of the same type and possesses a relatively lightweight network structure. The ablation experimental results further demonstrate that the EMC2A module significantly enhances the model’s performance by utilizing only a few parameters and appropriate cross-channel interactions.

The key to the feasibility of spectrum sharing between radar and wireless systems is effective mainlobe interference mitigation processing by the radar. Traditional array processing is capable to cancel sidelobe interferences only. This letter presents an innovative beamforming approach, the first of its kind, to eliminate wireless interference in both mainlobe and sidelobe directions based on a coherent phase-coding multiple-input multiple-output (MIMO) radar platform. The theoretical proof and conditions of simultaneous mainlobe interference cancellation and target detection using coherent MIMO radar are mathematically derived and numerically verified. The simulation results demonstrate the radar can effectively eliminate wireless interferences from base stations and mobile handsets during spectrum-sharing.