micro-Doppler Signatures Research Articles

Orientation-Independent Human Activity Recognition Using Complementary Radio Frequency Sensing.

RF sensing offers an unobtrusive, user-friendly, and privacy-preserving method for detecting accidental falls and recognizing human activities. Contemporary RF-based HAR systems generally employ a single monostatic radar to recognize human activities. However, a single monostatic radar cannot detect the motion of a target, e.g., a moving person, orthogonal to the boresight axis of the radar. Owing to this inherent physical limitation, a single monostatic radar fails to efficiently recognize orientation-independent human activities. In this work, we present a complementary RF sensing approach that overcomes the limitation of existing single monostatic radar-based HAR systems to robustly recognize orientation-independent human activities and falls. Our approach used a distributed mmWave MIMO radar system that was set up as two separate monostatic radars placed orthogonal to each other in an indoor environment. These two radars illuminated the moving person from two different aspect angles and consequently produced two time-variant micro-Doppler signatures. We first computed the mean Doppler shifts (MDSs) from the micro-Doppler signatures and then extracted statistical and time- and frequency-domain features. We adopted feature-level fusion techniques to fuse the extracted features and a support vector machine to classify orientation-independent human activities. To evaluate our approach, we used an orientation-independent human activity dataset, which was collected from six volunteers. The dataset consisted of more than 1350 activity trials of five different activities that were performed in different orientations. The proposed complementary RF sensing approach achieved an overall classification accuracy ranging from 98.31 to 98.54%. It overcame the inherent limitations of a conventional single monostatic radar-based HAR and outperformed it by 6%.

Photonics radar based LSS targets’ postures’ m-D and cadence frequency imaging using empirical wavelet transform technique

ABSTRACT Developing a photonics radar to detect the combined multiple simultaneous-behaviours/postures of low-slow-small (LSS) aerial targets and appropriately extracting their Doppler profile have become significant to enable air surveillance/security and guidance for unmanned aviation. A CW photonic radar of 5.3 GHz, and an empirical wavelet transform (EWT) based radar signal processing algorithm are developed and their sensing/measurement capabilities are tested with representative LSS target models: two/three blades propeller systems, a warhead-like cone-shaped target and a bionic bird. Open field experiments with different simultaneous-behaviours of these LSS targets are conducted, and performance validation of radar, in terms of micro-Doppler signature extractions, cadence frequency imaging and targets' behavioural parameters measurement, is analysed, quantitatively investigated and the results are presented. All the measurement results keep an average of 99% of agreement with the standard measurement values that evidence the compatibility of developed photonics radar for precision sensing of multiple simultaneous-behaviours/postures of LSS aerial targets.

Local maximum multisynchrosqueezing transform and its application

The synchrosqueezing technique is widely used for analyzing the time variations of non-stationary signals. Recently, the local maximum synchrosqueezing transform (LMSST) method has been presented to effectively improve the time-frequency (TF) representation, which seems to be a promising tool. However, the LMSST is unable to accurately characterize the amplitude of strongly non-stationary signals, making it rather challenging to extract accurate TF information for signals with strong frequency modulation. Therefore, there is a significant barrier preventing the development of more precise and sharper results from the micro-Doppler signals with strong frequency modulation and multi-component characteristics. To overcome this problem, we coined a novel LMSST method, namely local maximum multisynchrosqueezing transform (LMMSST). The LMMSST is on the basis of local maximizing TF reassignment and multiple synchrosqueezing operators in which an iterated redistribution program is used to concentrate the ambiguous TF energy with a stepwise approach. As a result, the LMMSST significantly enhances the concentration in terms of energy of TF results and performs better in addressing strong frequency modulation and multi-component signals. In addition, it also allows perfect signal reconstruction and accurate estimating of the instantaneous frequency. Numerical results and application cases verify the effectiveness of the LMMSST method.

Physics-Aware Generative Adversarial Networks for Radar-Based Human Activity Recognition

Generative adversarial networks (GANs) have recently been proposed for the synthesis of RF micro-Doppler signatures to address the issue of low sample support and enable the training of deeper neural networks (DNNs) for enhanced RF signal classification. But GANs suffer from systemic kinematic inconsistencies that decrease performance when GAN-synthesized data is used for training DNNs in human activity recognition. As a solution to this problem, this paper proposes the design of a multi-branch GAN (MBGAN), which integrates domain knowledge into its architecture, and physics-aware metrics based on correlation and curve-matching in the loss function. The quality of the synthetic samples generated is evaluated via image quality metrics, the ability to synthesize data that reflects human physical properties and generalize to broader subject profiles, and the achieved classification accuracy. Our experimental results show the proposed approach generates synthetic data for training that more accurately matches target kinematics, resulting in an increase of 9% in classification accuracy when classifying 14 different ambulatory human activities.

STRIDE: Systematic Radar Intelligence Analysis for ADRD Risk Evaluation with Gait Signature Simulation and Deep Learning.

Abnormal gait is a significant non-cognitive biomarker for Alzheimer's disease (AD) and AD-related dementia (ADRD). Micro-Doppler radar, a non-wearable technology, can capture human gait movements for potential early ADRD risk assessment. In this research, we propose to design STRIDE integrating micro-Doppler radar sensors with advanced artificial intelligence (AI) technologies. STRIDE embeds a new deep learning (DL) classification framework. As a proof of concept, we develop a "digital-twin" of STRIDE, consisting of a human walking simulation model and a micro-Doppler radar simulation model, to generate a gait signature dataset. Taking established human walking parameters, the walking model simulates individuals with ADRD under various conditions. The radar model based on electromagnetic scattering and the Doppler frequency shift model is employed to generate micro-Doppler signatures from different moving body parts (e.g., foot, limb, joint, torso, shoulder, etc.). A band-dependent DL framework is developed to predict ADRD risks. The experimental results demonstrate the effectiveness and feasibility of STRIDE for evaluating ADRD risk.

Model-Based Data Augmentation Applied to Deep Learning Networks for Classification of Micro-Doppler Signatures Using FMCW Radar

Deep neural networks (DNNs) have become a relevant subject in the classification of radio frequency signals and remote sensing data. A primary challenge is a tradeoff between obtaining data that are suitable for DNN training and the effort that making experimental measurements requires. Hence, the quality and quantity of data used for the training and testing of models are crucial for effective classifier development. The training dataset should cover a wide range of cases that synthesize the actual scenarios being classified. This work proposes a novel data augmentation method based on a deterministic model to generate a simulated dataset of radar micro-Doppler signatures suitable for unmanned aerial vehicle (UAV) target classification, without requiring measurement data. It is shown that the DNN trained using the properly generated model-based data offers improved classification accuracy performance. Results are presented for a two-class classification of the number of UAV motors using a 77-GHz frequency-modulated continuous-wave (FMCW) automotive radar system. The effectiveness of the proposed methodology is proven: a classification accuracy of 78.68% is achieved using a convolutional neural network (CNN) trained using the synthetic dataset, while an accuracy of 66.18% is achieved by using a typical signal processing data augmentation method on a limited measured dataset.

Exploring Radar Micro-Doppler Signatures for Recognition of Drone Types

In this study, we examine the use of micro-Doppler signals produced by different blades (i.e., puller and lifting blades) to aid in radar-based target recognition of small drones. We categorize small drones into three types based on their blade types: fixed-wing drones with only puller blades, multi-rotor drones with only lifting blades, and hybrid vertical take-off and landing (VTOL) fixed-wing drones with both lifting and puller blades. We quantify the radar signatures of the three drones using statistical measures, such as signal-to-noise ratio (SNR), signal-to-clutter ratio (SCR), Doppler speed, Doppler frequency difference (DFD), and Doppler magnitude ratio (DMR). Our findings show that the micro-Doppler signals of lifting blades in all three drone types were stronger than those of puller blades. Specifically, the DFD and DMR values of pusher blades were below 100 Hz and 0.3, respectively, which were much smaller than the 200 Hz and 0.8 values for lifting blades. The micro-Doppler signals of the puller blades were weaker and more stable than those of the lifting blades. Our study demonstrates the potential of using micro-Doppler signatures modulated by different blades for improving drone detection and the identification of drone types by drone detection radar.

Millimeter-Wave Radar Monitoring for Elder’s Fall Based on Multi-View Parameter Fusion Estimation and Recognition

Human activity recognition plays a vital role in many applications, such as body falling surveillance and healthcare for elder’s in-home monitoring. Instead of using traditional micro-Doppler signals based on time-frequency distribution, we turn to another way and use the Relax algorithm to process the radar echo so as to obtain the required parameters. In this paper, we aim at the multi-view idea in which two radars at different views work synchronously and fuse the features extracted from each radar, respectively. Furthermore, we discuss the common estimated time-frequency features and time-varying spatial features of multi-view radar-echo and then formulate the parameters matrix via principal component analysis, and finally transform them into the machine learning classifiers to make further comparisons. Simulations and results show that our proposed multi-view parameter fusion idea could lead to relative-high accuracy and robust recognition performance, which would provide a feasible application for future human–computer monitoring scenarios.

Echoformer: Transformer Architecture Based on Radar Echo Characteristics for UAV Detection

While recent years have witnessed an increasing number of commercial applications of unmanned aerial vehicles (UAVs), an imperative problem people have to face is the rapid growth of malicious use. So, it is imperative for security agencies to develop anti-UAV technology. The introduction of deep learning (DL) has a positive influence on radar signal processing, but DL-based methodologies have yet to be widespread in radar target detection because of the lack of unique architecture based on radar echo characteristics and the annotation method of radar data. In this article, a novel Transformer-based architecture is proposed, which transforms the problem of UAV detection into a binary classification task in each range cell. The complex encoder architecture and the Transformer-based extractor are designed to extract the Doppler frequency shift feature and the micro-Doppler signature (mDS) of a UAV simultaneously. The well-designed architecture based on radar echo characteristics can achieve a combination training of echoes with different coherent processing intervals (CPIs). In addition, we provide an annotation method and a data augmentation skill for our real measured dataset. The results of the experiment demonstrate that the proposed method has better detection performance and measuring accuracy under different SNRs in comparison with traditional radar target detection and other DL-based methods.

Human Activity Classification Based on Dual Micro-Motion Signatures Using Interferometric Radar

Micro-Doppler signatures obtained from the Doppler radar are generally used for human activity classification. However, if the angle between the direction of motion and radar antenna broadside is greater than 60°, the micro-Doppler signatures generated by the radial motion of human body reduce significantly, thereby degrading the performance of the classification algorithm. For the accurate classification of different human activities irrespective of trajectory, we propose a new algorithm based on dual micro-motion signatures, namely, the micro-Doppler and interferometric micro-motion signatures, using an interferometric radar. First, the motion of different parts of the human body is simulated using motion capture (MOCAP) data, which is further utilized for radar echo signal generation. Second, time-varying Doppler and interferometric spectrograms obtained from time-frequency analysis of a single Doppler receiver and interferometric output data, respectively, are fed as input to the deep convolutional neural network (DCNN) for feature extraction and the training/testing process. The performance of the proposed algorithm is analyzed and compared with a micro-Doppler signatures-based classifier. Results show that a dual micro-motion-based DCNN classifier using an interferometric radar is capable of classifying different human activities with an accuracy level of 98%, where Doppler signatures diminish considerably, providing insufficient information for classification. Verification of the proposed classification algorithm based on dual micro-motion signatures is also performed using a real radar test dataset of different human walking patterns, and a classification accuracy level of approximately 90% is achieved.

Radar Human Activity Recognition with an Attention-Based Deep Learning Network

Radar-based human activity recognition (HAR) provides a non-contact method for many scenarios, such as human-computer interaction, smart security, and advanced surveillance with privacy protection. Feeding radar-preprocessed micro-Doppler signals into a deep learning (DL) network is a promising approach for HAR. Conventional DL algorithms can achieve high performance in terms of accuracy, but the complex network structure causes difficulty for their real-time embedded application. In this study, an efficient network with an attention mechanism is proposed. This network decouples the Doppler and temporal features of radar preprocessed signals according to the feature representation of human activity in the time-frequency domain. The Doppler feature representation is obtained in sequence using the one-dimensional convolutional neural network (1D CNN) following the sliding window. Then, HAR is realized by inputting the Doppler features into the attention-mechanism-based long short-term memory (LSTM) as a time sequence. Moreover, the activity features are effectively enhanced using the averaged cancellation method, which improves the clutter suppression effect under the micro-motion conditions. Compared with the traditional moving target indicator (MTI), the recognition accuracy is improved by about 3.7%. Experiments based on two human activity datasets confirm the superiority of our method compared to traditional methods in terms of expressiveness and computational efficiency. Specifically, our method achieves an accuracy close to 96.9% on both datasets and has a more lightweight network structure compared to algorithms with similar recognition accuracy. The method proposed in this article has great potential for real-time embedded applications of HAR.

Radar-based human activity recognition with adaptive thresholding towards resource constrained platforms

Radar systems are increasingly being employed in healthcare applications for human activity recognition due to their advantages in terms of privacy, contactless sensing, and insensitivity to lighting conditions. The proposed classification algorithms are however often complex, focusing on a single domain of radar, and requiring significant computational resources that prevent their deployment in embedded platforms which often have limited memory and computational resources. To address this issue, we present an adaptive magnitude thresholding approach for highlighting the region of interest in the multi-domain micro-Doppler signatures. The region of interest is beneficial to extract salient features, meanwhile it ensures the simplicity of calculations with less computational cost. The results for the proposed approach show an accuracy of up to 93.1% for six activities, outperforming state-of-the-art deep learning methods on the same dataset with an over tenfold reduction in both training time and memory footprint, and a twofold reduction in inference time compared to a series of deep learning implementations. These results can help bridge the gap toward embedded platform deployment.

Indoor human detection based on micro-Doppler features in the presence of interference from moving clutter sources

In this paper, to address the problem of detecting the presence of human in indoor environments in the presence of moving clutter sources, an indoor human detection method that utilizes random forest to process micro-Doppler signatures and a single pair of TX/RX unit is proposed. In contrast to most of the existing methods that use both distance information and micro-Doppler information assuming no interference from moving clutter sources (window curtains, blinds, table fans, etc.), our proposed method relies only on micro-Doppler information for human detection in indoor environments with curtain and fan interferences. Based on our time–frequency analyses on the measured radar data, seven features, i.e., the mean and standard deviation of the doppler centroid, the mean and standard deviation of the span of envelopes, the silhouette size, the positive peak values, and the peak spread, are extracted from spectrograms. These features are fed into a random forest classifier for categorizing the state of a room into one of the five scenarios considered in this work, namely (1) a person entering the room, (2) a person leaving the room, (3) interference from curtain/blind, (4) interference from fan, and (5) an empty room. The proposed system has been validated using real-world experiments and be able to deliver an accuracy of 97.5% in classifying the scenarios.

Classification of flying object based on radar data using hybrid Convolutional Neural Network-Memetic Algorithm

In the last decade, the low cost and easy availability of Unmanned Aerial Vehicles (UAVs) have led to their enormous use in modern society, which leads to privacy and security issues. To keep an eye on the intruder UAV in the restricted area, it needs to classify the other flying objects, such as helicopters, birds, etc. Hence, this work is taken up by considering the Micro-Doppler Signature (MDS) of the flying objects from the different configurations of radar antenna array such as Uniform Linear Array (ULA) and Uniform Rectangular Array (URA). In order to obtain the MDS from the intruder UAV, proper positioning or configuration of the radar antenna array is needed to avoid performance degradation due to the large Angle of Arrival (AoA) of the received signal. A novel Hybrid Convolutional Neural Network-Memetic algorithm is proposed to classify the flying object, which is evaluated for both MDS data collected from the HB100 radar set-up by varying configurations and Real Doppler RAD-DAR (RDRD) existing dataset.

CW coherent detection lidar for micro-Doppler sensing and raster-scan imaging of drones.

We demonstrate a continuous-wave (CW) coherent detection lidar (CDL) capable of detecting micro-Doppler (propeller) signatures and acquiring raster-scan images of small unmanned aerial systems/vehicles (UAS/UAV). The system uses a narrow-linewidth 1550 nm CW laser and takes advantage of mature and low-cost fiber-optics components from the telecommunications industry. Using either collimated or focused probe beam geometry, lidar based detection of characteristic periodic motions of drone propellers up to a remote distance of 500 m has been achieved. Furthermore, by raster scanning a focused CDL beam with a galvo-resonant mirror beamscanner, two-dimensional images of flying UAVs up to 70 m range were obtained. Each pixel of the raster-scan images provides both lidar return signal amplitude and target radial speed information. The raster-scan images obtained up to 5 frames per second make it possible to discriminate various UAV types based on their profile and even resolve the presence of payloads. With feasible improvements, the anti-drone lidar is a promising alternative to expensive EO/IR and active SWIR cameras used in counter-UAV systems.

Polarization Scattering Matrix and Doppler Joint Estimation Based on Multichannel Spectrum Interpolation Clean

Polarization and micro-Doppler signatures are widely used for target detection and recognition in harsh sensing environments. However, accurately estimating polarization scattering matrices and Doppler frequencies of scattering centers remains challenging. This paper incorporates the multi-channel spectrum interpolation with the CLEAN algorithm. The proposed algorithm can estimate the Doppler frequencies and scattering matrices of target scattering centers from fully-polarized data with high precision. Compared with the traditional detection-after-imaging workflow, the proposed method takes an iterative suppression technique, which improves the estimation accuracy and reduces detection time. The effectiveness of the proposed method is verified based on the simulation and actual radar data. The estimation accuracy measured by polarized similarity is 99.9%, and the normalized root mean squared error of the estimated Doppler frequency is 4.8% in simulation.

Obfuscation of Human Micro-Doppler Signatures in Passive Wireless RADAR

When wireless communication signals impinge on a moving human they are affected by micro-Doppler. A passive receiver of the resulting signals can calculate the spectrogram that produces different signatures depending on the human activity. This constitutes a significant privacy breach when the human is unaware of it. This paper presents a methodology for preventing this when we want to do so by injecting into the transmitted signal frequency variations that obfuscate the micro-Doppler signature. We assume a system that uses orthogonal frequency division multiplexing (OFDM) and a passive receiver that estimates the spectrogram based on the instantaneous channel state information (CSI). We analyze the impact of our approach on the received signal and we propose two strategies that do not affect the demodulation of the digital communication signal at the intended receiver. To evaluate the performance of our approach we use an IEEE 802.11-based OFDM system and realistic human signal reflection models.

Radar-Based Noninvasive Person Authentication Using Micro-Doppler Signatures and Generative Adversarial Network

Radar-Based Noninvasive Person Authentication Using Micro-Doppler Signatures and Generative Adversarial Network

Person Identification Based on Fine-grained Micro-Doppler Signatures and UWB radar

Person Identification Based on Fine-grained Micro-Doppler Signatures and UWB radar

Editorial: RSN Editorial 2023

It is a pleasure to report that the Premium Award for the best paper published in the journal in 2020/21 is made to Samiur Rahman and Duncan Robertson of the University of St Andrews, Scotland, for their paper Classification of drones and birds using convolutional neural networks applied to radar micro-Doppler spectrogram images, which was published in the May 2020 issue, (Vol. 14 No. 5, pp. 653–661). Drones are becoming more and more widespread in both civil and military operations. It is necessary to be able to detect and classify these targets reliably, and radar is one of the most widely used sensors for the purpose. An important part of this involves distinguishing between drones and birds, which is complicated by the fact that birds and drones have comparable radar cross sections and travel at comparable speeds. However, the micro-Doppler modulation due to the flapping of wings of a bird or the rotation of propeller or rotor blades of a drone are significantly different, so provides a means of solving the problem. The paper describes and demonstrates a classification method based on Convolutional Neural Networks (CNNs) to recognise the features of the micro-Doppler signatures. Experimental data was gathered using two FMCW radars, one operating at 24 GHz and one at 94 GHz, at a local falconry. Excellent results were obtained, with classification accuracies better than 94% and in some cases very close to 100%. The paper is judged to be outstanding because it represents a substantial amount of work—both theoretical and experimental, because of its excellent and significant results, and because of the clarity of its writing. We warmly congratulate the authors on this award. The names of the members of the Editorial Board are listed on the journal page of the Wiley Online Library https://ietresearch.onlinelibrary.wiley.com/journal/17518792; the members are distinguished researchers who represent the full scope of the journal, and they come from all over the world. They help with reaching decisions on submitted papers, encouraging authors to submit their work to the journal, and proposing topics for Special Issues and Special Sections. Several have now reached the end of their term of appointment, and we thank them for their service over many years. We have also appointed a number of new members, and we welcome them to their task and look forward to their inputs. Finally, we express our gratitude to the reviewers for their time, expertise and hard work in refereeing papers and maintaining the reputation of the journal, both for quality and for rapid publication. This is an essential part of the publication process, but necessarily the reviewers must remain anonymous. This editorial is one place where we can acknowledge their contribution and record our thanks to them. Data sharing not applicable to this article as no datasets were generated or analysed during the current study.