787 results about "Radar signal processing" patented technology

The invention provides a sleep monitoring model training method, a sleep monitoring method and equipment. The method is applied to radar signal processing. The method comprises the following steps: acquiring a data set S1 and a data set S2; a pure radar feature extractor M3 is trained by using a pre-trained teacher network model M2 and the data set S1, the teacher network model M2 fuses the radar data and the pulse wave data in the data set S1 and outputs fused feature data, and the pure radar feature extractor M3 performs feature extraction on the radar data in the data set S1 and outputs radar feature data; training a bimodal sleep monitoring model M4 and a pure radar modal sleep monitoring model M5 by using the data set S2, and determining first sleep stage and / or respiratory event information by a first recognition layer according to fusion feature data output by the teacher network model M2, and the second identification layer determines second sleep stage and / or respiratory event information according to the radar feature data output by the pure radar feature extractor M3. According to the invention, the sleep monitoring task is efficiently completed at low cost.

The invention belongs to the technical field of radar signal processing, and discloses a sea surface small target detection method based on optimized characteristic mode decomposition, which comprises the following steps: S1, acquiring to-be-detected signal data; s2, decomposing an original signal into a plurality of modal components by using FMD, and selecting an envelope spectrum entropy as a fitness function; s3, performing global optimization on the fitness function in the FMD by using an SOS algorithm; s4, introducing a PSO algorithm to carry out local optimization on key parameters of the FMD; s5, components with low envelope spectrum entropy values and correlation coefficients larger than a threshold value are reserved; s6, extracting an envelope spectrum entropy and frequency band energy ratio feature from the screened modal components, introducing a Gini coefficient as a weighting factor, and constructing a GSEBE joint feature; and S7, inputting the entropy value of the envelope spectrum into a DELM classifier with a controllable false alarm, and realizing target detection based on comparison between a predicted value and a judgment threshold. According to the invention, the capability of distinguishing sea clutters and target echoes is enhanced, and more accurate classification detection is realized.

The invention relates to the technical field of computer vision and radar perception, in particular to a ship intelligent detection system based on a convolutional neural network and radar signal processing, which comprises a ship three-dimensional perception modeling module, a visual feature hierarchical fusion module, a target detection module and an anomaly detection module. The system emphatically utilizes deep learning methods such as a convolutional neural network and the like to realize three-dimensional space modeling and visual feature extraction of a ship by a radar in a water area environment. And a layered adaptive fusion and mutual information enhancement mechanism is adopted. The end-to-end detection model introduces a spatial hierarchy weighting strategy, so that the object detection accuracy and interpretability under the conditions of multi-target density, shielding and dynamic change in a complex water scene are improved. The system realizes continuous tracking, anomaly detection and risk early warning of ship navigation behaviors based on space-time dynamic modeling. The whole scheme has high precision, strong robustness and adaptive ability, and can meet the requirements of ship detection and intelligent management and control in complex water area environments such as smart ports and water traffic.

The invention discloses a human body posture estimation method based on radar point cloud imaging and multi-dimensional feature fusion, and relates to the cross technical field of computer vision and radar signal processing, and the method comprises the following three key technical links: firstly, improving the target resolution through spatial energy distribution estimation; reconstructing target three-dimensional space distribution by using the positive correlation between radar signal energy and a target reflection area and adopting a least square estimation algorithm; secondly, constructing a structured multi-dimensional point cloud matrix, and converting sparse radar point cloud into high-information-density imaging representation through a distance-speed hierarchical sorting strategy; and finally, designing a multi-dimensional feature fusion attitude estimation network, integrating three-dimensional convolution, a multi-head attention mechanism and a gating circulation unit, and realizing collaborative extraction of spatio-temporal features. According to the method, the problems of sparse target features, noise sensitivity and poor universality in traditional millimeter wave radar attitude estimation are solved.

The invention belongs to the technical field of intelligent wireless sensing and radar signal processing, and particularly relates to a millimeter wave radar gesture recognition feature processing method, which is particularly suitable for scenes with environment interference (such as walking of others and static clutter), and specifically comprises the following steps: S1, preliminary filtering by a self-adaptive filter; s2, carrying out improved I CEEMDAN decomposition; s3, I MF component classification and processing; s4, signal reconstruction; the experimental result shows that the method provides a robust and efficient solution for gesture recognition, and can be widely applied to the fields of man-machine interaction, virtual reality, intelligent equipment control and the like.

The invention discloses an airborne radar system and method oriented to a signal transmitting device, and belongs to the technical field of airborne radar signal processing. Received radar task instructions are analyzed, target characteristic parameters, environment constraint conditions and performance indexes are extracted, and mapping relations between task requirements and transmitting waveforms, power and time sequence parameters are established; based on the mapping relation, the transmitting device resources are modeled into a power, frequency spectrum and time sequence three-dimensional state space, and the resource margin and the conflict risk are monitored and predicted in real time; matching a current task situation with a historical strategy library in combination with a resource state, and selecting a historical strategy with the highest similarity as a basic launching scheme; optimizing a resource allocation demand of the basic scheme according to a time sequence and a priority sequence, and introducing a resource buffer mechanism and dynamic priority adjustment to solve a multi-task resource conflict; based on real-time environment data, a basic scheme is decomposed into independently adjustable strategy units, and after optimization and recombination, a transmitting strategy adaptive to a specific scene is generated.

The invention discloses a semi-supervised LPI radar signal modulation identification system and method based on entropy perception pseudo labels, and relates to the technical field of radar signal processing and mode identification. The system comprises a preprocessing module, a multi-scale reconstruction enhancer, a classification backbone network and a semi-supervised training module. The multi-scale reconstruction intensifier is used for reconstructing dual-channel separation through high-frequency detail enhancement and a low-frequency structure and enhancing discriminative characteristics in a noise environment; the classification backbone network introduces an adaptive contraction unit to realize channel-level noise suppression; and the semi-supervised training module dynamically evaluates the uncertainty of the unlabeled samples by adopting an entropy sensing mechanism, and generates weighted pseudo labels to carry out consistency regularization training. The method realizes signal modulation identification based on the system. According to the method, the problem of feature shielding under the condition of low signal-to-noise ratio is solved, the dependence of the model on labeled data is reduced through a reliable pseudo label generation mechanism, and stable and efficient modulation identification can still be realized in a severe channel environment with scarce labeled data.

The invention provides a radar signal depth feature extraction method and system based on adversarial sample defense, electronic equipment and a storage medium, and relates to the technical field of radar signal processing.The radar signal depth feature extraction method comprises the steps that a spacecraft synthetic aperture radar original echo signal is collected and converted into a time-frequency feature map, and intra-pulse and inter-pulse features are extracted in parallel to generate a combined matrix; receiving a deception jamming signal by using a polarization radar group, generating a signal data body without polarization influence through complex coherent superposition, inputting the deception jamming signal and the signal data body into a feature decoupling adversarial network, and separating bullet micro-motion target feature data by means of mutual information maximization constraint; and finally, inputting into a multi-scale local attention module to extract multi-band characteristic components, performing adaptive weight coefficient fusion according to power entropy, performing polarization channel energy correction, and outputting anti-interference fingerprint characteristics with micro-Doppler characteristic enhancement, so that anti-interference processing of the spacecraft synthetic aperture radar signals can be realized. And warhead target anti-interference fingerprint features with micro-Doppler feature enhancement characteristics are effectively extracted.

The invention provides a high-precision angle estimation method for a distributed millimeter wave radar network, a medium and equipment, and belongs to the technical field of radar signal processing. According to the method, a large-aperture MIMO radar system is constructed based on a plurality of small millimeter wave radars, and an initial rough angle value of a target is obtained by using two-dimensional fast Fourier transform; accurately calculating the walking position of the distance spectrum peak value of each virtual antenna according to the distance resolution of the radar and the rough angle value, extracting all distance spectrum peak value data according to the walking position, and generating a one-dimensional angle vector; performing angle dimension fast Fourier transform on the one-dimensional angle vector to generate an angle spectrum; calculating a target angle estimation value according to the angle spectrum peak value position; the above process is iteratively circulated until the error between two adjacent angle estimation values is smaller than a preset threshold value. According to the method, different types of distributed millimeter wave radar network architectures can be flexibly adapted, the precision problem caused by target distance walking is effectively eliminated, and the angle estimation precision is greatly improved.

The invention relates to the technical field of radar signal processing, and discloses a complex ground reflection environment-oriented dual-path target detection method, which comprises the following steps of: performing quantile truncation and discretization processing on original range profile data, mapping a processed signal to a D-channel discrete feature space and generating a D-dimensional discrete feature matrix; the D-dimensional discrete feature matrix is input into a dual-channel parallel processing architecture, a CFAR adaptive detection module is adopted in a first path to suppress strong clutters to generate a first response matrix, and a false attention mechanism is adopted in a second path to enhance weak targets to generate a second response matrix; performing spatial alignment and weighting processing on the first response matrix and the second response matrix, and performing cross-domain confidence fusion to output a comprehensive response matrix; and carrying out fixed threshold binarization processing on the comprehensive response matrix based on a global threshold to obtain a target detection result. The method has both local gain compensation and global adaptive suppression, and can realize more robust detection of a weak target under a complex background.

The invention belongs to the technical field of radar signal processing, and particularly relates to a low-confidence small target detection method in radar echoes based on a hybrid architecture, and the method comprises the steps: firstly carrying out the spectrum symmetric movement and dimension recombination of radar echo data, and generating five-dimensional tensors [B, T, C, H, W] containing time sequence features; then the tensor is input into a detection model formed by cascading a Hurglass 3D module and a YOLOv8 network, the Hurglass 3D module extracts multi-scale spatial-temporal features through a structure of three-dimensional convolution down-sampling, bottleneck layer and three-dimensional transposition convolution up-sampling, and feature fusion is achieved through jump connection; and finally, target detection is completed through a backbone network, a neck network and a decoupling detection head of the YOLOv8 network. According to the invention, through spatio-temporal feature combined extraction and small target feature enhancement, the detection accuracy and the positioning precision of the low signal-to-noise ratio small target in radar echoes are effectively improved.

The invention is suitable for the technical field of radar signal processing, and provides a tomographic SAR super-resolution imaging method based on a structured sparse network, and the method comprises the steps: firstly obtaining multi-channel SAR observation data, constructing multi-channel observation vector MMV data in a data domain, and constructing a multi-pixel signal model corresponding to the MMV data based on a neighborhood pixel elevation consistency hypothesis. The method comprises the following steps: designing a kernel principal component analysis KPCA expansion network model, carrying out dimension reduction and enhancement on MMV data, introducing a norm compressed sensing model on the basis of the MMV data after dimension reduction and enhancement, solving the compressed sensing model by using an ADMM iterative algorithm, expanding the ADMM algorithm into a deep network, reconstructing an elevation spectrum, and obtaining an SAR image super-resolution three-dimensional reconstruction result. According to the method, the super-resolution performance and the solving efficiency of three-dimensional reconstruction can be effectively improved, and high-resolution three-dimensional reconstruction of a large-scale scene can be efficiently realized.

The application discloses an improved radar two-dimensional ambiguity resolution method for multi-targets, comprising the following steps: arranging point trail data after radar signal processing according to pulse repetition period from small to large; constructing a reference lookup table for resolving range ambiguity based on the arranged data; constructing a reference lookup table for resolving velocity ambiguity based on the arranged data; traversing all the frequency combinations of radar transmission, selecting N groups from M groups of frequency for multi-target pairing; obtaining a range pairing table based on the reference lookup table for resolving range ambiguity, calculating the standard deviation between rows of the range pairing table, and solving the real range of targets; obtaining a velocity pairing table based on the reference lookup table for resolving velocity ambiguity, calculating the standard deviation between rows of the velocity pairing table, and solving the real velocity of targets; and merging and processing output target data. The application can solve the problem that the traditional one-dimensional set method cannot meet the real-time requirement when the number of targets is large and the ambiguity is large.

The invention discloses a radar bird flight feature extraction and behavior analysis method, and relates to the technical field of radar signal processing. Comprising the following steps: based on airport radar track data, constructing a multi-dimensional kinematics track portrait by calculating instantaneous characteristics such as track straightness and horizontal turning rate; determining an optimal clustering number by using an elbow rule, and performing unsupervised clustering on the track portrait by using a K-Means algorithm to realize automatic mode division of flight behaviors; performing qualitative and quantitative analysis and cross validation on a clustering result by combining UMAP dimension reduction visualization and a typical three-dimensional track reconstruction technology, and deeply interpreting connotations of various behavior modes; the method is solidified into a modular system including data acquisition, feature calculation and algorithm processing, and automation of the analysis process is achieved. According to the method, bird situation analysis is improved from traditional target identification to understanding of flight intentions, and a new technical support is provided for precise evaluation and intelligent early warning of airport bird strike risks.

A non-contact real-time monitoring system of physiological signs based on millimeter-wave radar includes a millimeter-wave radar and multiple modules for processing radar signals. The millimeter-wave radar is configured to continuously transmit electromagnetic wave signals and simultaneously receive echo signals, perform frequency mixing processing on the echo signals to obtain an intermediate frequency signal, and process the intermediate frequency signal to obtain a radar four-dimensional data matrix. Human body physiological signs are monitored by analyzing body thoracic cavity micro-motion information in signals through the modules; a target echo is processed by adopting a constant false alarm rate detection algorithm, and invalid signals are filtered. A self-adaptive range cell selection algorithm based on short-time stability of respiratory signals is adopted to capture radar echoes reflecting physiological movement. Mixed human body physiological sign signals are processed by using a VMD algorithm, and key parameters in VMD are optimized by using a GWO algorithm.

The invention discloses a radar moving target parameter preprocessing method and system based on classification, and relates to the technical field of radar signal processing. The method comprises the following steps: constructing a signal model for a radar moving target needing to be identified and processed in a region of interest for simulation, and establishing a moving target signal data set; classifying according to the motion condition of the moving target in the moving target signal data set, preprocessing the moving target signal according to a classification result, and obtaining feature information in a corresponding category; taking the feature information as sample data, and training a classification model through the sample data to obtain a trained classification model; and inputting a to-be-processed moving target signal into the trained classification model for classification and identification, and obtaining a corresponding classification test result. The method can effectively reduce the calculation amount, improve the parameter estimation speed and save calculation resources.

The invention discloses a video-radar-radio frequency multi-source data fusion analysis system based on multi-modal perception and deep learning. A video stream preprocessing module adopts ACNN of an attention mechanism to carry out key frame extraction on a video stream and realize target detection and classification; the radar signal processing module completes radar echo signal feature learning and target trajectory prediction through fusion of VAE and LSTM; the radio frequency signal analysis module constructs an RFID tag association model based on GNN to extract identity information. The data quality of a video sensor, a radar sensor and a radio frequency sensor is dynamically evaluated through an AFM, the multi-source feature weight is autonomously adjusted to achieve high-robustness fusion, and space-time matching of a target track-identity is completed in combination with three Gaussian hybrid clustering and a double-dynamic mapping algorithm. According to the method, the problem of target mismatching caused by insufficient cross-modal feature interaction is effectively solved, the target recognition precision and identity binding continuity in a complex scene are improved, and the tracking stability is kept when the sensor data is dynamically degraded.

The invention relates to the technical field of radar signal processing, in particular to a ground penetrating radar reinforcing steel bar clutter suppression method based on physical constraints, and mainly solves the problem that a data set is difficult to obtain in an existing ground penetrating radar reinforcing steel bar clutter removal method based on deep learning. The method is an improved method based on the CUT network, the CUT network structure and a comparative learning mechanism determine that the requirement of the network for the data size of a data set is low, a waveform smoothness constraint is added on this basis, the clutter removal effect and generalization ability are improved by introducing physical prior, the physical constraint serves as a regularization item, and the regularization efficiency is improved. The problem that a CUT network is prone to model collapse under a small data set is solved. Finally, the improved model is compared with other models through different evaluation indexes, and the result shows that the improved model has more advantages.

The invention provides a radar signal anti-interference processing method and system based on a space-time attention mechanism. The method comprises the following steps: mapping an original horizontal polarization channel signal and an original vertical polarization channel signal into an interference suppression space, and generating a three-dimensional feature tensor comprising an amplitude component, a polarization phase difference component and an interference suppression residual component; according to the amplitude component, dividing a radar observation area into multiple layers of target blocks in a spatial dimension, and calculating a space-time association weight between adjacent layers of target blocks through a space-time attention mechanism; and according to the space-time correlation weight, screening out a plurality of target blocks meeting a preset continuous motion condition, and decoding a motion mode of the plurality of target blocks by using a long short-term memory network to generate an anti-interference target trajectory coordinate and a velocity vector. According to the method, the polarization characteristics and the space-time attention mechanism are fused, the anti-interference effect of radar signal processing in a strong interference environment is improved, and then the detection precision of the multi-target motion trail is improved.

The invention relates to the technical field of radar signal processing, and discloses a method for calibrating radar echo signals on a mobile platform, which comprises the following steps of: acquiring original echo signals of a radar on the mobile platform under different working conditions and preprocessing the original echo signals, acquiring multi-source IMU sensor and differential GPS information and performing time sequence fusion; carrying out platform motion parameter estimation on the preprocessed echo signal; and based on a preset reference signal model, performing feature extraction on the echo signal, and obtaining feature parameters for calibration through time-frequency processing and spatial domain adaptive filtering. Multi-source IMU (inertial measurement unit) data and differential GPS (global positioning system) data are fused to obtain six-degree-of-freedom continuous motion parameters of a mobile platform, and time synchronization and preprocessing of echo signals are combined to realize dynamic calibration of original radar echo signals. And the problem of amplitude, phase and Doppler frequency deviation of the echo signal caused by the attitude and the motion state of the mobile platform is solved.

The invention discloses a distributed radar data fusion method, which relates to the technical field of radar signal processing and multi-sensor information fusion, and comprises the following steps: arranging a plurality of radar nodes, configuring and transmitting 24GHz frequency-modulated continuous wave signals, receiving echo signals reflected by a target, and transmitting the echo signals to the radar nodes; according to the invention, the radar data fusion system comprises a data acquisition and local processing module, a space-time registration module, an anti-interference module and a track association and fusion module, and a radar data fusion mode and a corresponding analysis result are managed, visualized and stored, so that radar data fusion management can be realized through cloud management and control of the Internet of Things; the target sensing precision, the system resource efficiency, the environmental adaptability, the engineering practicability and the like are remarkably broken through, and the scheme also has strong engineering adaptability, supports heterogeneous sensor dynamic networking, embedded deployment and millisecond-level real-time response, has been successfully applied to scenes such as intelligent transportation and military early warning, and has a wide application prospect. The comprehensive performance comprehensively exceeds the prior art.

The invention discloses a narrowband-broadband intelligent switching method of a radar, and belongs to the field of radar signal processing. Single radar wide-narrow band function integration is achieved through resource multiplexing, self-adaptive triggering and dynamic parameter configuration, detection tracking in a default narrow band mode is achieved, switching is triggered based on manual instructions and double thresholds, hardware such as a common antenna and a T / R assembly is reconstructed through time division multiplexing and software parameters, the signal synchronization time is shortened, and the target tracking response delay time is shortened; double-radar collaborative design is not needed, and the design workload is reduced. According to the invention, double radars are combined into a single radar, the hardware cost is greatly reduced, and the method is suitable for unmanned aerial vehicle-mounted, vehicle-mounted and other space-limited scenes and military reconnaissance, civil security and protection and other tasks.

The invention relates to the technical field of biological radar signal processing, in particular to an FMCW radar-based heart beat interval estimation method, which comprises the following steps of: S1, converting a chest vibration echo phase time sequence obtained by irradiating a chest area of a monitored object by an FMCW radar into an acceleration time sequence by using a second-order time derivative; s2, dynamically mapping the center frequency and the wavelet order in a preset frequency analysis interval, constructing a self-adaptive wavelet dictionary, then executing multi-order wavelet time domain convolution operation on the acceleration time sequence by using the dictionary, and aggregating time-frequency energy distribution to generate a time-frequency energy diagram; and S3, performing a deconvolution operation reconstruction strategy based on an energy-guided multi-stage time-frequency feature screening technology and wavelet function conjugation, generating an approximate time domain signal of heart beat vibration, and completing heart beat information inversion. According to the method, the accuracy and robustness of IBI extraction can be effectively improved under the condition of low signal-to-noise ratio, so that stable monitoring of light and moderate HRV (heart rate variability) is supported.

The invention discloses a radar measurement method, device and equipment, a medium and a product, and relates to the technical field of radar signal processing. According to the method, a space angle is divided into a main lobe area and a side lobe area; determining a phase modulation strategy of twice observation of the radar; the phase modulation strategy comprises the steps that phases of a main lobe area are kept consistent in two observations, and the phase difference of a side lobe area is 180 degrees; according to a phase modulation strategy, determining a directional diagram of expected radiation of the array antenna in two times of observation, and optimizing a unit excitation weighting vector in two times of observation to obtain an optimized value of the unit excitation weighting vector; according to the optimization value, performing phase modulation on a transmitting signal of the array antenna; and coherent superposition is carried out on echo signals reflected by the target and received by the radar in two times of observation. On the premise that the array size is not changed, the anti-interference capability and the spatial resolution of the radar are remarkably improved, and the monitoring precision of the radar on parameters such as distance, speed, deformation and angle is effectively improved.

Disclosed herein are an FFT processor, an FFT computing method, a radar signal processing system-on-chip, an integrated circuit, and an electromagnetic wave sensor. The FFT processor comprises two cascaded FFT kernels, and the FFT processor has at least two operating modes among a large-point-number FFT mode, a pipeline mode and an independent parallel mode, wherein when the FFT processor is in the large-point-number FFT mode, the two FFT kernels are configured to decompose FFT of N points into two instances of FFT; when the FFT processor is in the pipeline mode, the former FFT kernel of the two cascaded FFT kernels is configured to perform distance FFT, and the latter FFT kernel of the two cascaded FFT kernels is configured to perform Doppler FFT; and when the FFT processor is in the independent parallel mode, the two FFT kernels are configured to independently process data of different channels in parallel.

The invention discloses a phased array radar signal processing system with deterministic delay, and relates to the technical field of semiconductors, the system carries out equal-length wiring design on a link in a hardware level, a timestamp marking circuit is embedded in the link, a core processing module carries out multi-channel data alignment based on timestamp marks in a software level, and the data alignment is carried out based on the timestamp marks. The multi-channel data transmission delay deviation is solved through elastic buffer control, the most reasonable buffer depth and release phase parameters are determined through calculation, and therefore the buffer delay is minimized, the system achieves deterministic minimum delay through software and hardware collaborative design, data alignment and quick response are guaranteed, and the system is suitable for large-scale popularization and application. Low-delay and high-consistency transmission and processing of multi-channel signals are achieved, so that high-precision pointing control of radar beams and time consistency of multi-target tracking are achieved, and the high-synchronization and low-jitter requirements of phased array radar for high-speed signal processing are met.

The invention discloses a radar signal classification method and system based on a quantum classical hybrid convolutional neural network, and belongs to the technical field of quantum calculation and signal processing. According to the scheme, the classic radar signals are sequentially subjected to preprocessing, quantum phase encoding, quantum convolution feature extraction, quantum measurement and classic convolution neural network classification, and high-precision classification of the radar signals is achieved. According to the method, the parallel advantage of quantum calculation on high-dimensional feature extraction and the robustness of a classic neural network on classification decision are fully utilized, the classification accuracy and the anti-noise capability are remarkably improved, and the method is suitable for radar signal processing tasks in a complex environment.

The invention discloses a weather radar meteorological echo and non-meteorological echo identification system, and belongs to the technical field of meteorological radar signal processing. The method comprises the following steps: acquiring radar original data containing reflectivity factors, radial velocity and spectral width, and generating a three-dimensional feature matrix through format standardization, combined noise removal, neighborhood interpolation filling and parameter normalization; constructing a sample set through professional labeling, consistency verification and multi-dimensional data enhancement; a deep convolutional neural network containing a ResNet50 feature extraction module, a CBAM double attention module and a classification output module is constructed, and a binary cross entropy loss function, an Adam optimizer and an early stop regularization strategy are adopted for training optimization; to-be-recognized data is preprocessed and then input into the model, and a classification result and confidence are output. The method does not need manual feature design, significantly improves the recognition stability of echoes difficult to distinguish in a complex scene, adapts to different radars and regional environments, and meets the real-time processing requirements.

The invention provides a millimeter-wave radar personnel perception method based on a time-frequency domain and a deep CNN, and relates to the technical field of radar signal processing, and the method comprises the steps: carrying out the preprocessing, spectrogram conversion and enhancement of a millimeter-wave radar echo signal; spatial features are extracted by using depth separable convolution of a residual structure, time-frequency features are extracted by combining dual-tree complex wavelet transform and attention-enhanced cavity convolution, motion features are extracted through optical flow estimation and three-dimensional convolution, and the three features are adaptively fused; the method comprises the following steps: constructing a dynamic spatio-temporal reasoning network, obtaining key spatio-temporal features by using a recurrent neural tensor network, a non-local neural network and deformable convolution, extracting multi-scale features and performing adversarial feature alignment, and completing personnel target classification through a dynamic routing mechanism based on a capsule network. According to the method, clutter interference can be effectively suppressed, space, time frequency and motion information is fully utilized, accurate perception of personnel targets is realized, and the classification accuracy is improved.

An electronic device and a method for gesture recognition are disclosed. The electronic device includes a radar transceiver and a processor operably connected to the radar transceiver. The processor is configured to detect a triggering event. In response to detecting the triggering event, the processor is configured to transmit, via the radar transceiver, radar signals. The processor is also configured to identify a gesture from reflections of the radar signals received by the radar transceiver. The processor is further configured to determine whether the gesture is associated with the triggering event. Based on determining that the gesture is associated with the triggering event, the processor is configured to perform an action indicated by the gesture.