Method and system for recognizing human motion status through radar

Abstract

The present invention relates to the field of radar motion recognition technology, and specifically to a method and system for realizing human motion state recognition through radar, comprising the following steps: using a sensor to receive the echo signal of a millimeter-wave radar, analyzing the amplitude and phase changes of the signal, calculating the average value and standard deviation of the amplitude, comparing the received signal, recording the amplitude extreme points and phase mutation points, and obtaining the radar echo signal characteristics. In the present invention, by carefully analyzing the amplitude and phase changes of the radar echo signal, the execution process optimizes the monitoring of the human motion state. While extracting key signal features, the amplitude average value and standard deviation of the signal are calculated for continuous time periods, further improving the sensitivity and accuracy of signal processing. In addition, by analyzing the gradient value of the phase change and comparing the changes at adjacent time points, the method effectively identifies subtle changes in the human motion speed and greatly improves the ability to capture dynamic motion trajectories.

Description

Technical Field

[0001] The present invention relates to the field of radar motion recognition technology, and in particular to a method and system for realizing human motion state recognition by radar. Background Art

[0002] The field of radar motion recognition technology involves using radar systems to detect and identify the motion state of objects, especially the human body, in space. This technical field is mainly based on the transmission and reception of radar waves. By analyzing the changes in reflected waves, dynamic information such as the object's position, speed, and their changes is obtained. Radar motion recognition technology is widely used in security monitoring, health monitoring, interactive entertainment and other fields. The core content includes radar wave transmission modulation, echo signal capture, signal processing technology, and motion state analysis algorithm.

[0003] Among them, the method of realizing human motion state recognition through radar refers to using a specific type of radar equipment to emit electromagnetic waves and capture the changes in electromagnetic waves caused by human motion. The technical matters covered include the selection of radar waves, the design of transmitters and receivers, and the signal processing process for analyzing human motion characteristics. The specific method identifies the specific actions or overall motion state of the human body by analyzing the radar echo, and involves time-frequency analysis of the radar signal to extract motion information.

[0004] Existing technologies are inadequate for capturing rapid or subtle changes in motion, especially in motion recognition in multi-person environments and the accurate measurement of motion speed changes. As a result, they are unable to meet actual application needs in areas such as security monitoring and health monitoring that require high-precision monitoring. For example, quickly identifying specific movements in emergency situations or maintaining high-accuracy motion tracking in complex backgrounds become challenges, leading to misjudgments or missed detections in actual operations, affecting the overall performance and reliability of the system. Summary of the Invention

[0005] In order to solve the problem that the existing technology is insufficient in capturing fast or small changes in motion, especially in the obvious deficiencies in motion recognition and accurate measurement of motion speed changes in multi-person environments, which leads to the inability to meet actual application needs in fields such as security monitoring and health monitoring that require high-precision monitoring. For example, it is challenging to quickly identify specific actions in emergency situations or maintain high-accuracy motion tracking in complex backgrounds. In actual operations, it leads to misjudgments or missed detections, affecting the overall performance and reliability of the system. The embodiments of the present invention provide a method and system for realizing human motion state recognition by radar. The technical solution is as follows:

[0006] In one aspect, a method for realizing human motion state recognition by radar is provided, comprising the following steps:

[0007] S1: Use the sensor to receive the echo signal of the millimeter-wave radar, analyze the amplitude and phase changes of the signal, calculate the average and standard deviation of the amplitude, compare it with the received signal, record the amplitude extreme points and phase mutation points, and obtain the radar echo signal characteristics;

[0008] S2: Based on the radar echo signal characteristics, the phase information of the signal is segmented, the phase change gradient value is calculated, the gradient stability interval is analyzed, the human body motion trajectory is identified, the motion speed change is determined, and the motion pattern data is obtained;

[0009] S3: Based on the motion pattern data, extract the time points when the signal phase and amplitude are abnormal, identify the signal frequency components, compare the frequency and energy characteristics of the signal, determine the frequency pattern of the motion state, identify the key frequency characteristics, and obtain the key frequency identification result;

[0010] S4: Based on the key frequency recognition results, analyze the spectrum morphology differences, match the known frequency patterns, identify the spectrum characteristics during movement, classify the movement pattern, and obtain the movement state classification result;

[0011] S5: Based on the motion state classification result, calculate the motion change rate, analyze the violently fluctuating motion pattern, identify the change in echo signal intensity, judge the abnormality of human motion, and obtain the abnormal motion state indicator.

[0012] On the other hand, the radar echo signal characteristics include amplitude extreme points, phase mutation points and signal change amplitude; the motion pattern data include human motion trajectory, motion speed change rate and phase stability interval; the key frequency identification results include dominant frequency changes, energy distribution characteristics and frequency component differences; the motion state classification results include motion pattern matching degree, spectrum morphology difference and motion state category; the abnormal motion state indicators include static or accelerated abnormal conditions, multi-channel signal strength changes, and motion state change rate.

[0013] On the other hand, the steps of acquiring the radar echo signal characteristics are specifically as follows:

[0014] S101: Receive the millimeter-wave radar echo signal using a sensor, analyze the signal amplitude and phase information, calculate the signal amplitude mean and standard deviation within a continuous time period, compare the received real-time signal, identify the signal amplitude mutation interval, calculate the signal energy change rate, and obtain the signal amplitude change characteristics;

[0015] S102: Based on the signal amplitude change characteristics, analyze the phase change of the signal, compare the phase offsets at adjacent time points, analyze the continuity of the phase change, identify the cumulative offset trend of the phase change, determine the state of the echo signal, and obtain the phase offset characteristics;

[0016] S103: Calling the phase offset characteristics, synchronizing the signal segments with prominent signal amplitude and phase changes, calculating the rate of change of signal energy before and after the mutation point, determining the key change position in the echo signal, analyzing the extreme points of the echo signal amplitude and the phase turning points, and obtaining the radar echo signal characteristics.

[0017] On the other hand, the steps of acquiring the motion pattern data are specifically as follows:

[0018] S201: Based on the radar echo signal characteristics, segment the phase information in the continuous echo signal, calculate the phase change, screen the signal interval with abnormal phase change, calculate the average phase increment within the interval, and compare the phase change rate of each signal segment to obtain a phase change rate index;

[0019] S202: Calculate the signal phase amplitude range within a continuous time period based on the phase change rate indicator, compare the phase change directions of adjacent time windows, analyze the continuous change characteristics of the signal over time, identify the stable motion path of the human body, and obtain a stable motion trajectory;

[0020] S203: Calling the stable motion trajectory, analyzing the direction of human body movement, screening the time nodes of the motion trajectory direction change, determining the amplitude and duration of the trajectory direction adjustment, comparing the motion rates of adjacent trajectory segments, identifying the change of human body movement rhythm, recording the change range of movement direction and speed, and obtaining motion pattern data.

[0021] On the other hand, the phase increment mean within the calculation interval is calculated using the formula:

[0022]

[0023] And compare the phase change rate of each signal segment to obtain the phase change rate index;

[0024] in, Represents the mean phase increment within the signal interval, N represents the total number of sampling points within the selected signal interval, represents the phase increment of the i-th sampling point, Represents the phase standard deviation of the i-th sampling point, Represents the phase mean of the i-th sampling point.

[0025] On the other hand, the steps of obtaining the key frequency identification result are specifically as follows:

[0026] S301: Based on the motion pattern data, detecting phase and amplitude fluctuations of the echo signal, selecting time points with prominent change rates, calculating amplitude differences of continuous signals before and after the time points, analyzing the changing patterns of phase mutations, measuring the duration of signal fluctuations, selecting signal feature points with amplitude and phase mutations, and obtaining a signal fluctuation feature set;

[0027] S302: Calling the signal fluctuation feature set, extracting the echo signal at the corresponding time point, analyzing the amplitude change of the signal in the difference frequency segment, identifying the frequency components in the signal, calculating the rate of change of the frequency over time, determining the frequency offset trend between time points, analyzing the frequency distribution in adjacent time windows, and obtaining a frequency offset spectrum;

[0028] S303: Based on the frequency shift spectrum, analyze the energy density of each frequency interval, compare the energy proportion of each frequency band, screen the stable frequency area, identify the frequency characteristics in the normal motion state, determine the motion state matching relationship of the key frequency pattern, and obtain the key frequency identification result.

[0029] On the other hand, the steps of obtaining the motion state classification result are specifically as follows:

[0030] S401: Analyzing the spectrum morphology of the signal during human motion based on the key frequency recognition data, extracting the signal features corresponding to each frequency pattern, comparing the morphological differences of the signal waveforms, identifying the signal spectrum changes in each motion state, and obtaining a spectrum difference recognition result;

[0031] S402: Invoking the spectrum difference recognition result, comparing it with known frequency patterns, screening spectrum forms that meet the pattern characteristics, calculating the energy distribution ratio of each spectrum in the signal, analyzing the matching degree between each pattern, determining the corresponding relationship between each spectrum form and the human body movement state, and obtaining motion spectrum matching data;

[0032] S403: Call the motion spectrum matching data, analyze the proportion of motion pattern signals, screen the motion patterns with significant proportions, analyze the time duration of the corresponding patterns, compare the signal frequency changes between different motion states, determine the motion category to which the echo signal belongs, determine the motion pattern classification interval, and obtain the motion state classification result.

[0033] On the other hand, the energy distribution ratio of each spectrum in the signal is calculated using the formula:

[0034]

[0035] Analyze the matching degree between each pattern, determine the corresponding relationship between each spectrum form and human motion state, and obtain motion spectrum matching data;

[0036] Among them, E z Represents the energy distribution ratio of the zth spectrum in the signal, C zl represents the complex amplitude of the zth spectrum at the lth frequency point, u l represents the frequency value of the lth frequency point, and L represents the total number of frequency points.

[0037] On the other hand, the steps of obtaining the abnormal motion state indicator are specifically as follows:

[0038] S501: Based on the motion state classification result, calculate the motion state change speed in the continuous time window, calculate the state change duration, compare the motion state switching frequency with the difference time, determine the motion state fluctuation range, and generate the motion state dynamic characteristics;

[0039] S502: Invoking the dynamic characteristics of the motion state, analyzing the fluctuation of the motion state in the short term, counting the number of motion mode switches, determining the continuous stability of the motion mode, comparing the signal amplitudes in the motion state change intervals, calculating the signal energy gradient during the motion mode transition, and obtaining motion mode stability data;

[0040] S503: Call the motion pattern stability data, identify the signal strength changes of the multi-channel echo, analyze the echo energy distribution in each time period, screen the intervals with abnormal energy fluctuations, judge whether the human body is stationary or accelerating, and obtain the abnormal motion state indicator.

[0041] In another aspect, a system for recognizing a human body's motion state by using radar is provided. The system is applied to a method for recognizing a human body's motion state by using radar, comprising:

[0042] The feature extraction module uses a sensor to receive the echo signal of the millimeter-wave radar, analyzes the amplitude and phase changes of the signal, calculates the average and standard deviation of the amplitude, compares the received signal, records the amplitude extreme points and phase mutation points, and obtains the radar echo signal characteristics;

[0043] The motion pattern analysis module divides the phase information of the signal based on the characteristics of the radar echo signal, calculates the phase change gradient value, analyzes the gradient stability interval, identifies the human body motion trajectory, determines the motion speed change, and obtains motion pattern data;

[0044] The frequency feature recognition module extracts the time points of signal phase and amplitude abnormalities based on the motion pattern data, identifies the signal frequency components, compares the frequency and energy characteristics of the signal, determines the frequency pattern of the motion state, identifies the key frequency characteristics, and obtains the key frequency recognition results;

[0045] The spectrum matching and classification module analyzes the spectrum morphology differences based on the key frequency identification results, matches the known frequency patterns, identifies the spectrum characteristics during motion, classifies the motion patterns, and obtains the motion state classification results;

[0046] The abnormal motion state identification module calculates the motion change rate based on the motion state classification result, analyzes the violently fluctuating motion pattern, identifies the change in echo signal intensity, determines the abnormality of human motion, and obtains the abnormal motion state index.

[0047] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0048] By carefully analyzing the amplitude and phase changes of the radar echo signal, the execution process optimizes the monitoring of the human body's motion state. While extracting key signal features, the amplitude average and standard deviation of the signal are calculated for continuous time periods, further improving the sensitivity and accuracy of signal processing. In addition, by analyzing the gradient value of the phase change and comparing the changes at adjacent time points, this method effectively identifies subtle changes in the human body's motion speed and greatly improves the ability to capture dynamic motion trajectories. It not only improves the detail of signal analysis, but also enhances the system's adaptability and practical value to complex environments through the identification of abnormal motion states. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0050] Figure 1 It is a flow chart of the main steps of the present invention;

[0051] Figure 2 It is a system block diagram of the present invention. DETAILED DESCRIPTION

[0052] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0053] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as an "exemplary" in the present invention should not be interpreted as being preferred or advantageous over other embodiments or designs. Rather, the use of the word "exemplary" is intended to present concepts in a concrete manner. Furthermore, in the embodiments of the present invention, "and / or" can mean both or either of the two.

[0054] In the embodiments of the present invention, the terms "image" and "picture" may be used interchangeably. It should be noted that, when the distinction between them is not emphasized, their intended meanings are the same. The terms "of," "corresponding," and "corresponding" may be used interchangeably. It should be noted that, when the distinction between them is not emphasized, their intended meanings are the same.

[0055] In the embodiments of the present invention, sometimes a subscript such as W1 may be written as a non-subscript such as W1. When the difference is not emphasized, the meanings to be expressed are the same.

[0056] In order to make the technical problems, technical solutions and advantages to be solved by the present invention clearer, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0057] The embodiment of the present invention provides a method for realizing human motion state recognition by radar, such as Figure 1 As shown, the following steps are included:

[0058] S1: Use the sensor to receive the echo signal of the millimeter-wave radar, analyze the amplitude and phase changes of the echo signal, calculate the average and standard deviation of the amplitude in continuous time periods, compare it with the real-time received echo signal, screen the points of significant signal changes, identify key signal features, record the extreme points of the signal amplitude and the sudden change points of the phase, and obtain the radar echo signal characteristics;

[0059] S2: Based on the characteristics of radar echo signals, the phase information of continuous echo signals is segmented, the gradient value of phase change is calculated, the stable range of gradient change is analyzed, the continuous motion trajectory of the human body is identified, the phase changes at adjacent time points are compared, the changes in human motion speed are determined, and motion pattern data is obtained;

[0060] S3: Based on the motion pattern data, the time points at which the echo signal phase and amplitude change abnormally are extracted, the signal frequency components at the time points are identified, the frequency and energy characteristics of the signals at different time points are compared, the frequency patterns representing different motion states are determined, the key frequency characteristics are identified based on the energy distribution, the normal motion state of the human body is analyzed, and the key frequency identification results are obtained;

[0061] S4: Based on the key frequency identification results, analyze the differences in the spectral morphology of the signal under motion state, call the known frequency pattern, match it with each spectral morphology, identify the spectral characteristics of the signal when the human body is in motion, and classify the motion pattern according to the signal characteristics to obtain the motion state classification result;

[0062] S5: Based on the motion state classification results, calculate the motion state change rate between adjacent windows, analyze the motion pattern with short-term violent fluctuations, identify the signal intensity changes of multi-channel echoes, determine whether there are abnormal situations of human body movement being still or accelerating, and obtain the abnormal motion state index.

[0063] The characteristics of radar echo signals include amplitude extreme points, phase mutation points and signal change amplitude. The motion pattern data includes human motion trajectory, motion speed change rate and phase stability range. The key frequency identification results include dominant frequency changes, energy distribution characteristics and frequency component differences. The motion state classification results include motion pattern matching degree, spectrum morphology difference and motion state category. Abnormal motion state indicators include static or accelerated abnormal conditions, multi-channel signal strength changes, and motion state change rate.

[0064] The specific steps for obtaining radar echo signal features are as follows:

[0065] S101: Receive the millimeter-wave radar echo signal using a sensor, analyze the signal amplitude and phase information, calculate the signal amplitude mean and standard deviation within a continuous time period, compare the received real-time signal, identify the signal amplitude mutation interval, calculate the signal energy change rate, and obtain the signal amplitude change characteristics;

[0066] The signal is received using a 77GHz millimeter-wave radar module. The radar transmit power is set to 10dBm, the receive gain is set to 20dB, and the antenna is 2 meters away from the target object. The radar module decomposes the received echo signal into isotropic and orthogonal components through an I / Q mixer. The analog signal is converted to a digital signal using an analog-to-digital converter (ADC) with a sampling rate of 2.5MHz. The amplitude of the analyzed signal is calculated using the amplitude calculation formula: Where B(t) represents the instantaneous amplitude of the signal, X(t) represents the in-phase component of the received signal, and Y(t) represents the quadrature component of the received signal. The specific operation is as follows: During the reception of the echo signal, signal data is collected every 1ms, accumulating 1000 sampling points. The real-time amplitude mean and standard deviation are calculated every 50 data points using the sliding window method. The mean calculation formula is: The formula for calculating standard deviation is: Where P is the number of sampling points. 1000 sampling points are taken. The calculated mean represents the average amplitude of the signal within 1000 sampling periods. The standard deviation represents the degree of fluctuation in the signal amplitude. When compared with the received real-time signal, the amplitude mutation threshold is defined as twice the standard deviation of the amplitude mean. That is, when the real-time amplitude meets the following conditions, it is determined to be an amplitude mutation: or At 1000 sampling points, the signal energy change rate within the amplitude mutation interval is calculated. The energy calculation uses the following formula: The rate of change of energy is defined as: Among them, F before represents the energy of the 100 sampling points before the mutation point, F after It represents the energy of the 100 sampling points after the mutation point. When the energy change rate is greater than 10%, it is considered a significant mutation, and the signal amplitude change characteristics are obtained.

[0067] S102: Based on the signal amplitude change characteristics, analyze the phase change of the signal, compare the phase offsets at adjacent time points, analyze the continuity of the phase change, identify the cumulative offset trend of the phase change, determine the echo signal state, and obtain the phase offset characteristics;

[0068] The phase information of the received signal is obtained through I / Q demodulation, and the phase is calculated using the following formula: Compare the phase offsets at adjacent time points and set the phase offset to: Δθ q =θ q+1 -θ q , within 1000 sampling cycles, the sliding window method is used to calculate the phase change mean and standard deviation every 50 data points. The mean calculation formula is: The standard deviation is calculated as: To analyze the continuity of phase change, the phase change mutation threshold is defined as 2 times the standard deviation, that is: When the phase offset exceeds the mutation threshold for five consecutive sampling periods, it is determined to be a phase mutation, and the cumulative offset trend of the phase change is identified. The cumulative offset is: It is defined that when the cumulative offset exceeds 360 degrees, it is determined to be a phase reversal, the state of the echo signal is determined, and the phase offset characteristic is obtained.

[0069] S103: Invoke the phase offset characteristic, synchronize the signal segments with prominent signal amplitude and phase changes, calculate the rate of change of signal energy before and after the mutation point, determine the key change position in the echo signal, analyze the extreme value points of the echo signal amplitude and the phase turning point, and obtain the radar echo signal characteristics.

[0070] The signal amplitude and phase mutation segments are synchronized using the timestamp alignment method. Within the signal sampling period, the window length is set to 100 sampling points, and the signal energy change rate before and after the mutation point is defined as: Among them, F before represents the energy of the 100 sampling points before the mutation point, F after represents the energy of the 100 sampling points after the mutation point, and defines the energy change rate threshold as 10%, that is, when the change rate meets the following conditions, it is determined to be a mutation: K F >0.1 or K F <-0.1, determine the key change position in the echo signal, analyze the extreme points of amplitude and phase, the amplitude extreme point is defined as: Bmax =max(B(p)),B min =min(B(p)), the phase extreme point is defined as: θ max =max(θ(q)),θ min =min(θ(q)), determine the phase turning point, set the phase turning threshold to 30 degrees, and determine a phase turning point when the phase increment of five consecutive data points exceeds 30 degrees. Simultaneously analyze the positions of the amplitude extreme point and the phase turning point to determine the characteristics of the radar echo signal.

[0071] The specific steps for obtaining motion pattern data are as follows:

[0072] S201: Based on the radar echo signal characteristics, the phase information in the continuous echo signal is segmented, the phase change amount is calculated, the signal interval with abnormal phase change is screened, the phase increment mean within the interval is calculated, and the phase change rate of each signal segment is compared to obtain a phase change rate index;

[0073] Calculate the mean phase increment within the interval using the formula:

[0074]

[0075] And compare the phase change rate of each signal segment to obtain the phase change rate index;

[0076] in, Represents the mean phase increment within the signal interval, N represents the total number of sampling points within the selected signal interval, represents the phase increment of the i-th sampling point, Represents the phase standard deviation of the i-th sampling point, Represents the phase mean of the i-th sampling point;

[0077] The mean phase increment within the signal interval When calculating, Represents the phase increment of the i-th sampling point. This value is obtained by discrete sampling of the phase of the continuous echo signal. The calculation formula is as follows:

[0078]

[0079] in, and They represent the phase values ​​of the i-th and i-1-th sampling points respectively, and the phase values ​​are obtained by the radar echo signal acquisition device;

[0080] Phase standard deviation The calculation formula is as follows:

[0081]

[0082] in, Represents the phase value within a certain window interval, M represents the number of sampling points in the window, Represents the phase mean within the window, and the calculation formula is as follows:

[0083]

[0084] A radar echo signal sample collected by the data monitoring system contains N = 5 sampling points, and its phase values ​​are:

[0085] (unit: radians);

[0086] Calculate the phase increment:

[0087]

[0088] Phase mean:

[0089]

[0090] Phase standard deviation:

[0091]

[0092] Calculate the denominator:

[0093]

[0094] Calculate the normalized phase increment:

[0095]

[0096] Compute the mean phase increment:

[0097]

[0098] The result shows that the average phase increment within the signal interval is 0.24875 radians, which is used to measure the overall phase change trend of the echo signal.

[0099] S202: Based on the phase change rate indicator, calculate the signal phase amplitude range within a continuous time period, compare the phase change directions of adjacent time windows, analyze the continuous change characteristics of the signal over time, identify the stable motion path of the human body, and obtain a stable motion trajectory;

[0100] The signal phase change is set to θ(t), where t represents time. The signal data is collected at a sampling rate of 1000 Hz. The length of a single time window is set to 100 ms. Each time window contains 100 sampling points. The phase amplitude range is calculated using the sliding window method. The phase amplitude range is defined as the difference between the maximum phase and the minimum phase in the current window. The calculation formula is: Δθamp =θ max (t)-θ min (t), where θ max (t) and θ min (t) represents the maximum phase and minimum phase in the current window respectively. Assuming that the phase data in the current window is: θ = [10°, 12°, 15°, 9°, 8°, 14°, 11°, 13°, 16°, 17°], the maximum phase is θ max (t)=17°, the minimum phase is θ min (t) = 8°, the phase amplitude range is: Δθ amp =17°-8°=9°, compare the phase change direction of adjacent time windows, and define the phase change direction as: D θ (t)=sign(θ t+1 -θ t ), where the sign function is defined as: Assuming that the current adjacent phase data sequence is [10°, 12°, 15°, 9°, 8°], the phase change direction is: D θ (t) = [1, 1, -1, -1]. Analyze the continuous change characteristics of the signal over time. If the phase change direction remains consistent within 5 consecutive time windows, it is defined as a stable phase change state. If the phase change direction alternates within 3 consecutive time windows, it is defined as an unstable phase change state. Determine the trajectory change trend in the stable state and accumulate the phase change trend with 5 time windows as a period: If Θ trend >3 or Θ trend <-3, defined as a significant trend change, identifying the stable motion path of the human body and obtaining a stable motion trajectory.

[0101] S203: Calling a stable motion trajectory, analyzing the direction of human motion, screening the time nodes of the motion trajectory direction change, determining the amplitude and duration of the trajectory direction adjustment, comparing the motion rates of adjacent trajectory segments, identifying the changes in the human body's motion rhythm, recording the change range of motion direction and speed, and obtaining motion pattern data.

[0102] Define the phase change direction within the current time window as: D θ (t)=sign(θ t+1 -θ t ), the amplitude of trajectory direction adjustment is defined as the phase difference within adjacent time windows, and the calculation formula is: Δθ adjust =θ next -θ current, assuming that the data sequence of the current trajectory segment is: θ = [10°, 12°, 15°, 9°, 8°, 14°, 11°, 13°, 16°, 17°], between the third and fourth time windows, the phase adjustment amplitude is: Δθ adjust =9°-15°=-6°, the duration of direction adjustment is the number of adjacent window intervals, defined as: T θ =n×Δt, where n is the number of windows and Δt is the length of each window (100ms). If the direction adjustment duration is 3 windows, then: T θ =3×100ms=300ms. Comparing the motion rates of adjacent trajectory segments, the motion rate is defined as the phase change per unit time. The rate calculation formula is: Substitute the data: If the velocity change between adjacent trajectory segments exceeds 20%, it is defined as a sudden change in motion velocity, and the velocity change rate is defined as: Assuming that the rates of adjacent trajectory segments are [-20° / s, -24° / s], the rate change rate is: If the rate of change is greater than 20%, it is determined to be a significant rate change, and the change range of the movement direction and speed is recorded to obtain the movement pattern data.

[0103] The specific steps for obtaining key frequency identification results are:

[0104] S301: Based on the motion pattern data, detect the phase and amplitude fluctuations of the echo signal, select the time points with prominent change rates, calculate the amplitude differences of the continuous signals before and after the time points, analyze the change patterns of the phase mutation, measure the duration of the signal fluctuations, select the signal feature points of the amplitude and phase mutations, and obtain the signal fluctuation feature set;

[0105] The received echo signal is parsed by the I / Q demodulator to obtain the in-phase component U(τ) and the quadrature component V(τ). The phase calculation formula is: The amplitude calculation formula is: Filter the time points with prominent change rates and set the phase fluctuation rate to: The amplitude fluctuation rate is: Where Γτ is the time interval between adjacent sampling points, which is 1ms. The mutation threshold is set to the mean of the 100 data points before the current moment plus 2 times the standard deviation. The mutation threshold formula is defined as: in, and is the mean of the first 100 data points, δ ψ and δ W is the standard deviation, and is determined to be a mutation point when the following conditions are met: or Calculate the amplitude difference of the continuous signal before and after the time point. The amplitude difference is calculated as: ΓW=W after -W before , analyze the changing law of phase mutation and define the phase mutation rate as: The duration of signal fluctuation is measured. The fluctuation duration is defined as the time interval from the mutation point to the restoration of the stable state. The stable state is defined as the time point when the signal recovers to the range of ±1 times the standard deviation of the mean. The signal feature points of amplitude and phase mutations are screened to obtain the signal fluctuation feature set.

[0106] S302: Invoke the signal fluctuation feature set, extract the echo signal at the corresponding time point, analyze the amplitude change of the signal in the difference frequency segment, identify the frequency components in the signal, calculate the rate of change of the frequency over time, determine the frequency offset trend between time points, analyze the frequency distribution in adjacent time windows, and obtain a frequency offset spectrum;

[0107] The short-time Fourier transform (STFT) is used to analyze the amplitude change of the signal in the difference frequency band. The STFT transform formula is: Where G(g,τ) represents the complex form of the time-frequency signal, w(γ-τ) is the window function, and the Hanning window is selected. The window length is set to 100 ms, and the overlap rate is set to 50%. The amplitude change of the signal in the difference frequency segment is analyzed. The amplitude of the frequency component is extracted at intervals of 1 Hz frequency increments, and the frequency components in the signal are identified. The frequency change rate is defined as: Determine the frequency offset trend between time points. The frequency offset trend determination condition is defined as the consistent frequency change direction within five consecutive windows. If the following conditions are met, it is defined as a sudden change in the frequency offset trend: The frequency distribution in adjacent time windows is analyzed to obtain a frequency shift spectrum.

[0108] S303: Based on the frequency shift spectrum, analyze the energy density of each frequency interval, compare the energy proportion of each frequency band, screen the stable frequency area, identify the frequency characteristics in the normal motion state, determine the motion state matching relationship of the key frequency pattern, and obtain the key frequency identification result.

[0109] The energy density calculation formula is set as: Comparing the energy proportion of each frequency band, the frequency band energy proportion is defined as: Screening for stable frequency regions, defined as frequency intervals within five consecutive time windows where the frequency variation is less than 2Hz and the energy content exceeds 20%. Identifying frequency characteristics under normal motion conditions, determining the motion state matching relationship of key frequency patterns, setting the key frequency threshold range to frequency components between 40Hz and 70Hz, and determining that a key frequency pattern exists when the energy content exceeds 30% within this frequency interval, thereby obtaining key frequency identification results.

[0110] The specific steps for obtaining the motion state classification results are as follows:

[0111] S401: Analyze the spectrum morphology of the signal during human motion based on the key frequency recognition data, extract the signal features corresponding to each frequency pattern, compare the morphological differences of the signal waveforms, identify the signal spectrum changes in each motion state, and obtain spectrum difference recognition results;

[0112] The frequency characteristics of the received signal are extracted through short-time Fourier transform (STFT), and the spectral shape of the signal in the time ξ and frequency f dimensions is defined as: P(f,ξ)=|F(f,ξ)| 2 , where P(f,ξ) represents the power spectral density at time ξ and frequency f, and F(f,ξ) represents the complex spectrum of the signal. The signal features corresponding to each frequency mode are extracted, and the feature extraction formula is defined as: Among them, E k represents the eigenvalue of the kth frequency mode, W k (f) represents the weight function of the kth frequency mode, which is a normalized Gaussian distribution function and is defined as: Among them, μ k is the center frequency of the kth frequency mode, σ k is the standard deviation of the kth frequency mode, the center frequency range is set to 40 Hz to 70 Hz, and the standard deviation is 5 Hz. The extracted frequency mode eigenvalues ​​are processed by principal component analysis (PCA) method for dimensionality reduction, retaining more than 95% of the feature information. The waveform morphology differences under different frequency modes are compared, and the morphological difference is defined as: Among them, P k (ξ) represents the power spectrum density of the kth frequency mode at time ξ, The average power spectral density of the kth frequency mode is expressed. The morphological differences of different modes are compared, and the modes with morphological differences exceeding 1.5 times the standard deviation are screened out and judged as significant spectral differences, thus obtaining the spectral difference recognition results.

[0113] S402: Invoke the spectrum difference recognition results, compare with known frequency patterns, select spectrum forms that meet the pattern characteristics, calculate the energy distribution ratio of each spectrum in the signal, analyze the matching degree between each pattern, determine the corresponding relationship between each spectrum form and the human body movement state, and obtain motion spectrum matching data;

[0114] Calculate the energy distribution ratio of each spectrum in the signal using the formula:

[0115]

[0116] Analyze the matching degree between each pattern, determine the corresponding relationship between each spectrum form and human motion state, and obtain motion spectrum matching data;

[0117] Among them, E z Represents the energy distribution ratio of the zth spectrum in the signal, C zl represents the complex amplitude of the zth spectrum at the lth frequency point, u l represents the frequency value of the lth frequency point, and L represents the total number of frequency points;

[0118] C zl Represents the complex amplitude of the zth spectrum at the lth frequency point, which can be obtained by the fast Fourier transform (FFT) of the signal. The specific calculation process is as follows:

[0119] Perform Fourier transform on the time domain signal x(t) and obtain the complex spectrum represented as:

[0120]

[0121] The complex amplitude is calculated as:

[0122]

[0123] in:

[0124] x(t) is the time domain signal obtained by sampling, the sampling frequency is set to 1000 Hz, and it is directly obtained by a high-precision sensor;

[0125] f l is the lth frequency point, with a value range of 0 Hz to 500 Hz, a frequency interval of 1 Hz, and 500 frequency points;

[0126] Re(X(f l )) is the real part of the spectrum at the lth frequency point;

[0127] Im(X(f l )) is the imaginary part of the spectrum at the lth frequency point;

[0128] u lRepresents the frequency value of the lth frequency point, directly output by the spectrum analysis system, with a frequency resolution of 1 Hz, a frequency range of 0 Hz to 500 Hz, and a frequency number of L = 500;

[0129] Based on the above content, set the parameters as follows:

[0130] The frequency range of the zth spectrum is 20Hz to 100Hz, and the complex amplitude is obtained as follows:

[0131] Complex amplitude at the 20Hz frequency point

[0132] Complex amplitude at the 50Hz frequency point

[0133] Complex amplitude at the 100Hz frequency point

[0134] The frequency values ​​are set as follows:

[0135] 20Hz frequency value u 20 =20, 50Hz frequency value u 50 =50, 100Hz frequency value u 100 =100;

[0136] Substituting the above parameters into the formula:

[0137]

[0138] Perform specific calculations:

[0139]

[0140] Expand the denominator:

[0141] 1.0 2 +1.28 2 +0.78 2 =1.0+1.6384+0.6084=3.2468;

[0142] 20 2 +50 2 +100 2 =400+2500+10000=12900;

[0143] The denominator is fully expanded:

[0144]

[0145] Numerator expansion:

[0146] 20+64+78=162;

[0147] The calculation results are:

[0148]

[0149] The result shows that the energy distribution ratio of the zth spectrum in the signal is 0.791, reflecting the proportion of the zth spectrum form in the overall signal.

[0150] S403: Call motion spectrum matching data, analyze the proportion of motion pattern signals, select motion patterns with significant proportions, analyze the time duration of corresponding patterns, compare signal frequency changes between different motion states, determine the motion category to which the echo signal belongs, determine the motion pattern classification interval, and obtain the motion state classification result.

[0151] Call the motion spectrum matching data, analyze the proportion of motion mode signals, and define the proportion of motion mode signals as: Among them, J k Indicates the signal energy proportion of the kth frequency mode, P k (f,ξ) represents the power spectral density of the kth frequency mode at time ξ and frequency f. The motion mode with a significant proportion is screened out, and the significant threshold is defined as 0.2 (i.e., the proportion exceeds 20%). If the following conditions are met, it is determined to be a significant motion mode: J k >0.2, analyze the time persistence of the corresponding pattern, define time persistence as more than 5 consecutive time windows, and each window length is 100ms. Time persistence is calculated as: T k =n×Δξ, where n is the number of time windows and Δξ is the window length (100ms). If the time duration exceeds 500ms, it is determined to be a stable motion mode. The signal frequency changes between different motion states are compared, and the frequency change of adjacent modes is defined as: Δf k =f next -f current , the frequency change rate between adjacent modes is defined as: If the frequency change rate exceeds 10 Hz / s, it is determined to be a significant frequency change, and the motion category to which the echo signal belongs is determined. The motion mode classification interval is defined as: 40 Hz to 50 Hz → slow walking, 50 Hz to 60 Hz → normal walking, 60 Hz to 70 Hz → fast walking. The current frequency change pattern is matched with the above classification interval. If the corresponding frequency interval and frequency change rate conditions are met, the motion category to which the current echo signal belongs is determined, the motion mode classification interval is determined, and the motion state classification result is obtained.

[0152] The specific steps for obtaining abnormal motion status indicators are as follows:

[0153] S501: Based on the motion state classification result, calculate the motion state change speed in the continuous time window, calculate the state change duration, compare the motion state switching frequency with the difference time, determine the motion state fluctuation range, and generate the motion state dynamic characteristics;

[0154] Define motion state change as motion mode transition within a time window. Set the time window length to 100ms, and include 10 time windows per second. Define the state change speed as: Among them, V k Indicates the speed of motion state change, N c represents the number of motion pattern changes that occur within the window length, Q w Indicates the window length (100ms). Assuming that five mode switches occur within a 1-second window, then: times / second, calculate the duration of state change, and define the duration of state change as the time difference between two adjacent motion modes. The calculation formula is: Ω k =t2-t1, where t2 and t1 represent the time points of switching between two adjacent motion modes. Assuming that the two adjacent modes occur at 500ms and 1200ms, then: Ω k =1200ms-500ms=700ms. Compare the motion state switching frequency of the difference time. The switching frequency is defined as the number of switches occurring in a unit time (second). The formula is: Where Q is the length of the sampling interval. Assuming that 10 mode switches occur within 2 seconds, then: times / second to judge the fluctuation interval of the motion state. The fluctuation interval is defined as the time length between two adjacent state changes. When the fluctuation interval is less than 500ms and the state switching occurs more than 3 times in a row, it is defined as a high-frequency motion fluctuation interval, and the dynamic characteristics of the motion state are generated.

[0155] S502: Invoking the dynamic characteristics of the motion state, analyzing the fluctuation of the motion state in the short term, counting the number of motion mode switches, determining the continuous stability of the motion mode, comparing the signal amplitudes in the motion state change intervals, calculating the signal energy gradient during the motion mode transition, and obtaining motion mode stability data;

[0156] The degree of fluctuation is defined as the number of state changes that occur within a short time window (500ms). Assuming that three state switches occur within the 500ms window, the short-term fluctuation degree is defined as: Times / second, count the number of motion mode switches, define the number of switches as the total number of state switches that occur within a specified time window, assuming that 25 mode switches occur within 10 seconds, then: N c=25, to determine the continuous stability of the movement pattern. Stability is defined as the proportion of a certain state in the total time over a period of time, which is defined as: Among them, T stable Indicates the duration in this mode, T total Indicates the total time. Assuming that the mode lasts for 7 seconds in 10 seconds, then: Compare the signal amplitudes within the motion state change interval and set the signal amplitude difference to: Ω N =N next -N current , where N next and N current are the signal amplitudes in adjacent windows respectively. Assuming that the signal amplitude of the current window is 0.8 and that of the next window is 1.2, then: Ω N =1.2-0.8=0.4, calculate the signal energy gradient during motion mode conversion, and define the energy gradient as the rate of energy change in adjacent windows. The calculation formula is: Among them, L next and L current are the energies of adjacent windows respectively. Assuming that the energy of the current window is 2.5, the energy of the next window is 3.0, and the window length is 100ms, then: (Unit / s), and obtain the motion mode stability data.

[0157] S503: Call the motion pattern stability data, identify the signal strength changes of the multi-channel echo, analyze the echo energy distribution in each time period, screen the intervals with abnormal energy fluctuations, judge whether the human body is stationary or accelerating, and obtain the abnormal motion state indicator.

[0158] Call the motion mode stability data, identify the signal strength changes of the multi-channel echo, and set the echo signal strength received by the multi-channel to: Among them, I m (ζ) represents the signal strength of the mth receiving channel at time ζ, R m (ζ) and S m (ζ) are the in-phase component and the orthogonal component respectively. The echo energy distribution in each time period is analyzed and the energy is defined as: Screen the intervals with abnormal energy fluctuations and define the abnormal fluctuation threshold as the mean value of energy plus 2 times the standard deviation: in, is the mean energy, δ L is the standard deviation of energy. If the energy of a certain channel exceeds the threshold, it is judged as abnormal energy fluctuation, and the human body movement is judged to be stationary or accelerated, and the abnormal movement state index is obtained.

[0159] like Figure 2 As shown in FIG, a system for realizing human motion state recognition by radar includes:

[0160] The feature extraction module uses a sensor to receive the echo signal of the millimeter-wave radar, analyzes the amplitude and phase changes of the signal, calculates the average and standard deviation of the amplitude, compares the received signal, records the amplitude extreme points and phase mutation points, and obtains the radar echo signal characteristics;

[0161] The motion pattern analysis module is based on the characteristics of the radar echo signal, segments the signal phase information, calculates the phase change gradient value, analyzes the gradient stability interval, identifies the human motion trajectory, determines the motion speed change, and obtains the motion pattern data;

[0162] The frequency feature recognition module extracts the time points of signal phase and amplitude anomalies based on motion pattern data, identifies the signal frequency components, compares the frequency and energy characteristics of the signal, determines the frequency pattern of the motion state, identifies the key frequency characteristics, and obtains the key frequency recognition results;

[0163] The spectrum matching and classification module analyzes the spectrum morphology differences based on the key frequency recognition results, matches the known frequency patterns, identifies the spectrum characteristics during motion, classifies the motion patterns, and obtains the motion state classification results;

[0164] The abnormal motion state recognition module calculates the motion change rate based on the motion state classification results, analyzes the violently fluctuating motion patterns, identifies the changes in echo signal intensity, determines the abnormality of human motion, and obtains the abnormal motion state index.

[0165] It should be understood that the term "and / or" as used herein simply describes a relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A alone, A and B together, or B alone. A and B can be singular or plural. Furthermore, the character " / " as used herein generally indicates an "or" relationship between the associated objects, but it may also indicate an "and / or" relationship. For specific understanding, please refer to the context.

[0166] In this disclosure, "at least one" means one or more, and "plurality" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, "at least one of a, b, or c" can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or plural.

[0167] It should be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0168] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present invention.

[0169] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described equipment, devices and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0170] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interface, indirect coupling or communication connection of the device or unit, which can be electrical, mechanical or other forms.

[0171] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0172] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0173] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0174] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included in the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. A method for recognizing human motion status by radar, characterized in that: The method comprises: S1: Use the sensor to receive the echo signal of the millimeter-wave radar, analyze the amplitude and phase changes of the signal, calculate the average and standard deviation of the amplitude, compare it with the received signal, record the amplitude extreme points and phase mutation points, and obtain the radar echo signal characteristics; S2: Based on the radar echo signal characteristics, the phase information of the signal is segmented, the phase change gradient value is calculated, the gradient stability interval is analyzed, the human body motion trajectory is identified, the motion speed change is determined, and the motion pattern data is obtained; S3: Based on the motion pattern data, extract the time points when the signal phase and amplitude are abnormal, identify the signal frequency components, compare the frequency and energy characteristics of the signal, determine the frequency pattern of the motion state, identify the key frequency characteristics, and obtain the key frequency identification result; S4: Based on the key frequency recognition results, analyze the spectrum morphology differences, match the known frequency patterns, identify the spectrum characteristics during movement, classify the movement pattern, and obtain the movement state classification result; S5: Based on the motion state classification result, calculate the motion change rate, analyze the violently fluctuating motion pattern, identify the change in echo signal intensity, judge the abnormality of human motion, and obtain the abnormal motion state indicator.

2. The method for realizing human motion state recognition by radar according to claim 1, characterized in that: The radar echo signal characteristics include amplitude extreme points, phase mutation points and signal change amplitude; the motion pattern data includes human motion trajectory, motion speed change rate and phase stability interval; the key frequency identification results include dominant frequency changes, energy distribution characteristics and frequency component differences; the motion state classification results include motion pattern matching degree, spectrum morphology difference and motion state category; the abnormal motion state indicators include static or accelerated abnormal conditions, multi-channel signal strength changes, and motion state change rate.

3. The method for realizing human motion state recognition by radar according to claim 1, characterized in that: The steps of acquiring the radar echo signal characteristics are specifically as follows: S101: Receive the millimeter-wave radar echo signal using a sensor, analyze the signal amplitude and phase information, calculate the signal amplitude mean and standard deviation within a continuous time period, compare the received real-time signal, identify the signal amplitude mutation interval, calculate the signal energy change rate, and obtain the signal amplitude change characteristics; S102: Based on the signal amplitude change characteristics, analyze the phase change of the signal, compare the phase offsets at adjacent time points, analyze the continuity of the phase change, identify the cumulative offset trend of the phase change, determine the state of the echo signal, and obtain the phase offset characteristics; S103: Calling the phase offset characteristics, synchronizing the signal segments with prominent signal amplitude and phase changes, calculating the rate of change of signal energy before and after the mutation point, determining the key change position in the echo signal, analyzing the extreme points of the echo signal amplitude and the phase turning points, and obtaining the radar echo signal characteristics.

4. The method for realizing human motion state recognition by radar according to claim 1, characterized in that: The steps of acquiring the motion pattern data are specifically as follows: S201: Based on the radar echo signal characteristics, segment the phase information in the continuous echo signal, calculate the phase change, screen the signal interval with abnormal phase change, calculate the average phase increment within the interval, and compare the phase change rate of each signal segment to obtain a phase change rate index; S202: Calculate the signal phase amplitude range within a continuous time period based on the phase change rate indicator, compare the phase change directions of adjacent time windows, analyze the continuous change characteristics of the signal over time, identify the stable motion path of the human body, and obtain a stable motion trajectory; S203: Calling the stable motion trajectory, analyzing the direction of human body movement, screening the time nodes of the motion trajectory direction change, determining the amplitude and duration of the trajectory direction adjustment, comparing the motion rates of adjacent trajectory segments, identifying the change of human body movement rhythm, recording the change range of movement direction and speed, and obtaining motion pattern data.

5. The method for realizing human motion state recognition by radar according to claim 4, characterized in that: The phase increment mean within the calculation interval is calculated using the formula: ； And compare the phase change rate of each signal segment to obtain the phase change rate index; in, represents the mean phase increment within the signal interval, Represents the total number of sampling points in the selected signal interval, Representative The phase increment of the sampling points is Representative The phase standard deviation of the sampling points is Representative The phase mean of the sampling points.

6. The method for realizing human motion state recognition by radar according to claim 1, characterized in that: The steps of obtaining the key frequency identification result are specifically as follows: S301: Based on the motion pattern data, detecting phase and amplitude fluctuations of the echo signal, selecting time points with prominent change rates, calculating amplitude differences of continuous signals before and after the time points, analyzing the changing patterns of phase mutations, measuring the duration of signal fluctuations, selecting signal feature points with amplitude and phase mutations, and obtaining a signal fluctuation feature set; S302: Calling the signal fluctuation feature set, extracting the echo signal at the corresponding time point, analyzing the amplitude change of the signal in the difference frequency segment, identifying the frequency components in the signal, calculating the rate of change of the frequency over time, determining the frequency offset trend between time points, analyzing the frequency distribution in adjacent time windows, and obtaining a frequency offset spectrum; S303: Based on the frequency shift spectrum, analyze the energy density of each frequency interval, compare the energy proportion of each frequency band, screen the stable frequency area, identify the frequency characteristics in the normal motion state, determine the motion state matching relationship of the key frequency pattern, and obtain the key frequency identification result.

7. The method for realizing human motion state recognition by radar according to claim 1, characterized in that: The steps of obtaining the motion state classification result are specifically as follows: S401: Based on the key frequency recognition results, analyze the spectrum morphology of the signal during human motion, extract the signal features corresponding to each frequency mode, compare the morphological differences of the signal waveforms, identify the signal spectrum changes in each motion state, and obtain a spectrum difference recognition result; S402: Invoking the spectrum difference recognition result, comparing it with known frequency patterns, screening spectrum forms that meet the pattern characteristics, calculating the energy distribution ratio of each spectrum in the signal, analyzing the matching degree between each pattern, determining the corresponding relationship between each spectrum form and the human body movement state, and obtaining motion spectrum matching data; S403: Call the motion spectrum matching data, analyze the proportion of motion pattern signals, screen the motion patterns with significant proportions, analyze the time duration of the corresponding patterns, compare the signal frequency changes between different motion states, determine the motion category to which the echo signal belongs, determine the motion pattern classification interval, and obtain the motion state classification result.

8. The method for realizing human motion state recognition by radar according to claim 7, characterized in that: The energy distribution ratio of each spectrum in the signal is calculated using the formula: ； Analyze the matching degree between each pattern, determine the corresponding relationship between each spectrum form and human motion state, and obtain motion spectrum matching data; in, Representative The energy distribution ratio of the spectrum in the signal, Representative The spectrum in The complex amplitude at the frequency point, Representative The frequency value of the frequency point, Represents the total number of frequency points.

9. The method for realizing human motion state recognition by radar according to claim 1, characterized in that: The steps of obtaining the abnormal motion state indicator are specifically as follows: S501: Based on the motion state classification result, calculate the motion state change speed in the continuous time window, calculate the state change duration, compare the motion state switching frequency with the difference time, determine the motion state fluctuation range, and generate the motion state dynamic characteristics; S502: Invoking the dynamic characteristics of the motion state, analyzing the fluctuation of the motion state in the short term, counting the number of motion mode switches, determining the continuous stability of the motion mode, comparing the signal amplitudes in the motion state change intervals, calculating the signal energy gradient during the motion mode transition, and obtaining motion mode stability data; S503: Call the motion pattern stability data, identify the signal strength changes of the multi-channel echo, analyze the echo energy distribution in each time period, screen the intervals with abnormal energy fluctuations, judge whether the human body is stationary or accelerating, and obtain the abnormal motion state indicator.

10. A system for recognizing human motion status by radar, wherein the system is used to implement the method for recognizing human motion status by radar as claimed in any one of claims 1 to 9, characterized in that: The system comprises: The feature extraction module uses a sensor to receive the echo signal of the millimeter-wave radar, analyzes the amplitude and phase changes of the signal, calculates the average and standard deviation of the amplitude, compares the received signal, records the amplitude extreme points and phase mutation points, and obtains the radar echo signal characteristics; The motion pattern analysis module divides the phase information of the signal based on the characteristics of the radar echo signal, calculates the phase change gradient value, analyzes the gradient stability interval, identifies the human body motion trajectory, determines the motion speed change, and obtains motion pattern data; The frequency feature recognition module extracts the time points of signal phase and amplitude abnormalities based on the motion pattern data, identifies the signal frequency components, compares the frequency and energy characteristics of the signal, determines the frequency pattern of the motion state, identifies the key frequency characteristics, and obtains the key frequency recognition results; The spectrum matching and classification module analyzes the spectrum morphology differences based on the key frequency identification results, matches the known frequency patterns, identifies the spectrum characteristics during motion, classifies the motion patterns, and obtains the motion state classification results; The abnormal motion state identification module calculates the motion change rate based on the motion state classification result, analyzes the violently fluctuating motion pattern, identifies the change in echo signal intensity, determines the abnormality of human motion, and obtains the abnormal motion state index.

Images