Radar Signal Research Articles

Centralized feature pyramid‐based supervised deep learning for object detection model from GPR data

AbstractTo address low detection accuracy and speed due to the multisolvability of the ground‐penetrating radar signal, we proposed a novel centralized feature pyramid‐YOLOv6l–based model to enhance detection precision and speed in road damage and pipeline detection. The centralized feature pyramid was used to obtain rich intra‐layer features and improve the network performance. Our proposed model achieves higher accuracy compared with the existing detection models. We also built two new evaluating indexes, relative average precision and relative mean average precision, to fully evaluate the detection accuracy. To verify the applicability of our model, we conducted a road field detection experiment on a ground‐penetrating radar dataset we collected and found that the proposed model had good performance in increasing detection precision, achieving the highest mean average precision compared with YOLOv7, YOLOv5 and YOLOx models, with relative mean average precision and frame rate per second at 16.38% and 30.5%, respectively. The detection information for the road damage and pipeline were used to conduct three‐dimensional imaging. Our model is suitable for object detection in ground‐penetrating radar images, thereby providing technical support for road damage and underground pipeline detection.

Radar-Based Elderly Fall Detection Using Smoothed Pseudo Wigner Ville Distribution and XGBoost Learning.

Falls among the elderly population pose significant health risks, often leading to morbidity and decreased quality of life. Traditional fall detection methods, namely wearable devices and cameras, have limitations such as lighting conditions and privacy concerns. Radar-based fall detection has emerged as a promising alternative, offering unobtrusive technique. In this study, an attempt has been made to classify fall detection using smoothed pseudo wigner-ville distribution (SPWVD) images and XGBoost learning. For this, online publicly available radar database (N=15) is considered. Radar signals is employed to SPWVD for time-frequency representation images. Ten features are extracted and applied to XGBoost learning. Experiments are performed and performance is evaluated using 10-fold cross validation. The proposed approach is able to discriminate elderly fall. Using XGBoost learning, the approach yields a maximum average classification accuracy, f1-score, precision, sensitivity, specificity, and kappa scores of 87.47%, 87.38%, 88.12%, 86.81%, 88.31% and 74.94% respectively. The combination of conventional features with concentration measures and median frequency obtained the second best performance. Thus, the proposed framework could be utilized for accurate and efficient detection of falls among the elderly population in their private spaces.

MP-Gait: Fine-grained Parkinson's Disease Gait Impairment Assessment with Robust Feature Analysis

Patients with Parkinson's disease (PD) often show gait impairments including shuffling gait, festination, and lack of arm and leg coordination. Quantitative gait analysis can provide valuable insights for PD diagnosis and monitoring. Prior work has utilized 3D motion capture, foot pressure sensors, IMUs, etc. to assess the severity of gait impairment in PD patients These sensors, despite their high precision, are often expensive and cumbersome to wear which makes them not the best option for long-term monitoring and naturalistic deployment settings. In this paper, we introduce mP-Gait, a millimeter-wave (mmWave) radar-based system designed to detect the gait features in PD patients and predict the severity of their gait impairment. Leveraging the high frequency and wide bandwidth of mmWave radar signals, mP-Gait is able to capture high-resolution reflected signals from different body parts during walking. We develop a pipeline to detect walking, extract gait features using signal analysis methods, and predict patients' UPDRS-III gait scores with a machine learning model. As gait features from PD patients with gait impairment are correctly and robustly extracted, mP-Gait is able to observe the fine-grained gait impairment severity fluctuation caused by medication response. To evaluate mP-Gait, we collected gait features from 144 participants (with UPDRS-III gait scores between 0 and 2) containing over 4000 gait cycles. Our results show that mP-Gait can achieve a mean absolute error of 0.379 points in predicting UPDRS-III gait scores.

Assessment of Soil Horizons and Their Matric Potential from Ground-Penetrating Radar Signal Attributes

Soil plays significant roles in different phases and in the continuous existence of human life. Its comprehensive knowledge, particularly as related to its physical characteristics, enhances its utilization, conservation, and management. The traditional methods of soil study are characterized with some pitfalls such as much time needed to perform such assessments. There are also issues of invasiveness that affect the soil structures and discrete sampling that may not reflect true spatial attributes in the outcome of such techniques. These problems are largely due to the concealing nature of soil layers that made its thorough evaluation difficult. In this study, an alternative geophysical approach has been adopted. The technique is the ground-penetrating method (GPR) that utilizes electromagnetic pulse energy via its equipment’s sensors, which can allow the investigation of soil properties, even in its concealing state. This study aimed at qualitatively evaluating the soil horizons and the matric potentials using the GPR signal attributes within the unsaturated zone with a view of having insight into the test field’s characterization. Field data measurements were obtained using MALA ProEX GPR equipment with its accessories manufactured by MALA Geosciences, Stockholm, Sweden. Evaluation of the processed field data results and computed attributes show soil characteristics variations with depth that was interpreted as the layers. This can be seen from the GPR data presentation as an image representing the subsurface of the zones of propagation of the pulse energy. Spectral analysis of the GPR signals allows for the delineation of two zones of contrasting features, which were tagged as high and low matric potentials. Although the conventional direct measurement of the matric potential was not made at the time of the study to complement and confirm the veracity of the approach, the results indicate the possibility of the approach towards a quick and in situ technique of soil investigations. Such evaluation may be valuable input in precision agriculture where accurate data are sought for implementation.

A fast method for intra-pulse parameters estimation of polyphase-coded radar signals based on FRFT

A fast method for intra-pulse parameters estimation of polyphase-coded radar signals based on FRFT

Doppler Radar Sensor-Based Fall Detection Using a Convolutional Bidirectional Long Short-Term Memory Model.

Falls among the elderly are a common and serious health risk that can lead to physical injuries and other complications. To promptly detect and respond to fall events, radar-based fall detection systems have gained widespread attention. In this paper, a deep learning model is proposed based on the frequency spectrum of radar signals, called the convolutional bidirectional long short-term memory (CB-LSTM) model. The introduction of the CB-LSTM model enables the fall detection system to capture both temporal sequential and spatial features simultaneously, thereby enhancing the accuracy and reliability of the detection. Extensive comparison experiments demonstrate that our model achieves an accuracy of 98.83% in detecting falls, surpassing other relevant methods currently available. In summary, this study provides effective technical support using the frequency spectrum and deep learning methods to monitor falls among the elderly through the design and experimental validation of a radar-based fall detection system, which has great potential for improving quality of life for the elderly and providing timely rescue measures.

Intra-Pulse Modulation Recognition of Radar Signals Based on Efficient Cross-Scale Aware Network.

Radar signal intra-pulse modulation recognition can be addressed with convolutional neural networks (CNNs) and time-frequency images (TFIs). However, current CNNs have high computational complexity and do not perform well in low-signal-to-noise ratio (SNR) scenarios. In this paper, we propose a lightweight CNN known as the cross-scale aware network (CSANet) to recognize intra-pulse modulation based on three types of TFIs. The cross-scale aware (CSA) module, designed as a residual and parallel architecture, comprises a depthwise dilated convolution group (DDConv Group), a cross-channel interaction (CCI) mechanism, and spatial information focus (SIF). DDConv Group produces multiple-scale features with a dynamic receptive field, CCI fuses the features and mitigates noise in multiple channels, and SIF is aware of the cross-scale details of TFI structures. Furthermore, we develop a novel time-frequency fusion (TFF) feature based on three types of TFIs by employing image preprocessing techniques, i.e., adaptive binarization, morphological processing, and feature fusion. Experiments demonstrate that CSANet achieves higher accuracy with our TFF compared to other TFIs. Meanwhile, CSANet outperforms cutting-edge networks across twelve radar signal datasets, providing an efficient solution for high-precision recognition in low-SNR scenarios.

Low Probability of Intercept Radar Signal Recognition Based on Semi-Supervised Support Vector Machine

Low Probability of Intercept Radar Signal Recognition Based on Semi-Supervised Support Vector Machine

Raindrop size distribution (DSD) retrieval from polarimetric radar observations using neural networks

As a key component of rainfall estimation, the understanding of raindrop size distribution (DSD) is a long-standing goal in meteorology and hydrology. Given that weather radar can observe the precipitation microphysics over large spatial and temporal scales, it has been broadly applied in DSD estimation. Traditional polynomial regression algorithms that correlate DSD parameters and radar signatures are still widely applied due to their simple structure and acceptable accuracy. This study proposes a new DSD retrieval model using dual-polarization radar observations based on long short-term memory (LSTM) network techniques. Three schemes able to retrieve the parameters of a normalized gamma DSD (LSTM-D0, LSTM-Nw, and LSTM-μ) are proposed with different combinations of polarimetric radar measurement inputs. All LSTM estimators exhibit better performance than the polynomial regression method. The Nash-Sutcliffe efficiency coefficient for estimates of drop median diameter (D0) and intercept parameter (Nw) increases from 0.93 and 0.70 to 0.95 and 0.93 respectively at Chilbolton station. Poor estimates of the shape parameter (μ) using the polynomial regression estimator complicate real applications, whereas the remarkable improvement of LSTM model estimation facilitates practical applications. The temporal and spatial predictability is then estimated to investigate long-term estimator performance for various radars, or at least for all radar pixels of a single radar. The predictability, measured by the Nash coefficient, increases temporally by 0.08, 0.31, and 0.39 and spatially by 0.03, 0.19, and 0.23 for the parameters D0, log10Nw, and μ respectively. This study contributes to improving quantitative precipitation estimates from radar polarimetry, enabling a better understanding of precipitation microphysics.

Frequency Modulation Recognition for Radar Signal based on Resnet-LSTM Network

In order to satisfy the modulation recognition requirements for radar signal with large scale changes in pulse-width and bandwidth, the Resnet-LSTM network is proposed in this paper. First, the waveform is preprocessed by self-correlation, and then the I/Q waveform and self-correlation result are as the network input. Secondly, the local characteristics were extracted by Resnet network; and lastly the LSTM network is adopted to extract the serialization representation. The proposed algorithm avoids the flaw of CNN network cannot adapt to variable length, and problem of memory forgetting of the LSTM network for long sequence is reduced. The simulation shows that the modulation recognition accuracy is more than 96.1% over the detection sensitivity for LFM, Parabolic-NLFM, Triangular-NLFM, Sine-NLFM, Sawtooth-NLFM and FSK signals.

Ultra-Wideband Digital Receive Method Based on Low-Speed Analog-to-Information Sampling

Owing that the bandwidth of radar signal is very small compared with the receiving bandwidth of electronic reconnaissance system, the received signal has sparse frequency spectrum in short time. The ultra-wideband digital receive method based on Analog-to-Information is proposed in this paper, which can obtain the capability of wideband digital receiving by low-speed sampling. Firstly, the analog signal is modulated by pseudo-random signal; next the signal is filtered by low-pass filter and sampled with low speed ADC; and then the original signal can be reconstructed by orthogonal matching pursuit algorithm. Finally, the simulation demonstrates that the original signal can be recon-structed even that the sampling speed goes down 8 times.

1D-CNN-Transformer for Radar Emitter Identification and Implemented on FPGA

Deep learning has brought great development to radar emitter identification technology. In addition, specific emitter identification (SEI), as a branch of radar emitter identification, has also benefited from it. However, the complexity of most deep learning algorithms makes it difficult to adapt to the requirements of the low power consumption and high-performance processing of SEI on embedded devices, so this article proposes solutions from the aspects of software and hardware. From the software side, we design a Transformer variant network, lightweight convolutional Transformer (LW-CT) that supports parameter sharing. Then, we cascade convolutional neural networks (CNNs) and the LW-CT to construct a one-dimensional-CNN-Transformer(1D-CNN-Transformer) lightweight neural network model that can capture the long-range dependencies of radar emitter signals and extract signal spatial domain features meanwhile. In terms of hardware, we design a low-power neural network accelerator based on an FPGA to complete the real-time recognition of radar emitter signals. The accelerator not only designs high-efficiency computing engines for the network, but also devises a reconfigurable buffer called “Ping-pong CBUF” and two-level pipeline architecture for the convolution layer for alleviating the bottleneck caused by the off-chip storage access bandwidth. Experimental results show that the algorithm can achieve a high recognition performance of SEI with a low calculation overhead. In addition, the hardware acceleration platform not only perfectly meets the requirements of the radar emitter recognition system for low power consumption and high-performance processing, but also outperforms the accelerators in other papers in terms of the energy efficiency ratio of Transformer layer processing.

Respiratory motion-corrected T1 mapping of the abdomen.

The purpose of this study was to investigate an approach for motion-corrected T1 mapping of the abdomen that allows for free breathing data acquisition with 100% scan efficiency. Data were acquired using a continuous golden radial trajectory and multiple inversion pulses. For the correction of respiratory motion, motion estimation based on a surrogate was performed from the same data used for T1 mapping. Image-based self-navigation allowed for binning and reconstruction of respiratory-resolved images, which were used for the estimation of respiratory motion fields. Finally, motion-corrected T1 maps were calculated from the data applying the estimated motion fields. The method was evaluated in five healthy volunteers. For the assessment of the image-based navigator, we compared it to a simultaneously acquired ultrawide band radar signal. Motion-corrected T1 maps were evaluated qualitatively and quantitatively for different scan times. For all volunteers, the motion-corrected T1 maps showed fewer motion artifacts in the liver as well as sharper kidney structures and blood vessels compared to uncorrected T1 maps. Moreover, the relative error to the reference breathhold T1 maps could be reduced from up to 25% for the uncorrected T1 maps to below 10% for the motion-corrected maps for the average value of a region of interest, while the scan time could be reduced to 6-8s. The proposed approach allows for respiratory motion-corrected T1 mapping in the abdomen and ensures accurate T1 maps without the need for any breathholds.

MRI retrospective respiratory gating and cardiac sensing by CW Doppler radar: A feasibility study.

This study investigates the feasibility of non-contact retrospective respiratory gating and cardiac sensing using continuous wave Doppler radar deployed in an MRI system. The proposed technique can complement existing sensors which are difficult to apply for certain patient populations. We leverage a software-defined radio for continuous wave radar at 2.4 GHz to detect in-vivo respiratory and cardiac timescrolled signals. In-bore radar signal demodulation is verified with full electromagnetic simulations, and its functionality is validated on a test bench and within the MR bore with four normal subjects. Radar sensing was compared against well-known references: electrocardiography on a test bench, system bellows, and pulsed plethysmography sensors with in the MRI bore. The feasibility of noncontact cardiac rate sensing, dynamic breathing sequence synchronization, and in-bore motion correction for retrospective respiratory gating applications was demonstrated. Optimal radar front-end system arrangement, along with spectral isolation and narrow bandwidth of operation, enable MRI-compatible and interference-free motion sensing. The signal-to-noise-ratio degradation by the radar integration was within 4.5% on phantom images. We confirmed that in-bore retrospective motion correction using CW Doppler radar is feasible without MRI system constraints. Non-contact motion correction sensing in MRI may provide better patient handling and through put by complementing existing system sensors and motion correction algorithms.

TC–Radar: Transformer–CNN Hybrid Network for Millimeter-Wave Radar Object Detection

In smart transportation, assisted driving relies on data integration from various sensors, notably LiDAR and cameras. However, their optical performance can degrade under adverse weather conditions, potentially compromising vehicle safety. Millimeter-wave radar, which can overcome these issues more economically, has been re-evaluated. Despite this, developing an accurate detection model is challenging due to significant noise interference and limited semantic information. To address these practical challenges, this paper presents the TC–Radar model, a novel approach that synergistically integrates the strengths of transformer and the convolutional neural network (CNN) to optimize the sensing potential of millimeter-wave radar in smart transportation systems. The rationale for this integration lies in the complementary nature of CNNs, which are adept at capturing local spatial features, and transformers, which excel at modeling long-range dependencies and global context within data. This hybrid approach allows for a more robust and accurate representation of radar signals, leading to enhanced detection performance. A key innovation of our approach is the introduction of the Cross-Attention (CA) module, which facilitates efficient and dynamic information exchange between the encoder and decoder stages of the network. This CA mechanism ensures that critical features are accurately captured and transferred, thereby significantly improving the overall network performance. In addition, the model contains the dense information fusion block (DIFB) to further enrich the feature representation by integrating different high-frequency local features. This integration process ensures thorough incorporation of key data points. Extensive tests conducted on the CRUW and CARRADA datasets validate the strengths of this method, with the model achieving an average precision (AP) of 83.99% and a mean intersection over union (mIoU) of 45.2%, demonstrating robust radar sensing capabilities.

Design and Implementation of a Photonic-Based Electronic Warfare System

Nowadays, the Radio frequency (RF) Photonics become an inevitable candidate to address several military related potential applications including electronic warfare (EW), photonic signal processing (PSP), photonic-based RF transportation, and photonic communications. As part of this emerging technology development/requirement, we designed a photonic-based EW systems (PEWS) in the optisystem environment (later implemented using optoelectronic components) to extract various radar waveforms such as continuous wave (CW), pulsed wave, and frequency/phase modulated wave. All these radar waveforms are transmitted and captured by the proposed/implemented PEW system, and then processed to construct the radar signatures from its electromagnetic (EM) spectrum/signals. The key parameters of various waveforms generated and processed in our research work are varied, over the time, during the performance validation tests. The values of key parameters of the waveforms: RF CW signal frequencies, pulse repetition times (PRTs), pulse-widths, Barker code phase modulations, Frank code poly-phase modulations, sweep frequencies, and RF power levels; are 100 Hz through 8 GHz, 10 ms through 2 µs, 750 ns through 2 ns, 0o /80o, 0o /90o /180o /270o, and -84 dBm through 30 dBm, respectively. The details of PEWS design approaches, their implementation methodologies, and different performance validation experimental results are reported, and analyzed. The limitations, and possible immediate research contributions/requirements are also listed.

An efficient gradient descent approach to separate a mixture of secondary surveillance radar replies based on disjoint component analysis

AbstractThe expansion of air traffic has led to an increase in mixed secondary surveillance radar (SSR) signal replies, which occur when multiple replies arrive at the receiver antenna simultaneously. These overlapping signals render the messages unrecoverable, leading to a loss of information. Additionally, the existing methods do not effectively address the issue of handling different types of signals with varying structures and characteristics. The authors validate the effectiveness of the disjoint component analysis (DCA) criterion for SSR signals and introduce a new DCA‐based algorithm designed to optimise the separation process. Through several simulations, the proposed algorithm demonstrates robust performance across various reception parameters. Additionally, it achieves good results when applied to real‐world data, showing its practical applicability and efficiency.

Short-Term Precipitation Radar Echo Extrapolation Method Based on the MS-DD3D-RSTN Network and STLoss Function.

Short-term precipitation forecasting is essential for agriculture, transportation, urban management, and tourism. The radar echo extrapolation method is widely used in precipitation forecasting. To address issues like forecast degradation, insufficient capture of spatiotemporal dependencies, and low accuracy in radar echo extrapolation, we propose a new model: MS-DD3D-RSTN. This model employs spatiotemporal convolutional blocks (STCBs) as spatiotemporal feature extractors and uses the spatial-temporal loss (STLoss) function to learn intra-frame and inter-frame changes for end-to-end training, thereby capturing the spatiotemporal dependencies in radar echo signals. Experiments on the Sichuan dataset and the HKO-7 dataset show that the proposed model outperforms advanced models in terms of CSI and POD evaluation metrics. For 2 h forecasts with 20 dBZ and 30 dBZ reflectivity thresholds, the CSI metrics reached 0.538, 0.386, 0.485, and 0.198, respectively, representing the best levels among existing methods. The experiments demonstrate that the MS-DD3D-RSTN model enhances the ability to capture spatiotemporal dependencies, mitigates forecast degradation, and further improves radar echo prediction performance.

Non-Contact Blood Pressure Estimation From Radar Signals by a Stacked Deformable Convolution Network.

This study introduces a contactless blood pressure monitoring approach that combines conventional radar signal processing with novel deep learning architectures. During the preprocessing phase, datasets suitable for synchronization are created by integrating Kalman filtering, multiscale bandpass filters, and a periodic extraction method in the time domain. These data comprise data on chest micro variations, encapsulating a complex array of physiological and biomedical information reflective of cardiac micromotions. The Radar-based Stacked Deformable convolution Network (RSD-Net) integrates channel and spatial self attention mechanisms within a deformable convolutional framework to enhance feature extraction from radar signals. The network architecture systematically employs deformable convolutions for initial deep feature extraction from individual signals. Subsequently, continuous blood pressure estimation is conducted using self attention mechanisms on feature map from single source coupled with multi-feature map channel attention. The performance of model is corroborated via the open-source dataset procured using a non-invasive 24 GHz six-port continuous wave radar system. The dataset, encompassing readings from 30 healthy individuals subjected to diverse conditions including rest, the Valsalva maneuver, apnea, and tilt-table examinations. It serves to substantiate the validity and resilience of the proposed method in the non-contact assessment of continuous blood pressure. Evaluation metrics reveal Pearson correlation coefficients of 0.838 for systolic and 0.797 for diastolic blood pressure predictions. The Mean Error (ME) and Standard Deviation (SD) for systolic and diastolic blood pressure measurements are -0.32 ±6.14 mmHg and -0.20 ±5.50 mmHg, respectively. The ablation study assesses the contribution of different structural components of the RSD-Net, validating their significance in the overall of model performance.

Radar Signatures Associated with Quasi-Linear Convective System Mesovortices

Abstract Recent operationally driven research has generated a framework, known as the three ingredients method and mesovortex warning system, that can help forecasters anticipate mesovortex development and issue warnings within quasi-linear convective systems (QLCSs). However, dual-polarization radar data has not yet been incorporated into this framework. Therefore, several dual- and single-polarization radar signatures associated with QLCS mesovortices were analyzed to determine if they could provide additional information about mesovortex development and intensity. An analysis of 167 mesovortices showed that 1) KDP drops precede ∼95% of mesovortices and provide an initial indication of where a mesovortex may develop; 2) midlevel KDP cores are a potentially useful precursor signature because they precede a majority of mesovortices and have higher magnitudes for mesovortices that produce wind damage or tornadoes; 3) low-level KDP cores and areas of enhanced spectrum width have higher magnitudes for mesovortices that produce wind damage or tornadoes but tend to develop at about the same time as the mesovortex, which makes them more useful as diagnostic than as predictive signatures; and 4) as range from the radar increases, the radar signatures become less useful in anticipating mesovortex intensity but can still be used to anticipate mesovortex development or build confidence in mesovortex existence. Significance Statement The purpose of this study is to look at weather radar features that might help forecasters predict the development and intensity of tornadoes and strong winds within linear thunderstorm systems. Our results show that the intensity and trends of some radar features are helpful in showing when these hazards might develop and how strong they might be, while other radar features are less helpful. This information can help forecasters focus on the most useful radar features and ultimately provide the best possible warnings.