Search

Device-free indoor identification of people with high accuracy is the key to providing personalized services. Visual methods are the solution but they require a clear view and good lighting conditions. Additionally, the intrusive nature leads to privacy concerns. A robust identification and classification system using the mmWave radar and an improved density-based clustering algorithm along with LSTM are proposed in this paper. The system leverages mmWave radar technology to overcome challenges posed by varying environmental conditions on object detection and recognition. The point cloud data are processed using a refined density-based clustering algorithm to extract ground truth in a 3D space accurately. A bi-directional LSTM network is employed for individual user identification and intruder detection. The system achieved an overall identification accuracy of 93.9% and an intruder detection rate of 82.87% for groups of 10 individuals, demonstrating its effectiveness.

In the context of all-digital radar systems, phase-modulated continuous wave (PMCW) based on pseudorandom binary sequences (PRBSs) appears to be a prominent candidate modulation scheme for applications such as autonomous driving. Among the reasons for its candidacy are its simplified transmitter architecture and lower linearity requirements (e.g., compared to orthogonal-frequency division multiplexing radars), as well as its high velocity unambiguity and multiple-input multiple-output operation capability, all of which are characteristic of digital radars. For appropriate operation of a PMCW radar, choosing a PRBS whose periodic autocorrelation function (PACF) has low sidelobes and high robustness to Doppler shifts is paramount. In this sense, this article performs an analysis of Doppler shift tolerance of the PACFs of typically adopted PRBSs in PMCW radar systems supported by simulation and measurement results. To accurately measure the Doppler-shift-induced degradation of PACFs, peak power loss ratio (PPLR), peak sidelobe level ratio (PSLR), and integrated-sidelobe level ratio (ISLR) were used as metrics. Furthermore, to account for effects on targets whose ranges are not multiples of the range resolution, oversampled PACFs are analyzed.

Ground-based synthetic aperture radars (GBSAR) are popular instruments widely used for the monitoring of infrastructures. One of the main problems of ground-based interferometric radars is the elevation ambiguity. Multiple-input multiple-output (MIMO) arrays could solve this problem. This work proposes a study on possible MIMO configurations to achieve elevation resolution in ground-based radar measurements. Specifically, two array configurations are compared: a random sparse array suitable for the compressive sensing technique, and a non-uniform array. The two solutions are compared by means of simulations and experimental tests. An ad hoc system has been developed to jointly test the two configurations, and results obtained in a controlled and real urban scenario are shown. It is found that both systems are able to solve elevation ambiguity. The non-uniform array seems to achieve good performance in a general scenario, while the CS processing can outperform the other only after optimization, depending on the specific scenario and application.

The identification of weak vital signs has always been one of the difficulties in the field of life detection. In this paper, a novel vital sign detection and extraction method with high efficiency, high precision, high sensitivity and high signal-to-noise ratio is proposed. Based on the NVA6100 pulse radar system, the radar matrix which contains several radar pulse detection signals is received. According to the characteristics of vital signs and radar matrices, the Singular Value Decomposition (SVD) is adopted to perform signal denoising and decomposition after preprocessing, and the temporal and spatial eigenvectors of each principal component are obtained. Through the energy proportion screening, the Wavelet Transform decomposition and linear trend suppression, relatively pure vital signs in each principal component, are obtained. The human location is detected by the Energy Entropy of spatial eigenvectors, and the respiratory signal and heartbeat signal are restored through a Butterworth Filter and an MTI harmonic canceller. Finally, through an analysis of the performance of the algorithm, it is proved to have the properties of efficiency and accuracy.

Continuous-wave Doppler radar (CWDR) can be used to remotely detect physiological parameters, such as respiration and heart signals. However, detecting and separating multiple targets remains a challenging task for CWDR. While complex transceiver architectures and advanced signal processing algorithms have been demonstrated as effective for multiple target separations in some scenarios, the separation of equidistant sources within a single antenna beam remains a challenge. This paper presents an alternative phase tuning approach that exploits the diversity among target distances and physiological parameters for multi-target detection. The design utilizes a voltage-controlled analog phase shifter to manipulate the phase correlation of the CWDR and thus create different signal mixtures from the multiple targets, then separates them in the frequency domain by suppressing individual signals sequentially. We implemented the phase correlation system based on a 2.4 GHz single-channel CWDR and evaluated it against multiple mechanical and human targets. The experimental results demonstrated successful separation of nearly equidistant targets within an antenna beam, equivalent to separating physiological signals of two people seated shoulder to shoulder.

Floods are a major cause of loss of lives, destruction of infrastructure, and massive damage to a country’s economy. Floods, being natural disasters, cannot be prevented completely; therefore, precautionary measures must be taken by the government, concerned organizations such as the United Nations Office for Disaster Risk Reduction and Office for the coordination of Human Affairs, and the community to control its disastrous effects. To minimize hazards and to provide an emergency response at the time of natural calamity, various measures must be taken by the disaster management authorities before the flood incident. This involves the use of the latest cutting-edge technologies which predict the occurrence of disaster as early as possible such that proper response strategies can be adopted before the disaster. Floods are uncertain depending on several climatic and environmental factors, and therefore are difficult to predict. Hence, improvement in the adoption of the latest technology to move towards automated disaster prediction and forecasting is a must. This study reviews the adoption of remote sensing methods for predicting floods and thus focuses on the pre-disaster phase of the disaster management process for the past 20 years. A classification framework is presented which classifies the remote sensing technologies being used for flood prediction into three types, which are: multispectral, radar, and light detection and ranging (LIDAR). Further categorization is performed based on the method used for data analysis. The technologies are examined based on their relevance to flood prediction, flood risk assessment, and hazard analysis. Some gaps and limitations present in each of the reviewed technologies have been identified. A flood prediction and extent mapping model are then proposed to overcome the current gaps. The compiled results demonstrate the state of each technology’s practice and usage in flood prediction.

Oceanic eddy is a common natural phenomenon that has large influence on human activities, and the measurement and detection of offshore eddies are significant for oceanographic research. The previous classical detecting methods, such as the Okubo&ndash, Weiss algorithm (OW), vector geometry algorithm (VG), and winding angles algorithm (WA), not only depend on expert&rsquo, s experiences to set an accurate threshold, but also need heavy calculations for large detection regions. Differently from the previous works, this paper proposes a deep eddy detection neural network with pixel segmentation skeleton on high frequency radar (HFR) data, namely, the deep eddy detection network (DEDNet). An offshore eddy detection dataset is firstly constructed, which has origins from the sea surface current data measured by two HFR systems on the South China Sea. Then, a spatial globally optimum and strong detail-distinguishing pixel segmentation network is presented to automatically detect and localize offshore eddies in a flow chart. An eddy detection network based on fully convolutional networks (FCN) is also presented for comparison with DEDNet. Experimental results show that DEDNet performs better than the FCN-based eddy detection network and is competitive with the classical statistics-based methods.

The measurement and analysis of the arterial pulse wave provides information about the state of vascular health. When measuring blood pressure according to Riva-Rocci, the systolic and diastolic blood pressure is measured non-invasively with an inflatable pressure cuff on the upper arm. Today&rsquo, s blood pressure monitors analyze the pulse wave in reference to the rising or falling cuff pressure. With the help of additional pulse wave analysis, one can determine the pulse rate and the heart rate variability. In this paper, we investigated the concept, the construction, and the limitations of ultrawideband (UWB) radar and continuous wave (CW) radar, which provide continuous and non-invasive pulse wave measurements. We integrated the sensors into a complete measurement system. We measured the pulse wave of the cuff pressure, the radar sensor (both UWB and CW), the optical sensor, and ultrasonic Doppler as a reference. We discussed the results and the sensor characteristics. The main conclusion was that the resolution of the pulse radar was too low, even with a maximum bandwidth of 10 GHz, to measure pulse waves reliably. The continuous wave radar provides promising results for a phantom if adjusted properly with phase shifts and frequency. In the future, we intend to develop a CW radar solution with frequency adaption.

International audience; The automated quantification of the behaviour of freely moving animals is increasingly needed in applied ethology. State-of-the-art approaches often require tags to identify animals, high computational power for data collection and processing, and are sensitive to environmental conditions, which limits their large-scale utilization, for instance in genetic selection programs of animal breeding. Here we introduce a new automated tracking system based on millimetre-wave radars for real time robust and high precision monitoring of untagged animals. In contrast to conventional video tracking systems, radar tracking requires low processing power, is independent on light variations and has more accurate estimations of animal positions due to a lower misdetection rate. To validate our approach, we monitored the movements of 58 sheep in a standard indoor behavioural test used for assessing social motivation. We derived new estimators from the radar data that can be used to improve the behavioural phenotyping of the sheep. We then showed how radars can be used for movement tracking at larger spatial scales, in the field, by adjusting operating frequency and radiated electromagnetic power. Millimetre-wave radars thus hold considerable promises precision farming through high-throughput recording of the behaviour of untagged animals in different types of environments.

Breast microwave sensing (BMS) has been studied as a potential technique for cancer detection due to the observed microwave properties of malignant and healthy breast tissues. This work presents a novel radar-based image reconstruction algorithm for use in BMS that reframes the radar image reconstruction process as an optimization problem. A gradient descent optimizer was used to create an optimization-based radar reconstruction (ORR) algorithm. Two hundred scans of MRI-derived breast phantoms were performed with a preclinical BMS system. These scans were reconstructed using the ORR, delay-and-sum (DAS), and delay-multiply-and-sum (DMAS) beamformers. The ORR was observed to improve both sensitivity and specificity compared to DAS and DMAS. The estimated sensitivity and specificity of the DAS beamformer were 19% and 44%, respectively, while for ORR, they were 27% and 56%, representing a relative increase of 42% and 27%. The DAS reconstructions also exhibited a hot-spot image artifact, where a localized region of high intensity that did not correspond to any physical phantom feature would be present in an image. This artifact appeared like a tumour response within the image and contributed to the lower specificity of the DAS beamformer. This artifact was not observed in the ORR reconstructions. This work demonstrates the potential of an optimization-based conceptualization of the radar image reconstruction problem in BMS. The ORR algorithm implemented in this work showed improved diagnostic performance and fewer image artifacts compared to the widely employed DAS algorithm.

Microwave breast imaging has seen increasing use in clinical investigations in the past decade with over eight systems having being trialled with patients. The majority of systems use radar-based algorithms to reconstruct the image shown to the clinician which requires an estimate of the dielectric properties of the breast to synthetically focus signals to reconstruct the image. Both simulated and experimental studies have shown that, even in simplified scenarios, misestimation of the dielectric properties can impair both the image quality and tumour detection. Many methods have been proposed to address the issue of the estimation of dielectric properties, but few have been tested with patient images. In this work, a leading approach for dielectric properties estimation based on the computation of many candidate images for microwave breast imaging is analysed with patient images for the first time. Using five clinical case studies of both healthy breasts and breasts with abnormalities, the advantages and disadvantages of computational patient-specific microwave breast image reconstruction are highlighted.

With the wide application of convolutional neural networks (CNNs), a variety of ship detection methods based on CNNs in synthetic aperture radar (SAR) images were proposed, but there are still two main challenges: (1) Ship detection requires high real-time performance, and a certain detection speed should be ensured while improving accuracy; (2) The diversity of ships in SAR images requires more powerful multi-scale detectors. To address these issues, a SAR ship detector called Duplicate Bilateral YOLO (DB-YOLO) is proposed in this paper, which is composed of a Feature Extraction Network (FEN), Duplicate Bilateral Feature Pyramid Network (DB-FPN) and Detection Network (DN). Firstly, a single-stage network is used to meet the need of real-time detection, and the cross stage partial (CSP) block is used to reduce the redundant parameters. Secondly, DB-FPN is designed to enhance the fusion of semantic and spatial information. In view of the ships in SAR image are mainly distributed with small-scale targets, the distribution of parameters and computation values between FEN and DB-FPN in different feature layers is redistributed to solve the multi-scale detection. Finally, the bounding boxes and confidence scores are given through the detection head of YOLO. In order to evaluate the effectiveness and robustness of DB-YOLO, comparative experiments with the other six state-of-the-art methods (Faster R-CNN, Cascade R-CNN, Libra R-CNN, FCOS, CenterNet and YOLOv5s) on two SAR ship datasets, i.e., SSDD and HRSID, are performed. The experimental results show that the AP50 of DB-YOLO reaches 97.8% on SSDD and 94.4% on HRSID, respectively. DB-YOLO meets the requirement of real-time detection (48.1 FPS) and is superior to other methods in the experiments.

Network slicing is a powerful paradigm for network operators to support use cases with widely diverse requirements atop a common infrastructure. As 5G standards are completed, and commercial solutions mature, operators need to start thinking about how to integrate network slicing capabilities in their assets, so that customer-facing solutions can be made available in their portfolio. This integration is, however, not an easy task, due to the heterogeneity of assets that typically exist in carrier networks. In this regard, 5G commercial networks may consist of a number of domains, each with a different technological pace, and built out of products from multiple vendors, including legacy network devices and functions. These multi-technology, multi-vendor and brownfield features constitute a challenge for the operator, which is required to deploy and operate slices across all these domains in order to satisfy the end-to-end nature of the services hosted by these slices. In this context, the only realistic option for operators is to introduce slicing capabilities progressively, following a phased approach in their roll-out. The purpose of this paper is to precisely help designing this kind of plan, by means of a technology radar. The radar identifies a set of solutions enabling network slicing on the individual domains, and classifies these solutions into four rings, each corresponding to a different timeline: (i) as-is ring, covering today’s slicing solutions; (ii) deploy ring, corresponding to solutions available in the short term; (iii) test ring, considering medium-term solutions; and (iv) explore ring, with solutions expected in the long run. This classification is done based on the technical availability of the solutions, together with the foreseen market demands. The value of this radar lies in its ability to provide a complete view of the slicing landscape with one single snapshot, by linking solutions to information that operators may use for decision making in their individual go-to-market strategies., H2020 European Projects 5G-VINNI (grant agreement No. 815279) and 5G-CLARITY (grant agreement No. 871428), Spanish national project TRUE-5G (PID2019-108713RB-C53)

This paper proposes the implementation of and experimentation with GPR for real-time automatic detection of buried IEDs. GPR, consisting of hardware and software, was implemented. A UWB antenna was designed and implemented, particularly for the operation of the GPR. The experiments were conducted in order to demonstrate the real-time automatic detection of buried IEDs using GPR with an R-CNN algorithm. In the experiments, the GPR was mounted on a pickup truck and a maintenance train in order to find the IEDs buried under a road and a railway, respectively. B-scan images were collected using the implemented GPR. R-CNN-based detection for the hyperbolic pattern, which indicates the buried IED, was performed along with pre-processing, for example, using zero offset removal, and background removal and filtering. Experimental results in terms of detecting the hyperbolic pattern in B-scan images were shown and verified that the proposed GPR system is superior to the conventional one using region analysis processing-based detection. Results also showed that pre-processing is required in order to improve and/or clean the hyperbolic pattern before detection. The GPR can automatically detect IEDs buried under roads and railways in real time by detecting the hyperbolic pattern appearing in the collected B-scan image.

Airborne radars are susceptible to a large number of clutter, noise and variable jamming signals in the real environment, especially when faced with active main lobe jamming, as the waveform shortcut technology in the traditional regime can no longer meet the actual battlefield radar anti-jamming requirements. Therefore, it is necessary to study anti-main-lobe jamming techniques for airborne radars in complex environments to improve their battlefield survivability. In this paper, we propose an airborne radar waveform design method based on a deep reinforcement learning (DRL) algorithm under clutter and jamming conditions, after previous research on reinforcement-learning (RL)-based airborne radar anti-jamming waveform design methods that have improved the anti-jamming performance of airborne radars. The method uses a Markov decision process (MDP) to describe the complex operating environment of airborne radars, calculates the value of the radar anti-jamming waveform strategy under various jamming states using deep neural networks and designs the optimal anti-jamming waveform strategy for airborne radars based on the duelling double deep Q network (D3QN) algorithm. In addition, the method uses an iterative transformation method (ITM) to generate the time domain signals of the optimal waveform strategy. Simulation results show that the airborne radar waveform designed based on the deep reinforcement learning algorithm proposed in this paper improves the signal-to-jamming plus noise ratio (SJNR) by 2.08 dB and 3.03 dB, and target detection probability by 26.79% and 44.25%, respectively, compared with the waveform designed based on the reinforcement learning algorithm and the conventional linear frequency modulation (LFM) signal at a radar transmit power of 5 W. The airborne radar waveform design method proposed in this paper helps airborne radars to enhance anti-jamming performance in complex environments while further improving target detection performance.

We propose in this work a dynamic group sparsity (DGS) based time-frequency feature extraction method for dynamic hand gesture recognition (HGR) using millimeter-wave radar sensors. Micro-Doppler signatures of hand gestures show both sparse and structured characteristics in time-frequency domain, but previous study only focus on sparsity. We firstly introduce the structured prior when modeling the micro-Doppler signatures in this work to further enhance the features of hand gestures. The time-frequency distributions of dynamic hand gestures are first modeled using a dynamic group sparse model. A DGS-Subspace Pursuit (DGS-SP) algorithm is then utilized to extract the corresponding features. Finally, the support vector machine (SVM) classifier is employed to realize the dynamic HGR based on the extracted group sparse micro-Doppler features. The experiment shows that the proposed method achieved 3.3% recognition accuracy improvement over the sparsity-based method and has a better recognition accuracy than CNN based method in small dataset.

A 24 GHz millimeter-wave direct-conversion radio-frequency (RF) receiver with wide-range and precise I/Q mismatch calibration is designed in 65 nm CMOS technology for radar sensor applications. The CMOS RF receiver is based on a quadrature direct-conversion architecture. Analytic relations are derived to clearly exhibit the individual contributions of the I/Q amplitude and phase mismatches to the image-rejection ratio (IRR) degradation, which provides a useful design guide for determining the range and resolution of the I/Q mismatch calibration circuit. The designed CMOS RF receiver comprises a low-noise amplifier, quadrature down-conversion mixer, baseband amplifier, and quadrature LO generator. Controlling the individual gate bias voltages of the switching FETs in the down-conversion mixer having a resistive load is found to induce significant changes at the amplitude and phase of the output signal. In the calibration process, the mixer gate bias tuning is first performed for the amplitude mismatch calibration, and the remaining phase mismatch is then calibrated out by the varactor capacitance tuning at the LO buffer’s LC load. Implemented in 65 nm CMOS process, the RF receiver achieves 31.5 dB power gain, −35.2 dBm input-referred 1 dB compression power, and 4.8–7.1 dB noise figure across 22.5–26.1 GHz band, while dissipating 106.2 mA from a 1.2 V supply. The effectiveness of the proposed I/Q mismatch calibration is successfully verified by observing that the amplitude and phase mismatches are improved from 1.0–1.5 dB to 0.02–0.19 dB, and from 10.8–23.8 to 1.1–3.2 degrees, respectively.

In this study, we investigate a millimeter wave (mmWave) synthetic aperture radar (SAR) imaging scheme utilizing a low-cost frequency modulated continuous wave (FMCW) radar to take part in non-destructive testing which could be a useful tool for both civilian and military demands. The FMCW radar working in the frequency range from 76 GHz to 81 GHz is equipped with a 2-D moving platform aiming to reconstruct the 2-D image of the shape of the target object. Due to the lab environment containing several devices and furniture, various noise and interference signals from the floor are not avoidable. Therefore, the digital signal processing algorithms are joined to remove the undesired signals as well as improve the target recognition. This study adopts the range migration algorithms (RMAs) on the processed reflected signal data to form the image of the target because of its verified ability in this type of mission. On the other hand, the integration of compressed sensing (CS) algorithms into the SAR imaging system is also researched which helps to improve the performance of the system by reducing the measurement duration while still maintaining the image quality. Three minimization algorithms are used involving the imaging system as the CS solvers reconstruct the radar data before being processed by RMA to form the image. The proposed imaging scheme demonstrates its good ability with high azimuth resolution in the mission of detecting tiny cracks in the rebar of reinforced concrete. In addition, the participation of CS algorithms improves the performance of the scheme as the cracks on the rebar can be located on the images, which are reconstructed from only 30% of the dataset. The comparison of CS solvers shows that ADMM outperforms the other candidates in the reconstruction task.

In this paper, the extraction of the life activity spectrum based on the millimeter (mm) wave radar is designed to realize the detection of target objects and the threshold trigger module. The maximum likelihood estimation method is selected to complete the design of the average early warning probability trigger function. The threshold trigger module is designed for the echo signal of static objects in the echo signal. It will interfere with the extraction of Doppler frequency shift results. The moving target detection method is selected, and the filter is designed. The static clutter interference is filtered without affecting the phase difference between the detection sequences, and the highlight target signal is improved. The frequency and displacement of thoracic movement are used as the detection data. Through the Fourier transform calculation of the sequence, the spectrum value is extracted within the estimated range of the heartbeat and respiration spectrum, and the heartbeat and respiration signals are picked up. The proposed design uses Modelsim and Quartus for CO-simulation to complete the simulation verification of the function, extract the number of logical units occupied by computing resources, and verify the algorithm with the vital signs experiment. The heartbeat and respiration were detected using the sports bracelet; the relative errors of heartbeat detection were 0–6.3%, the respiration detection was 0–9.5%, and the relative errors of heartbeat detection were overwhelmingly less than 5%.

A multi-channel backscatter communication and radar sensing system is proposed and demonstrated in this paper. Frequency modulated continuous wave (FMCW) radar ranging is integrated with simultaneous uplink data transmission from a self-packaged active radio frequency (RF) tag. A novel package solution is proposed for the RF tag. With the proposed package, the RF tag can transmit a 32-QAM signal up to 2.5 Gbps and QPSK signal up to 8 Gbps. For a multi-tag scenario, we proposed using spread spectrum code to separate the data from each tag. In this case, tags can be placed at arbitrary locations without adjacent channel interference. Proof-of-concept simulations and measurements are demonstrated. A 625 Mbps data rate is achieved in a dual-tag scenario for two tags.

As a new method to detect vital signs, Ultra-wideband (UWB) radar could continuously monitor human respiratory signs without contact. Aimed at addressing the problem of large interference and weak acquisition signal in radar echo signals from complex scenes, this paper adopts a UWB radar echo signal processing method that combines strong physical sign information extraction at P time and Variational Mode Decomposition (VMD) to carry out theoretical derivation. Using this novel processing scheme, respiration and heartbeat signals can be quickly reconstructed according to the selection of the appropriate intrinsic mode functions (IMFs), and the real-time detection accuracy of human respiratory signs is greatly improved. Based on an experimental platform, the data collected by the UWB radar module were first verified against the measured values obtained at the actual scene. The results of a validation test proved that our UWB radar echo signal processing method effectively eliminated the respiratory clutter signal and realized the accurate measurement of respiratory and heartbeat signals, which would prove the existence of life and further improve the quality of respiration and heartbeat signal and the robustness of detection.

Machine Learning (ML) methods have become state of the art in radar signal processing, particularly for classification tasks (e.g., of different human activities). Radar classification can be tedious to implement, though, due to the limited size and diversity of the source dataset, i.e., the data measured once for initial training of the Machine Learning algorithms. In this work, we introduce the algorithm Radar Activity Classification with Perceptual Image Transformation (RACPIT), which increases the accuracy of human activity classification while lowering the dependency on limited source data. In doing so, we focus on the augmentation of the dataset by synthetic data. We use a human radar reflection model based on the captured motion of the test subjects performing activities in the source dataset, which we recorded with a video camera. As the synthetic data generated by this model still deviates too much from the original radar data, we implement an image transformation network to bring real data close to their synthetic counterpart. We leverage these artificially generated data to train a Convolutional Neural Network for activity classification. We found that by using our approach, the classification accuracy could be increased by up to 20%, without the need of collecting more real data.

A Ka-band dual-polarization magnetoelectric (ME) dipole antenna array based on three-dimensional (3D)-printed technology with low sidelobe level (SLL) is proposed in this paper. The metal posts and cross-slots are explored to build a novel subarray with 2 × 2-unit ME-dipoles as the basic element. Creatively, a square waveguide to cross-slots transition with a pyramid horn cavity structure is investigated to feed the ME-dipole subarray. Furthermore, two types of power-tapering corporate-feed networks with laminated structures are used to design an 8 × 8-unit low-SLL array. The fabricated array has a relative bandwidth (VSWR < 2) of 14.3% and 17.1%, with a realized gain higher than 25.8 dBi and 26.1 dBi for the H-pol. and V-pol., respectively. The maximum radiation efficiency for both arrays is 73.2%. The measured first sidelobe levels are less than –17.5 dB for both polarizations. With competitive performance and low fabrication cost, the proposed dual-polarization ME-dipole antenna array would be valuable for polarization-agile radar and communication systems.

Respiration rate monitoring using ultra-wideband (UWB) radar is preferred because it provides contactless measurement without restricting the person’s privacy. This study considers a novel non-contact-based solution using a single-input multiple-output (SIMO) UWB impulse radar. In the proposed system, the collected radar data are converted to several narrow-band signals using the generalized Goertzel algorithm (GGA), which are used as the input of the designed phased arrays for position estimation. In this context, we introduce the incoherent signal subspace methods (ISSM) for the direction of arrivals (DOAs) and distance evaluation. Meanwhile, a beam focusing approach is used to determine each individual and estimate their breathing rate automatically based on a linearly constrained minimum variance (LCMV) beamformer. The experimental results prove that the proposed algorithm can achieve high estimation accuracy in a variety of test environments, with an error of 2%, 5%, and 2% for DOA, distance, and respiration rate, respectively.

The ability to monitor Sprained Ankle Rehabilitation Exercises (SPAREs) in home environments can help therapists to ascertain if exercises have been performed as prescribed. Whilst wearable devices have been shown to provide advantages such as high accuracy and precision during monitoring activities, disadvantages such as limited battery life, users' inability to remember to charge and wear the devices are often the challenges for their usage. Also, video cameras, which are notable for high frame rates and granularity, are not privacy-friendly. This paper, therefore, proposes the use and fusion of unobtrusive and privacy-friendly sensing solutions for data collection and processing during SPAREs in home environments. Two Infrared Thermopile Array (ITA-32) thermal sensors and two Frequency Modulated Continuous Wave (FMCW) Radar sensors were used to simultaneously monitor 15 healthy participants during SPAREs which involved twisting their ankle in 4-fundamental movement patterns namely (i) extension, (ii) flexion, (iii) eversion and (iv) inversion. Experimental results indicated the ability to identify thermal blobs of participants performing the 4 fundamental movement patterns of the human ankle. Cluster-based analysis of data gleaned from the ITA-32 sensors and the FMCW Radar sensors indicated average classification accuracy of 96.9% with K-Nearest Neighbours, Neural Network, AdaBoost, Decision Tree, Stochastic Gradient Descent and Support Vector Machine, amongst others.

In this paper, we analyze and mitigate the cross-channel interference, which is found in multiple-input multiple-output (MIMO) radio frequency (RF) sensing systems. For a millimeter wave (mm-Wave) MIMO system, we present a geometrical three-dimensional (3D) channel model to simulate the time-variant (TV) trajectories of a moving scatterer. We collected RF data using a state-of-the-art radar known as Ancortek SDR-KIT 2400T2R4, which is a frequency-modulated continuous wave (FMCW) MIMO radar system operating in the K-band. The Ancortek radar is currently the only K-band MIMO commercial radar system that offers customized antenna configurations. It is shown that this radar system encounters the problem of interference between the various subchannels. We propose an optimal approach to mitigate the problem of cross-channel interference by inducing a propagation delay in one of the channels and apply range gating. The measurement results prove the effectiveness of the proposed approach by demonstrating a complete elimination of the interference problem. The application of the proposed solution on Ancortek’s SDR-KIT 2400T2R4 allows resolving all subchannel links in a distributed MIMO configuration. This allows using MIMO RF sensing techniques to track a moving scatterer (target) regardless of its direction of motion.

Ground penetrating radar (GPR) systems are sensors that are able to acquire underground images by scanning the surface of the soil/pavement under investigation. Usually, a GPR system records its own position along the scan line, using a mechanical odometer, i.e., a rolling wheel in contact with the ground. This simple and cheap solution can be ineffective on uneven terrains. In this paper, a positioning system based on an interferometric radar is presented. This kind of radar is able to detect small displacements of the targets in its field of view. Such a capability was used to track the GPR position along a line. The system was validated with simulations and tested in a realistic experimental scenario.

Designing beampatterns with constant beamwidth over a wide range of frequencies is useful in many applications in speech, radar, sonar and communication. In this paper, we design constant-beamwidth beamformers for concentric ring arrays. The proposed beamformers utilize the circular geometry to provide improved beamwidth consistency compared to beamformers which are designed for linear sensor arrays of the same order. In the proposed configuration, all sensors on each ring share the same weight value. This constraint significantly simplifies the beamformers and reduces the hardware and computational resources required in a physical setup. Furthermore, a theoretical justification of the beamforming method is provided. We demonstrate the advantages of the proposed beamformers compared to the one-dimensional configuration in terms of directivity index, white noise gain and sidelobe attenuation.

This article presents the hardware implementation and a behavioral model-based RF system modeling and simulation (M&amp, S) study of compressive sensing (CS) based 2D angle-of-arrival (AoA) measurement system for 2–18 GHz radar electronic support measures (RESM). A 6-channel ultra-wideband RF digital receiver was first developed using a PXIe-based multi-channel digital receiver paired with a 6-element random-spaced 2D cavity-backed-spiral-antenna array. Then the system was tested in an open lab environment. The measurement results showed that the system can measure AoA of impinging signals from 2–18 (GHz) with overall RMSE of estimation at 3.60, 2.74, 1.16, 0.67 and 0.56 (deg) in L, S, C, X and Ku bands, respectively. After that, using the RF high-fidelity M&amp, S (RF HF-M&amp, S) approach, a 6-channel AoA measurement system behavioral model was also developed and studied using a radar electronic warfare (REW) engagement scenario. The simulation result showed that the airborne AoA measurement system could successfully measure an S-band ground-based target acquisition radar signal in the dynamic REW environment. Using the RF HF-M&amp, S model, the applicability of the system in other frequencies within 2–18 (GHz) was also studied. The simulation results demonstrated that the airborne AoA measurement system can be used for 2–18 GHz RESM applications.

Radar technology is constantly evolving, and new applications are arising, particularly for the millimeter wave bands. A novel application for radar is gait monitoring for fall prevention, which may play a key role in maintaining the quality of life of people as they age. Alarming statistics indicate that one in three adults aged 65 years or older will experience a fall every year. A review of the sensors used for gait analysis and their applications to technology-based fall prevention interventions was conducted, focusing on wearable devices and radar technology. Knowledge gaps were identified, such as wearable radar development, application specific signal processing and the use of machine learning algorithms for classification and risk assessment. Fall prevention through gait monitoring in the natural environment presents significant opportunities for further research. Wearable radar could be useful for measuring gait parameters and performing fall risk-assessment using statistical methods, and could also be used to monitor obstacles in real-time.

In this paper, the localization problem of a mobile robot equipped with a Doppler–azimuth radar (D–AR) is investigated in the environment with multiple landmarks. For the type (2,0) robot kinematic model, the unknown modeling errors are generally aroused by the inaccurate odometer measurement. Meanwhile, the inaccurate odometer measurement can also give rise to a type of unknown bias for the D–AR measurement. For reducing the influence induced by modeling errors on the localization performance and enhancing the practicability of the developed robot localization algorithm, an adaptive fading extended Kalman filter (AFEKF)-based robot localization scheme is proposed. First, the robot kinematic model and the D–AR measurement model are modified by considering the impact caused by the inaccurate odometer measurement. Subsequently, in the frame of adaptive fading extended Kalman filtering, the way to the addressed robot localization problem with unknown biases is sought out and the stability of the developed AFEKF-based localization algorithm is also discussed. Finally, in order to testify the feasibility of the AFEKF-based localization scheme, three different kinds of modeling errors are considered and the comparative simulations are conducted with the conventional EKF. From the comparative simulation results, it can be seen that the average localization error under the developed AFEKF-based localization scheme is [0.0245 m0.0224 m0.0039 rad]T and the average localization errors using the conventional EKF are [1.0405 m2.2700 m0.1782 rad]T, [0.4963 m0.3482 m0.0254 rad]T and [0.2774 m0.3897 m0.0353 rad]T, respectively, under the three cases of the constant bias, the white Gaussian stochastic bias and the bounded uncertainty bias.

This paper develops a framework to track the trajectory of a target in 2D by considering a moving ownship able to measure bearing measurements. Notably, the framework allows one to incorporate additional information (e.g., obtained via intelligence) such as knowledge on the fact the target’s trajectory is contained in the intersection of some sets or the fact it lies outside the union of other sets. The approach is formally characterized by providing a constrained maximum likelihood estimation (MLE) formulation and by extending the definition of the Cramér–Rao lower bound (CRLB) matrix to the case of MLE problems with inequality constraints, relying on the concept of generalized Jacobian matrix. Moreover, based on the additional information, the ownship motion is chosen by mimicking the Artificial Potential Fields technique that is typically used by mobile robots to aim at a goal (in this case, the region where the target is assumed to be) while avoiding obstacles (i.e., the region that is assumed not to intersect the target’s trajectory). In order to show the effectiveness of the proposed approach, the paper is complemented by a simulation campaign where the MLE computations are carried out via an evolutionary ant colony optimization software, namely, mixed-integer distributed ant colony optimization solver (MIDACO-SOLVER). As a result, the proposed framework exhibits remarkably better performance, and in particular, we observe that the solution is less likely to remain stuck in unsatisfactory local minima during the MLE computation.

Today, a lot of research on autonomous driving technology is being conducted, and various vehicles with autonomous driving functions, such as ACC (adaptive cruise control) are being released. The autonomous vehicle recognizes obstacles ahead by the fusion of data from various sensors, such as lidar and radar sensors, including camera sensors. As the number of vehicles equipped with such autonomous driving functions increases, securing safety and reliability is a big issue. Recently, Mobileye proposed the RSS (responsibility-sensitive safety) model, which is a white box mathematical model, to secure the safety of autonomous vehicles and clarify responsibility in the case of an accident. In this paper, a method of applying the RSS model to a variable focus function camera that can cover the recognition range of a lidar sensor and a radar sensor with a single camera sensor is considered. The variables of the RSS model suitable for the variable focus function camera were defined, the variable values were determined, and the safe distances for each velocity were derived by applying the determined variable values. In addition, as a result of considering the time required to obtain the data, and the time required to change the focal length of the camera, it was confirmed that the response time obtained using the derived safe distance was a valid result.

As an autonomous system, an anti-radiation loitering munition (LM) experiences uncertainty in both a priori and sensed information during loitering because it is difficult to accurately know target radar information in advance, and the sensing performance of the seeker is affected by disturbance and errors. If, as it does in the state of the art, uncertainties are ignored and the LM travels its planned route, its battle effectiveness will be severely restricted. To tackle this problem, this paper studies the method of autonomous planning and control of loitering routes using limited a priori information of target radar and real-time sensing results. We establish a motion and sensing model based on the characteristics of anti-radiation LMs and use particle filtering to iteratively infer the target radar information. Based on model predictive control, we select a loitering path to minimize the uncertainty of the target information, so as to achieve trajectory planning control that is conducive to the acquisition of target radar information. Simulation results show that the proposed method can effectively complete the autonomous trajectory planning and control of anti-radiation LMs under uncertain conditions.

In this paper, we present a novel cooperative scheme of joint optimal resource allocation, such that the overall performance of the coexisting radar-communications (CRC) system can be improved. In our proposed scheme, target detection and multiuser communication are performed by radar and communication subsystems at the same time, as well as a control center, which is responsible for joint resource management. We aim to minimize the ISLR for target detection and maximize the sum-rate for communications simultaneously by jointly optimizing the band assignment and transmit power allocation. Since the resulting optimization problem involving two performance metrics and a binary constraint is a multiobjective nonconvex problem, a two-tier iterative decomposition (TT-ID) approach is devised to obtain the globally optimal solution. However, compared with the conventional radar signals, the autocorrelation function of the devised radar signal may still have relatively high sidelobes. In particular, when the data transmission becomes the primary purpose of the CRC system, the sidelobe performance gets worse. As a consequence, some weak targets are most likely overshadowed by the adjacent strong targets through the matched filtering at the radar receiver. To address this, a spectral estimation algorithm based on the Bayes Cauchy–Gaussian (Bayes–CG) model is employed to further reduce the range sidelobes of the matched filter output at the radar receiver according to the prior distribution of the desired autocorrelation. Finally, several numerical results are provided to show the merits of the proposed method.

In this paper, comprehensive mPoint, a method for generating 3D (range, azimuth, and elevation) point cloud of human targets using a Frequency-Modulated Continuous Wave (FMCW) signal and Multi-Input Multi-Output (MIMO) millimeter wave radar is proposed. Distinct from the TI-mPoint method proposed by TI technology, a comprehensive mPoint method considering both the static and dynamic characteristics of radar reflected signals is utilized to generate a high precision point cloud, resulting in more comprehensive information of the target being detected. The radar possessing 60&ndash, 64 GHz FMCW signal with two sets of different dimensional antennas is utilized in order to experimentally verify the results of the methodology. By using the proposed process, the point cloud data of human targets can be obtained based on six different postures of the underlying human body. The human posture cube and point cloud accuracy rates are defined in the paper in order to quantitively and qualitatively evaluate the quality of the generated point cloud. Benefitting from the proposed comprehensive mPoint, evidence shows that the point number and the accuracy rate of the generated point cloud compared with those from the popular TI-mPoint can be largely increased by 86% and 42%, respectively. In addition, the noise level of multipath reflection can be effectively reduced. Moreover, the length of the algorithm running time is only 1.6% longer than that of the previous method as a slight tradeoff.

Physical objects are usually not designed with interaction capabilities to control digital content. Nevertheless, they provide an untapped source for interactions since every object could be used to control our digital lives. We call this the missing interface problem: Instead of embedding computational capacity into objects, we can simply detect users’ gestures on them. However, gesture detection on such unmodified objects has to date been limited in the spatial resolution and detection fidelity. To address this gap, we conducted research on micro-gesture detection on physical objects based on Google Soli’s radar sensor. We introduced two novel deep learning architectures to process range Doppler images, namely a three-dimensional convolutional neural network (Conv3D) and a spectrogram-based ConvNet. The results show that our architectures enable robust on-object gesture detection, achieving an accuracy of approximately 94% for a five-gesture set, surpassing previous state-of-the-art performance results by up to 39%. We also showed that the decibel (dB) Doppler range setting has a significant effect on system performance, as accuracy can vary up to 20% across the dB range. As a result, we provide guidelines on how to best calibrate the radar sensor.

Multi-target tracking (MTT) generally requires either a network of Doppler radar receivers distributed at different locations or a phased array radar. The targets moving with small/no radial velocity or angular velocity only cannot be detected and localized completely by deploying Doppler radar without antenna arrays or multiple receivers. To resolve this issue, we present a new MTT algorithm based on 2-D velocity measurements, namely, radial and angular velocities, using dual-frequency interferometric radar. The contributions of the proposed research are twofold: First, we introduce the mathematical model and implementation of the proposed algorithm by explicitly establishing the relationship between 2-D velocity measurements and kinematic state of the target in terms of Cartesian coordinates. Based on 2-D velocity measurement function, the proposed MTT algorithm comprises the following steps: (i) data association using global nearest neighbor (GNN) method (ii) target state estimation using interacting multiple model (IMM) estimator combined with square-root cubature Kalman filter (SCKF) (iii) track management using rule-based M/N logic. Second, performance of the proposed algorithm is evaluated in terms of tracking accuracy, computational complexity and IMM mean model probabilities. Simulation results for different scenarios with multiple targets moving in different tracks have been presented to verify the effectiveness of the proposed algorithm.

Continuous Wave (CW) radars systems, especially air-coupled Ground-Penetrating Radar (GPR) or Through-Wall Imaging Radar (TWIR) systems, echo signals reflected from a stationary target with high energy, which may cause receiver saturation. Another effect caused by reflection of stationary targets is noticeable as background within a radargram. Nowadays, radar systems use automatic gain control to prevent receiver saturation. This paper proposes a method to remove stationary targets automatically from the received signal. The method was designed for a radar system with a moving platform, with an assumption that the distance between the surface and target is constant. The design is proposed of an SFCW radar with an integrated system for real-time multiple static target Echo Cancellation (EC). The proposed EC system removes the static target using active Integrated Circuit (IC) components, which generate the corresponding EC signal for each frequency step of the SFCW radar and sum it with the received echo signal. This has the main advantage of removing even multiple echoes at any distance, and excludes the need for a high-dynamic-range receiver. Additionally, the proposed system has minimal impact on the radar size and power consumption. Besides static target removal, the antenna coupling can be removed if the signal appears to be constant. The operating frequency was selected between 500 MHz and 2.5 GHz, due to the limitation of the used electronic components. The experimental results show that the simulated target’s echo using a cable with a known length could be suppressed to up to 38 dB. Experimental results using a moving radar platform and the real environment scenario with static and dynamic targets, show that the proposed EC system could achieve up to 20 dB attenuation of the static target. The system does not affect any other target of interest, which can even move at any distance during the measurement. Therefore, this could be a promising method for further compact implementation into SFCW radars, or any other radar type that generates CW single frequencies.

A method of direction-of-arrival (DoA) estimation for FMCW (Frequency Modulated Continuous Wave) radar is presented. In addition to MUSIC, which is the popular high-resolution DoA estimation algorithm, deep learning has recently emerged as a very promising alternative. It is proposed in this paper to use a 3D convolutional neural network (CNN) for DoA estimation. The 3D-CNN extracts from the radar data cube spectrum features of the region of interest (RoI) centered on the potential positions of the targets, thereby capturing the spectrum phase shift information, which corresponds to DoA, along the antenna axis. Finally, the results of simulations and experiments are provided to demonstrate the superior performance, as well as the limitations, of the proposed 3D-CNN.

Autonomous vehicles perceive objects through various sensors. Cameras, radar, and LiDAR are generally used as vehicle sensors, each of which has its own characteristics. As examples, cameras are used for a high-level understanding of a scene, radar is applied to weather-resistant distance perception, and LiDAR is used for accurate distance recognition. The ability of a camera to understand a scene has overwhelmingly increased with the recent development of deep learning. In addition, technologies that emulate other sensors using a single sensor are being developed. Therefore, in this study, a LiDAR data-based scene understanding method was developed through deep learning. The approaches to accessing LiDAR data through deep learning are mainly divided into point, projection, and voxel methods. The purpose of this study is to apply a projection method to secure a real-time performance. The convolutional neural network method used by a conventional camera can be easily applied to the projection method. In addition, an adaptive break point detector method used for conventional 2D LiDAR information is utilized to solve the misclassification caused by the conversion from 2D into 3D. The results of this study are evaluated through a comparison with other technologies.

In this paper we study the code design problem of a new form of linear frequency modulation phase-coded (LFM-PC) hybrid signal with wide Doppler tolerance based on a range-Doppler discrete ambiguity function (DAF) to get better detection performance and anti-jamming capability. The DAF of the LFM-PC inter pulse signal is derived within the Doppler tolerance. Two optimization models are established. One is single pulse sequence design (SSD) for Doppler tolerance extension based on minimum integral normalized sidelobe level (INSL), the other is multi pulse sequence set design (MSSD) for signal orthogonality based on the minimizing sum of the normalized DAF sidelobe (NDAFSL) and discrete cross ambiguity function (DCAF). Two low-complexity signal optimization methods based on alternating direction method of multiplier (ADMM) are proposed, respectively. The simulation results show that the optimized signals have either wide Doppler tolerance or good orthogonal performance, and the optimization methods (i.e., SSD-ADMM and MSSD-ADMM) have the characteristics of fast convergence speed and low operation amount.

Passive Coherent Location methods and techniques have an established position in the modern state-of-the-art radar. Inexpensive, easy to deploy and undetectable for other sensors, passive radars are growing in popularity. Due to that, a need arises to develop proper methods of any possible kind of countermeasure. In this work, a method of detection and localization of hidden PCL systems is proposed. Authors exploit certain physical features of an RF receiver in order to detect such a passive systems. Results of selected hardware measurements are presented as a proof of concept. Summarized findings are followed by an extensive discussion of conditions related with the method implementation in a real world scenarios.

Drowsiness when in command of a vehicle leads to a decline in cognitive performance that affects driver behavior, potentially causing accidents. Drowsiness-related road accidents lead to severe trauma, economic consequences, impact on others, physical injury and/or even death. Real-time and accurate driver drowsiness detection and warnings systems are necessary schemes to reduce tiredness-related driving accident rates. The research presented here aims at the classification of drowsy and non-drowsy driver states based on respiration rate detection by non-invasive, non-touch, impulsive radio ultra-wideband (IR-UWB) radar. Chest movements of 40 subjects were acquired for 5 m using a lab-placed IR-UWB radar system, and respiration per minute was extracted from the resulting signals. A structured dataset was obtained comprising respiration per minute, age and label (drowsy/non-drowsy). Different machine learning models, namely, Support Vector Machine, Decision Tree, Logistic regression, Gradient Boosting Machine, Extra Tree Classifier and Multilayer Perceptron were trained on the dataset, amongst which the Support Vector Machine shows the best accuracy of 87%. This research provides a ground truth for verification and assessment of UWB to be used effectively for driver drowsiness detection based on respiration.

This paper deals with bistatic track association and deghosting in the classical frequency modulation (FM)-based multi-static primary surveillance radar (MSPSR). The main contribution of this paper is a novel algorithm for bistatic track association and deghosting. The proposed algorithm is based on a hierarchical model which uses the Indian buffet process (IBP) as the prior probability distribution for the association matrix. The inference of the association matrix is then performed using the classical reversible jump Markov chain Monte Carlo (RJMCMC) algorithm with the usage of a custom set of the moves proposed by the sampler. A detailed description of the moves together with the underlying theory and the whole model is provided. Using the simulated data, the algorithm is compared with the two alternative ones and the results show the significantly better performance of the proposed algorithm in such a simulated setup. The simulated data are also used for the analysis of the properties of Markov chains produced by the sampler, such as the convergence or the posterior distribution. At the end of the paper, further research on the proposed method is outlined.

Foreign Object Debris (FOD) refers to any foreign material on the airfield that may injure and threaten the aircraft and airport system. Due to the complex background on the airfield pavement and weak target echoes in long-distance monitoring, it is not easy to detect objects of various types and sizes. The existing FOD radar system’s detection method has a short effective range, and the detectable objects’ radar cross-section intensity is no less than −20 dBsm. In this paper, we propose an integrated FOD automatic target detection algorithm for millimeter-wave (MMW) surveillance radar to improve small target detection under long-range conditions of over 660 m. The signal form of FOD and a clutter model of ground clutter received by millimeter-wave radar are primarily utilized and established theoretically. The runway edge detection means that it is employed based on the in-continuity features as the runway region of interest during the automatic extraction step. Following the clutter map constant false alarm detection algorithm, we utilize a time-domain algorithm that functions as the vital detection processor. Moreover, an explicit definition of the FOD detection performance is developed in a characteristic quantitative way. This criterion involves an absolute reference value for all FOD radar systems. The well-designed FOD frequency-modulated continuous-wave MMW surveillance radar is utilized, and actual experiments are carried out in a real airport in Beijing, China. The results validate the proposed method’s effectiveness and the superior performance of FOD target detection in long-range situations.

One of the most crucial emergencies that require instant action to be taken during traveling across water is the so-called man overboard (MOB). Thus, constant monitoring equipment needs to be installed for the fast notice and detection of the victim to be rescued, if an incident happens. Despite the fact that different installations such as radar sensors, thermal cameras etc., can be handy, a combination of these could be beneficial yet it would increase the complexity. Nevertheless, the full potential may be not reached yet. The key component to what needs to be done in order to achieve the utmost accuracy is artificial intelligence (AI). That is, with the aid of AI, one can deploy an automated surveillance system capable of making its own humanlike decisions regarding such incidents like MOB. To achieve this, fully organized real-time cooperation among the concerned system components is essential. The latter holds since in such dynamically changing operational environments like these, information must be distributed fast, errorless and reliably to the decision center. This study aims to analyze and demonstrate the outcome of an integrated sensor-based system that utilizes AI, implemented for ship incidents. Different machine learning algorithms were used where each one of them made use of information that originated from a cluster of radar sensors located remotely. In particular, the deployed system’s objective is to detect human motion so it can be used to protect against potentially fateful events during ship voyages.

In this paper, a high gain 77-GHz receiver with a low noise figure (NF) was designed and implemented in a 40-nm CMOS process. With the purpose of making better use of active devices, an extra inductor, Ld, is adopted in the new neutralization technique. The three-stage differential low noise amplifier (LNA) using the proposed technique improves the voltage gain and reduces the NF. The receiver design utilizes an active double-balanced Gilbert mixer with a transformer coupling network between the transconductance stage and the switch stage. The flicker noise contribution from the switch MOS transistors is largely reduced due to the low DC current of the switch pairs. The LO signal is provided by an on-chip fundamental voltage-controlled oscillator (VCO) with a tuning range from 70.5 to 78.1 GHz. A conversion gain of 32 dB and a NF of 11.86 dB are achieved at 77 GHz by the designed receiver. The LNA as well as the mixer consume a total DC power of 33.2 mW and occupy a core size of 1 × 0.38 mm2.

Automotive millimeter-wave (MMW) radar is essential in autonomous vehicles due to its robustness in all weather conditions. Traditional commercial automotive radars are limited by their resolution, which makes the object classification task difficult. Thus, the concept of a new generation of four-dimensional (4D) imaging radar was proposed. It has high azimuth and elevation resolution and contains Doppler information to produce a high-quality point cloud. In this paper, we propose an object classification network named Radar Transformer. The algorithm takes the attention mechanism as the core and adopts the combination of vector attention and scalar attention to make full use of the spatial information, Doppler information, and reflection intensity information of the radar point cloud to realize the deep fusion of local attention features and global attention features. We generated an imaging radar classification dataset and completed manual annotation. The experimental results show that our proposed method achieved an overall classification accuracy of 94.9%, which is more suitable for processing radar point clouds than the popular deep learning frameworks and shows promising performance.

Recently, as technology has advanced, the use of in-vehicle infotainment systems has increased, providing many functions. However, if the driver’s attention is diverted to control these systems, it can cause a fatal accident, and thus human–vehicle interaction is becoming more important. Therefore, in this paper, we propose a human–vehicle interaction system to reduce driver distraction during driving. We used voice and continuous-wave radar sensors that require low complexity for application to vehicle environments as resource-constrained platforms. The proposed system applies sensor fusion techniques to improve the limit of single-sensor monitoring. In addition, we used a binarized convolutional neural network algorithm, which significantly reduces the computational workload of the convolutional neural network in command classification. As a result of performance evaluation in noisy and cluttered environments, the proposed system showed a recognition accuracy of 96.4%, an improvement of 7.6% compared to a single voice sensor-based system, and 9.0% compared to a single radar sensor-based system.