Search

Integrating compressed sensing (CS) with millimeter-wave (mmW) holography has shown great potential to achieve lightweight onboard hardware, low sampling ratio, and high-speed sensing. However, conventional CS-driven algorithms are always limited by nontrivial adjusting of parameters and excessive computational cost caused by plenty of iterations. To address this problem, we propose a lightweight model-based deep learning framework (LFIST-Net) for mmW 3-D holography, by combining the interpretability of fast iterative shrinkage-thresholding algorithm (FISTA) and tuning-free merit of data-driven deep neural network. First, the single-frequency (SF) holographic imaging technique is integrated into FISTA, which serves as the sensing kernels, to avoid large-scale matrix multiplications. Subsequently, the kernel-based FISTA (KFISTA) is mapped into layer-fixed and parameter-learnable LFIST-Net, whose weights are relaxed to be layer-varied. The updating of key parameters in LFIST-Net, including step sizes, thresholds, and momentum coefficients, are regularized by soft-plus function to ensure the non-negativity and monotonicity. As for 3-D holography implementation, the ``1-D + 2-D'' scheme is adopted, where the matched filtering (MF) and well-trained LFIST-Net are used for range focusing and reconstructions of azimuth slices. Without losing efficiency, the range-focused subechoes are processed parallelly in 3-D cube form. Experiments, including both simulated and measured tests based on a commercial mmW radar, prove that LFIST-Net is capable of reconstructing the imaging scene precisely. In particular, in near-field mmW 3-D holography tests, both numerical and visual results demonstrate LFIST-Net yields compelling reconstruction performance while maintaining high computational speed compared with MF-based, conventional CS-driven, and network-based methods.

With the development of the radar sensing technology, hand gesture sensing and recognition has attracted much attention. This letter adopts a frequency-modulated continuous wave (FMCW) radar to achieve short-range hand gesture sensing and recognition. Specifically, the range, Doppler, and angle parameters of hand gestures are measured by fast Fourier transformation (FFT) and multiple signal classification (MUSIC) algorithm, respectively. The mixup (MP) algorithm combined with augmentation (AU) algorithm using a weight factor is applied to expand the hand gesture data. Then, a complementary multidimensional feature fusion network-based hand gesture recognition (CMFF-HGR) is designed to extract the features and achieve HGR. Finally, a series of experiments are carried out to verify the effectiveness of the proposed approach, and the results show that the recognition accuracy is higher than the existing alternatives with low computational complexity.

Target detection is studied for a cloud multiple-input multiple-output (MIMO) radar using quantized measurements. According to the local sensor quantization strategies and fusion strategies, this paper discusses three methods: quantize local test statistics which are linearly fused (QTLF), quantize local test statistics which are optimally fused (QTOF), and quantize local received signals which are optimally fused (QROF). We first directly analyze the detection performance of each method when the quantizer output is represented as a discrete random variable, where it is difficult to obtain a closed-form expression for the detection probability. Then, an approximate description for the quantization is analyzed for the case of a Gaussian signal and a closed-form expression of the detection probability is obtained. We prove that the QTOF method outperforms the QTLF method in general, and for small SCNR the QROF method has the best detection performance among the three methods, while for large SCNR the QROF method performs the worst. The correctness of theoretical analysis is verified by simulations.

The higher bandwidth inverse synthetic aperture radar (ISAR) can obtain the higher resolution radar images, which can provide more target information and help improve radar target detection and recognition. It is essential to study how to achieve a precise high-resolution (HR) ISAR image utilizing limited measurement echoes. The existing neural-network-based ISAR imaging methods extract features only from limited measurement echoes, and the common features in HR ISAR images are not utilized sufficiently, which limits the imaging performance improvement. Moreover, in their loss functions, there are no explicit constraints on the correct recovery of strong scattering points, which are important in reflecting the target characteristics. In this letter, we propose a conditional probabilistic generative model to achieve the HR ISAR imaging. By optimizing the well-designed Kullback-Leibler (KL) divergence between conditional prior and approximate posterior probability distribution in the loss function, the common features contained in training HR radar images can be learned, and a suitable prior probability distribution for the latent variable can be obtained. To accurately recover the positions and relative amplitudes of strong scattering points, we blend a similarity measurement that is sensitive to the large values' locations in a vector with the adversarial loss. Both visual and numerical results of extensive experiments prove that the proposed model can obtain enhanced effectiveness and efficiency compared with some counterparts.

Radar emitter classification (REC) plays an increasingly significant role in the electronic reconnaissance system. Due to there are many unreliable factors in traditional feature-based methods, this article focuses on improving the accuracy and stability of REC based on multipaths of original radar signals. A novel aggregated multipath extreme gradient boosting (AMP-XGBoost) is therefore put forward. Multi-path, including multi-scale, multi-domain transformations and their concatenations, is developed to exploit more information of the original signal, which contributes to providing more distinguishable features. XGBoost is used to automatically extract the features contained in these paths and complete recognition. Finally, multiple paths are sifted and aggregated according to certain weights to obtain a higher accuracy. Experiments are carried out based on signals from 6 different intra-pulse modulation mode radars with the same radio frequency (RF) range. It is demonstrated that the proposed method has higher REC accuracy than the methods only based on a single scale or domain. In the meantime, experimental results under different low SNRs show that the proposed method has higher stability. Finally, experiments based on the measured aviation radar data proves the superiority of the proposed method.

Global positioning system (GPS) and inertial measurement units (IMUs) are often combined to produce navigation systems for airborne imaging platforms. The current state-of-the-art radar technology allows for radars to pulse at very high rates. GPS and IMU update rates are not fast enough to accurately report the platform position for each radar pulse. Independent GPS and IMUs cannot provide positional accuracy for long term stability. Traditional techniques, such as the Kalman and particle filter, are used to fuse GPS and IMU measurements. The Kalman filter excels for linear and Gaussian systems whereas the particle filter excels at non-linear and non-Gaussian systems. Sensor fusion techniques are used to help correct for IMU errors and provide the positional accuracy required for synthetic aperture radar (SAR) imaging applications. However, SAR requires the fusion algorithms to provide faster update rates. This paper explores the use of an up-sampled particle filter (UPF) for SAR to provide highly accurate position estimates at sampling frequencies comparable to radar pulse rates and overcome the limitations of standard interpolation techniques. This up-sampled particle filter is proven through simulations and instrumentation with a NovAtel GPS and IMU. The UPF technique allows for the GPS/IMU sampling rate to be different from the radar pulse repetition frequency (PRF) while providing accurate position solutions for each radar pulse capable of compensating for the phase history required for focusing a SAR image. The algorithms are instrumented in a SAR system and the position estimates are further validated and demonstrated through captured SAR images.

The use of Wi-Fi signals for human sensing has gained significant interest over the past decade. Such techniques provide affordable and reliable solutions for healthcare-focused events such as vital sign detection, prevention of falls and long-term monitoring of chronic diseases, among others. Currently, there are two major approaches for Wi-Fi sensing: (1) passive Wi-Fi radar (PWR) which uses well established techniques from bistatic radar, and channel state information (CSI) based wireless sensing (SENS) which exploits human-induced variations in the communication channel between a pair of transmitter and receiver. However, there has not been a comprehensive study to understand and compare the differences in terms of effectiveness and limitations in real-world deployment. In this paper, we present the fundamentals of the two systems with associated methodologies and signal processing. A thorough measurement campaign was carried out to evaluate the human activity detection performance of both systems. Experimental results show that SENS system provides better detection performance in a line-of-sight (LoS) condition, whereas PWR system performs better in a non-LoS (NLoS) setting. Furthermore, based on our findings, we recommend that future Wi-Fi sensing applications should leverage the advantages from both PWR and SENS systems.

Ground-Penetrating Radar (GPR) technology plays an important role in near-surface geophysical survey. Usually, the dataset acquired by higher frequency antenna has higher resolution but limited penetration depth; while the dataset collected by lower one has deeper penetration depth but lower resolution. It is necessary to fuse several different frequency datasets into a composite displayed profile to get a trade-off between penetration depth and resolution. In such case, we propose a novel multi-frequency GPR data fusion method and test it on the data acquired from a limestone quarry in the Taihang Mountains of China. In our algorithm, time-varying weighting factors are calculated by virtues of a sliding time window, i.e. designed with segmented signals. According to this approach, we can achieve better local characteristics of the signal as well as the smoothness of the signal waveform. The results show that the spectrum bandwidth of the fused signal is broadened, and the fusion profile significantly improves the imaging of internal structures for limestone on different scales.

Microwave imaging with large rotating angle and sparse sampling is an attractive approach to obtain the high-resolution target image with reduced radar resource. However, the popular imaging methods, e.g., Range-Doppler (RD), back projection (BP), and sparse recovery (SR), are difficult to deal with large rotating angle and sparse sampling simultaneously. In recent years, deep learning (DL) has been widely studied and been successfully used to handle the problems in computer vision. However, since most existing DL networks are put forward for the real visual image and a large amount of data is essential for network training, DL cannot be directly used to process the complex and sparse target echo for microwave imaging. In this article, a new learning imaging framework is proposed and a model-driven learning imaging network (MDLI-Net) is built for high-resolution microwave imaging with large rotating angle and sparse sampling. In the proposed framework, the electromagnetic scattering model is used to generate the training data efficiently, and the sparse microwave imaging theory is applied to guide the design of the deep imaging network. By inputting the 2-D sparse complex-valued target echo, the trained MDLI-Net can output the high-resolution and focused target image efficiently. The effectiveness of the proposed learning imaging method is validated by experiment results with both simulated and real data.

Recent deep learning (DL) detectors adopted by radar or sonar (RS) are normally trained with transfer learning, where the typical workflow is to pretrain a convolutional neural network (CNN) on external large-scale classification datasets (e.g., ImageNet) as the backbone and then finetune the entire detector on detection datasets. Though transfer learning could effectively avoid overfitting, transferred models are usually redundant and might not generalize well on RS datasets. To achieve high generalization and to eliminate the dependence on transfer learning, a self-trained target detection method is established by including Automatic Deep Learning (AutoDL) to design optimal detectors. This self-trained target detection consists of three stages. First, a derived classification dataset (DCD) consisting of image blocks of targets and backgrounds is derived from detection datasets. Then, a memory-efficient Differentiable Architecture Search algorithm with flexible search space and large inputs (FL-DARTS), which is characterized by its predefined multistride convolutions, poolings, and unique super-structure, is proposed to automatically design and self-train optimal CNNs on DCDs. Finally, self-trained AutoDL detectors are implemented with the automatic backbone designed by FL-DARTS. We evaluated three self-trained AutoDL detectors on the public SAR ship detection dataset (SSDD) and the self-made sonar common target detection dataset (SCTD). The experiments show that while the number of parameters of automatic backbones designed for SSDD and SCTD are only 11.8% and 15.2% of that of ResNet50, self-trained AutoDL detectors implemented with automatic backbones significantly outperform their transfer learning detectors and achieve state-of-the-art detection precisions and high detection speeds. Data, codes are publicly available.

Convective precipitation nowcasting remains challenging due to the fast change in convective weather. Radar images are the most important data source in nowcasting research area. This study proposes a radar data-based U-Net model for precipitation nowcasting. The nowcasting problem is first transformed into an image-to-image translation problem in deep learning under the U-Net architecture, which is based on convolutional neural networks (CNNs). The input of the model is five consecutive radar images; the output is the predicted radar reflectivity image. The model consists of three operations: upsampling, downsampling, and skip connection. Three methods, U-Net, TREC, and TrajGRU, are used for comparison in the experiments. The experimental results show that both deep learning methods outperform the TREC method, and the CNN-based U-Net can achieve almost the same performance as TrajGRU which is a recurrent neural network (RNN)-based model. With the advantages that U-Net is simple, efficient, easy to understand, and customize, this result shows the great potential of CNN-based models in addressing time-series applications.

Different from conventional radar systems, for the single-photon radar, a single-photon detector acts as the receiver to detect the echo signal with only a few photons, which can be used to achieve ultrahigh sensitivity for long-distance target detection. In this letter, the heterodyne single-photon radar at terahertz frequencies is studied, for the first time. First, the working principle of the developed heterodyne single-photon radar is presented, and the target echo signal is derived. Subsequently, the estimation method of the target distance and the Doppler frequency is proposed, and the performance is analyzed by probability density function (PDF) derivation. Simulation results show good agreement with the theoretical analysis. This work can pave the way to the development of a new radar paradigm.

Ultrawideband (UWB) multiple-input-multiple-output (MIMO) radar is widely used for through-wall imaging (TWI) due to its excellent penetrability and large aperture. Multichannels in the MIMO radar system are usually time-division multiplexing based on microwave switches to reduce the complexity of the system in engineering. The switching process of the channel will bring time delay, which cannot be ignored in the TWI of the moving target. The switching time delay will cause the defocus and position shift of the TWI of the moving target. This letter proposes a motion compensation method based on multiframe data fusion (MFDF) used for correcting the echo of the through-wall moving target. A geometric model is established in the proposed method through the echo of the current frame and the next frame, and the compensated signal is obtained through the geometric solution. The proposed method is compared with before compensation and the traditional single-channel motion compensation algorithm (SCMCA) through simulation and experimental data verification. The visual images and quantitative results show that the proposed motion compensation method can obtain a good focus image of the through-wall moving target and reduce the positioning error.

Millimetre-wave (mmWave) radar is increasing in popularity for human activity recognition, due to its advantages of high resolution, non-intrusive nature and suitability for various environments. In this paper, we present a novel human posture estimation system using mmWave radars. The system detects people with arbitrary postures in indoor environments at close distances (within two metres), and estimates the posture by localising the key joints. We use two mmWave radars to capture the scene and a neural network model to estimate the posture. The neural network model consists of a part detector that estimates the subject’s joint positions, and a spatial model that learns the correlation between the joints. A temporal correlation step is introduced to further refine the estimate when in real-time operation. The system can provide an accurate posture estimate of the person in real-time at 20 fps, with a mean localisation error of 12.2 cm and an average precision of 71.3%.

Ground-penetrating radar (GPR) is a well-known geophysical electromagnetic method used to detect the underground facilities such as landmines, pipelines, and cavities. In general, the clutter presented in GPR B-scan image obscures the underground objects, thus damaging the performance of the underground object detection algorithm. In this letter, we proposed a new clutter suppression method based on robust autoencoder (RAE). The proposed algorithm decomposes a GPR B-scan image into its low-rank and sparse components. The low-rank component catches the clutter, whereas the sparse component captures the underground object responses. The commonly used clutter removal algorithms, mean subtraction (MS), singular value decomposition (SVD), robust principal component analysis (RPCA), and morphological component analysis (MCA), are compared with the proposed algorithm on both the numerical simulated data and real GPR data. The visual and quantitative results demonstrate the effectiveness of the proposed RAE-based algorithm over the widely used state-of-the-art clutter removal algorithms.

Nonline-of-sight (NLOS) radar imaging is a novel technique that can inverse the scattering characteristics of targets in the NLOS area, which has been one of the hot pots of radar imaging field. However, the existing NLOS radar mainly focuses on 1-D or 2-D imaging, which inevitably suffers from the geometric loss of real 3-D scenes, and its applications are restricted in the urban environment. In this article, we propose an NLOS radar 3-D imaging model and method for looking around corner (LAC) situation by multi-input-multioutput (MIMO) millimeter-wave (mmW) array antennas. In this scheme, first, the model of NLOS radar 3-D imaging with mmW MIMO antennas is established and the multipath scattering of targets with this model is analyzed. Then, the theoretical resolution of LAC 3-D imaging is derived and discussed. Second, exploiting the three bounces of LAC and extraction of linear structure, an effective imaging algorithm with mirror projection theory and Radon transform, dubbed as mirror symmetry backprojection (MSBP), is proposed for 3-D image focusing. Moreover, to suppress the uncertainties of phase caused by both LAC and system error, the minimum entropy principle is introduced to MSBP. Finally, an NLOS 3-D imaging system with 77-GHz mmW MIMO radio frequency module and 2-D rails is developed. Different types of targets, such as metal balls and ornaments, are tested in LAC. The results demonstrate that our NLOS technique can not only provide a high-quality 3-D focusing of the hidden targets but also extract positions of targets without prior knowledge of the NLOS area.

Aerosol extinction coefficient (AEC) is a crucial factor of aerosol optical properties that have an important influence on the atmospheric process. As a combination of laser technology and radar technology, LiDAR is a powerful remote sensing technology for aerosol measurement. However, many uncertainties still exist in LiDAR data retrieval because frequently used retrieval methods need some assumptions or complex numerical operations for retrieving AEC, which may cause large deviation. In this letter, combining the advantages and disadvantages of Mie scattering LiDAR and high spectral resolution LiDAR (HSRL), a new inversion model based on deep belief network (DBN) is proposed to predict AEC, which can effectively avoid the uncertainty caused by many assumptions and improve the detection accuracy of Mie scattering LiDAR. The experiment results indicate that the trained DBN model is robust and satisfactory and provides a competitive solution for predicting AEC of Mie scattering LiDAR. In addition, this letter reveals that deep learning method has huge potential for LiDAR data retrieval.

With the development of the Internet of things, radar-based human activity recognition is becoming more and more important, because they play an indispensable role in fields such as safety and health monitoring. In this work, a novel network named 1-D dense attention neural network (1-D-DAN) is proposed for the radar-based human activity recognition. In the proposed network, a novel attention mechanism network structure specifically designed for radar spectrogram is proposed, equipping 1-D convolutional network with attention mechanism. With the x-axis of the spectrogram represents time and the y-axis represents frequency, the proposed attention mechanism includes two branches: 1) time attention branch and 2) frequency attention branch. Moreover, a dense attention operation that can make full use of features in the network is also introduced in the proposed attention mechanism. Experimental results show that compared with the state-of-the-art methods, our proposed 1-D-DAN achieves the highest accuracy in human activity recognition with the lowest computational complexity.

Sea-Surface small target detection is challenging for maritime radar. Unfortunately, conventional detection methods are often limited to complex marine environment and low signal-to-clutter ratio (SCR). This article presents a multi-frame detection approach for sea-surface small target by using deep convolutional neural network. The moving targets can be reconstructed and detected from the sequential Range-Doppler (RD) spectra. A two-step detection framework is proposed, where the intra-frame and the inter-frame detection is achieved by using the differences of features and inter-frame correlations between moving target and sea clutter, respectively. The proposed approach has been verified on both the simulated and real sea-surface small targets, which shows better detection performance than the conventional multi-frame detection algorithms. Additionally, this approach exhibits acceptable generalization ability.

Vertical-looking radar (VLR) is a significant milestone in the development of insect radars with the capability of detecting the behavior of migratory insects and their biological parameters. In current VLRs, high-speed continuous sampling and long-time integration can barely be performed simultaneously, leading to a low detection probability for tiny insects (weight < 10 mg). Based on the large amount of data acquired by our developed high-range resolution insect radar, the insect echo signals and vertical motion characteristics are initially analyzed and demonstrate that the linear-motion mode is dominant in insect migration; also, the echo signal power of most insects follows the gamma distribution. Based on these characteristics, a long-time integration and detection method for detecting migratory insects, especially tiny targets from echo signals that often dip below the noise level, is proposed. The radial target velocity is also measured as one of the output parameters. The theoretical derivation and optimal choice of detection thresholds are also presented. Simulation and experimental results demonstrate that the proposed method exhibits better insect detection performance and effectively increases the detection range compared with conventional methods. In addition, the measured target velocity can be directly applied to current continuous-sampling VLRs for the ascent and descent rate analysis. Many typical insect migration phenomena have been detected effectively utilizing our developed VLR, and the measured ascent and descent rates of insects agree well with typical take-off, cruising, and landing behaviors. This is the first reported successful VLR application on take-off and landing behaviors of migratory tiny and dense insects.

In this article, a hypersonic target electromagnetic (EM) scattering echo model combined with the inhomogeneous zonal medium model (IZMM) and the classical scattering center model (SCM) is proposed with a distributed satelliteborne array radar as the detection platform. A parallel physical optics (PO) method is used for multiview inverse synthetic aperture radar (ISAR) imaging of a moving hypersonic target covered with plasma sheath based on the analysis of high-resolution range profile in the S-X ultrawideband range, reconstructing 2-D EM scattering echo data (the target) and motion compensation. The results show that the surface of the inhomogeneous plasma sheath flow field is an excitation layer with random and irregular fluctuation characteristics, which increases the false scattering centroid of the 1-D range profile of the hypersonic target and can interfere with and disrupt the radar localization of the target along the radial direction. In addition, shallow scattering of EM waves occurs in the plasma sheath, and the average signal intensity of the target can gradually reduce from 0.5 x 10⁻⁵ at 60 km and 20 Ma to 0.1 x 10⁻⁵ at 30 km and 20 Ma, with a fivefold weakening of the overall scattered echo signal. In particular, the faster the hypersonic target travels at 30-km altitude, the weaker the imaged scattered echo signal becomes, with the average intensity of the imaged signal weakening by approximately threefold from 15 to 25 Ma. This study provides considerable technical support and data assurance to establish a synthetic aperture radar (SAR) automatic target recognition (ATR) database, and the findings of this study can be used as a reference for fine-structure feature analysis of hypersonic targets for feature extraction and the classification and identification of targets.

In current wireless communication and electronic systems, digital signals and electromagnetic (EM) radiation are processed by different modules. Here, we propose a mechanism to fuse the modulation of digital signals and the manipulation of EM radiation on a single programmable metasurface. The programmable metasurface consists of massive subwavelength-scale digital coding elements. A set of digital states of all elements forms simultaneous digital information roles for modulation and the wave-control sequence code of the programmable metasurface. By designing digital coding sequences in the spatial and temporal domains, the digital information and far-field patterns of the programmable metasurface can be programmed simultaneously and instantly in desired ways. For the experimental demonstration of the mechanism, we present a programmable wireless communication system. The same system can realize transmissions of digital information in single-channel modes with beam-steerable capability and multichannel modes with multiple independent information. The measured results show the excellent performance of the programmable system. This work provides excellent prospects for applications in fifth- or sixth-generation wireless communications and modern intelligent platforms for unmanned aircrafts and vehicles.

The deep convolutional neural network (CNN) has been extensively applied to polarimetric synthetic radar (PolSAR) imagery classification. However, its success is greatly dependent on numerous labeled samples for revealing and modeling the characteristics of different targets, thus remaining a challenge in maintaining high accuracy in limited sample cases. To address this issue, a deep reinforcement learning (RL)-based PolSAR image classification framework, named deep Q-fully CNN (DQFCN), is proposed in this article. In this framework, two ways are adopted to boost the classification performance while reducing training samples. On the information utilization hand, the spatial neighboring information and polarimetric decomposition information of PolSAR data are both extracted to enrich the feature representation of the sample. Meanwhile, the 3-D CNN architecture is adopted to learn the spatial-polarimetric jointed characteristics simultaneously. On the model learning hand, two RL learning strategies are employed to promote classification performance. The first one is learning from scratch, which does not use any label information as prior knowledge but learns from its self-generated experience. Learning from pretraining is the second strategy in which the networks are sequentially trained from labeled samples and experience data to reduce the time cost. As far as we know, it is the first time that an RL-based fully CNN has been proposed for PolSAR image classification. Experiments on three benchmark datasets prove the effectiveness of the proposed framework, suggesting that the two adopted strategies achieve boosted performance in all experiments, particularly in a limited sample size.

Traditional micro-Doppler (m-D)-based human activity classification system using monostatic radar suffers from the drawback that classification performance is vulnerable to the variation of human motion aspect angle. This leads to a performance degradation if the human movements are not directly toward or away with respect to the radar line of sight. The multistatic radar system has been suggested as an effective solution to solve the problem, as it can observe the target from multiple views and achieve favorable aspect angles to the targets. In this article, a novel human activity classification method based on motion orientation determining using multistatic m-D signals is proposed. First, the aspect angles of target motion direction with respect to each radar nodes are inferred by using the proposed motion orientation estimation method. The multistatic m-D data are then divided into several intervals based on the measured angle, and the data in the same interval are fused at the data level. Finally, the classification results are obtained through the adaptive weighted decision-level fusion. Compared with the traditional multistatic classification method, due to the consideration of the time-varying human motion aspect angle, the proposed method is more reasonable in data fusion and has better classification performance.

With the development of new active deception jamming, radar anti-jamming has become a major research hotspot, and the recognition of jamming type is one of its key steps. In recent years, deep learning has been successfully applied in the field of radar jamming recognition, such as convolutional neural networks (CNN). However, it is difficult to effectively improve the accuracy of deep learning algorithms in the case of small sample. Furthermore, ensemble learning and transfer learning can effectively improve the model generalization performance. For the small sample problem, this article proposes a weighted ensemble CNN with transfer learning (WECNN-TL)-based radar active deception jamming recognition algorithm. The main idea of this method is to obtain the time-frequency distribution maps of jamming signals by short-time Fourier transform (STFT), and then, their real parts, imaginary parts, moduli, and phases are combined differently to construct multiple datasets. Finally, an ensemble CNN model with weighted voting and transfer learning is constructed to realize jamming recognition. Experiments on the simulated and measured mixed dataset (including 12 types of samples) show that the proposed method can get better recognition performance than random forest (RF), support vector machine (SVM), and some CNN-based methods.

Traditional range-instantaneous Doppler (RID) methods for maneuvering target imaging suffer from the problems of low resolution and poor noise suppression. We propose a new super-resolution inverse synthetic aperture radar (ISAR) imaging method based on deep-learning-assisted time-frequency analysis (TFA). Our deep neural network resembles the basic structure of a U-net with two additional convolutional-upsampling layers and l₁-norm loss function for super-resolution generation and noise suppression. The neural network is trained in advance to learn the mapping function between the low-resolution time-frequency spectrum inputs and their high-resolution references. Then, the linear TFA assisted by the pretrained network is integrated into the RID-based ISAR imaging system and is found to achieve sharply focused and denoised target image with super-resolution. Both the simulated and real radar data are used to evaluate the performance of the proposed method. Numerical experimental results demonstrate the superiority of the proposed ISAR imaging method over traditional ones.

Radar detection and communication are two of several sub-tasks essential for the operation of next-generation autonomous vehicles (AVs). The former is required for sensing and perception, more frequently so under various unfavorable environmental conditions such as heavy precipitation; the latter is needed to transmit time-critical data. Forthcoming proliferation of faster 5G networks utilizing mmWave is likely to lead to interference with automotive radar sensors, which has led to a body of research on the development of Joint Radar Communication (JRC) systems and solutions. This paper considers the problem of time-sharing for JRC, with the additional simultaneous objective of minimizing the average age of information (AoI) transmitted by a JRC-equipped AV. We first formulate the problem as a Markov Decision Process (MDP). We then propose a more general multi-agent system, with an appropriate medium access control protocol (MAC), which is formulated as a partially observed Markov game (POMG). To solve the POMG, we propose a multi-agent extension of the Proximal Policy Optimization (PPO) algorithm, along with algorithmic features to enhance learning from raw observations. Simulations are run with a range of environmental parameters to mimic variations in real-world operation. The results show that the chosen deep reinforcement learning methods allow the agents to obtain good results with minimal a priori knowledge about the environment.

Low imaging spatial resolution hinders through-the-wall radar imaging (TWRI) from reconstructing complete human postures. This letter mainly discusses a convolutional neural network (CNN)-based human posture reconstruction method for TWRI. The training process follows a supervision-prediction learning pipeline inspired by the cross-modal learning technique. Specifically, optical images and TWRI signals are collected simultaneously using a self-develop radar containing an optical camera. Then, the optical images are processed with a computer-vision-based supervision network to generate ground-truth human skeletons. Next, the same type of skeleton is predicted from corresponding TWRI signals using a prediction network. After training, the model shows complete predictions in wall-occlusive scenarios solely using TWRI signals. Experiments show comparable quantitative results with the state-of-the-art vision-based methods in nonwall-occlusive scenarios and accurate qualitative results with wall occlusion.

Adaptive and targeted allocation of mobile sensing agents, in the form of unmanned aerial vehicles (UAVs) with software defined radar (UAV-SDRadar) payloads, enable mapping of surface soil moisture in regions where in situ wireless sensor networks (WSNs) undersample soil moisture or upscaling models perform poorly. This work presents an optimization-based UAV path planning methodology that seeks to maximize UAV flight coverage over areas where a complementing WSN yields upscaled soil moisture estimates with high uncertainty. By recursively mapping soil moisture over such areas, the combined UAV and WSN instrumentation can gradually capture the domain's true mean soil moisture. A series of numerical simulations are presented to demonstrate the algorithm's basic function while considering real-world and feasible operational scenarios.

Storm nowcasting relies on reasonably fast sampled radar data, and deep learning (DL) can be used to harness this vast amount of data. Despite all the publications on this topic over the past five years, there are still ad hoc assumptions and a lack of standardization. This work addresses aspects that have not yet been analyzed on the development of DL models for nowcasting systems, such as the effects of different history lengths or using non-convex metrics during the training phase. For example, we show that even if the loss function is varied, it does not significantly influence the predictions, and that the number of predicted frames has a significant impact. We used the experiments' results to propose different models and compare their performance against other DL models. The results show that the proposed models outperform, in many aspects, the existing implementations.

Target detection in a high-frequency surface-wave radar (HFSWR) system is a challenging task because radar returns are strongly polluted by various sources of interference. To address the detection problem, this letter presents an automatic detection method based on multidirection dictionary learning for HFSWR. First, we perform clutter identification and statistical analysis to become aware of the time-varying clutter environment. The analysis of real data shows that the clutter in an HFSWR system has spatial correlations and geometric directions. Second, motivated by this information, we design a multidirection dictionary learning-based constant false alarm rate (MDDL-CFAR) detector in which the spatial and geometric direction information is well represented by multidirectional dictionaries. The MDDL-CFAR can simultaneously learn dictionaries and estimate clutter statistics to adaptively set the detection threshold. Experimental results on HFSWR data sets demonstrate the effectiveness of the proposed detection method.

Polysomnography (PSG) is the gold-standard for sleep apnea and hypopnea syndrome (SAHS) diagnosis. Because the PSG system is not suitable for long-term continuous use owing to the high cost and discomfort caused by attached multi-channel sensors, alternative methods using a non-contact sensor have been investigated. However, the existing methods have limitations in that the radar-person distance is fixed, and the detected apnea hypopnea (AH) event cannot be provided in real-time. In this paper, therefore, we propose a novel approach for real-time AH event detection with impulse-radio ultra-wideband (IR-UWB) radar using a deep learning model. 36 PSG recordings and simultaneously measured IR-UWB radar data were used in the experiments. After the clutter was removed, IR-UWB radar images were segmented by sliding a 20-s window at 1-s shift, and categorized into two classes: AH and N. A hybrid model combining the convolutional neural networks and long short-term memory networks was trained with the data, which consisted of class-balanced segments. Time sequenced classified outputs were then fed to an event detector to identify valid AH events. Therefore, the proposed method showed a Cohen’s kappa coefficient of 0.728, sensitivity of 0.781, specificity of 0.956, and an accuracy of 0.930. According to the apnea-hypopnea index (AHI) estimation analysis, the Pearson’s correlation coefficient between the estimated AHI and reference AHI was 0.97. In addition, the average accuracy and kappa of SAHS diagnosis was 0.98 and 0.96, respectively, for AHI cutoffs of ≥ 5, 15, and 30 events/h. The proposed method achieved the state-of-the-art performance for classifying SAHS severity without any hand-engineered feature regardless of the user’s location. Our approach can be utilized for a cost-effective and reliable SAHS monitoring system in a home environment.

Person reidentification (ReID) systems play a key role in intelligent visual surveillance systems and have widespread applications, for example, in public security. Usually, person ReID systems can identify a person with cameras. In this article, we focus on the relatively unexplored area of using low-cost automotive radar for the person ReID problem. Unlike the radar-based person identification, person ReID has some characteristics, such as the uncooperative scenes and the long-term robustness. Therefore, we design a new deep learning network to extract spatiotemporal information from 4-D radar point clouds. We also build a data set of radar point clouds collected from the real-world person ReID scenarios. The evaluation result shows that our method achieves 91% CMC-1 accuracy on the ReID task. Besides, for the person identification task, our method also achieves accuracies of 98% and 91% for 15 and 40 individuals, respectively. In addition, we discuss the potential of using radar for person ReID problems and intuitively explain the new method's performance. Finally, we analyze the robustness and the influence of different parameters on the method and the contributions of different modules to the network model. The results of our experiment indicate that radar-based ReID not only preserves privacy but also outperforms camera-based ReID in some cases, such as in low-light environments or with substantial clothing changes.

Except for the slight difference of micromotion parameters, some decoys and warheads have the same geometry and micromotion form. As a result, recognition of similar space cone-cylinder targets is one of the difficult problems in ballistic target recognition. In recent years, due to the good effect of deep neural networks (DNNs) in optical target recognition, space cone-cylinder target recognition methods based on DNN have attracted wide attention. However, these DNN-based methods only recognize the space cone-cylinder targets with different shapes and different micromotion forms. Moreover, these methods require some time-consuming preprocessing operations, which need to observe the target for at least one micromotion period. To recognize similar space cone-cylinder targets, we propose a complex-valued coordinate attention networks (CV-CANets)-based end-to-end recognition method. Firstly, we establish the signal model of space cone-cylinder targets. Secondly, we propose CV-CA blocks by transforming the coordinate attention mechanism into the complex-valued domain. Then, we construct CV-CANet based on the proposed CV-CA blocks. Finally, the proposed CV-CANet is trained and tested by the narrowband radar echo data, which is generated by electromagnetic calculation. Compared with the convolutional neural network (CNN)-based recognition methods, the proposed method can not only recognize the similar space cone-cylinder targets but also is superior in terms of time cost and observation requirement. Extensive experiments validate that the proposed recognition method is effective when the targets only have a slight difference on the precession angular frequency and the observation time is less than half a period.

Ultrawideband (UWB) radar can achieve ultrahigh-resolution inverse synthetic aperture radar (ISAR) imaging of noncooperative targets by transmitting UWB signals. However, the spatial-variant (SV) high-order migration through range cell (MTRC) and phase errors produced by the UWB radar system have seriously challenged the feasibility of conventional ISAR imaging algorithms. Moreover, maneuvering targets has exacerbated this problem compared with the steady ones. In this article, a UWB ISAR imaging algorithm of maneuvering targets with joint high-order motion compensation and azimuth scaling (JHOMCAS) is proposed. For the azimuth SV linear MTRC and 2-D SV high-order MTRC caused by the maneuvering rotational motion of the targets, the cascaded generalized keystone transform (GKT) is adopted for precise correction. It is worth noting that, when eliminating the SV MTRC by the cascaded GKT, the 2-D SV high-order phase errors induced by the maneuvering rotational motion must be accurately compensated, or MTRC correction will fail. The traditional autofocus methods usually only address the phase errors shared by the total target without due attention to the fine SV property. In response to this problem, this article first develops a joint 2-D SV autofocus and azimuth scaling algorithm (JSVAAS) to achieve the integration of SV high-order phase error compensation and azimuth scaling. A JHOMCAS algorithm is proposed to perform the joint processing of GKT and JSVAAS, ``GKT-JSVAAS-GKT.'' This approach helps accomplish the high-precision UWB ISAR imaging of maneuvering targets, and the well-focused and scaled UWB ISAR images obtained will build a sound foundation for target classification and recognition. Extensive experiments based on both scattering point simulation data and electromagnetic calculation data verify that the proposed algorithm outperforms conventional ISAR imaging approaches in UWB ISAR imaging of maneuvering targets.

This letter deals with an imaging strategy able to manage effectively data collected on multiple lines by means of a Mini-Unmanned Aerial Vehicle (M-UAV) radar system operating in Sounder mode. The strategy, named multilines imaging approach (MIA), allows an effective 3-D pseudo-representation of the investigated volume. At the first step, MIA faces the problem of reconstructing 2-D domains (slices) by exploiting data collected on one or more lines. Then, MIA interpolates the 2-D reconstructions to provide the 3-D representation. The imaging of each slice is formulated as a linear inverse scattering problem, which is solved by means of the truncated singular value decomposition (TSVD) regularization scheme. The MIA effectiveness is assessed by processing real data collected at Archeological Park of Paestum and Velia, Paestum, Italy.

Deep learning is emerging as a powerful tool in scientific applications, such as radar-based convective storm nowcasting. However, it is still a challenge to extend the application of a well-trained deep learning nowcasting model, which demands to incorporate the learned knowledge at a certain location to other locations characterized by different precipitation features. This article designs a transfer learning framework to tackle this problem. A convolutional neural network (CNN)-based nowcasting method is utilized as the benchmark, based on which two transfer learning models are constructed through fine-tune and maximum mean discrepancy (MMD) minimization. The base CNN model is trained using radar data in the source study domain near Beijing, China, whereas the transferred models are applied to the target domain near Guangzhou, China, with only a small amount of data in the target area. The influence of a varying number of target data samples on the nowcasting performance is quantified. The experimental results demonstrate that the deep transfer learning models can improve the nowcasting skills.

In this letter, a compact wideband substrate integrated waveguide (SIW) monopulse comparator is proposed. The TE₁₀ and TE₂₀ modes of an SIW transmission line are used to generate in-phase and out-of-phase excitation fields for the sum and difference beams without complex phase shift network. The monopulse comparator can realize maximum 0.4-dB amplitude balance, 3.6° phase balance for both sum and difference ports, and -37.0-dB isolation coefficient within the operating bandwidth of 9.43-10.65 GHz. In addition, to integrate the monopulse comparator with a low-cost beam scanning capability, six monopulse comparators are used as the sources to excite a flat Luneburg lens. The experimental result demonstrates that ±58° beam coverage range with around -20.0-dB null depth and 15.0-dBi gain can be realized. The advantages of the proposed monopulse multibeam antenna, including low profile, low cost, wide beam scanning range, and wide operating bandwidth, make it a very promising solution for low-cost monopulse radar systems.

A microwave photonic multiple-input and multiple-output (MIMO) radar is proposed and demonstrated to implement high-resolution imaging. In the proposed system, multiple orthogonal linearly frequency modulated (LFM) signals are generated by heterodyning between two optical frequency combs, which enables a MIMO transmitting array with a simple and reconfigurable structure. The receiving array uses photonic frequency mixing to implement multiple channel separation and de-chirp processing simultaneously. This microwave photonic MIMO radar can have a large operation bandwidth and a large equivalent aperture, which helps to achieve high-resolution imaging in both range and azimuth directions. In the experiment, a microwave photonic 48 MIMO radar is established with a 2-GHz bandwidth in each channel. Based on this MIMO radar, high-resolution back-projection (BP) imaging with a theoretical range resolution of 7.5 cm and azimuth resolution of 1.85 is demonstrated. The experimental results can verify the feasibility of the proposed MIMO radar, which is a good solution to high-resolution radar imaging by combining microwave photonic and MIMO technologies.

The linear frequency‐modulated frequency agile radar (FAR) can be used for synthesizing high‐range‐resolution profiles (HRRP), and also has excellent electronic counter‐countermeasures performance. Similar to the Newtonalized orthogonal matching pursuit (NOMP) for line spectral estimation problem, the NOMP for the FAR radar termed as NOMP‐FAR is designed to process each coarse range bin to extract the HRRP and velocities of multiple targets, including the guide for determining the oversampling factor and the stopping criterion. In addition, it is shown that the target will cause false alarm in the nearby coarse range bins, and a post‐processing algorithm is proposed to suppress the ghost targets. Numerical simulations are conducted to demonstrate the effectiveness of NOMP‐FAR.

Classifiers based on machine learning are usually trained to distinguish between several known classes. For an electronic intelligence application, however, it is of great importance to recognize if an intercepted signal belongs to an unknown radar emitter. In the machine learning literature, this task is called open-set recognition. This article investigates six approaches in several configurations to recognize unknown emitters. It is based on a hierarchical emission model that understands emissions as a language with an inherent hierarchical structure. We consider two general approaches, which are the ""memoryless"" Markov chain and the Long Short-Term Memory recurrent neural network, which is especially designed to ""remember"" the past. The performance is demonstrated with two evaluation metrics in ten scenarios that contain different combinations of known and unknown emitters. An evaluation with corrupted data provides an estimate on the methods' accuracies under challenging conditions. The results show that unknown emitters that do not use known waveforms are reliably recognized even with corrupted data, while unknown emitters that are more similar to known ones are harder to detect.

In-band full-duplex (IBFD) technology is promised to deliver us from the scarcity of spectral resources as well as create novel multifunction wireless systems [1] . This concept was initially investigated in the 1960s for continuous-wave radar applications [2] , and, in the past decade, it has undergone a shift in research toward communications [3] – [7] and converged RF systems [8] , [9] . Since 2010, more than 600 IEEE publications alone have focused on at least one aspect of the technology, including more than 400 conference papers, 200 journal articles, and 20 magazine features [10] . After digesting these numbers, it is fair to ask: Why has IBFD functionality not been incorporated into a wireless standard yet?

Shared spectrum usage is inevitable due to the ongoing increase in wireless services and bandwidth requirements. Spectrum monitoring is a key enabler for efficient spectrum sharing by multiple radio access technologies (RATs). In this paper, we present signal classification using deep neural networks to identify various radio technologies and their associated interferences. We use Convolutional Neural Networks (CNN) to perform signal classification and employ six well-known CNN models to train for ten signal classes. These classes include LTE, Radar, WiFi and FBMC (Filter Bank Multicarrier) and their interference combinations, which include, LTE+Radar, LTE+WiFi, FBMC+Radar, FBMC+WiFi, WiFi+Radar and Noise. The CNN models include, AlexNet, VGG16, ResNet18, SqueezeNet, InceptionV3 and ResNet50. The radio signal data sets for training and testing of CNN-based classifiers are acquired using a USRP-based experimental setup. Extensive measurements of these radio technologies (LTE, WiFi, Radar and FBMC) are done over different locations and times to generate a robust dataset. We propose a novel (spectrogram) representation called the Quarter-spectrogram (Q-spectrogram) that squeezes temporal and frequency information for input to CNN models. While considering classification accuracy, model complexity and prediction time for a single input Q-spectrogram (image), ResNet18 (CNN model) gives the best overall performance with 98% classification accuracy. While SqueezeNet (CNN model) offers the lowest model complexity which makes it very suitable for resource-constrained radio monitoring devices and also offers the least prediction time of 110 msec. Moreover, we also propose a simple WiFi classification scheme that buffers several WiFi Q-spectrograms and then makes a decision about WiFi’s presence and also gives a quantified measure of WiFi traffic density.

Millimeter-wave (MMW) radar sensors are considered key components of autonomous vehicles. Because of the performance degeneration of cameras and lidars under inclement weather conditions, robust autonomy must rely on radar sensors to perform target detection and classification. Unlike basic target classifier methods in literature that make use of target velocity, the proposed approach is far more comprehensive and can be applied to targets with zero-Doppler. Depending on the radar type and target range, this paper presents four target classification models based on four different types of radar data: statistical RCS, distributed (time-domain) RCS, range-azimuth angle radar images and 3D radar images. The classification models are implemented by machine learning approaches artificial neural network (ANN) and convolutional neural network (CNN) with a comprehensive simulated dataset. Good classification accuracies are demonstrated, and the proposed model is validated with measured data. Different radar target classification approaches are compared, which clearly reveals the trade-off between classification performance and system complexity. The proposed radar target classification methods can be applied effectively to both static and dynamic targets, at near or far ranges, using traditional or imaging radars, resulting in improved safety for autonomous vehicles in a wide variety of complex environments.

Femtocell access point gives an efficient solution to furnish peak data rates in indoor wireless access systems. Propagation of the signal will get up-shot because of few considerations in advanced communication appliances. The maximum simulation reflection coefficient ( S 11 ) of proposed antenna is 45.12 dB, directivity is 6.54 dBi with the efficiency of 60% and at 60 GHz, and the measurement value of 36.35 is observed which covers the complete RADAR applications which have an unlicensed bandwidth. The proposed tree-shaped unequal slotted antenna is well suited for millimeter-wave applications because of its good bandwidth and less dimension.

The impending spectrum congestion imposed by the emergence of new bandwidth-thirsty applications may be mitigated by the integration of radar and classic communications functionalities in a common system. Furthermore, the merger of a sensing component into wireless communication networks has raised interest in recent years and it may become a compelling design objective for 6G. This article presents the evolution of the hitherto separate radar and communication systems towards their amalgam known as a joint radar and communication (RADCOM) system. Explicitly, we propose to integrate a radio sensing component into 6G. We consider an ultra-dense network (UDN) scenario relying on an active multistatic radar configuration and on cooperation between the access points across the entire coverage area. The technological trends required to reach a feasible integration, the applications anticipated and the open research challenges are identified, with an emphasis on high-accuracy network synchronization. The successful integration of these technologies would facilitate centimeter-level resolution, hence supporting compelling high-resolution applications for next-generation networks, such as robotic cars and industrial assembly lines., 10 pages, 3 figures, accepted for publication in IEEE Vehicular Technology Magazine

Biomimetic antenna arrays inspired by the fly Ormia ochracea showed a promising improvement of the angle estimation capabilities of radar sensors. So far, there is usually a loss of output power associated with this improvement decreasing the detectability of weak radar targets. In this paper, an electronically switchable two-element biomimetic antenna array is presented for the first time. This array provides the possibility to switch between a biomimetic antenna mode with enhanced phase sensitivity and a conventional antenna mode with better SNR. Circuit requirements are discussed, the design process is described, and a realization in the 77-GHz range using PIN diodes as switching elements is presented. Radar measurements verify the concept. By switching, the phase sensitivity of the realized array can be enhanced by a factor of 3 with a relative power loss of maximum 14 dB.