Optimization and Performance Enhancement of Gesture Recognition Algorithm Based on FMCW Millimeter-Wave Radar

Gesture recognition plays an increasingly important role as the requirements of intelligent systems for human-computer interaction methods increase.To improve the accuracy of the millimeter-wave radar gesture detection algorithm with limited computational resources,this study improves the detection performance in terms of optimized features and interference filtering.The accuracy of the algorithm is improved by refining the combination of gesture features using a self-constructed dataset,and biometric filtering is introduced to reduce the interference of inanimate object motion.Finally,experiments demonstrate the effectiveness of the proposed algorithm in both mitigating interference from inanimate objects and accurately recognizing gestures.Results show a notable 93.29%average reduction in false detections achieved through the integration of biometric filtering into the algorithm’s interpretation of target movements.Additionally,the algorithm adeptly identifies the six gestures with an average accuracy of 96.84%on embedded systems.

Multiscale Feature Fusion for Gesture Recognition Using Commodity Millimeter-Wave Radar

Gestures are one of the most natural and intuitive approach for human-computer interaction.Compared with traditional camera-based or wearable sensors-based solutions,gesture recognition using the millimeter wave radar has attracted growing attention for its characteristics of contact-free,privacy-preserving and less environmentdependence.Although there have been many recent studies on hand gesture recognition,the existing hand gesture recognition methods still have recognition accuracy and generalization ability shortcomings in shortrange applications.In this paper,we present a hand gesture recognition method named multiscale feature fusion(MSFF)to accurately identify micro hand gestures.In MSFF,not only the overall action recognition of the palm but also the subtle movements of the fingers are taken into account.Specifically,we adopt hand gesture multiangle Doppler-time and gesture trajectory range-angle map multi-feature fusion to comprehensively extract hand gesture features and fuse high-level deep neural networks to make it pay more attention to subtle finger movements.We evaluate the proposed method using data collected from 10 users and our proposed solution achieves an average recognition accuracy of 99.7%.Extensive experiments on a public mmWave gesture dataset demonstrate the superior effectiveness of the proposed system.

Co-Sharing Waveform Design for Millimeter-Wave Radar Communication Systems

Millimeter-wave(mmWave)radar communication has emerged as an important technique for future wireless systems.However,the interference between the radar signal and communication data is the main issue that should be considered for the joint radar communication system.In this paper,a co-sharing waveform(CSW)is proposed to achieve communication and radar sensing simultaneously.To eliminate the co-interference between the communication and sensing signal,signal splitting and processing methods for communication data demodulation and radar signal processing are given respectively.Simulation results show that the bit error rate(BER)of CSW is close to that of the pure communication waveform.Moreover,the proposed CSW can achieve better performance than the existing waveforms in terms of range and velocity estimation.

Probabilistic modeling of multifunction radars with autoregressive kernel mixture network

The task of modeling and analyzing intercepted multifunction radars(MFRs)pulse trains is vital for cognitive electronic reconnaissance.Existing methodologies predominantly rely on prior information or heavily constrained models,posing challenges for non-cooperative applications.This paper introduces a novel approach to model MFRs using a Bayesian network,where the conditional probability density function is approximated by an autoregressive kernel mixture network(ARKMN).Utilizing the estimated probability density function,a dynamic programming algorithm is proposed for denoising and detecting change points in the intercepted MFRs pulse trains.Simulation results affirm the proposed method's efficacy in modeling MFRs,outperforming the state-of-the-art in pulse train denoising and change point detection.

A Single-Board Integrated Millimeter-Wave Asymmetric Full-Digital Beamforming Array for B5G/6G Applications

In this article,a single-board integrated millimeter-wave(mm-Wave)asymmetric full-digital beamforming(AFDBF)array is developed for beyond-fifth-generation(B5G)and sixth-generation(6G)communications.The proposed integrated array effectively addresses the challenge of arranging a large number of ports in a full-digital array by designing vertical connections in a three-dimensional space and successfully integrating full-digital transmitting(Tx)and receiving(Rx)arrays independently in a single board.Unlike the traditional symmetric array,the proposed asymmetric array is composed of an 8×8 Tx array arranged in a square shape and an 8+8 Rx array arranged in an L shape.The center-to-center distance between two adjacent elements is 0.54k0 for both the Tx and Rx arrays,where k0 is the free-space wavelength at 27 GHz.The proposed AFDBF array possesses a more compact structure and lower system hardware cost and power consumption compared with conventional brick-type full-digital arrays.In addition,the energy efficiency of the proposed AFDBF array outperforms that of a hybrid beamforming array.The measurement results indicate that the operating frequency band of the proposed array is 24.25–29.50 GHz.An eight-element linear array within the Tx array can achieve a scanning angle ranging from-47°to+47°in both the azimuth and the elevation planes,and the measured scanning range of each eight-element Rx array is–45°to+45°.The measured maximum effective isotropic radiated power(EIRP)of the eight-element Tx array is 43.2 dBm at 28.0 GHz(considering the saturation point).Furthermore,the measured error vector magnitude(EVM)is less than 3%when 64-quadrature amplitude modulation(QAM)waveforms are used.

Non-LOS target localization via millimeter-wave automotive radar

This paper considers the non-line-of-sight(NLOS)vehicle localization problem by using millimeter-wave(MMW)automotive radar.Several preliminary attempts for NLOS vehicle detection are carried out and achieve good results.Firstly,an electromagnetic(EM)wave NLOS multipath propagation model for vehicle scene is established.Subsequently,with the help of available multipath echoes,a complete NLOS vehicle localiza-tion algorithm is proposed.Finally,simulation and experimental results validate the effectiveness of the established EM wave propagation model and the proposed NLOS vehicle localization algorithm.

Automatic Identification of Clear-Air Echoes Based on Millimeter-wave Cloud Radar Measurements

Millimeter-wave cloud radar(MMCR)provides the capability of detecting the features of micro particles inside clouds and describing the internal microphysical structure of the clouds.Therefore,MMCR has been widely applied in cloud observations.However,due to the influence of non-meteorological factors such as insects,the cloud observations are often contaminated by non-meteorological echoes in the clear air,known as clear-air echoes.It is of great significance to automatically identify the clear-air echoes in order to extract effective meteorological information from the complex weather background.The characteristics of clear-air echoes are studied here by combining data from four devices:an MMCR,a laser-ceilometer,an L-band radiosonde,and an all-sky camera.In addition,a new algorithm,which includes feature extraction,feature selection,and classification,is proposed to achieve the automatic identification of clear-air echoes.The results show that the recognition algorithm is fairly satisfied in both simple and complex weather conditions.The recognition accuracy can reach up to 95.86%for the simple cases when cloud echoes and clear-air echoes are separate,and 88.38%for the complicated cases when low cloud echoes and clear-air echoes are mixed.

Application of X-band Polarimetric Phased-array Radars in Quantitative Precipitation Estimation

The performance of different quantitative precipitation estimation(QPE) relationships is examined using the polarimetric variables from the X-band polarimetric phased-array radars in Guangzhou,China.Three QPE approaches,namely,R(ZH),R(ZH,ZDR) and R(KDP),are developed for horizontal reflectivity,differential reflectivity and specific phase shift rate,respectively.The estimation parameters are determined by fitting the relationships to the observed radar variables using the T-matrix method.The QPE relationships were examined using the data of four heavy precipitation events in southern China.The examination shows that the R(ZH) approach performs better for the precipitation rate less than 5 mm h-1, and R(KDP) is better for the rate higher than 5 mm h-1, while R(ZH,ZDR) has the worst performance.An adaptive approach is developed by taking the advantages of both R(ZH) and R(KDP) approaches to improve the QPE accuracy.

Millimeter-wave LFMCW radar water surface detection experiment and its imaging algorithm

A millimeter-wave linear frequency modulated continuous wave(LFM CW)radar is applied to water surface detection.This paper presents the experiment and imaging algorithm.In imaging processing,water surface texture can hardly be seen in the results obtained by traditional imaging algorithm.To solve this problem,we propose a millimeter-wave LFMCW radar imaging algorithm for water surface texture.Different from the traditional imaging algorithm,the proposed imaging algorithm includes two improvements as follows:Firstly,the interference from static targets is removed through a frequency domainfilter;Secondly,the multiplicative noises are reduced by the maximum likelihood estimation method,which is used to estimatethe azimuth spectrum parameters to calculate the energy of water surface echo.Final results show that the proposed algorithmcan obtain water surface texture,which means that the proposed algorithm is superior to the traditional imaging algorithm.

Towards Converged Millimeter-Wave/Terahertz Wireless Communication and Radar Sensing

Converged communication and radar sensing systems have attained increasing attention in recent years.The development of converged radar-data systems is reviewed,with a special focus on millimeter/terahertz systems as a promising trend.Firstly,we present historical development and convergence technology concept for communication-radar systems,and highlight some emerging technologies in this area.We then provide an updated and comprehensive survey of several converged systems operating in different microwave and millimeter frequency bands,by providing some selective typical communication and radar sensing systems.In this part,we also summarize and compare the system performance in terms of maximum range/range resolution for radar mode and Bit Error Rate(BER)/wireless distance for communication mode.In the last section,the convergence of millimeter/terahertz communication-radar system is concluded by analyzing the prospect of millimeter-wave/terahertz technologies in providing ultrafast data rates and high resolution for our smart future.

A 37 GHz Millimeter-Wave Antenna Array for 5G Communication Terminals

This work presents,design and specific absorption rate(SAR)analysis of a 37GHz antenna,for 5th Generation(5G)applications.The proposed antenna comprises of 4-elements of rectangular patch and an even distribution.The radiating element is composed of copper material supported by Rogers RT5880 substrate of thickness,0.254 mm,dielectric constant(εr),2.2,and loss tangent,0.0009.The 4-elements array antenna is compact in size with a dimension of 8mm×20mm in length and width.The radiating patch is excited with a 50 ohms connector i.e.,K-type.The antenna resonates in the frequency band of 37 GHz,that covers the 5G applications.The antenna behavior is studied both in free space and in the proximity of the human body.Three models of the human body,i.e.,belly,hand,and head(contain skin,fat,muscles,and bone)are considered for on-body simulations.At resonant frequency,the antenna gives a boresight gain of 11.6 dB.The antenna radiates efficiently with a radiated efficiency of more than 90%.Also,it is observed that the antenna detunes to the lowest in the proximity of the human body,but still a good impedance matching is achieved considering the−10 dB criteria.Moreover,SAR is also being presented.The safe limit of 2 W/kg for any 10 g of biological tissue,specified by the European International Electro Technical Commission(IEC)has been considered.The calculated values of SAR for human body models,i.e.,belly,hand and head are 1.82,1.81 and 1.09 W/kg,respectively.The SAR values are less than the international recommendations for the three models.Furthermore,the simulated and measured results of the antenna are in close agreement,which makes it,a potential candidate for the fifth-generation smart phones and other handheld devices.

Modulated-ISRJ rejection using online dictionary learning for synthetic aperture radar imagery

In electromagnetic countermeasures circumstances,synthetic aperture radar(SAR)imagery usually suffers from severe quality degradation from modulated interrupt sampling repeater jamming(MISRJ),which usually owes considerable coherence with the SAR transmission waveform together with periodical modulation patterns.This paper develops an MISRJ suppression algorithm for SAR imagery with online dictionary learning.In the algorithm,the jamming modulation temporal properties are exploited with extracting and sorting MISRJ slices using fast-time autocorrelation.Online dictionary learning is followed to separate real signals from jamming slices.Under the learned representation,time-varying MISRJs are suppressed effectively.Both simulated and real-measured SAR data are also used to confirm advantages in suppressing time-varying MISRJs over traditional methods.

Comparison of Liquid Water Content Retrievals for Airborne Millimeter-Wave Radar with Different Particle Parameter Schemes

In the application of the physical iterative method to retrieve millimeter-wave radar liquid water content(LWC)and liquid water path(LWP),particle parameter scheme is the main factor affecting retrieval performance.In this paper,synchronous measurements of an airborne millimeter-wave radar and a hot-wire probe in stratus cloud are used to compare the LWC retrievals of the oceanic and continental particle parameter scheme with diameter less than 50μm and the particle parameter scheme with diameter less than 500μm and 1500μm(scheme 1,scheme 2,scheme 3,and scheme4,respectively).The results show that the particle parameter scheme needs to be selected according to the reflectivity factor when using the physical iterative method to retrieve the LWC and LWP.When the reflectivity factor is less than-30 d BZ,the retrieval error of scheme 1 is the minimum.When the reflectivity factor is greater than-30 d BZ,the retrieval error of scheme 4 is the minimum.Based on the reflectance factor value,the LWP retrievals of scheme 4 are closer to the measurements,the average relative bias is 5.2%,and the minimum relative bias is 4.4%.Compared with other schemes,scheme 4 seems to be more useful for the LWC and LWP retrieval of stratus cloud in China.

Analysis of the joint detection capability of the SMILE satellite and EISCAT-3D radar

The Solar wind Magnetosphere Ionosphere Link Explorer(SMILE)satellite is a small magnetosphere–ionosphere link explorer developed cooperatively between China and Europe.It pioneers the use of X-ray imaging technology to perform large-scale imaging of the Earth’s magnetosheath and polar cusp regions.It uses a high-precision ultraviolet imager to image the overall configuration of the aurora and monitor changes in the source of solar wind in real time,using in situ detection instruments to improve human understanding of the relationship between solar activity and changes in the Earth’s magnetic field.The SMILE satellite is scheduled to launch in 2025.The European Incoherent Scatter Sciences Association(EISCAT)-3D radar is a new generation of European incoherent scatter radar constructed by EISCAT and is the most advanced ground-based ionospheric experimental device in the high-latitude polar region.It has multibeam and multidirectional quasi-real-time three-dimensional(3D)imaging capabilities,continuous monitoring and operation capabilities,and multiple-baseline interferometry capabilities.Joint detection by the SMILE satellite and the EISCAT-3D radar is of great significance for revealing the coupling process of the solar wind–magnetosphere–ionosphere.Therefore,we performed an analysis of the joint detection capability of the SMILE satellite and EISCAT-3D,analyzed the period during which the two can perform joint detection,and defined the key scientific problems that can be solved by joint detection.In addition,we developed Web-based software to search for and visualize the joint detection period of the SMILE satellite and EISCAT-3D radar,which lays the foundation for subsequent joint detection experiments and scientific research.

A Survey of Gesture Recognition Using Frequency Modulated Continuous Wave Radar

With technology advances and human requirements increasing, human-computer interaction plays an important role in our daily lives. Among these interactions, gesture-based recognition offers a natural and intuitive user experience that does not require physical contact and is becoming increasingly prevalent across various fields. Gesture recognition systems based on Frequency Modulated Continuous Wave (FMCW) millimeter-wave radar are receiving widespread attention due to their ability to operate without wearable sensors, their robustness to environmental factors, and the excellent penetrative ability of radar signals. This paper first reviews the current main gesture recognition applications. Subsequently, we introduce the system of gesture recognition based on FMCW radar and provide a general framework for gesture recognition, including gesture data acquisition, data preprocessing, and classification methods. We then discuss typical applications of gesture recognition systems and summarize the performance of these systems in terms of experimental environment, signal acquisition, signal processing, and classification methods. Specifically, we focus our study on four typical gesture recognition systems, including air-writing recognition, gesture command recognition, sign language recognition, and text input recognition. Finally, this paper addresses the challenges and unresolved problems in FMCW radar-based gesture recognition and provides insights into potential future research directions.

A target parameter estimation method via atom-reconstruction in radar mainlobe jamming

Mainlobe jamming(MLJ)brings a big challenge for radar target detection,tracking,and identification.The suppression of MLJ is a hard task and an open problem in the electronic counter-counter measures(ECCM)field.Target parameters and target direction estimation is difficult in radar MLJ.A target parameter estimation method via atom-reconstruction in radar MLJ is proposed in this paper.The proposed method can suppress the MLJ and simultaneously provide high estimation accuracy of target range and angle.Precisely,the eigen-projection matrix processing(EMP)algorithm is adopted to suppress the MLJ,and the target range is estimated effectively through the beamforming and pulse compression.Then the target angle can be effectively estimated by the atom-reconstruction method.Without any prior knowledge,the MLJ can be canceled,and the angle estimation accuracy is well preserved.Furthermore,the proposed method does not have strict requirement for radar array construction,and it can be applied for linear array and planar array.Moreover,the proposed method can effectively estimate the target azimuth and elevation simultaneously when the target azimuth(or elevation)equals to the jamming azimuth(or elevation),because the MLJ is suppressed in spatial plane dimension.

Anti-swarm UAV radar system based on detection data fusion

There is a growing body of research on the swarm unmanned aerial vehicle(UAV)in recent years,which has the characteristics of small,low speed,and low height as radar target.To confront the swarm UAV,the design of anti-UAV radar system based on multiple input multiple output(MIMO)is put forward,which can elevate the performance of resolution,angle accuracy,high data rate,and tracking flexibility for swarm UAV detection.Target resolution and detection are the core problem in detecting the swarm UAV.The distinct advantage of MIMO system in angular accuracy measurement is demonstrated by comparing MIMO radar with phased array radar.Since MIMO radar has better performance in resolution,swarm UAV detection still has difficulty in target detection.This paper proposes a multi-mode data fusion algorithm based on deep neural networks to improve the detection effect.Subsequently,signal processing and data processing based on the detection fusion algorithm above are designed,forming a high resolution detection loop.Several simulations are designed to illustrate the feasibility of the designed system and the proposed algorithm.

Overview of radar detection methods for low altitude targets in marine environments

In this paper,a comprehensive overview of radar detection methods for low-altitude targets in maritime environments is presented,focusing on the challenges posed by sea clutter and multipath scattering.The performance of the radar detection methods under sea clutter,multipath,and combined conditions is categorized and summarized,and future research directions are outlined to enhance radar detection performance for low-altitude targets in maritime environments.

Efficient 2-D MUSIC algorithm for super-resolution moving target tracking based on an FMCW radar

Frequency modulated continuous wave(FMCW)radar is an advantageous sensor scheme for target estimation and environmental perception.However,existing algorithms based on discrete Fourier transform(DFT),multiple signal classification(MUSIC)and compressed sensing,etc.,cannot achieve both low complexity and high resolution simultaneously.This paper proposes an efficient 2-D MUSIC algorithm for super-resolution target estimation/tracking based on FMCW radar.Firstly,we enhance the efficiency of 2-D MUSIC azimuth-range spectrum estimation by incorporating 2-D DFT and multi-level resolution searching strategy.Secondly,we apply the gradient descent method to tightly integrate the spatial continuity of object motion into spectrum estimation when processing multi-epoch radar data,which improves the efficiency of continuous target tracking.These two approaches have improved the algorithm efficiency by nearly 2-4 orders of magnitude without losing accuracy and resolution.Simulation experiments are conducted to validate the effectiveness of the algorithm in both single-epoch estimation and multi-epoch tracking scenarios.

Study on Quantitative Precipitation Estimation by Polarimetric Radar Using Deep Learning

Accurate radar quantitative precipitation estimation(QPE)plays an essential role in disaster prevention and mitigation.In this paper,two deep learning-based QPE networks including a single-parameter network and a multi-parameter network are designed.Meanwhile,a self-defined loss function(SLF)is proposed during modeling.The dataset includes Shijiazhuang S-band dual polarimetric radar(CINRAD/SAD)data and rain gauge data within the radar’s 100-km detection range during the flood season of 2021 in North China.Considering that the specific propagation phase shift(KDP)has a roughly linear relationship with the precipitation intensity,KDP is set to 0.5°km^(-1 )as a threshold value to divide all the rain data(AR)into a heavy rain(HR)and light rain(LR)dataset.Subsequently,12 deep learning-based QPE models are trained according to the input radar parameters,the precipitation datasets,and whether an SLF was adopted,respectively.The results suggest that the effects of QPE after distinguishing rainfall intensity are better than those without distinguishing,and the effects of using SLF are better than those that used MSE as a loss function.A Z-R relationship and a ZH-KDP-R synthesis method are compared with deep learning-based QPE.The mean relative errors(MRE)of AR models using SLF are improved by 61.90%,51.21%,and 56.34%compared with the Z-R relational method,and by 38.63%,42.55%,and 47.49%compared with the synthesis method.Finally,the models are further evaluated in three precipitation processes,which manifest that the deep learning-based models have significant advantages over the traditional empirical formula methods.