An efficient and training-sample-reducing space-time adaptive processing (STAP) algorithm based on sparse representation for ground clutter suppression in airborne radar is proposed in this paper. First of all, the principle and problems of sample matrix inversion-based STAP and sparse representation (SR)-based STAP algorithms are reviewed. Then, the conception of the local space-time spectrum (LSTS) of clutter is considered by exploiting the intrinsic sparsity nature of clutter in local beams and the Doppler domain. To estimate the LSTS using the sparse representation technique in a cost-effective way, a variable space-time mask matrix is designed. Finally, the reduced-dimension clutter plus noise covariance clutter matrix and the corresponding adaptive weight vector are calculated based on the estimated LSTS. Numerical results with both simulated data and Mountain-Top data demonstrate that the new algorithm provides an excellent performance of clutter suppression and moving target detection with only one training range cell and significant computational savings compared with existing SR-based STAP algorithms.

Space-time adaptive processing (STAP) based on sparse recovery (SR-STAP) techniques exhibits significantly better performance than conventional STAP algorithms within a very small number of snapshots. However, when the clutter patches do not locate exactly on the discrete space-time grid points, the performances of SR-STAP algorithms degrade severely. In this letter, a low-complexity off-grid STAP algorithm based on local search clutter subspace estimation is proposed to overcome this issue. In the proposed algorithm, the global atoms are first selected from the reduced-dimension global STAP dictionary using the design selection criterion. Then, the optimal atoms are searched from the local STAP dictionary. Finally, these space-time steering vectors corresponding to the optimal atoms are used to construct the clutter subspace iteratively, and the STAP weight is obtained by projecting the snapshot on the subspace orthogonal to the clutter subspace. Numerical experiments with both simulated and Mountain-Top data are carried out to demonstrate the effectiveness of the proposed algorithm.

Even though deep learning (DL) has achieved excellent results on some public data sets for synthetic aperture radar (SAR) automatic target recognition(ATR), several problems exist at present. One is the lack of transparency and interpretability for most of the existing DL networks. Another is the neglect of unknown target classes which are often present in practice. To solve the above problems, a deep generation as well as recognition model is derived based on Conditional Variational Auto-encoder (CVAE) and Generative Adversarial Network (GAN). A feature space for SAR-ATR is built based on the proposed CVAE-GAN model. By using the feature space, clear SAR images can be generated with given class labels and observation angles. Besides, the feature of the SAR image is continuous in the feature space and can represent some attributes of the target. Furthermore, it is possible to classify the known classes and reject the unknown target classes by using the feature space. Experiments on the MSTAR data set validate the advantages of the proposed method.

Three-dimensional (3-D) imaging using multiple-input multiple-output (MIMO) radar is a new technique which may solve the inherent problems in interferometric inverse synthetic aperture radar (InISAR). But the imaging effect using conventional correlation method is usually poor due to the non-orthogonality of transmitting waveforms with the same frequency. Sparse recovery is hopeful to improve the imaging result by exploiting the sparsity of target 3-D image. However, the existing 3-D imaging method based on sparse recovery has to reshape the 3-D MIMO echo into a vector. So, huge memory spaces and excessive amounts of computation time are required. In this paper, a MIMO radar 3-D imaging method based on multi-dimensional sparse recovery is proposed. First, after splitting and recombining the target 3-D image, the MIMO echo is expressed in a form of tensor-matrix product and a tensor model is built which needs less memory space and computation time than the vector model. In the image tensor of recombined target 3-D image, only limited regions contain the target signal. This prior information of signal support is combined with the signal sparsity to improve the sparse recovering effect. Furthermore, a multi-dimensional sparse recovery algorithm exploiting sparsity constraint and support constraint is proposed to reconstruct the 3-D image. Results of simulated MIMO data and real ISAR data show that, compared with the conventional method, the proposed method can not only save the memory and computation but is superior in the imaging quality.

Multiple-input multiple-output (MIMO) radar imaging is a new technique to obtain the radar image of aerospace targets. Orthogonal waveform design is one of the important issues for MIMO radar imaging. However, the fully orthogonal waveforms in the same frequency and with the arbitrary time delay do not exist in practice. Thus, the imaging result using nonorthogonal waveforms based on matched filtering (MF) method is usually unsatisfactory if further processing like digital beam forming (DBF) is not used. Sparse recovery (SR) method is possible to restrain the mutual interference of nonorthogonal waveforms by exploiting the sparsity of targets and improve the imaging quality. In this article, waveform design issue in SR-based MIMO imaging method is studied. The difference in the designs of waveforms in MF method and SR method is discussed. Based on requirements analysis, a comprehensive optimization model is built for waveform design and the existing cycle algorithm (CA) is modified to solve the model. Considering the fact that the target scene is always changing, waveforms should be adjusted along with the dynamic scene. Therefore, an adaptive waveform optimization method is further proposed based on the cognition of target scene. The dimension of SR model is reduced and the waveforms are optimized according to the cognitive target length. Moreover, based on the reconstructed target range profiles, transmitting waveforms together with recovery algorithm are further optimized to match the target better. Simulation results show that the waveforms after optimization are better than the nonoptimized waveforms and the proposed adaptive optimization method is valid and robust for the dynamic target scene.