Synthetic aperture radar (SAR) automatic target recognition (ATR) plays an important role in SAR image interpretation. However, at least hundreds of training samples are usually required for each target type in the existing SAR ATR algorithms. In this article, a novel few-shot learning framework named hybrid inference network (HIN) is proposed to tackle the problem of SAR target recognition with only a few training samples. The recognition procedure of HIN consists of two main stages. In the first stage, an embedding network is utilized to map the SAR images into an embedding space. In the second stage, a hybrid inference strategy that combines the inductive inference and the transductive inference is adopted to classify the samples in the embedding space. In the inductive inference section, each sample is recognized independently according to a metric based on Euclidean distance. In the transductive inference section, all samples are recognized as a whole according to their manifold structures by label propagation. Finally, in the hybrid inference section, the classification result is obtained by combining the above two inference methods. To train the framework more effectively, a novel loss function named enhanced hybrid loss is proposed to constrain samples to gain better interclass separability in the embedding space. Experimental results on the moving and stationary target acquisition and recognition (MSTAR) benchmark data set illustrate that HIN performs well in few-shot SAR image classification.

In recent studies, synthetic aperture radar (SAR) automatic target recognition (ATR) algorithms based on convolutional neural network (CNN) have achieved high recognition rates in the moving and stationary target acquisition and recognition (MSTAR) data set. However, the correlation between clutter in the training and test data sets is ignored in these algorithms, although most of them used only the center part of the images by removing a lot of the clutter but not everything, which may result in better performance than what would be achieved in the operational scenarios. To tackle this problem, we propose a target segmentation method based on morphological operations to generate data sets without clutter. Then, we design the large-margin softmax (LM-softmax) batch-normalization CNN (LM-BN-CNN) structure, which utilizes the LM-softmax classifier in the last layer to increase the separability of samples after clutter removal. In addition, this structure performs BN with constant mean and variance to increase the convergence speed and reduce overfitting. Experiments on the MSTAR data set have shown that LM-BN-CNN obtains better performance than the available CNNs designed for SAR ATR of ground vehicles, and it has robustness to large depression angle variation, configuration variants, and version variants.

This paper addresses the problem of radar-based human gait recognition based on the dual-channel deep convolutional neural network (DC-DCNN). To enrich the limited radar data set of human gaits and provide a benchmark for classifier training, evaluation, and comparison, it proposes an effective method for radar echo generation from the infrared, publicly accessible motion capture (MOCAP) data set. According to the different nonstationary characteristics of micro-Doppler (m-D) for the torso and limbs, it enhances their distinguishable joint time-frequency (JTF) features by applying the short-time Fourier transforms (SFTFs) with varying sliding window length and then designs the DC-DCNN structure to achieve refined human gait recognition by separate feature extraction and fusion. Experiments have shown that compared with the traditional single-channel deep convolutional neural network (SC-DCNN), the proposed method achieves higher recognition accuracy in refined human gait classification without incurring additional radar resources and could be readily extended to refined recognition of other human activities.

Radio Frequency Interference (RFI) is a key issue for Synthetic Aperture Radar (SAR) because it can seriously degrade the imaging quality, leading to the misinterpretation of the target scattering characteristics and hindering the subsequent image analysis. To address this issue, we present a narrow-band interference (NBI) and wide-band interference (WBI) mitigation algorithm based on deep residual network (ResNet). First, the short-time Fourier transform (STFT) is used to characterize the interference-corrupted echo in the time–frequency domain. Then, the interference detection model is built by a classical deep convolutional neural network (DCNN) framework to identify whether there is an interference component in the echo. Furthermore, the time–frequency feature of the target signal is extracted and reconstructed by utilizing the ResNet. Finally, the inverse time–frequency Fourier transform (ISTFT) is utilized to transform the time–frequency spectrum of the recovered signal into the time domain. The effectiveness of the interference mitigation algorithm is verified on the simulated and measured SAR data with strip mode and terrain observation by progressive scans (TOPS) mode. Moreover, in comparison with the notch filtering and the eigensubspace filtering, the proposed interference mitigation algorithm can improve the interference mitigation performance, while reducing the computation complexity.

Restricted by the observation condition, synthetic aperture radar (SAR) automatic target classification based on deep learning usually suffers from insufficient training samples. To tackle this problem, a novel few-shot learning (FSL) framework for SAR target classification, i.e., the mixed loss graph attention network (MGA-Net), is proposed. The classification procedure of the MGA-Net consists of three main stages. In the first stage, the task set is expanded by the data augmentation module to increase diversity. In the second stage, the embedding network is designed to map samples to the embedding space with strong intra-class similarity and inter-class divergence. In the third stage, the multilayer graph attention network (GAT) is constructed and updated according to a novel mixed loss to obtain the classification result. In particular, the data augmentation module alleviates the desire of training samples under large model capacity and enhances the robustness to noise and viewing angle variation; the multilayer GAT accurately captures relations between samples by the attention mechanism; and the mixed loss increases the inter-class separability and accelerates convergence. Experimental results under various few-shot observation settings of the MSTAR and the OpenSARShip benchmark datasets demonstrate that the MGA-Net obtains higher accuracy than typical FSL methods and exhibits robustness to large depression angle variation.

In recent studies, synthetic aperture radar (SAR) automatic target recognition (ATR) algorithms that are based on the convolutional neural network (CNN) have achieved high recognition rates in the moving and stationary target acquisition and recognition (MSTAR) dataset. However, in a SAR ATR task, the feature maps with little information automatically learned by CNN will disturb the classifier. We design a new enhanced squeeze and excitation (enhanced-SE) module to solve this problem, and then propose a new SAR ATR network, i.e., the enhanced squeeze and excitation network (ESENet). When compared to the available CNN structures that are designed for SAR ATR, the ESENet can extract more effective features from SAR images and obtain better generalization performance. In the MSTAR dataset containing pure targets, the proposed method achieves a recognition rate of 97.32% and it exceeds the available CNN-based SAR ATR algorithms. Additionally, it has shown robustness to large depression angle variation, configuration variants, and version variants.