This letter proposes a dual-stream physics-aware attention framework for Specific Emitter Identification (SEI). The extracted deep features from traditional SEI methods lack explicit correspondence with hardware physical characteristics. To enhance feature interpret ability and robustness, we integrate Physics-Informed Pulse Signal Decomposition (PI-PSD) with Local-Focused STFT Attention Transformer Block (LFST-ATB). PI-PSD employs specialized edge and energy kernels to capture hardware I/Q impairments, while LFST-ATB efficiently processes time-frequency features through local attention mechanism. Experimental results show over 95% classification accuracy under challenging 10-20 dB SNR conditions. The framework demonstrates the effectiveness of combining physical domain expertise with attention mechanisms for robust system identification.

The synthetic aperture radar (SAR) image of a complex target can be approximated by the composite composition of typical scatter bodies, by segmenting the SAR target image, the complex target can be decomposed into a structural combination of multiple scatterers. Based on the above conclusions, this paper proposes to model the structural components of complex targets under high-resolution observation conditions and construct a complex target imaging model, decompose a large complex ship target into multiple scattering bodies, coupled structures and large distribution areas, enhance the structured feature of complex targets based on the a priori knowledge of the coupling characteristics and distribution characteristics of known scatterers, and achieve the modeling of complex targets. this paper proposes a SAR imaging model with a combination of structural and statistical features to provide a new technical way of utilizing the data effectively.

This paper introduces a Specific Emitter Identification (SEI) methodology with a Demodulation Embedding Convolutional Neural Network (DE-CNN). Distinct from prior research endeavors, the paper focuses on analyzing raw real signals, bypassing the traditional down-conversion and I/Q demodulation process to retain more of the intrinsic characteristics of the transmitted signal. Our approach embedding an I/Q demodulation layer within the CNN, enabling efficient preprocessing of raw real signals for SEI. Based on the analog impairment function of SMW200A signal generator, we obtained a transmit signal with analog I/Q imbalance in the semi-physical simulation. Compared with the original I/Q signal,the method based on the raw real signals can improve by up to 3.4 percent.

In recent years, researches on the recognition for Inverse Synthetic Aperture Radar (ISAR) images continue to deepen, while most methods only use the amplitude information of the ISAR image data. Besides, high-order terms in the complex-valued (CV) received signals for maneuvering space targets will cause defocusing on the ISAR images, which affects the accuracy of the recognition. For a steadily rotating maneuvering target, its high-order phase information between frames is relevant, and this information can be used to facilitate recognition. To this end, this letter proposes an end-to-end recognition framework in the CV domain based on the transformer model. It uses multi-scale feature extraction strategy and CV attention mechanism to get the local and global hybrid feature. Besides, A spatio-temporal transformer (STT) block is proposed to obtain the spatio-temporal correlation between image frames to assist recognition. Finally, a residual CNN block is introduced to promote diversity in the captured representations. In the experimental part, the recognition results of the proposed method on the real and simulated dataset are better than those of other methods. Compared with the classic sequence recognition method CVLSTM, the recognition accuracy and kappa coefficient of the proposed method are increased by approximately 5.6% and 5.4% respectively.

In MEO spaceborne-airborne BiSAR systems, the velocity and slant range histories are very different between the receiving and transmitting platforms. Under the condition of a large slant angle, the echo has serious spatial variability in the azimuth direction, which causes the azimuth defocus. In this paper, the bistatic SAR geometric models of satellite and aircraft are firstly established. After giving the range model, the pattern of spatial variation in azimuth dimension was analyzed. The nonlinear chirp scaling algorithm was used to correct the spatial variation, and the effectiveness of the proposed algorithm is verified by simulation.

The automatic registration of multi-modal remote sensing data (such as optical and SAR) is a challenging task because of the significant non-linear radiation difference between these data, as well as the transformation of rotation and scaling. In order to solve the above problems, this paper proposes a two-step strategy. Firstly, the improved HOPC algorithm is introduced to obtain matching point pairs, and then a weighted strategy is used to calculate the global affine transformation matrix. In the first step, an improved Harris operator is used to extract the points of interest, and the matching accuracy is maintained while the amount of calculation is reduced. Then the matching loss calculated by the HOPC algorithm is used to calculate the contribution weight of the image block, which is utilized to calculate the global transformation matrix. The results show that the method in this paper has strong robustness to complex nonlinear radiation differences, and the two-step strategy greatly improves the accuracy of matching, which is better than similar matching algorithms in performance.

Multiple input multiple output synthetic aperture radar (MIMO SAR) can solve the high resolution and wide swath imaging conflicts of traditional SAR. In the time domain, short term shift orthogonal (STSO) waveforms of different transmitting channels were used to separate the echoes from closely spaced scatterers. And in the space domain, digital beam forming (DBF) was used to separate the echoes from widely spaced scatterers. In this paper, a novel phase coding scheme based on Golay complementary sequence is proposed. Based on the idea of STSO waveforms, phase coding scheme could be used to separate and image the echoes of different receiving antennas. Theoretical derivations and simulation results validate the effectiveness of the proposed coding scheme.

This letter proposes a complex-valued convolutional gated recurrent unit (CV-ConvGRU) network for the three-dimensional rotation refocusing task of a synthetic aperture radar (SAR) ship target. To take advantage of the amplitude and phase information of complex SAR images, all elements of CV-ConvGRU, including the convolutional layer, activation function, update gate and reset gate, are extended to the complex domain. Based on CV-ConvGRU, a complex-valued SAR ship refocusing network (CV-SSRN) architecture is designed for refocusing experiments. To verify the robustness of the proposed CV-ConvGRU over ConvGRU on information perception, this letter also raises a real-valued SAR ship refocusing network (RV-SSRN), which has the same degree of freedom as CV-SSRN. Finally, experiments are carried out, and all results show the superiority of the proposed method on refocusing accuracy.

Inverse synthetic aperture radar (ISAR) is an effective detection method for targets. However, for the maneuvering targets, the Doppler frequency induced by an arbitrary scatterer on the target is time-varying, which will cause defocus on ISAR images, and bring difficulties for the further recognition process. It is hard for traditional methods to well refocus all positions on the target well. In recent years, generative adversarial networks (GAN) achieves great success in image translation. However, the current refocusing models ignore the information of high-order terms containing in the relationship between real parts and imaginary parts of the data. To this end, an end-to-end refocusing network, named Complex-valued Pix2pixHD (CVPHD) is proposed to learn the mapping from defocus to focus, which utilizes complex-valued (CV) ISAR images as input. A complex-valued instance normalization layer is applied to mine the deep relationship between the complex parts by calculating the covariance of them and accelerate the training. Subsequently, an innovative adaptively weighted loss function is put forward to improve the overall refocusing effect. Finally, the proposed CVPHD is tested with the simulated and real dataset, and both can get well-refocused results. The results of comparative experiments show that the refocusing error can be reduced if extending the pix2pixHD network to the CV domain and the performance of CVPHD surpasses other autofocus methods in refocusing effects. 1The code and dataset have been available online (https://github.com/yhx-hit/CVPHD).

Recently, researches on the classification for inverse synthetic aperture radar (ISAR) images continue to deepen. However, the maneuvering and attitude adjustment of space targets will bring high-order terms to received echoes which cause defocus on ISAR images and affect classification. The current classification models ignore the information of high-order terms containing in the relationship of real parts and imaginary parts of data. To this end, this letter proposes an end-to-end framework, called CV-GNN, specifically for the classification of defocused ISAR images under the few-shot condition. It models the features of real parts and imaginary parts of complex-valued (CV) images as graph information reasoning. Specifically, the deep relationship between them is mined to contribute to classification by complex-valued graph convolution. Moreover, the backpropagation process is derived in detail for updating the weights and bias of the network. The proposed method is then experimented with a mixed few-shot dataset of real and simulated data. Compared with the state-of-the-art methods, CV-GNN performs well in defocused image classification for each class of targets, and ablation studies verify the effectiveness of complex-valued network and graph neural network. The code and dataset will be available online (https://github.com/yhx-hit/cv_gnn).

As an innovative concept of high-resolution and wide-swath system, the low-oversampled staggered synthetic aperture radar (SAR) can not only deal with the blind ranges, but also suppress range ambiguities and reduce the data volume. Due to the variation of pulse repetition interval (PRI), there will be echo pulse loss and nonuniform sampling in azimuth. Generally, the existing reconstruction algorithms mostly resample the nonuniformly sampled signal into a uniform grid, and then perform conventional focused processing. However, the accuracy of the resampling is limited, and the advantage of the nonuniformity over uniform sampling in terms of reconstruction performance is ignored, especially with low oversampling factors. In this paper, a reconstruction algorithm for low-oversampled staggered SAR is proposed based on the sparsity Bayesian learning in the presence of a nonlinear PRI variation strategy. To ensure that the blind range distribution, which depends on the PRI variation strategy, brings a superior reconstruction performance, we define a novel objective function and optimize a sequence of nonlinear PRI variation with genetic algorithm. On the basis of the optimized sequence, the proposed reconstruction algorithm performs the second-order keystone transform to achieve range curvature correction for nonuniformly sampled data in azimuth. Then, a nonuniform observation model is established. The sparsity Bayesian learning (SBL) using a hierarchical form of the Laplace prior is applied to reconstruct the focused images directly with the nonuniform sampling. Simulations and experiments on raw data generated in staggered SAR mode with low oversampling factors are performed to verify the effectiveness of the proposed method.

In the synthetic aperture radar (SAR) images, moving ship targets are defocused due to the movement, which leads to the problem of poor classification accuracy. Therefore, this paper proposes an amplitude-phase-type complex-valued convolutional neural network (AP-CV-CNN) architecture called CV-MotionNet to classify SAR moving ship targets without motion compensation. It utilizes both amplitude and phase information of complex SAR images. CV-MotionNet uses amplitude-phase-type activation function to processing amplitude and phase information more conducive. Then, the proposed CV-MotionNet is tested on simulated five-types SAR moving ship target classification task and GF-3 SAR ship classification. Simulation and experiment show that the classification error can be further reduced if using CV-MotionNet instead of real-valued CNN (RV-CNN) with the same degree of freedom.

The recognition of satellite's attitude change plays an important role in the detection, tracking and recognition of space targets, as well as the evaluation, verification of space events and environmental monitoring and prediction. In this paper, 3D-CNN model is used to extract features from spatial and temporal dimensions, and then 3D convolution is carried out to capture motion information from multiple consecutive frames. Four common attitude changes of three different kinds of satellites are simulated, which are orbit change, spin, reconnaissance and maneuver. A proper number of consecutive frames are sent into packets and sent to the network for training. The experimental result shows that 3D-CNN model has a competitive performance.

In this paper, a variable-decoupling method for synthetic aperture radars (SAR) with three-dimensional constant acceleration is proposed. For SAR with constant acceleration, a high-order approximate slant range model is re-established. On this basis, the spectrum is obtained by the method of series reversion (MSR) that has five independent variables coupling, which makes the accurate processing of the spectrum difficult. Aiming at this problem, a variable-decoupling method based on Doppler centroid estimation and inertial navigation data is proposed for SAR with 3-D constant acceleration and MSR-based spectrum. Combined with the improved chirp-scaling algorithm (ICSA) which is based on the MSR-based spectrum, an improved wide-range imaging result is obtained.

Deep learning method is widely applied in modern artificial intelligence technology for Signal Modulation Recognition (SMR). Compared to CPUs and GPUs, FPGAs are highly energy-efficient and have low-latency streaming capabilities, which are more suitable for energy-sensitive or real-time machine learning projects. High-level synthesis (HLS) can automatically convert the logical structure described by a high-level language into a description by a low-level abstraction language. In this paper, we propose a system to optimize Deep Confidence Network (CDBN) by loops pipelining and unroll, memory buffering and partitioning, and implement an energy-efficient HLS-based FPGA Convolutional CDBN accelerator for SMR based on Virtex-7 platform. The accelerator system run at 150MHz and has 28% higher throughput and 80.5% less power consumption than a GPU implementation.

A transfer learning method based on Weighted Histogram of Oriented Gradient (WHOG) features for ships identification is proposed, which uses labeled ships at different resolutions to identify fixed resolution ships. An improved HOG features called WHOG is presented, which have a better description of the contours on different types of ships. The training and the test samples at different resolutions obey different distributions. The JDA method considers probabilistic adaptation without performing spatial alignment. To solve this problem, Mapped Alignment-Joint Distribution Adaptation (MA-JDA) method is proposed. MA is utilized to map the source and target domain data to the same feature space, then JDA is utilized to perform probabilistic adaptation to improve transfer learning performance. Extensive experiments demonstrate that the superiority of WHOG features over traditional HOG features and the MA-JDA method is better than several state-of-the-art transfer learning methods.

With the successful application of convolution neural network (CNN) in image recognition field, this paper presents the complex-valued convolutional network (CV-CNN) using different activation functions. Then, four different activation functions of sigmoid, tanh, Leaky-ReLU and ELU were tested in typical polarimetric SAR image classification tasks. Experiments on benchmark datasets of Flevoland shows that CV-CNN using ELU activation function performs the best, with faster convergence speed and much higher recognition rate.

This paper presents bistatic synthetic aperture radar imaging preliminary results with multiGNSS transmitters and a fixed receiver. Geometry, ambiguity function and imaging algorithms are discussed to describe multi-GNSS BiSAR system. Simulation results are provided to demonstrate the performance improvement of the amount of information of a given scene.

Aircraft detection has become a research hotspot due to its important military and traffic status. It is very challenging since noisy background is easy to mix with the target, meanwhile, there are small and dense distributed targets in some images. This paper presents an end to end aircraft detection framework based on Mask R-CNN. First, a self-attention feature pyramid network (SA-FPN) is proposed to suppress the noise and highlight foreground. Then, in order to reduce the false alarm and increase the detection performance, we redesign the aspect ratios of the anchors. The experimental result shows that our detection method has a competitive performance.

Windmills have the characteristics of small area and small quantity in remote sensing images, so the traditional methods of object classification and recognition are not suitable for the recognition of windmills. In this paper, we analyzed the spectral information and shape characteristics of windmill, and proposed a technique of recognition windmills in remote sensing images based on SVM (support vector machines) and morphological attribute filters. The main idea of technique can be parted into two steps: the remote sensing image are divided into windmill and windmill-like areas, using morphological attribute filters to filter out the windmill-like areas. In addition, we have recognized the distributed windmills group in the images of four regions, and verify the accuracy of the recognition technique.

Fast Moving targets always are shifted or smeared outside the scene in different images sequence to make video by Circle Synthetic Aperture Radar (SAR). In this paper, a novel moving target tracking approach with the shadow detection and tracking (SDT) is presented based on Convolution Neural Network. Based on the shadow characteristic of moving target in SAR imagery, CNN tracking classification is employed on potential moving target candidates extracted from a sequence of temporal and spatial sub-aperture SAR images to detect and track the moving targets. By the simulation experiments and performance analysis, the validity of the proposed algorithm can be demonstrated. Real data set processing results are provided to demonstrate the effectiveness of the proposed approach.

In the SAR image, the road recognition is conducive to the SAR image interpretation using in traffic monitoring, GIS information, and Geographical mapping, but the road is difficult to extract for blurring by speckles. Based on mathematical morphology, a new road extraction method is proposed in this paper. After the pre-processing to reduce the influence of the speckles, the binary image information is gained by the Otsu method. Then, the information without the road information is removed by the mathematical morphological opening operation. In addition, after being corroded and reconstructed, the complete road boundary is detected by edge detection operations, and the result is relocated on the original image. Compared with the morphological method, road extraction is done by applying the Zernike moments. Orthogonal property of Zernike moment basis functions guarantees the statistically independence of coefficients in extracted feature vectors. The proposed method is evaluated on the SAR Image data. Results show that presented method outperforms recently presented works due to its high performance.

It presents an approach of moving target detection by multichannel synthetic aperture radar (SAR), which the receivers displaced in heterogeneous arrays. The approach achieves the maximal unaliased band of radial velocities and Minimum detectable velocity, retains full resolution SAR images, the multiple measurement vectors were employed for improvement of the target focusing, and requires no increase in receiver samples. The proposed multi-channel synthetic aperture radar system and the associated signal processing are detailed, and the approach is numerically demonstrated via simulation and raw data experiments.