Suppression of radar-to-radar jammers, especially the mainbeam has been an urgent demand in vehicular sensing systems with expected increased number vehicles equipped radar systems. This paper deals suppression deceptive jammers frequency diverse array (FDA)-multiple-input multiple-output (MIMO) radar, utilizing its extra degrees-of-freedom (DOFS) range domain. At modelling stage, false targets, which lag several pulses behind true target, are considered as a typical form jammers. To this...

This paper presents a framework based on multilayer bi-LSTM network (bidirectional Long Short-Term Memory) for multimodal sensor fusion to sense and classify daily activities' patterns high-risk events such as falls. The data collected in this work are continuous activity streams from FMCW radar three wearable inertial sensors the wrist, waist, ankle. Each has variable duration stream so that transitions between activities can happen at random times within stream, without resorting...

Recognition of human movements with radar for ambient activity monitoring is a developed area research that yet presents outstanding challenges to address. In real environments, activities and are performed seamless motion, continuous transitions between different duration large range dynamic motions, compared discrete fixed-time lengths which typically analysed in the literature. This paper proposes novel approach based on recurrent LSTM Bi-LSTM network architectures classification. uses...

This review explores radar‐based techniques currently utilised in the literature to monitor small unmanned aerial vehicle (UAV) or drones; several challenges have arisen due their rapid emergence and commercialisation within mass market. The potential security threats posed by these systems are collectively presented legal issues surrounding successful integration briefly outlined. Key difficulties involved identification hence tracking of ‘radar elusive’ discussed, along with how research...

This paper presents an approach for detection and tracking a micro-UAV using the multistatic radar NetRAD. Experimental trials were performed NetRAD allowing analysis of real data to assess difficulty target. The UAV is based on both time domain micro-Doppler signatures, in order enhance discrimination between ground clutter returns. procedure shown improve clutter/target discrimination, comparison Doppler-shift procedure. able compensate limited quality measurement generated by each...

This paper presents both simulation and experimental results of micro-drone rotor blade electromagnetic scattering. The focus this work is investigating the variation these reflections as a function variables such polarization, frequency azimuth angle. clearly show strong in scattering with frequency. Experimental validation variations was investigated similar trends were found. Doppler components from an operational varying polarizations are shown, demonstrate expected signals received by...

In this letter, we propose two methods for personnel recognition and gait classification using deep convolutional neural networks (DCNNs) based on multistatic radar micro-Doppler signatures. Previous DCNN-based schemes have mainly focused monostatic scenarios, whereas directional diversity offered by is exploited in letter to improve accuracy. We first the voted DCNN (VMo-DCNN) method, which trains DCNNs each receiver node separately fuses results binary voting. By merging fusion step into...

In this letter we present the use of experimental human micro-Doppler signature data gathered by a multistatic radar system to discriminate between unarmed and potentially armed personnel walking along different trajectories.Different ways extracting suitable features from spectrograms signatures are discussed, in particular empirical such as Doppler bandwidth, periodicity others, extracted Singular Value Decomposition (SVD) vectors.High classification accuracy vs (between 90-97% depending...

This study presents the use of micro‐Doppler signatures collected by a multistatic radar to detect and discriminate between micro‐drones hovering flying while carrying different payloads, which may be an indication unusual or potentially hostile activities. Different features have been extracted tested, namely related cross‐section micro‐drones, as well singular value decomposition centroid signatures. In particular, added benefit using information in comparison with conventional is...

Preliminary results on the use of multistatic radar and micro‐Doppler analysis to detect discriminate between micro‐drones hovering carrying different payloads are presented. Two suitable features related centroid signature have been identified used perform classification, investigating also added benefit using information from a as opposed conventional monostatic system. Very good performance with accuracy above 90% has demonstrated for classification micro‐drones.

This article covers radar signal processing for sensing in the context of assisted living (AL). is presented through three example applications: human activity recognition (HAR) activities daily (ADL), respiratory disorders, and sleep stages (SSs) classification. The common challenge classification discussed within a framework measurements/preprocessing, feature extraction, algorithms supervised learning. Then, specific challenges applications from standpoint are detailed their data ad hoc...

Radar-based human motion recognition is crucial for many applications, such as surveillance, search and rescue operations, smart homes, assisted living. Continuous in real-living environment necessary practical deployment, i.e., classification of a sequence activities transitioning one into another, rather than individual activities. In this paper, novel dynamic range-Doppler trajectory (DRDT) method based on the frequency-modulated continuous-wave (FMCW) radar system proposed to recognize...

In this work, the authors present results for classification of different classes targets (car, single and multiple people, bicycle) using automotive radar data neural networks. A fast implementation algorithms detection, tracking, micro‐Doppler extraction is proposed in conjunction with transceiver TEF810X microcontroller unit SR32R274 manufactured by NXP Semiconductors. Three types networks are considered, namely a classic convolutional network, residual combination recurrent problems...

Suppressing the main-beam deceptive jamming in traditional radar systems is challenging. Furthermore, observations corrupted by false targets generated smart jammers, which are not independent and identically distributed because of pseudo-random time delay. This turn complicates task suppression. In this paper, a new suppression approach proposed, using nonhomogeneous sample detection frequency diverse array-multiple-input multiple-output with non-perfectly orthogonal waveforms. First,...

Although typically associated with large-scale, defense -related use to monitor ships and aircraft, radar has been employed in the past few years for a number of short-range, civilian applications. We have discussed presented some examples used support health-care provisions, help vital signs patients at risk their daily activities, useful proxy more general physical cognitive well-being. Unlike cameras wearables, does not collect sensitive images people monitored or require users wear,...

Although traditionally associated with defence and security domains, radar sensing has attracted significant interest in recent years healthcare applications. These include the monitoring of vital signs such as respiration, heartbeat, blood pressure, analysis gait mobility levels, classification human activities to promptly detect critical events falls, well evaluation fitness reactivity levels. The attractiveness against alternative technologies wearable sensors or cameras lies its...

Human activity recognition (HAR) plays a vital role in many applications, such as surveillance, in-home monitoring, and health care. Portable radar sensor has been increasingly used HAR systems combination with deep learning (DL). However, it is both difficult time-consuming to obtain large-scale dataset reliable labels. Insufficient labeled data often limit the generalization of DL models. As result, performance models will drop when being applied new scenario. In this sense, only labeling...

Unconstrained human activities recognition with a radar network is considered. A hybrid classifier combining both CNNs and RNNs for spatial-temporal pattern extraction proposed. The two-dimensional (2D-CNNs) are first applied to the data perform spatial feature on input spectrograms. Subsequently, gated recurrent units bidirectional implementations used capture long- short-term temporal dependencies in maps generated by 2D-CNNs. Three NN-based fusion methods were explored compared utilize...

Radar-based human motion and activity recognition is currently a topic of great research interest, as the aging population increases older individuals prefer an independent lifestyle. This technology has wide range applications, such fall detection in assisted living, gesture for human-machine interfaces, many more. Numerous studies exist on various approaches radar-based capture classification. However, most these employ rather artificial data, often obtained laboratory environments,...

This paper analyses the experimental results from recent monostatic and bistatic radar measurements of multiple birds as well a quadcopter micro-drone. The system deployed for these was UCL developed NetRAD system. aim this work is to evaluate key differences observed by between different Measurements are presented simultaneous co/cross polarized data co-polar data. obtained show comparable signature within time domain marked difference in Doppler domain, various comparison wing beat...

The accurate classification of activity patterns based on radar signatures is still an open problem and a key to detect anomalous behavior for security health applications. This paper presents novel iterative convolutional neural network strategy with autocorrelation pre-processing instead the traditional micro-Doppler image classify activities or subjects accurately. proposed uses deep learning framework automatic definition extraction features. followed by supervised classifier label...

This paper investigates the selection of different combinations features at multistatic radar nodes, depending on scenario parameters, such as aspect angle to target and signal-to-noise ratio, dwell time, polarization, frequency band. Two sets experimental data collected with system NetRAD are analyzed for two separate problems, namely classification unarmed versus potentially armed multiple personnel, personnel recognition individuals based walking gait. The results show that overall...

Dynamic hand gesture recognition is of great importance for human-computer interaction. In this paper, we present a method to discriminate the four kinds dynamic gestures, snapping fingers, flipping rotation and calling, using radar micro-Doppler sensor. Two features are extracted from time-frequency spectrum support vector machine used classify these gestures. The experimental results on measured data demonstrate that proposed can produce classification accuracy higher than 88.56%.