Search

In practical radar applications, the diversity of wideband transmission signals presents a significant challenge for radar target recognition systems. Traditional electromagnetic (EM) simulation methods often require the point-by-point sampling of target echo signals under specific radiation sources, and this process must be repeated for different transmission signals. This results in extensive EM computations and low computational efficiency. Additionally, the physical attribute information of the target is often obscured within the simulated echoes, complicating feature extraction. To address these issues, we propose a novel method for the efficient and rapid modeling and analysis of complex target time-domain echoes based on a forward scattering center model. This method constructs an impulse response model of the target under unit impulse signal excitation, representing the inherent scattering properties of the target and remaining unaffected by changes in the radiation source. Subsequently, this model is convolved with arbitrary wideband input signals to quickly reconstruct the wideband echo signals of the target. Numerical examples validate the accuracy and effectiveness of the proposed model. This method offers several advantages: firstly, it provides high computational efficiency by quickly convolving with the input signals, thereby avoiding the extensive EM calculations required by traditional methods due to changes in the radiation source. Secondly, it achieves significant data compression; the proposed echo model only requires the model parameters to be calculated at the central frequency point, enabling the rapid reconstruction of target echo data across a wideband range and effectively reducing storage requirements. Finally, it presents clear and complete physical attributes by employing a "cause-to-effect" forward-modeling approach, where the model parameters fully represent the inherent physical properties of the target. This effectively addresses the issue of physical interpretability in optical region radar target recognition. [ABSTRACT FROM AUTHOR]

Tornadoes, as highly destructive weather events, require accurate detection for effective decision‐making. Traditional radar‐based tornado detection algorithms (TDA) face challenges with limited tornado feature extraction capabilities, leading to high false alarm rates and low detection probabilities. This study introduces the Multi‐Task Identification Network (MTI‐Net), leveraging Doppler radar data to enhance tornado recognition. MTI‐Net integrates tornado detection and estimation tasks to acquire comprehensive spatial and locational information. As part of MTI‐Net, we introduce a novel backbone network of Multi‐Head Convolutional Block (MHCB), which incorporates Spatial and Channel Attention Units (SAU and CAU). SAU optimizes local tornado feature extraction, while CAU reduces false alarms by enhancing dependencies among input variables. Experiments demonstrate the superiority of MTI‐Net over TDA, with a decrease in false alarm rates from 0.94 to 0.46 and an increase in hit rates from 0.23 to 0.81, highlighting the effectiveness of MTI‐Net in handling small‐scale tornado events. Plain Language Summary: Tornadoes, highly destructive small‐scale weather phenomena, demand accurate detection for informed decision‐making. Although meteorological radars are commonly utilized for tornado identification, current methods often suffer from false alarms or missed detections due to radar noise. In this study, we introduce the multi‐task learning‐based identification network (MTI‐Net), which not only enables tornado detection but also estimates tornado counts within radar data. We integrate Convolutional Neural Networks (CNNs) with Transformer techniques to enhance the model's ability to capture tornado information. CNNs detect local details using filters, while Transformers manage global connections through attention mechanisms. A series of experiments demonstrate significant improvements in tornado detection with MTI‐Net compared to traditional methods. Key Points: A tornado dataset with detailed radar features was created over China from 2017 to 2023Multi‐task learning was designed to simultaneously infer tornado detection and tornado number estimationIntegration of spatial and channel attention units can better extract tornado features from radar data [ABSTRACT FROM AUTHOR]

In the current complex situations of electronic intelligence (ELINT), the authors present a radar emitter structure (RES) identification method based on deep learning at a new level to address the issue of incomplete cognitive information. Firstly, due to the fact that existing simulation data cannot fully reflect the structure features of the entire radar emitter, the structure feature‐level RES model is built using direct digital synthesiser (DDS) technology and radio frequency (RF) simulation platform. Afterwards, considering that the structure features are reflected in the frequency domain, a stacked frequency sparse auto encoder (sFSAE) network is constructed by adding a constraint term in frequency domain to the loss function of sparse auto encoder (SAE). Using deep learning to extract structure features with constraints in different domains is instructive for feature extraction techniques under variable operating parameters. Finally, the extracted structure features are input into the Softmax classifier to perform the identification from the radar signal to the RES. The experimental results show that the proposed method has high generalisation ability and robustness under different modulation types, different operating parameters and different signal to noise ratio (SNR). It also has a high identification rate even for untrained modulated signals. [ABSTRACT FROM AUTHOR]

With the continuous advancement of autonomous driving and monitoring technologies, there is increasing attention on non-intrusive target monitoring and recognition. This paper proposes an ArcFace SE-attention model-agnostic meta-learning approach (AS-MAML) by integrating attention mechanisms into residual networks for pedestrian gait recognition using frequency-modulated continuous-wave (FMCW) millimeter-wave radar through meta-learning. We enhance the feature extraction capability of the base network using channel attention mechanisms and integrate the additive angular margin loss function (ArcFace loss) into the inner loop of MAML to constrain inner loop optimization and improve radar discrimination. Then, this network is used to classify small-sample micro-Doppler images obtained from millimeter-wave radar as the data source for pose recognition. Experimental tests were conducted on pose estimation and image classification tasks. The results demonstrate significant detection and recognition performance, with an accuracy of 94.5%, accompanied by a 95% confidence interval. Additionally, on the open-source dataset DIAT-μRadHAR, which is specially processed to increase classification difficulty, the network achieves a classification accuracy of 85.9%. [ABSTRACT FROM AUTHOR]

In the realm of short-range radar applications, the focus on detecting "low, slow, and small" (LSS) targets has escalated, marking a pivotal aspect of critical area defense. This study pioneers the use of one-dimensional convolutional neural networks (1D-CNNs) for direct slow-time dimension radar feature extraction, sidestepping the complexity tied to frequency and wavelet domain transformations. It innovatively employs a network architecture enriched with multi-frequency multi-scale deformable convolution (MFMSDC) layers for nuanced feature extraction, integrates attention modules to foster comprehensive feature connectivity, and leverages linear operations to curtail overfitting. Through comparative evaluations and ablation studies, our methodology not only simplifies the analytic process but also demonstrates superior classification capabilities. This establishes a new benchmark for efficiently classifying low-altitude entities, such as birds and unmanned aerial vehicles (UAVs), thereby enhancing the precision and operational efficiency of radar detection systems. [ABSTRACT FROM AUTHOR]

Radar emitter signal sorting (RESS) is a crucial process in contemporary electronic battlefield situation awareness. Separating pulses belonging to the same radar emitter from interleaved radar pulse sequences with a lack of prior information, high density, strong overlap, and wide parameter distribution has attracted increasing attention. In order to improve the accuracy of RESS under scenarios with limited labeled samples, this paper proposes an RESS model called TR-RAGCN-AFF-RESS. This model transforms the RESS problem into a pulse-by-pulse classification task. Firstly, a novel weighted adjacency matrix construction method was proposed to characterize the structural relationships between pulse attribute parameters more accurately. Building upon this foundation, two networks were developed: a Transformer(TR)-based interleaved pulse sequence temporal feature extraction network and a residual attention graph convolutional network (RAGCN) for extracting the structural relationship features of attribute parameters. Finally, the attention feature fusion (AFF) algorithm was introduced to fully integrate the temporal features and attribute parameter structure relationship features, enhancing the richness of feature representation for the original pulses and achieving more accurate sorting results. Compared to existing deep learning-based RESS algorithms, this method does not require many labeled samples for training, making it better suited for scenarios with limited labeled sample availability. Experimental results and analysis confirm that even with only 10% of the training samples, this method achieves a sorting accuracy exceeding 93.91%, demonstrating high robustness against measurement errors, lost pulses, and spurious pulses in non-ideal conditions. [ABSTRACT FROM AUTHOR]

The authors present multiple machine learning‐based methods for distinguishing maritime targets from sea clutter. The main goal for this classification framework is to aid future millimetre wave radar system design for marine autonomy. Availability of empirical data at this frequency range in the literature is scarce. The classification and anomaly detection techniques reported here use experimental data collected from three different field trials from three different millimetre wave radars. Two W‐band radars operating at 77 and 94 GHz and a G‐band radar operating at 207 GHz were used for the field trial data collection. The dataset encompasses eight classes including sea clutter returns. The other targets are boat, stand up paddleboard/kayak, swimmer, buoy, pallet, stationary solid object (i.e. rock) and sea lion. The Doppler signatures of the targets have been investigated to generate feature values. Five feature values have been extracted from Doppler spectra and four feature values from Doppler spectrograms. The features were trained on a supervised learning model for classification as well as an unsupervised model for anomaly detection. The supervised learning was performed for both multi‐class and 2‐class (sea clutter and target) classification. The classification based on spectrum features provided an 84.3% and 80.1% validation and test accuracy respectively for the multi‐class classification. For the spectrogram feature‐based learning, the validation and test accuracy for multi‐class increased to 93.3% and 88.7% respectively. For the 2‐class classification, the spectrum feature‐based training accuracies are 88.1% and 86.8%, whereas with the spectrogram feature‐based model, the values are 95% and 94.1% for validation and test accuracies respectively. A one class support vector machine was also applied to an unlabelled dataset for anomaly detection training, with 10% outlier data. The cross‐validation accuracy has shown very good agreement with the expected anomaly detection rate. [ABSTRACT FROM AUTHOR]

In autonomous vehicles, the LiDAR and radar sensors are indispensable components for measuring distances to objects. While deep-learning-based algorithms for LiDAR sensors have been extensively proposed, the same cannot be said for radar sensors. LiDAR and radar share the commonality of measuring distances, but they are used in different environments. LiDAR tends to produce less noisy data and provides precise distance measurements, but it is highly affected by environmental factors like rain and fog. In contrast, radar is less impacted by environmental conditions but tends to generate noisier data. To reduce noise in radar data and enhance radar data augmentation, we propose a LiDAR-to-Radar translation method with a voxel feature extraction module, leveraging the fact that both sensors acquire data in a point-based manner. Because of the translation of high-quality LiDAR data into radar data, this becomes achievable. We demonstrate the superiority of our proposed method by acquiring and using data from both LiDAR and radar sensors in the same environment for validation. [ABSTRACT FROM AUTHOR]

Hail is a type of severe convective weather disaster characterized by abundant water vapor and strong updrafts, resulting in intense and high reflectivity echoes in hail clouds, often accompanied by an overhanging form. Although hail research has made great progress, it is still challenging to achieve accurate identification of hail. Compared with traditional radar, dual-polarization radar can output a variety of polarization parameters and provide information about the shape and phase of precipitation particles, which is conducive to the identification of hail particles. In this study, dual-polarization radar data are used to explore more hail features from various perspectives, starting with the morphological characteristics of hail clouds and using common feature extraction methods in the field of image processing. A comprehensive approach to high-dimensional features is developed. Using machine learning methods, hail identification models are constructed in both the traditional mechanism feature space and the new feature space constructed in this study. Experimental results strongly confirm the significant effectiveness of the five-dimensional new mechanism features developed in this paper for hail identification. [ABSTRACT FROM AUTHOR]

With the rapid development of modern military countermeasure technology, deep distinguish hostile radar is essential in electronic warfare. However, traditional radio frequency (RF) feature extraction methods can easily be interfered by signal information and fail due to the lack of research on RF feature extraction techniques for complex situations. Therefore, in this paper, first, the generation mechanism of RF structure information is discussed, and the influence of different signal information introduced by different operating parameters on RF structure feature extraction is analyzed. Then, an autoencoder (AE) network and an autoencoder metric (AEM) network are designed, introducing metric learning ideas, so that the extracted deep RF structure features have good stability and divisibility. Finally, radar emitter structure (RES) inversion is realized using the centroid-matching method. The experimental results demonstrate that this method exhibits good inversion performance under variable operating parameters (modulation type, frequency, bandwidth, input power). RES inversion including unknown operating parameters is realized for the first time, and it is shown that metric learning has the advantage of separability of RF feature extraction, which can provide an idea in emitter and RF feature extraction. [ABSTRACT FROM AUTHOR]

Target recognition mainly focuses on three approaches: optical-image-based, echo-detection-based, and passive signal-analysis-based methods. Among them, the passive signal-based method is closely integrated with practical applications due to its strong environmental adaptability. Based on passive radar signal analysis, we design an "end-to-end" model that cascades a noise estimation network with a recognition network to identify working modes in noisy environments. The noise estimation network is implemented based on U-Net, which adopts a method of feature extraction and reconstruction to adaptively estimate the noise mapping level of the sample, which can help the recognition network to reduce noise interference. Focusing on the characteristics of radar signals, the recognition network is realized based on the multi-scale convolutional attention network (MSCANet). Firstly, deep group convolution is used to isolate the channel interaction in the shallow network. Then, through the multi-scale convolution module, the finer-grained features of the signal are extracted without increasing the complexity of the model. Finally, the self-attention mechanism is used to suppress the influence of low-correlation and negative-correlation channels and spaces. This method overcomes the problem of the conventional method being seriously disturbed by noise. We validated the proposed method in 81 kinds of noise environment, achieving an average accuracy of 94.65%. Additionally, we discussed the performance of six machine learning algorithms and four deep learning algorithms. Compared to these methods, the proposed MSCANet achieved an accuracy improvement of approximately 17%. Our method demonstrates better generalization and robustness. [ABSTRACT FROM AUTHOR]

Feature extraction and recognition of underwater targets are important in military and civilian areas. This paper studied water surface acoustic wave (WSAW) detection by a millimeter wave (mmWave) radar. The mmWave-based endpoint detection method of the WSAW was introduced. Simulated results show that the continuous wavelet transform (CWT) method has a better detection performance. A 77 GHz large aperture antenna mmWave radar sensor and an underwater acoustic transmitter have been applied to conduct laboratory experiments. Still water surface experimental results verify that the CWT method has better detection capability, and the mmWave radar can accurately detect even 155 nm WSAW. Wavy water surface experimental results demonstrate the ability of the mmWave radar to analyze the time-frequency feature of the weak WSAW signal. These works indicate the potential of mmWave radar for the cross-medium detection and recognition of underwater targets. [ABSTRACT FROM AUTHOR]

This paper intends to propose an automated deep learning-based land cover classification model of remote sensing images. The model includes (i) pre-processing, (ii) feature extraction and (iii) classification. The captured synthetic-aperture radar (SAR) and Landsat-8 images are initially pre-processed using the Gabor filtering model. Subsequently, from SAR images the gray-level-co-occurrence matrix-based texture characteristics are extracted, and temperature vegetation index-based characteristics, normalized vegetation index-based features, normalized difference index-based features and coloration index features are extracted from Landsat-8 images. Finally, the extracted features are subjected to an optimized deep belief network (DBN), where the weight is fine-tuned by the optimization logic. For this, a new Sunflower adopted Red Deer (SARD) algorithm is introduced in this work that hybrids the concept of Red Deer algorithm and Sunflower optimization. The performance of the proposed classification model is compared over other conventional models concerning different measures. Especially, the accuracy of the presented work (SARD+DBN) for Testcase3 is 5, 7, 6 and 30% better than existing DA + DBN, JA + DBN, SLnO+DBN and LA + DBN methods, respectively. [ABSTRACT FROM AUTHOR]

This article introduces a long-range sensing system based on millimeter-wave radar, which is used to detect the roadside boundaries and track trains for trains. Due to the high speed and long braking distance of trains, existing commercial vehicle sensing solutions cannot meet their needs for long-range target detection. To address this challenge, this study proposes a long-range perception system for detecting road boundaries and trains based on millimeter-wave radar. The system uses high-resolution, long-range millimeter-wave radar customized for the strong scattering environment of rail transit. First, we established a multipath scattering theory in complex scenes such as track tunnels and fences and used the azimuth scattering characteristics to eliminate false detections. A set of accurate calculation methods of the train's ego-velocity is proposed, which divides the radar detection point clouds into static target point clouds and dynamic target point clouds based on the ego-velocity of the train. We then used the road boundary curvature, global geometric parallel information, and multi-frame information fusion to extract and fit the boundary in the static target point stably. Finally, we performed clustering and shape estimation on the radar track information to identify the train and judge the collision risk based on the position and speed of the detected train and the extracted boundary information. The paper makes a significant contribution by establishing a multipath scattering theory for complex scenes of rail transit to eliminate radar false detection and proposing a train speed estimation strategy and a road boundary feature point extraction method that adapt to the rail environment. As well as building a perception system and installing it on the train for verification, the main line test results showed that the system can reliably detect the road boundary more than 400 m ahead of the train and can stably detect and track the train. [ABSTRACT FROM AUTHOR]

There has been increased interest in recognizing the dynamic and flexible changes in shipborne multi-function radar (MFR) working modes. The working modes determine the distribution of pulse descriptor words (PDWs). However, building the mapping relationship from PDWs to working modes in reconnaissance systems presents many challenges, such as the duration of the working modes not being fixed, incomplete temporal features in short PDW slices, and delayed feedback of the reconnaissance information in long PDW slices. This paper recommends an MFR working mode recognition method based on the ShakeDrop regularization dual-path attention temporal convolutional network (DP-ATCN) with prolonged temporal feature preservation. The method uses a temporal feature extraction network with the Convolutional Block Attention Module (CBAM) and ShakeDrop regularization to acquire a high-dimensional space mapping of temporal features of the PDWs in a short time slice. Additionally, with prolonged PDW accumulation, an enhanced TCN is introduced to attain the temporal variation of long-term dependence. This way, secondary correction of MFR working mode recognition results is achieved with both promptness and accuracy. Experimental results and analysis confirm that, despite the presence of missing and spurious pulses, the recommended method performs effectively and consistently in shipborne MFR working mode recognition tasks. [ABSTRACT FROM AUTHOR]

This paper proposed a novel texture feature extraction technique for radar remote sensing image retrieval application using adaptive tetrolet transform and Gray level co-occurrence matrix. Tetrolets have provided fine texture information in the radar image. Tetrominoes have been employed on each decomposed radar image and best pattern of tetrominoes has been chosen which represents the better radar image geometry at each decomposition level. All three high pass components of the decomposed radar image at each level and low pass component at the last level are considered as input values for Gray level co-occurrence matrix (GLCM), where GLCM provides the spatial relationship among the pixel values of decomposed components in different directions at certain distances. The GLCMs of decomposed components are computed in (1). (0, π/2, π, 3π/2), (2). (π/4, 3π/4, 5π/4, 7π/4) (3). (0, π/4, π/2, 3π/4, π, 3π/2, 5π/4, 7π/4) directions individually and subsequently a texture feature descriptor is constructed by computing statistical parameters from the corresponding GLCMs. The retrieval performance is validated on two standard radar remote sensing image databases: 20-class satellite remote sensing dataset and 21-class land-cover dataset. The average metrices i.e., precision, recall and F-score are 61.43%, 12.29% and 20.47% for 20-class satellite remote sensing dataset while 21-class land-cover dataset have achieved 67.75%, 9.03% and 15.94% average metrices. The retrieved results show the better accuracy as compared to the other related state of arts radar remote sensing image retrieval methods. [ABSTRACT FROM AUTHOR]

In ground static target detection, polarimetric high-resolution radar can distinguish the target from the strong ground clutter by reducing the clutter power in the range cell and providing additional polarimetric features. Since the energy of a target is split over several range cells, the resulting detection problem is called polarimetric range extended target (RET) detection, where all target scattering centers should be considered. In this paper, we propose a novel polarimetric RET detection method via adaptive range weighted feature extraction. Specifically, polarimetric features of range cells are extracted, and a pretrained attention-mechanism-based module is used to adaptively calculate range cells weights, which are used to accumulate the range cells features as detection statistics. While calculating weights, both amplitude and polarimetric features are considered. This method can make the most of polarization information and improve the accumulation effect, thus increasing the discrimination between targets and clutter. The effectiveness of the proposed method is verified compared to both popular energy-domain detection methods and existing feature-domain detection methods, and the results show that our method exhibits superior detection performance. Moreover, we further analyze our method on different target models and different clutter distributions to prove that our method is suitable for different types of targets and clutter. [ABSTRACT FROM AUTHOR]

Micro-Doppler (m-D) analysis is the most effective mechanism for detecting rotating targets or components; however, it fails when the target rotation plane is perpendicular to the radar line of sight (LOS). The vortex electromagnetic wave (VEMW) provides a unconventional structure of wavefront phase modulation on the cross-plane of the radar LOS, on which the radial m-D vanishes while the rotational Doppler (RD) appears. In the absence of the position of rotation center, this paper focuses on the micromotion parameters estimation based on RD effect for rotating target, and then proposes an estimation procedure, referred to as the two-step method. The micromotion parameters of the rotating target include the rotation attitude, the rotation radius and the position of the rotation center while the latter is coupled to the former two. Firstly, the micromotion parameters are roughly estimated based on the RD curve parameters obtained from the time-frequency (TF) spectrum of the received signal. Secondly, the maximum likelihood estimation (MLE) is used to accurately estimate the micromotion parameters. In addition, the Cramér–Rao bound (CRB) of parameter estimation is derived. The simulation studies the influencing factors of estimation performance and verifies that the proposed estimation method can provide excellent estimation accuracy of the micromotion parameters. [ABSTRACT FROM AUTHOR]

The goal of this paper is to propose a method to achieve a higher classification rate in Polarimetric Synthetic Aperture Radar (PolSAR) image classification. In our work, PolSAR features are extracted from Convolutional Neural Networks (CNNs) and also Graph Convolutional Networks (GCNs). Due to the construction of the adjacency matrix on all the data, traditional GCNs usually suffer from a substantial computational cost, particularly in large‐scale remote sensing (RS) problems. To this end, first of all, we propose a new mini‐batch GCN (called Mini‐GCN), which allows to train large‐scale GCNs in a mini‐batch fashion. More significantly, our designed mini‐GCN is capable of inferring out‐of‐sample data without re‐training networks and improving classification performance. Furthermore, as CNNs and GCNs can extract different types of PolSAR features, an intuitive solution to break the performance bottleneck of a single model is to fuse them. Since mini‐GCNs can perform batch‐wise network training (enabling the combination of CNNs and GCNs), we can use the feature fusion strategy. Therefore, in this paper, a local graph‐based fusion method is proposed to couple dimension reduction and feature fusion of the information extracted from the designed CNN and Mini‐GCN. Experimental results on real PolSAR data are very encouraging. Compared to the methods using only single feature and stacking all the features together, the proposed feature fusion method improves the overall classification accuracy on the real PolSAR data sets for more than 5%. Moreover, the experiments conducted on PolSAR datasets, demonstrate the advantages of the used mini‐GCNs over the traditional GCNs and the superiority of the proposed feature fusion method with regards to the single CNN or GCN models. [ABSTRACT FROM AUTHOR]

Accurately detecting falls and providing clear directions for the fall can greatly assist medical staff in promptly developing rescue plans and reducing secondary injuries during transportation to the hospital. In order to facilitate portability and protect people's privacy, this paper presents a novel method for detecting fall direction during motion using the FMCW radar. We analyze the fall direction in motion based on the correlation between different motion states. The range–time (RT) features and Doppler–time (DT) features of the person from the motion state to the fallen state were obtained by using the FMCW radar. We analyzed the different features of the two states and used a two-branch convolutional neural network (CNN) to detect the falling direction of the person. In order to improve the reliability of the model, this paper presents a pattern feature extraction (PFE) algorithm that effectively eliminates noise and outliers in RT maps and DT maps. The experimental results show that the method proposed in this paper has an identification accuracy of 96.27% for different falling directions, which can accurately identify the falling direction and improve the efficiency of rescue. [ABSTRACT FROM AUTHOR]

Sleep posture has a crucial impact on the incidence and severity of obstructive sleep apnea (OSA). Therefore, the surveillance and recognition of sleep postures could facilitate the assessment of OSA. The existing contact-based systems might interfere with sleeping, while camera-based systems introduce privacy concerns. Radar-based systems might overcome these challenges, especially when individuals are covered with blankets. The aim of this research is to develop a nonobstructive multiple ultra-wideband radar sleep posture recognition system based on machine learning models. We evaluated three single-radar configurations (top, side, and head), three dual-radar configurations (top + side, top + head, and side + head), and one tri-radar configuration (top + side + head), in addition to machine learning models, including CNN-based networks (ResNet50, DenseNet121, and EfficientNetV2) and vision transformer-based networks (traditional vision transformer and Swin Transformer V2). Thirty participants (n = 30) were invited to perform four recumbent postures (supine, left side-lying, right side-lying, and prone). Data from eighteen participants were randomly chosen for model training, another six participants' data (n = 6) for model validation, and the remaining six participants' data (n = 6) for model testing. The Swin Transformer with side and head radar configuration achieved the highest prediction accuracy (0.808). Future research may consider the application of the synthetic aperture radar technique. [ABSTRACT FROM AUTHOR]

Determining the attitude of a non-cooperative target in space is an important frontier issue in the aerospace field, and has important application value in the fields of malfunctioning satellite state assessment and non-cooperative target detection in space. This paper proposes a non-cooperative target attitude estimation method based on the deep learning of ground and space access (GSA) scene radar images to solve this problem. In GSA scenes, the observed target satellite can be imaged not only by inverse synthetic-aperture radar (ISAR), but also by space-based optical satellites, with space-based optical images providing more accurate attitude estimates for the target. The spatial orientation of the intersection of the orbital planes of the target and observation satellites can be changed by fine tuning the orbit of the observation satellite. The intersection of the orbital planes is controlled to ensure that it is collinear with the position vector of the target satellite when it is accessible to the radar. Thus, a series of GSA scenes are generated. In these GSA scenes, the high-precision attitude values of the target satellite can be estimated from the space-based optical images obtained by the observation satellite. Thus, the corresponding relationship between a series of ISAR images and the attitude estimation of the target at this moment can be obtained. Because the target attitude can be accurately estimated from the GSA scenes obtained by a space-based optical telescope, these attitude estimation values can be used as training datasets of ISAR images, and deep learning training can be performed on ISAR images of GSA scenes. This paper proposes an instantaneous attitude estimation method based on a deep network, which can achieve robust attitude estimation under different signal-to-noise ratio conditions. First, ISAR observation and imaging models were created, and the theoretical projection relationship from the three-dimensional point cloud to the ISAR imaging plane was constructed based on the radar line of sight. Under the premise that the ISAR imaging plane was fixed, the ISAR imaging results, theoretical projection map, and target attitude were in a one-to-one correspondence, which meant that the mapping relationship could be learned using a deep network. Specifically, in order to suppress noise interference, a UNet++ network with strong feature extraction ability was used to learn the mapping relationship between the ISAR imaging results and the theoretical projection map to achieve ISAR image enhancement. The shifted window (swin) transformer was then used to learn the mapping relationship between the enhanced ISAR images and target attitude to achieve instantaneous attitude estimation. Finally, the effectiveness of the proposed method was verified using electromagnetic simulation data, and it was found that the average attitude estimation error of the proposed method was less than 1°. [ABSTRACT FROM AUTHOR]

Non-imaging radar can achieve the detection and localization of moving targets, but it faces difficulties in the classification of targets. Aiming for the application of moving target classification by low/medium resolution non-imaging radar, this paper proposes a novel feature extraction method, based on the statistical characteristics of echo amplitude with the L-band fully polarimetric radar. A feature plane, composed of the 3rd-order central moment (skewness) and 4th-order central moment (kurtosis) as the statistical characteristics of the echo envelope, is established. In addition, two types of moving targets, pedestrians and non-motorized vehicles, are able to be effectively distinguished according to whether the echo signals of different polarizations have overlapping areas in the feature plane. The L-band fully polarimetric radar has been developed and field experiments have been conducted. The experimental results verify that the kurtosis and skewness of the fully polarimetric echo amplitude of the pedestrians are very close, and there is an overlapping area in the feature plane, while the statistical characteristics of the fully polarimetric echo signal of non-motor vehicles are different, and there is no overlapping area in the feature plane. This proposed feature extraction method has the advantage of being simple and robust, compared to the traditional imaging approach. [ABSTRACT FROM AUTHOR]

Identity authentication based on Doppler radar respiration sensing is gaining attention as it requires neither contact nor line of sight and does not give rise to privacy concerns associated with video imaging. Prior research demonstrating the recognition of individuals has been limited to isolated single-subject scenarios. When two equidistant subjects are present, identification is more challenging due to the interference of respiration motion patterns in the reflected radar signal. In this research, respiratory signature separation techniques are functionally combined with machine learning (ML) classifiers for reliable subject identity authentication. An improved version of the dynamic segmentation algorithm (peak search and triangulation) was proposed, which can extract distinguishable airflow profile-related features (exhale area, inhale area, inhale/exhale speed, and breathing depth) for medium-scale experiments of 20 different participants to examine the feasibility of extraction of an individual’s respiratory features from a combined mixture of motions for subjects. Independent component analysis with the joint approximation of diagonalization of eigenmatrices (ICA-JADE) algorithm was employed to isolate individual respiratory signatures from combined mixtures of breathing patterns. The extracted hyperfeature sets were then evaluated by integrating two different popular ML classifiers, k-nearest neighbor (KNN) and support vector machine (SVM), for subject authentication. Accuracies of 97.5% for two-subject experiments and 98.33% for single-subject experiments were achieved, which supersedes the performance of prior reported methods. The proposed identity authentication approach has several potential applications, including security/surveillance, the Internet-of-Things (IoT) applications, virtual reality, and health monitoring. [ABSTRACT FROM AUTHOR]

As a noncontact and noninvasive sensor, radar offers attractive modality for human motion recognition in many fields, such as surveillance, smart homes, and assisted living. As a dynamic process, a comprehensive multidomain analysis in stream is crucial for human motion recognition. In this article, a novel spatial–temporal convolution long short-term memory (ST-ConvLSTM) network using dynamic range-Doppler frames (DRDF) based on portable frequency-modulated continuous-wave (FMCW) radar is proposed to address this problem. First, DRDF is introduced to characterize different human motions in time, range, Doppler, and radar cross section (RCS) domains with a time-sequenced range-Doppler maps. Then, ConvLSTM cell is investigated to extract continuous 2-D image features by combining both convolution operation and LSTM cell. Furthermore, a spatial attention module is utilized to emphasize the spatial distribution of human motion in the range-Doppler domain, while a temporal attention module is designed to obtain optimal temporal weights considering behavior continuity. Finally, an extensive radar dataset from 16 volunteers demonstrated its feasibility and superiority in the classification of six typical daily human motions. The contributions of attention modules and its robustness facing individual diversity are also investigated and discussed. [ABSTRACT FROM AUTHOR]

Non‐contact emotion recognition is a new research field. Using millimetre‐wave radar does not require users to wear any equipment, and there is no privacy violation. This study proposes a new emotion recognition method, which uses millimetre‐wave radar to transmit frequency‐modulated continuous wave signals and extracts and separates the time domain signals of heartbeat and respiration of subjects through the echo of human reflection. According to the characteristics of collected signals, a deep learning framework combining one‐dimensional convolutional neural network and Bidirectional Long Short‐Term Memory neural networks is designed for feature extraction and classification. Experiments show that this method has high average recognition accuracy for four emotions in the case of person‐independent. The excellent range resolution, higher system integration, and lower power consumption of millimetre‐wave radar will profoundly impact the development of human–computer interaction, modern medical care, and education. [ABSTRACT FROM AUTHOR]

Doppler-radar-based continuous human motion recognition recently has attracted extensive attention, which is a favorable choice for privacy and personal security. Existing results of continuous human motion recognition (CHMR) using mmWave FMCW Radar are not considered the continuous human motion with the high similarity problem. In this paper, we proposed a new CHMR algorithm with the consideration of the high similarity (HS) problem, called as CHMR-HS, by using the modified Transformer-based learning model. As far as we know, this is the first result in the literature to investigate the continuous HMR with the high similarity. To obtain the clear FMCW radar images, the background and target signals of the detected human are separated through the background denoising and the target extraction algorithms. To investigate the effects of the spectral-temporal multi-features with different dimensions, Doppler, range, and angle signatures are extracted as the 2D features and range-Doppler-time and range-angle-time signatures are extracted as the 3D features. The 2D/3D features are trained into the adjusted Transformer-encoder model to distinguish the difference of the high-similarity human motions. The conventional Transformer-decoder model is also re-designed to be Transformer-sequential-decoder model such that Transformer-sequential-decoder model can successfully recognize the continuous human motions with the high similarity. The experimental results show that the accuracy of our proposed CHMR-HS scheme are 95.2% and 94.5% if using 3D and 2D features, the simulation results also illustrates that our CHMR-HS scheme has advantages over existing CHMR schemes. [ABSTRACT FROM AUTHOR]

Automatic waveform recognition of overlapping low probability of intercept (LPI) radar signals is an important and challenging task in electronic reconnaissance of the increasingly complicated spectrum environment. In this article, an overlapping LPI waveform recognition processing framework incorporating residual attention-aided U-net generative adversarial network (GAN) and multiinstance multilabel (MIML) classifier is proposed. This framework includes five cascade modules and can achieve satisfactory recognition performance by training with single type of signals only. First, the training signals are transformed into time–frequency images. Then, a residual attention U-net GAN (RAUGAN) with residual learning is employed to reconstruct signal images from noise-contaminated images and with the supervision of the high-quality ones. After that, an instance generation module with asymmetric convolutions generates instance representations, which are then fed into the subsequent residual attention MIML classifier (RAMIML). Finally, an adaptive threshold calibration module is implemented to obtain appropriate thresholds for the final decision. Besides, two loss functions are elaborately designed for the RAUGAN and RAMIML, respectively. Extensive experimental results validate the recognition performance of the proposed framework with a recognition accuracy of 80$\%$ at signal-to-noise ratio $>-18$ dB and show higher robustness on the power ratios and generative performance compared with other state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Asan important means in low-altitude airspace surveillance, passive radar has been widely studied. With the increasing complexity of the low-altitude environment, the urgent need for radar's capability of automatic target recognition (ATR) emerges. In the field of ATR for passive radar, the method based on radar cross section (RCS) is an important direction for the simplicity of feature extraction. In this article, we exploit the compensated quasi-echo-power (CQEP), i.e., quasi-RCS, to realize ATR in passive radar. We propose an ATR method on the basis of the angular diversity. First, we divide the angular space, which consists of four components of the incident angle and scattering angle of electromagnetic wave, into multiple subspaces. Then, we build a subrecognizer in each angular subspace according to the CQEP distribution characteristics. Each receiving station of the multistatic passive radar recognizes targets in an angular subspace corresponding to its observation and outputs a preliminary decision. Based on the preliminary decisions of all receiving stations, a voting strategy is adopted to make the final decision on the unknown target class in the fusion center. Experimental results based on real-life target data show that the proposed method has a significant improvement on the average correct recognition rate with fusion of three receiving stations, which validates the proposed method. [ABSTRACT FROM AUTHOR]

Radar signal anomaly detection is an effective method to detect potential threat targets. Given the low Accuracy of the traditional AE model and the complex network of GAN, an anomaly detection method based on ResNet-AE is proposed. In this method, CNN is used to extract features and learn the potential distribution law of data. LSTM is used to discover the time dependence of data. ResNet is used to alleviate the problem of gradient loss and improve the efficiency of the deep network. Firstly, the signal subsequence is extracted according to the pulse's rising edge and falling edge. Then, the normal radar signal data are used for model training, and the mean square error distance is used to calculate the error between the reconstructed data and the original data. Finally, the adaptive threshold is used to determine the anomaly. Experimental results show that the recognition Accuracy of this method can reach more than 85%. Compared with AE, CNN-AE, LSTM-AE, LSTM-GAN, LSTM-based VAE-GAN, and other models, Accuracy is increased by more than 4%, and it is improved in Precision, Recall, F1-score, and AUC. Moreover, the model has a simple structure, strong stability, and certain universality. It has good performance under different SNRs. [ABSTRACT FROM AUTHOR]

Weather radar echo extrapolation, which predicts future echoes based on historical observations, is one of the complicated spatial–temporal sequence prediction tasks and plays a prominent role in severe convection and precipitation nowcasting. However, existing extrapolation methods mainly focus on a defective echo-motion extrapolation paradigm based on finite observational dynamics, neglecting that the actual echo sequence has a more complicated evolution process that contains both nonlinear motions and the lifecycle from initiation to decay, resulting in poor prediction precision and limited application ability. To complement this paradigm, we propose to incorporate a novel long-term evolution regularity memory (LERM) module into the network, which can memorize long-term echo-evolution regularities during training and be recalled for guiding extrapolation. Moreover, to resolve the blurry prediction problem and improve forecast accuracy, we also adopt a coarse–fine hierarchical extrapolation strategy and compositive loss function. We separate the extrapolation task into coarse and fine two levels which can reduce the downsampling loss and retain echo fine details. Except for the average reconstruction loss, we additionally employ adversarial loss and perceptual similarity loss to further improve the visual quality. Experimental results from two real radar echo datasets demonstrate the effectiveness of our methodology and show that it can accurately extrapolate the echo evolution while ensuring the echo details are realistic enough, even for the long term. Our method can further be improved in the future by integrating multimodal radar variables or introducing certain domain prior knowledge of physical mechanisms. It can also be applied to other spatial–temporal sequence prediction tasks, such as the prediction of satellite cloud images and wind field figures. [ABSTRACT FROM AUTHOR]

In the complex and changeable marine environment, it is difficult to achieve high-performance detection based on statistical theory for small sea surface detectors in practical applications. In this work, a method for detecting small targets on the sea surface based on sequence features is proposed from the perspectives of feature extraction and feature classification on a basis of real data. The sequence-feature method first extracts three sequence features from the radar echo sequence, namely, the instantaneous phase (IP), Doppler spectrum entropy, and short-time Fourier transform (STFT) marginal spectrum. The features are used to train the bidirectional long short-term memory (Bi-LSTM) networks model so that it has the ability to distinguish the target and the sea clutter. The measured dataset verifies that the proposed detector can achieve the detection of sea surface targets with controllable false alarm rate (FAR), and the performance is better than several existing detectors. [ABSTRACT FROM AUTHOR]

Typhoons, a kind of devastating natural disaster, have caused incalculable damages worldwide. The meteorological radar image is essential for weather forecasting, especially typhoons. The weather nowcasting (future 0–6 h) can be implemented via extrapolating radar images without using the primary weather forecasting method—the numerical weather prediction model. However, the existing related techniques based on statistics or artificial intelligence were not efficient enough. In this article, a novel radar image extrapolation algorithm named dynamic multiscale fusion-generative adversarial network (DMSF-GAN) was proposed. DMSF-GAN captures the future radar image distribution based on current radar images through modifying the GAN. In the generative module of GAN, an auto-encoder consisting of dynamic inception-3-D and feature connection blocks extracts significant features from current radar images. The feasibility of the proposed model was verified on a real radar image dataset, and the experimental results proved that the proposed algorithm could effectively capture the location and pattern of the future radar echo, especially for typhoon weather systems. Compared with the mainstream methods of radar image extrapolation such as optical-flow and recurrent neural network (RNN)-based models, DMSF-GAN has a more superior and robust performance, which is also suitable for running on low-configuration machines. [ABSTRACT FROM AUTHOR]

During the observation of micromotion targets in space, inverse synthetic aperture radar usually obtains the narrowband and wideband echoes simultaneously. In order to exploit their rich information in target electromagnetic scattering, shape, structure, and motion, this article proposes a recognition method of space micromotion targets based on decision fusion. The proposed method extracts physical features from the radar cross section and the joint time–frequency distribution from narrowband echoes, while extracts the data features from high-resolution range profiles and range-instantaneous-Doppler image by convolution neural network. Finally, particle swarm optimization is adopted to decision-level fusion so as to realize high-precision recognition. The recognition results of electromagnetic simulated data under various conditions have demonstrated the effectiveness and robustness of the proposed method. [ABSTRACT FROM AUTHOR]

In an airborne maritime radar, inverse synthetic aperture radar (ISAR) is used to image and classify non-cooperative targets. In this article, we investigate a 3D-ISAR as an alternative representation that can potentially improve the final target classification by automatically extracting key features from the radar data, such as the length, width, and height of a target. The technique works by estimating the target scatterers’ positions using measurements from multiple ISAR images. This has previously been achieved using a single receive channel that exploits the temporal motion of the target or with a multichannel dual-baseline interferometric system that uses the phase differences in both the along- and across-track directions. In this article, we combine aspects of these two techniques using a single along-track baseline suitable for airborne maritime radar systems. [ABSTRACT FROM AUTHOR]

Target classification is of great value when the number of transceivers in a sensing system is relatively small. This article proposes a high-accuracy and efficient classification method with machine learning techniques on frequency-modulated-continuous-wave (FMCW) radar. We first establish the novel mapping relationship from physical space to range-Doppler (PS-RD) image based on wave propagation theory, by which four physical features that effectively capture the kinematic and geometrical characteristics of targets, including speed, total reflectivity (ToRe), area, and incidence angle, are extracted from range-Doppler (R-D) image. Then, a multilayer perceptron (MLP) with a single hidden layer is employed to realize the classification. Since the above-mentioned four physical features, derived from wave physics, are chosen as the input of the neural network, our classifier does not work in a black-box way. The computational complexity of the whole classifier is the same as that of a 2-D fast Fourier transform (FFT), which guarantees a real-time operation. As an example, the proposed classifier is applied to the automotive radar system, where road targets are to be classified into five categories, including pedestrian, bike, sedan, truck/bus, and other static objects. Real-world data obtained from 77 GHz FMCW radars are provided for validation, where the proposed physics-assisted classifier turns out to outperform the state of the art in automotive radar application. The overall accuracy of the real data is about 99% even with complex multiple-target cases. [ABSTRACT FROM AUTHOR]

Jamming will seriously affect the detection ability of radar, so it is essential to suppress the jamming of radar echoes. Interrupted-sampling repeater jamming (ISRJ) based on a digital-radio-frequency-memory (DRFM) device can generate false targets at the victim radar by the interception and repeating of the radar transmission signal, which is highly correlated with the true target signal. ISRJ can achieve main lobe jamming and has both deception and oppressive jamming effects, so it is difficult for the existing methods to suppress this jamming effectively. In this paper, we propose a deep-learning-based anti-jamming network, named MSMD-net (Multi-stage Multi-domain joint anti-jamming depth network), for suppressing ISRJ main lobe jamming in the radar echo. In the first stage of MSMD-net, considering that the target signal is difficult to detect under a high jamming-to-signal ratio (JSR), we propose a preprocessing method of limiting filtering on the time-frequency domain to reduce the JSR using the auxiliary knowledge of radar. In the second stage, taking advantage of the discontinuity of the jamming in the time domain, we propose a UT-net network that combines the U-net structure and the transformer module. The UT-net performs target feature extraction and signal reconstruction in the signal time-frequency domain and preliminarily realizes the suppression of the jamming component. In the third stage, combined with phase information, a one-dimensional complex residual convolution U-net network (ResCU-net) is constructed in the time domain to realize jamming filtering and signal recovery further. The experimental results show that MSMD-net can obtain the best jamming suppression effect under different transmitted signals, different jamming modes, and different jamming parameters. [ABSTRACT FROM AUTHOR]

Target detection in sea clutter is of great significance in military radar research. Because the characteristics of sea clutter are complex and easily affected by wind direction, the method of suppressing sea clutter by using sea clutter characteristics to reproduce is not advantageous. To address this problem, this article focuses on the direct extraction of the target echo. According to the difference in fractional characteristics between the target echo and sea clutter, fractional Fourier transform (FRFT) is introduced to extract the target echo. In this article, a fractional domain change coefficient clustering method is established to identify the range units of the target, and a fractional domain filtering method based on the minimax is proposed to extract the target spectrum of target-dominated range units, so as to separate the target echo from sea clutter. Simulated and measured experiments prove that this method can accurately identify targets and extract target information under various sea states and a different number of targets. [ABSTRACT FROM AUTHOR]

Small target detection in high-resolution sea clutter is one of the important problems in radar target detection. We propose a new detector that adopts the visibility graph (VG) algorithm and the graph convolution neural network (GCN). This detector extracts the graph feature of radar echo networks for target detection after converting the phase information of radar echo into complex networks. Different from the existing detector based on graph connectivity, the VG algorithm does not need radar data preprocessing and it can directly convert the radar data into complex networks by judging whether the series data are visible mutually. We extracted the graph feature that can effectively distinguish the background clutter and target echo by GCN instead of calculating the statistic of graphs manually. Experiments on the IPIX radar datasets show that the proposed method achieves superior performance than the existing detector based on graph connectivity, especially in a short observation time. When the observation time is 0.256 s, the average accuracy of #17, #54, and #320 datasets can reach 84.82%, 94.84%, and 90.59%, respectively. [ABSTRACT FROM AUTHOR]

In this paper, a feature extraction technique based on the electromagnetic (EM) representation of radar signals is presented. In particular, we focus on ground-penetrating radar (GPR) imaging, where we model the backscatter from varying 2-D geometric shapes with arbitrary local coordinate rotations. Due to the electrically small nature of buried targets and the bending of the radar signal at the air–soil interface, we focus on exact methods to model the surface current density induced on scattering surfaces. Overcomplete basis sets are derived from the EM descriptions to represent the scene sparsely. From this proposed modeling framework, we devise a novel methodology to exploit the prediction of scattering behavior to extract features for classification from radar scenes when multiple buried scattering surfaces are present. We see that our method can identify and reconstruct buried scattering geometries in the presence of false targets that are brought about by the nonlinear nature of the exact EM modeling methods. A noniterative algorithm based on the conjugate of Green’s function is developed to solve for the surface current in an unknown domain using multifrequency, multiaperture data. Our modeling and feature extraction algorithms are numerically validated for different target shapes buried in lossy soil profiles. [ABSTRACT FROM AUTHOR]

For skywave over-the-horizon radar, beamforming techniques are often used to suppress airspace radio frequency interference because the high-frequency band is shared by many devices. To address the problems that the traditional beamforming method is not capable of recognizing the electromagnetic environment and that its performance is greatly affected by the accuracy of signal feature estimation, a cognitive beamforming method using range-Doppler (RD) map features for skywave radar is proposed. First, the RD map is weighted by a local attention model, and then, texture features are extracted as the inputs to a support vector machine. Finally, the support vector machine is used to predict the optimal diagonal loading factor. Simulation results show that the output signal-to-interference-plus-noise ratio is improved compared with previous methods. The proposed method is suitable for many kinds of common unsatisfactory scenarios, making it beneficial for engineering implementation. [ABSTRACT FROM AUTHOR]

Due to the increasing demand for spectrum resources, the co-existence of communications and radar systems has been proposed that allows radar and communications systems to operate in the same frequency band. On the other hand, deep learning has shown great potential in revolutionizing communications systems. In this work, we investigate the use of deep learning in communications systems subject to interference from radar systems. Specifically, we consider a single-carrier communications system. Linear frequency-modulated (LFM) and frequency-modulated continuous-wave (FMCW) are considered for radar. Several important system parameters, including the level of noise and interference, the radar interference coverage, the symbol duration, feature extraction methods and the number of hidden layers are investigated for the performance of the detector. Fully connected deep neural network (FCDNN) and long short-term memory (LSTM) detectors are implemented, where principle component analysis (PCA) is applied to preprocess the observed signals for the FCDNN detector. Numerical results show that the learning-based detector achieves comparable performance in the radar-communication system to the traditional detector but without interference cancellation. Preprocessing the received signals with PCA can improve the performance of FCDNN when interference is strong. Also, LSTM shows more robust performance than FCDNN when the channel has time-related distortion. [ABSTRACT FROM AUTHOR]

The micro-Doppler (m-D) modulations to radar backscattering introduced by the flexible body articulations and complicated movement patterns of human movers can provide valuable information for activity classification and help to identify the interested targets. In particular, the m-D signal of limbs, as a highly distinctive feature of human activities, can be used as an effective clue to discriminate between the armed and unarmed persons, as well as the humans against other small animals. In this article, a novel theoretical method is proposed to extract the target m-D trajectories through an integrated application of modified Viterbi algorithm and Hough transform. Through this method, multiple components corresponding to various target scattering parts and their respective m-D trajectories can be accurately extracted and estimated, even in the overlapping regions of different scattering parts in the time–frequency (TF) distribution. The employed search method enhances upon the traditional ones and improves the efficiency of finding the optimal paths considerably. Finally, a series of experiments is conducted to illustrate the validity and performance of the proposed techniques. Compared to short-time Fourier transform (STFT) peak detection and traditional Viterbi algorithm, the average error of m-D frequency estimated by the proposed algorithm is reduced by 82.1% and 71.8%, respectively. Besides, the processing time is reduced by 36.4% compared to the traditional Viterbi algorithm. [ABSTRACT FROM AUTHOR]

Registration for multisensor or multimodal image pairs with a large degree of distortions is a fundamental task for many remote sensing applications. To achieve accurate and low-cost remote sensing image registration, we propose a multiscale framework with unsupervised learning, named MU-Net. Without costly ground truth labels, MU-Net directly learns the end-to-end mapping from the image pairs to their transformation parameters. MU-Net stacks several deep neural network (DNN) models on multiple scales to generate a coarse-to-fine registration pipeline, which prevents the backpropagation from falling into a local extremum and resists significant image distortions. We design a novel loss function paradigm based on structural similarity, which makes MU-Net suitable for various types of multimodal images. MU-Net is compared with traditional feature-based and area-based methods, as well as supervised and other unsupervised learning methods on the optical-optical, optical-infrared, optical-synthetic aperture radar (SAR), and optical-map datasets. Experimental results show that MU-Net achieves more comprehensive and accurate registration performance between these image pairs with geometric and radiometric distortions. We share the code implemented by Pytorch at https://github.com/yeyuanxin110/MU-Net. [ABSTRACT FROM AUTHOR]

With the rapid increase of the number of autonomous driving vehicles, more and more radars working on a similar frequency band are equipped on vehicles, which incurs risks of automotive radar interference. Therefore, a precise interference recognition method is becoming a compelling task. In this article, a novel interference recognition network, called IRNet, is proposed to recognize eight types of interference signals that include mutual interference, unintended interference, and adverse intended interference. First, autocorrelation features of interference signals are obtained via calculating their autocorrelation functions (ACFs) and converted as two-dimensional feature images. Next, these images are employed as inputs of the IRNet that owns significant representation power and adaptive feature selection ability. Finally, the prediction types of interference will be output via the IRNet directly. The robustness of autocorrelation features is verified via simulations. The simulation results show that the proposed method can achieve 90.85% overall recognition accuracy when the jamming-to-noise ratio (JNR) is −14 dB and nearly 100% when JNR $> -8$ dB. Compared with six state-of-the-art methods, the IRNet achieves much better recognition performance, especially under lower JNR conditions with relatively lower and acceptable computational complexity. Results on measured signals also verify the powerful generalization ability of the proposed method. [ABSTRACT FROM AUTHOR]

Recently, radar-based human activity recognition (HAR) has attracted the attention of researchers as it has been proven that a deep learning (DL) model can be automatically determined by learning a radar dataset. However, unlike general optical image data, the process of collecting and labeling radar data for training the DL model requires considerable manpower and costs. Therefore, an approach that can learn the maximum number of features from a limited radar dataset is essential. Moreover, even if the DL models are trained using a dataset obtained from multiple geometries, performance can be degraded for geometries that are unknown to the trained model. Therefore, we propose a novel radar-based HAR combining a range–time–Doppler (RTD) map and a range-distributed-convolutional neural network (RD-CNN). Unlike the time–Doppler (TD) map, which is mainly used for radar-based HAR, the proposed RTD map provides several human activity-related features by extending the TD map to three dimensions according to the range. The proposed RD-CNN is a new DL model that performs HAR by using the RD layer to extract Doppler features, excluding the range information of RTD map. To verify the performance of the proposed model, experiments were conducted by using the University of Glasgow “radar signatures of human activities,” which is an open dataset for radar-based HAR research. The comparison results of the proposed model and CNNs with the same number of parameters demonstrated a higher recognition accuracy and a lower recognition error even for unknown geometries in the training dataset. [ABSTRACT FROM AUTHOR]

For the target with 3-D rotation, the 3-D synthetic aperture radar (SAR) imaging is very important for the feature extraction and classification. To solve this issue, a novel 3-D imaging algorithm through the airborne SAR system with a single antenna is proposed in this article, which has great advantages for the simplification of system structure compared with the traditional interferometric system. The proposed 3-D airborne SAR imaging algorithm can be implemented with three steps: 1) the azimuth signal is modeled as multicomponent linear frequency modulation (LFM) signal due to the relative movement between the target and radar. 2) The scatterer height position can be obtained by estimating the frequency modulation rate (FMR) for the LFM signal. 3) The 3-D airborne SAR image is obtained via the range-Doppler (RD) algorithm. Furthermore, the reconstruction performance under different rotation patterns, including roll, pitch, and yaw, is analyzed. The availability of the presented novel technique is demonstrated by the results of simulated and real experimental data. [ABSTRACT FROM AUTHOR]

Aiming at the technical difficulty of marine radar to detect small targets embedded in the sea clutter, this article proposed a three-feature fusion detection method based on singular spectrum analysis. First, considering that the number of coherent pulses used by radar in scanning mode is usually small (64 or less), this method combines the application of radar historical scan data and current frame data, transfers the feature extraction method from intraframe to interframe, and extracts three features that consist of cumulative major singular value (CMSV), linear degree of second singular vector (LDSSV), and linear degree of third singular vector (LDTSV) from singular space of the cell under test (CUT). Second, in view of the unideal distribution of sea clutter samples, a 3-D concave hull learning algorithm based on the geometry shape of sea clutter samples under the framework of anomaly detection is developed by improving the original convex hull algorithm, and target detection is realized in feature space using this algorithm. Under the same parameter condition, the measured CSIR data verify the two following points: first, the performance of detector using concave hull learning algorithm is better than that of convex hull learning algorithm; second, the detection performance of the proposed detector is obviously better than that of tri-time–frequency (TF)-feature detector, trifeature-based detector, consistency factor detector, and fractal-based detector. [ABSTRACT FROM AUTHOR]

In this study, a feature analysis and extraction method was proposed for specific emitter identification based on the signal generation mechanisms of radar transmitters. The generation of radar signals by radar transmitters was analyzed theoretically and experimentally. In the analysis, the main source of unintentional modulation in radar signals was identified, and the frequency stabilization of the solid-state frequency source, the nonlinear characteristics of the radio frequency amplifier chain, and the envelope of the pulse front edge were extracted as features for specific emitter identification. Subsequently, these characteristics were verified through simulation. The results revealed that the features extracted by this method exhibit "fingerprint characteristics" and can be used to identify specific radar emitters. [ABSTRACT FROM AUTHOR]

In this article, a new microwave-radar-based technique for short-range detection and classification of multiple human and vehicle targets crossing a monitored area is proposed. This approach, which can find applications in both security and infrastructure surveillance, relies upon the processing of the scattered-field data acquired by low-cost off-the-shelf components, i.e., a 24 GHz frequency-modulated continuous wave (FMCW) radar module and a Raspberry Pi mini-PC. The developed method is based on an ad hoc processing chain to accomplish the automatic target recognition (ATR) task, which consists of blocks performing clutter and leakage removal with an infinite impulse response (IIR) filter, clustering with a density-based spatial clustering of applications with noise (DBSCAN) approach, tracking using a Benedict-Bordner $\alpha $ - $\beta $ filter, features extraction, and finally classification of targets by means of a $k$ -nearest neighbor ($k$ -NN) algorithm. The approach is validated in real experimental scenarios, showing its capabilities in correctly detecting multiple targets belonging to different classes (i.e., pedestrians, cars, motorcycles, and trucks). [ABSTRACT FROM AUTHOR]