CN112731380B - Human body intelligent monitoring method and monitoring equipment based on millimeter waves - Google Patents
Human body intelligent monitoring method and monitoring equipment based on millimeter waves Download PDFInfo
- Publication number
- CN112731380B CN112731380B CN202011488371.0A CN202011488371A CN112731380B CN 112731380 B CN112731380 B CN 112731380B CN 202011488371 A CN202011488371 A CN 202011488371A CN 112731380 B CN112731380 B CN 112731380B
- Authority
- CN
- China
- Prior art keywords
- millimeter wave
- signals
- data
- signal
- wave monitoring
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 205
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000003062 neural network model Methods 0.000 claims abstract description 36
- 238000003909 pattern recognition Methods 0.000 claims abstract description 32
- 238000012216 screening Methods 0.000 claims abstract description 24
- 238000012806 monitoring device Methods 0.000 claims abstract description 16
- 238000007781 pre-processing Methods 0.000 claims abstract description 14
- 238000001914 filtration Methods 0.000 claims description 30
- 230000006870 function Effects 0.000 claims description 20
- 238000004891 communication Methods 0.000 claims description 16
- 238000012545 processing Methods 0.000 claims description 16
- 230000008030 elimination Effects 0.000 claims description 11
- 238000003379 elimination reaction Methods 0.000 claims description 11
- 230000004888 barrier function Effects 0.000 claims description 9
- 230000005021 gait Effects 0.000 claims description 9
- 230000029058 respiratory gaseous exchange Effects 0.000 claims description 8
- 230000036772 blood pressure Effects 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000007405 data analysis Methods 0.000 claims description 4
- 230000000149 penetrating effect Effects 0.000 claims 2
- 230000003068 static effect Effects 0.000 claims 2
- 238000004458 analytical method Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 3
- 238000001228 spectrum Methods 0.000 description 3
- 238000006073 displacement reaction Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000013075 data extraction Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000002203 pretreatment Methods 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/88—Radar or analogous systems specially adapted for specific applications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/02—Systems using reflection of radio waves, e.g. primary radar systems; Analogous systems
- G01S13/50—Systems of measurement based on relative movement of target
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/02—Systems using reflection of radio waves, e.g. primary radar systems; Analogous systems
- G01S13/50—Systems of measurement based on relative movement of target
- G01S13/58—Velocity or trajectory determination systems; Sense-of-movement determination systems
- G01S13/583—Velocity or trajectory determination systems; Sense-of-movement determination systems using transmission of continuous unmodulated waves, amplitude-, frequency-, or phase-modulated waves and based upon the Doppler effect resulting from movement of targets
- G01S13/584—Velocity or trajectory determination systems; Sense-of-movement determination systems using transmission of continuous unmodulated waves, amplitude-, frequency-, or phase-modulated waves and based upon the Doppler effect resulting from movement of targets adapted for simultaneous range and velocity measurements
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/02—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00
- G01S7/35—Details of non-pulse systems
- G01S7/352—Receivers
- G01S7/354—Extracting wanted echo-signals
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/02—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00
- G01S7/41—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/02—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00
- G01S7/41—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section
- G01S7/415—Identification of targets based on measurements of movement associated with the target
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/02—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00
- G01S7/41—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section
- G01S7/417—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section involving the use of neural networks
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Electromagnetism (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The invention provides a human body intelligent monitoring method and monitoring equipment based on millimeter waves, wherein the method comprises the following steps: at least one millimeter wave monitoring device is arranged in the monitoring space, linear frequency modulation continuous millimeter waves are transmitted into the monitoring space through the millimeter wave monitoring device, and millimeter wave signals reflected in the monitoring space are received in real time; preprocessing the millimeter wave monitoring signals, analyzing the signal types of the millimeter wave monitoring signals by adopting a data pattern recognition model according to the preprocessed millimeter wave monitoring signals, and screening millimeter wave monitoring signals related to targets; analyzing and calculating target state information by adopting a neural network model according to the millimeter wave monitoring signals related to the target; the method comprises the steps of sending target state information to a monitoring server or a user side in real time, wherein the target state information at least comprises one of the following steps: multi-target position information, multi-human body posture information, human body physiological information, and a plurality of moving object information. The method has the advantages of sensitive target identification, accurate monitoring result, strong anti-interference capability and the like.
Description
Technical Field
The invention relates to the technical field of millimeter wave identification and monitoring, in particular to a human body intelligent monitoring method and monitoring equipment based on millimeter waves.
Background
Millimeter wave refers to electromagnetic wave with the wavelength of 1-10 mm, which is located in the overlapping wavelength range of microwave and far infrared wave, thus having the characteristics of two wave spectrums. Compared with light waves, millimeter waves are less influenced by natural light and heat radiation sources; the millimeter wave frequency range is 30GHz-300GHz, and the millimeter wave frequency range has the characteristics of high precision and high resolution; the beam of millimeter wave is narrower, and the beam of millimeter wave is much narrower than the beam of microwave under the same antenna size, so that small objects with closer distances can be distinguished or the details of the objects can be observed more clearly. The propagation of millimeter waves is much less affected by weather than laser light, and can be considered to have all-weather characteristics. Millimeter wave components are much smaller in size and easier to miniaturize than microwaves.
At present, cameras are used for monitoring space environment, but as people pay more attention to personal privacy, a non-sensitive monitoring technology capable of effectively identifying a human body without privacy disclosure is urgently needed. Based on the characteristics possessed by the millimeter waves, the millimeter waves are widely applied to the fields of communication, radar, remote sensing, radio astronomy and the like, and at present, some human body gesture recognition technologies adopting the millimeter waves are already appeared on the market, but the recognition process of the prior art is relatively complex, interference signals, noise signals and the like in millimeter wave signals cannot be effectively eliminated, obstacles cannot be accurately recognized, eliminated or bypassed, and the obtained recognition results are inaccurate and have little reference significance. Moreover, the existing camera technology is prone to revealing user privacy risks.
Disclosure of Invention
In view of the above-mentioned shortcomings in the prior art, the present invention aims to: the human body intelligent monitoring method and the monitoring equipment based on millimeter waves are provided, aiming at millimeter wave signals collected in a monitoring space, the signals are subjected to digital filtering, space multipath interference elimination, space noise processing and other preprocessing, and interference signals, noise signals, obstacle signals and the like in the signals can be effectively eliminated. Then adopting a data pattern recognition model to analyze the signal types of millimeter wave monitoring signals, screening millimeter wave monitoring signals related to the target, and eliminating the obstacle of a space stationary object which is not related to the target; and analyzing and calculating target state information by adopting a neural network model according to the millimeter wave monitoring signals related to the target. The method has the advantages of sensitive target identification, accurate monitoring result, strong anti-interference capability and the like.
A human body intelligent monitoring method based on millimeter waves comprises the following steps:
At least one millimeter wave monitoring device is arranged in the monitoring space, linear frequency modulation continuous millimeter waves are transmitted into the monitoring space through the millimeter wave monitoring device, and millimeter wave signals reflected in the monitoring space are received in real time;
Preprocessing the millimeter wave monitoring signals, analyzing the signal types of the millimeter wave monitoring signals by adopting a data pattern recognition model according to the preprocessed millimeter wave monitoring signals, and screening millimeter wave monitoring signals related to targets; analyzing and calculating target state information by adopting a neural network model according to the millimeter wave monitoring signals related to the target;
The method comprises the steps of sending target state information to a monitoring server or a user side in real time, wherein the target state information at least comprises one of the following steps: multi-target position information, multi-human body posture information, human body physiological information, and a plurality of moving object information.
Further, the preprocessing of the millimeter wave monitoring signal specifically includes: converting the millimeter wave monitoring signal from an analog signal to a digital signal, and performing inverse Fourier transform on the millimeter wave monitoring signal to obtain a transformed time domain digital signal; and sequentially carrying out signal digital filtering, space multipath interference elimination and space noise processing on the time domain digital signals.
Further, the digital signal filtering method for the time domain digital signal specifically includes:
S101: setting digital filtering parameters, and performing anti-interference mean digital filtering on the time domain digital signals of the millimeter wave monitoring signals;
S102: predicting the data at the K+1 time from the data at the K time, and estimating the prediction error at the K+1 time from the prediction error at the K time;
S103: calculating Kalman gain according to the data at the K moment and the predicted data at the K+1 moment, calculating the optimal estimated value of the data, and calculating the predicted error of the current moment K;
s104: step S102 and step S103 are looped.
Further, the method for eliminating the space multipath interference to the time domain digital signal specifically comprises the following steps:
S201: acquiring a time domain digital signal S K of millimeter waves received after the current moment K is transmitted, and calculating the weight Q K of the current moment K;
S202: acquiring a time domain digital signal S K+1 of millimeter waves transmitted at the moment K+1, and calculating the weight Q K+1 of the moment K+1; :
S203: generating multipath interference cancellation amount: Δs=s K·QK-SK+1·QK+1, and effective data after interference cancellation is calculated: s=s K - Δs;
s204: and (3) looping the steps S201 to S203 until all the data are converged.
Further, the spatial noise processing is performed on the time domain digital signal, specifically including:
Performing autocorrelation digital noise signal monitoring and cross correlation digital noise signal monitoring on a time domain digital signal of the millimeter wave monitoring signal, and screening out a digital noise signal;
And calculating the phase difference time domain of the digital noise signals, guiding the digital noise signals into a delayer, guiding the output signals of the delayer and the previous noise signals into a multiplier, guiding the output signals of the multiplier into an integrator, guiding the output signals of the integrator into a digital FIR filter, and outputting a digital noise function.
Further, the analyzing the signal types of the millimeter wave monitoring signals by adopting a data pattern recognition model according to the preprocessed millimeter wave monitoring signals, and screening the millimeter wave monitoring signals related to the targets specifically comprises:
Judging whether the effective signals of the pre-processed millimeter wave monitoring signals are annihilated or not, if yes, filtering through a self-adaptive weak signal filter, filtering out the effective signals, analyzing the signal types of the effective signals of the millimeter wave monitoring signals by adopting a data pattern recognition model, screening the millimeter wave monitoring signals related to the targets, and eliminating the space stationary object barriers unrelated to the targets; if not, the data pattern recognition model is adopted to analyze the signal types of the effective signals of the millimeter wave monitoring signals, the millimeter wave monitoring signals related to the targets are screened, and the space stationary object barriers unrelated to the targets are eliminated.
Further, the data pattern recognition model includes:
Acquiring an effective signal of the millimeter wave monitoring signal as input data of a data pattern recognition model; and carrying out KNN recursion processing on the data, classifying the data by a Bayesian classifier, carrying out correlation comparison on the data set, extracting the related data as effective data, establishing a related data function, and carrying out data analysis on the related data function.
Further, the method for analyzing and calculating the target state information according to the millimeter wave monitoring signals related to the target by adopting a neural network model specifically comprises the following steps:
Doppler/micro Doppler operation is carried out on millimeter wave monitoring signals related to the target, and space polar coordinate data are obtained; according to Doppler/micro Doppler calculation results and space polar coordinate data, analyzing and calculating target state information by adopting a neural network model;
The target state information includes at least one of: target position information, human body posture information, human body physiological information, and object information; the position information at least comprises distance, position distribution and angle, the human body posture information at least comprises speed, track, posture, gesture, gait and gesture, the human body physiological information at least comprises heart rate, respiration and blood pressure, and the object information at least comprises size, shape and moving speed.
Further, the neural network model includes:
S301: acquiring Doppler/micro Doppler operation results of millimeter wave monitoring signals as learning data of a neural network model;
S302: taking the K moment learning type data vector X K as an input layer;
s303: determining an input weight vector U by a weight value W, and determining a vector function of an implicit layer at the moment K:
SK＝f(UK·XK+W·SK-1)
S304: determining an output weight vector V, and determining a vector function of an output layer at the moment K: o K＝g(V·SK);
S305: after the data learning at the time K is completed, the next time data learning is performed, and steps S302 to S305 are repeated.
A millimeter wave-based human intelligent monitoring device, comprising:
The microstrip antenna comprises at least one transmitter and one receiver, and is used for transmitting linear frequency modulation continuous millimeter waves and receiving reflected millimeter wave signals in real time;
The millimeter wave chip is used for converting the millimeter wave monitoring signal from an analog signal to a digital signal and preprocessing the millimeter wave monitoring signal;
The microprocessor is in communication connection with the millimeter wave chip and is used for analyzing the signal types of the millimeter wave monitoring signals by adopting a data pattern recognition model according to the preprocessed millimeter wave monitoring signals and screening the millimeter wave monitoring signals related to the targets; analyzing and calculating target state information by adopting a neural network model according to the millimeter wave monitoring signals related to the target;
The communication module is in communication connection with the microprocessor and is used for sending the target state information to the monitoring server or the user side in real time.
Compared with the prior art, the invention has the following advantages:
The invention provides a human body intelligent monitoring method and monitoring equipment based on millimeter waves, which aim at millimeter wave signals collected in a monitoring space, the signals are subjected to pretreatment such as digital filtering, space multipath interference elimination, space noise treatment, space stationary object obstacle elimination and the like, and interference signals, noise signals, obstacle signals and the like in the signals can be effectively eliminated. Then adopting a data pattern recognition model to analyze the signal types of millimeter wave monitoring signals and screening millimeter wave monitoring signals related to targets; and analyzing and calculating target state information by adopting a neural network model according to the millimeter wave monitoring signals related to the target. The method has the advantages of sensitive human body identification, accurate monitoring result, strong anti-interference capability and the like.
Drawings
Fig. 1 is a monitoring flow chart of a human body intelligent monitoring method based on millimeter waves in a first embodiment of the invention;
FIG. 2 is a control flow chart of digital filtering of a time domain digital signal in a first embodiment of the present invention;
Fig. 3 is a control flow diagram of spatial multipath interference cancellation for a time domain digital signal in accordance with a first embodiment of the present invention;
FIG. 4 is a control flow diagram of spatial noise processing of a time domain digital signal in accordance with one embodiment of the present invention;
fig. 5 is a control flow chart of analyzing millimeter wave monitoring signals by using a data pattern recognition model in the first embodiment of the present invention;
FIG. 6 is a flow chart illustrating the analysis of a data pattern recognition model according to a first embodiment of the present invention;
FIG. 7 is a control flow chart of the first embodiment of the invention for analyzing target state information using a neural network model;
FIG. 8 is a flowchart illustrating a neural network model analysis according to an embodiment of the present invention;
fig. 9 is a communication block diagram of a millimeter wave-based intelligent human body monitoring device in a second embodiment of the present invention;
Fig. 10 is a schematic block diagram of a millimeter wave-based intelligent human body monitoring device in a second embodiment of the present invention;
fig. 11 is a system block diagram of a millimeter wave-based human body intelligent monitoring system in a second embodiment of the present invention.
Detailed Description
Embodiments of the technical scheme of the present invention will be described in detail below with reference to the accompanying drawings. The following examples are only for more clearly illustrating the technical aspects of the present invention, and thus are merely examples, which should not be construed as limiting the scope of the present invention.
Embodiment one:
referring to fig. 1, a human body intelligent monitoring method based on millimeter waves includes the following steps:
At least one millimeter wave monitoring device is arranged in the monitoring space, linear frequency modulation continuous millimeter waves are transmitted into the monitoring space through the millimeter wave monitoring device, and millimeter wave signals reflected in the monitoring space are received in real time. Specifically, the monitoring space is preset, and the monitoring space can be a room of a family, a processing workshop of an enterprise, an office place of the enterprise and the like; the arrangement quantity of the millimeter wave monitoring devices can be specifically determined according to the size and shape of the monitoring space, for example, four millimeter wave monitoring devices can be arranged at four corners of the square monitoring space, irregular monitoring space can be specifically arranged according to the monitoring visual angle, and the overall monitoring can be basically achieved.
Preprocessing the millimeter wave monitoring signals, analyzing the signal types of the millimeter wave monitoring signals by adopting a data pattern recognition model according to the preprocessed millimeter wave monitoring signals, and screening millimeter wave monitoring signals related to targets; and analyzing and calculating target state information by adopting a neural network model according to the millimeter wave monitoring signals related to the target. Specifically, the pretreatment method comprises the following steps: converting the millimeter wave monitoring signal from an analog signal to a digital signal, and performing inverse Fourier transform on the millimeter wave monitoring signal to obtain a transformed time domain digital signal; and sequentially carrying out signal digital filtering, space multipath interference elimination and space noise processing on the time domain digital signals.
The method comprises the steps of sending target state information to a monitoring server or a user side in real time, wherein the target state information at least comprises one of the following steps: multi-target position information, multi-human body posture information, human body physiological information, and a plurality of moving object information. Specifically, a plurality of millimeter wave monitoring devices can access a local server or a cloud server through a wireless local area network or an operator network, various monitoring information in a monitoring space is input into the access server through signal communication, and the server is connected with a user operation and maintenance platform and user mobile equipment. The position information at least comprises distance, position distribution and angle, the human body posture information at least comprises speed, track, posture, gesture, gait and gesture, the human body physiological information at least comprises heart rate, respiration and blood pressure, and the object information at least comprises size, shape and moving speed.
According to the human body intelligent monitoring method based on millimeter waves, firstly, millimeter wave signals are subjected to pretreatment such as digital filtering, space multipath interference elimination, space noise treatment and the like, and interference signals, noise signals, obstacle signals and the like in the signals can be effectively eliminated. And then analyzing the signal types of the millimeter wave monitoring signals by adopting a data pattern recognition model, screening the millimeter wave monitoring signals related to the target, and eliminating the obstacle of the space stationary object which is not related to the target. Finally, according to millimeter wave monitoring signals related to the target, a neural network model is adopted to analyze and calculate target state information, and through monitoring and analyzing various states such as a power spectrum, a human body displacement, a moving speed, a moving track, human body micro-fluctuation, a human body gait and the like of millimeter waves on a human body/object, physiological parameters such as human body posture, gait, gesture, number of people, movement track, human heart rate and respiration and the like are analyzed and calculated. The method has the advantages of sensitive human body identification, accurate monitoring result, strong anti-interference capability and the like.
Referring to fig. 2, the method of digitally filtering the time domain digital signal of the millimeter wave monitoring signal is as follows:
S101: setting digital filtering parameters, and performing anti-interference mean digital filtering on the time domain digital signals of the millimeter wave monitoring signals;
S102: predicting the data at the K+1 time from the data at the K time, and estimating the prediction error at the K+1 time from the prediction error at the K time;
S103: calculating Kalman gain according to the data at the K moment and the predicted data at the K+1 moment, calculating the optimal estimated value of the data, and calculating the predicted error of the current moment K;
s104: step S102 and step S103 are looped.
Thus, the interference signals in the millimeter wave monitoring signals can be preliminarily filtered.
Referring to fig. 3, the method for performing spatial multipath interference cancellation on the time domain digital signal of the millimeter wave monitoring signal is as follows:
S201: acquiring a time domain digital signal S K of millimeter waves received after the current moment K is transmitted, and calculating the weight Q K of the current moment K;
S202: acquiring a time domain digital signal S K+1 of millimeter waves transmitted at the moment K+1, and calculating the weight Q K+1 of the moment K+1; :
S203: generating multipath interference cancellation amount: Δs=s K·QK-SK+1·QK+1, and effective data after interference cancellation is calculated: s=s K - Δs;
s204: and (3) looping the steps S201 to S203 until all the data are converged.
Thus, the interference signals in the millimeter wave monitoring signals can be effectively eliminated.
Referring to fig. 4, the method of spatial noise processing of the time domain digital signal of the millimeter wave monitoring signal is as follows:
Performing autocorrelation digital noise signal monitoring and cross correlation digital noise signal monitoring on a time domain digital signal of the millimeter wave monitoring signal, and screening out a digital noise signal;
And calculating the phase difference time domain of the digital noise signals, guiding the digital noise signals into a delayer, guiding the output signals of the delayer and the previous noise signals into a multiplier, guiding the output signals of the multiplier into an integrator, guiding the output signals of the integrator into a digital FIR filter, and outputting a digital noise function.
Thus, the noise signal in the millimeter wave monitoring signal can be effectively eliminated.
In the human body intelligent monitoring method based on millimeter waves, for millimeter wave signals collected in a monitoring space, preprocessing of the millimeter wave signals sequentially passes through digital filtering, space multipath interference elimination, space noise processing and the like, so that interference signals, noise signals, obstacle signals and the like in the millimeter wave monitoring signals can be effectively eliminated. And further, powerful data support is provided for subsequent target identification and target state analysis, the sensitivity and agility of target identification are ensured, the accuracy and reliability of target monitoring results are improved, and the anti-interference capability is strong.
Referring to fig. 5, the method of analyzing the millimeter wave monitoring signal using the data pattern recognition model is as follows:
Judging whether the effective signals of the pre-processed millimeter wave monitoring signals are annihilated or not, if yes, filtering through a self-adaptive weak signal filter, filtering out the effective signals, analyzing the signal types of the effective signals of the millimeter wave monitoring signals by adopting a data pattern recognition model, screening the millimeter wave monitoring signals related to the targets, and eliminating the space stationary object barriers unrelated to the targets; if not, the data pattern recognition model is adopted to analyze the signal types of the effective signals of the millimeter wave monitoring signals, the millimeter wave monitoring signals related to the targets are screened, and the space stationary object barriers unrelated to the targets are eliminated.
Referring to fig. 6, the data pattern recognition model recognition process is as follows:
Acquiring an effective signal of the millimeter wave monitoring signal as input data of a data pattern recognition model; and carrying out KNN recursion processing on the data, classifying the data by a Bayesian classifier, carrying out correlation comparison on the data set, extracting the related data as effective data, establishing a related data function, and carrying out data analysis on the related data function.
Therefore, the monitoring target can be sensitively and rapidly identified, and the identification accuracy is high. After the monitoring target is identified, the obstacle elimination of the space stationary object is also needed, and the interference factors in the millimeter wave monitoring signals can be further eliminated by adopting modes of passing, bypassing and the like, so that the accuracy and reliability of the target monitoring result are improved, and the anti-interference capability is strong.
Referring to fig. 7, the method for calculating the target state information using the neural network model analysis is as follows:
Doppler/micro Doppler operation is carried out on millimeter wave monitoring signals related to the target, and space polar coordinate data are obtained; according to Doppler/micro Doppler calculation results and space polar coordinate data, analyzing and calculating target state information by adopting a neural network model;
the target state information includes at least one of: multi-target position information, multi-human body posture information, human body physiological information, and a plurality of moving object information; the position information at least comprises distance, position distribution and angle, the human body posture information at least comprises speed, track, posture, gesture, gait and gesture, the human body physiological information at least comprises heart rate, respiration and blood pressure, and the object information at least comprises size and shape.
Referring to fig. 8, the neural network model analysis process described above is as follows:
S301: acquiring Doppler/micro Doppler operation results of millimeter wave monitoring signals as learning data of a neural network model;
S302: taking the K moment learning type data vector X K as an input layer;
s303: determining an input weight vector U by a weight value W, and determining a vector function of an implicit layer at the moment K:
SK＝f(UK·XK+W·SK-1)
S304: determining an output weight vector V, and determining a vector function of an output layer at the moment K: o K＝g(V·SK);
S305: after the data learning at the time K is completed, the next time data learning is performed, and steps S302 to S305 are repeated.
Therefore, the target can be accurately and efficiently monitored, the state information of the monitored target is analyzed, and the target monitoring result is accurate and has strong anti-interference capability.
In specific implementation, the neural network model may be an RNN neural network model.
Embodiment two:
referring to 9, a millimeter wave-based human intelligent monitoring device, comprising:
The microstrip antenna comprises at least one transmitter and one receiver, and is used for transmitting the linear frequency modulation continuous millimeter wave and receiving the reflected millimeter wave signal in real time. Specifically, a one-or multiple-and-one-or multiple-receiving microstrip antenna emits a chirped continuous millimeter wave to a detection space. The millimeter wave is projected onto the detected object or human body to generate a certain reflected signal, which is received by the microstrip antenna.
The millimeter wave chip is in communication connection with the microstrip antenna and the millimeter wave chip, and the millimeter wave chip is used for converting millimeter wave monitoring signals from analog signals to digital signals and preprocessing the millimeter wave monitoring signals. Specifically, the millimeter wave chip provides a linear frequency modulation continuous millimeter wave with a certain transmitting power for the microstrip antenna, and at the same time, receives a reflected signal obtained by the microstrip antenna. The digital-to-analog conversion circuit in the chip is responsible for converting the analog signal into a digital signal. The built-in SOC of the chip will preprocess the received transmit signal.
The microprocessor is in communication connection with the millimeter wave chip and is used for analyzing the signal types of the millimeter wave monitoring signals by adopting a data pattern recognition model according to the preprocessed millimeter wave monitoring signals and screening the millimeter wave monitoring signals related to the targets; and analyzing and calculating target state information by adopting a neural network model according to the millimeter wave monitoring signals related to the target. Specifically, the microprocessor receives the preprocessing signal transmitted by the millimeter wave chip and carries out specific algorithm processing, so that a series of target parameters such as the size, distance, angle, position distribution, speed, track, shape, posture, gesture, heart rate, respiration, blood pressure and the like of a detected object or human body are obtained.
The communication module is in communication connection with the microprocessor and is used for sending the target state information to the monitoring server or the user side in real time. Specifically, the communication module receives the result parameter signal output by the microprocessor, and transmits the result parameter to a local area network, a wireless local area network or an operator wireless network. And the local or cloud server receives the result sent by the communication module.
In the implementation, the monitoring equipment can directly adopt a millimeter wave sensor, and in the implementation, the neural network model can be an RNN neural network model.
Referring to fig. 10, a microstrip antenna ant of a millimeter wave sensor, a radio frequency transceiver millimeter wave driving chip SRchip, a signal preprocessing SOC unit SIGNALPRE-proc, a data extraction speed, an angle, a distance, and other various relevant quantities.
Referring to fig. 11, a millimeter wave-based human body intelligent monitoring system, to which the above millimeter wave-based human body intelligent monitoring device may be applied, includes a plurality of millimeter wave sensors, a monitoring server, a user mobile device, and a user operation and maintenance platform, which are respectively in communication connection with the monitoring server.
The human body intelligent monitoring equipment based on the millimeter waves can move into a monitoring system, and the system can pre-process millimeter wave signals through digital filtering, space multipath interference elimination, space noise processing and the like, and can effectively eliminate interference signals, noise signals, barrier signals and the like in the signals. Then analyzing the signal types of the millimeter wave monitoring signals, screening the millimeter wave monitoring signals related to the target, and eliminating the obstacle of the space stationary object which is not related to the target. Finally, according to millimeter wave monitoring signals related to the target, analyzing and calculating target state information, and analyzing various states such as power spectrum, human body displacement, moving speed, moving track, human body micro-fluctuation, human body gait and the like of millimeter waves on a human body/object, and analyzing and calculating physiological parameters such as human body state, gait, posture, number of people, moving track, human heart rate, respiration and the like. The method has the advantages of sensitive human body identification, accurate monitoring result, strong anti-interference capability and the like.
Finally, it is noted that the above embodiments are only for illustrating the technical solution of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the embodiments, it should be understood by those skilled in the art that the technical solution of the present invention may be modified or substituted without departing from the spirit and scope of the technical solution of the present invention, and the present invention is intended to be covered in the scope of the present invention.
Claims (2)
1. The human body intelligent monitoring method based on millimeter waves is characterized by comprising the following steps of:
At least one millimeter wave monitoring device is arranged in the monitoring space, linear frequency modulation continuous millimeter waves are transmitted into the monitoring space through the millimeter wave monitoring device, and millimeter wave signals reflected in the monitoring space are received in real time;
Preprocessing the millimeter wave monitoring signals, analyzing the signal types of the millimeter wave monitoring signals by adopting a data pattern recognition model according to the preprocessed millimeter wave monitoring signals, and screening millimeter wave monitoring signals related to targets; analyzing and calculating target state information by adopting a neural network model according to the millimeter wave monitoring signals related to the target;
the method comprises the steps of sending target state information to a monitoring server or a user side in real time, wherein the target state information at least comprises one of the following steps: multi-target position information, multi-human body posture information, human body physiological information, and a plurality of moving object information;
the preprocessing of the millimeter wave monitoring signal specifically comprises the following steps: converting the millimeter wave monitoring signal from an analog signal to a digital signal, and performing inverse Fourier transform on the millimeter wave monitoring signal to obtain a transformed time domain digital signal; sequentially carrying out signal digital filtering, space multipath interference elimination and space noise processing on the time domain digital signals;
The method for performing signal digital filtering on the time domain digital signal specifically comprises the following steps:
S101: setting digital filtering parameters, and performing anti-interference mean digital filtering on the time domain digital signals of the millimeter wave monitoring signals;
S102: predicting the data at the K+1 time from the data at the K time, and estimating the prediction error at the K+1 time from the prediction error at the K time;
S103: calculating Kalman gain according to the data at the K moment and the predicted data at the K+1 moment, calculating the optimal estimated value of the data, and calculating the predicted error of the current moment K;
S104: looping through step S102 and step S103;
The method for eliminating the space multipath interference to the time domain digital signal specifically comprises the following steps:
S201: acquiring a time domain digital signal S K of millimeter waves received after the current moment K is transmitted, and calculating the weight Q K of the current moment K;
s202: acquiring a time domain digital signal S K+1 of millimeter waves transmitted at the moment K+1, and calculating the weight Q K+1 of the moment K+1;
s203: generating multipath interference cancellation amount: Δs=s K·QK-SK+1·QK+1, and effective data after interference cancellation is calculated: s=s K - Δs;
s204: step S201 to step S203 are circulated until all data are converged;
The spatial noise processing for the time domain digital signal specifically comprises:
Performing autocorrelation digital noise signal monitoring and cross correlation digital noise signal monitoring on a time domain digital signal of the millimeter wave monitoring signal, and screening out a digital noise signal;
calculating the phase difference time domain of the digital noise signals, guiding the digital noise signals into a delayer, guiding the output signals of the delayer and the previous noise signals into a multiplier, guiding the output signals of the multiplier into an integrator, guiding the output signals of the integrator into a digital FIR filter, and outputting a digital noise function;
the method for analyzing the signal types of the millimeter wave monitoring signals by adopting a data pattern recognition model according to the preprocessed millimeter wave monitoring signals, and screening the millimeter wave monitoring signals related to targets specifically comprises the following steps:
Judging whether the effective signals of the pre-processed millimeter wave monitoring signals are annihilated or not, if yes, filtering through a self-adaptive weak signal filter, filtering out the effective signals, analyzing the signal types of the effective signals of the millimeter wave monitoring signals by adopting a data pattern recognition model, screening the millimeter wave monitoring signals related to the targets, and eliminating the space stationary object barriers unrelated to the targets; if not, analyzing the signal types of the effective signals of the millimeter wave monitoring signals by adopting a data pattern recognition model, screening the millimeter wave monitoring signals related to the targets, and eliminating the space stationary object barriers unrelated to the targets;
The data pattern recognition model includes:
acquiring an effective signal of the millimeter wave monitoring signal as input data of a data pattern recognition model; carrying out KNN recursion on the data, classifying the data by a Bayesian classifier, carrying out correlation comparison on the data set, extracting the related data as effective data, establishing a related data function, and carrying out data analysis on the related data function;
the method for analyzing and calculating the target state information by adopting the neural network model according to the millimeter wave monitoring signals related to the target specifically comprises the following steps:
Doppler/micro Doppler operation is carried out on millimeter wave monitoring signals related to the target, and space polar coordinate data are obtained; according to Doppler/micro Doppler calculation results and space polar coordinate data, analyzing and calculating target state information by adopting a neural network model;
The target state information includes at least one of: multi-target position information, multi-human body posture information, human body physiological information, and a plurality of moving object information; the position information at least comprises distance, position distribution and angle, the human body posture information at least comprises speed, track, posture, gait and gesture, the human body physiological information at least comprises heart rate, respiration and blood pressure, and the object information at least comprises size, shape and moving speed;
the neural network model includes:
S301: acquiring Doppler/micro Doppler operation results of millimeter wave monitoring signals as learning data of a neural network model;
S302: taking the K moment learning type data vector X K as an input layer;
s303: determining an input weight vector U by a weight value W, and determining a vector function of an implicit layer at the moment K:
SK＝f(UK·XK+W·SK-1)
S304: determining an output weight vector V, and determining a vector function of an output layer at the moment K: o K＝g(V·SK);
S305: finishing the data learning at the moment K, carrying out the data learning at the next moment, and circulating the steps S302 to S305;
After monitoring the target recognition, the method further comprises the steps of eliminating the obstacle of the space static object in a penetrating and bypassing mode;
The neural network model adopts an RNN neural network model.
2. Human intelligent monitoring equipment based on millimeter wave, characterized by comprising:
The microstrip antenna comprises at least one transmitter and one receiver, and is used for transmitting linear frequency modulation continuous millimeter waves and receiving reflected millimeter wave signals in real time;
The millimeter wave chip is used for converting the millimeter wave monitoring signal from an analog signal to a digital signal and preprocessing the millimeter wave monitoring signal;
The microprocessor is in communication connection with the millimeter wave chip and is used for analyzing the signal types of the millimeter wave monitoring signals by adopting a data pattern recognition model according to the preprocessed millimeter wave monitoring signals and screening the millimeter wave monitoring signals related to the targets; analyzing and calculating target state information by adopting a neural network model according to the millimeter wave monitoring signals related to the target;
the communication module is in communication connection with the microprocessor and is used for sending the target state information to the monitoring server or the user side in real time;
the preprocessing of the millimeter wave monitoring signal specifically comprises the following steps: converting the millimeter wave monitoring signal from an analog signal to a digital signal, and performing inverse Fourier transform on the millimeter wave monitoring signal to obtain a transformed time domain digital signal; sequentially carrying out signal digital filtering, space multipath interference elimination and space noise processing on the time domain digital signals;
The method for performing signal digital filtering on the time domain digital signal specifically comprises the following steps:
S101: setting digital filtering parameters, and performing anti-interference mean digital filtering on the time domain digital signals of the millimeter wave monitoring signals;
S102: predicting the data at the K+1 time from the data at the K time, and estimating the prediction error at the K+1 time from the prediction error at the K time;
S103: calculating Kalman gain according to the data at the K moment and the predicted data at the K+1 moment, calculating the optimal estimated value of the data, and calculating the predicted error of the current moment K;
S104: looping through step S102 and step S103;
The method for eliminating the space multipath interference to the time domain digital signal specifically comprises the following steps:
S201: acquiring a time domain digital signal S K of millimeter waves received after the current moment K is transmitted, and calculating the weight Q K of the current moment K;
s202: acquiring a time domain digital signal S K+1 of millimeter waves transmitted at the moment K+1, and calculating the weight Q K+1 of the moment K+1;
s203: generating multipath interference cancellation amount: Δs=s K·QK-SK+1·QK+1, and effective data after interference cancellation is calculated: s=s K - Δs;
s204: step S201 to step S203 are circulated until all data are converged;
The spatial noise processing for the time domain digital signal specifically comprises:
Performing autocorrelation digital noise signal monitoring and cross correlation digital noise signal monitoring on a time domain digital signal of the millimeter wave monitoring signal, and screening out a digital noise signal;
calculating the phase difference time domain of the digital noise signals, guiding the digital noise signals into a delayer, guiding the output signals of the delayer and the previous noise signals into a multiplier, guiding the output signals of the multiplier into an integrator, guiding the output signals of the integrator into a digital FIR filter, and outputting a digital noise function;
the method for analyzing the signal types of the millimeter wave monitoring signals by adopting a data pattern recognition model according to the preprocessed millimeter wave monitoring signals, and screening the millimeter wave monitoring signals related to targets specifically comprises the following steps:
Judging whether the effective signals of the pre-processed millimeter wave monitoring signals are annihilated or not, if yes, filtering through a self-adaptive weak signal filter, filtering out the effective signals, analyzing the signal types of the effective signals of the millimeter wave monitoring signals by adopting a data pattern recognition model, screening the millimeter wave monitoring signals related to the targets, and eliminating the space stationary object barriers unrelated to the targets; if not, analyzing the signal types of the effective signals of the millimeter wave monitoring signals by adopting a data pattern recognition model, screening the millimeter wave monitoring signals related to the targets, and eliminating the space stationary object barriers unrelated to the targets;
The data pattern recognition model includes:
acquiring an effective signal of the millimeter wave monitoring signal as input data of a data pattern recognition model; carrying out KNN recursion on the data, classifying the data by a Bayesian classifier, carrying out correlation comparison on the data set, extracting the related data as effective data, establishing a related data function, and carrying out data analysis on the related data function;
the method for analyzing and calculating the target state information by adopting the neural network model according to the millimeter wave monitoring signals related to the target specifically comprises the following steps:
Doppler/micro Doppler operation is carried out on millimeter wave monitoring signals related to the target, and space polar coordinate data are obtained; according to Doppler/micro Doppler calculation results and space polar coordinate data, analyzing and calculating target state information by adopting a neural network model;
The target state information includes at least one of: multi-target position information, multi-human body posture information, human body physiological information, and a plurality of moving object information; the position information at least comprises distance, position distribution and angle, the human body posture information at least comprises speed, track, posture, gait and gesture, the human body physiological information at least comprises heart rate, respiration and blood pressure, and the object information at least comprises size, shape and moving speed;
the neural network model includes:
S301: acquiring Doppler/micro Doppler operation results of millimeter wave monitoring signals as learning data of a neural network model;
S302: taking the K moment learning type data vector X K as an input layer;
s303: determining an input weight vector U by a weight value W, and determining a vector function of an implicit layer at the moment K:
SK＝f(UK·XK+W·SK-1)
S304: determining an output weight vector V, and determining a vector function of an output layer at the moment K: o K＝g(V·SK);
S305: finishing the data learning at the moment K, carrying out the data learning at the next moment, and circulating the steps S302 to S305;
After monitoring the target recognition, the method further comprises the steps of eliminating the obstacle of the space static object in a penetrating and bypassing mode;
The neural network model adopts an RNN neural network model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011488371.0A CN112731380B (en) | 2020-12-16 | 2020-12-16 | Human body intelligent monitoring method and monitoring equipment based on millimeter waves |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011488371.0A CN112731380B (en) | 2020-12-16 | 2020-12-16 | Human body intelligent monitoring method and monitoring equipment based on millimeter waves |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112731380A CN112731380A (en) | 2021-04-30 |
| CN112731380B true CN112731380B (en) | 2024-06-14 |
Family
ID=75602487
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011488371.0A Active CN112731380B (en) | 2020-12-16 | 2020-12-16 | Human body intelligent monitoring method and monitoring equipment based on millimeter waves |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112731380B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113645269B (en) * | 2021-06-29 | 2022-06-07 | 北京金茂绿建科技有限公司 | Millimeter wave sensor data transmission method and device, electronic equipment and storage medium |
| CN113786180B (en) * | 2021-10-25 | 2023-10-20 | 中国科学技术大学 | Human blood pressure detection device based on millimeter wave radar signal |
| CN113985393B (en) * | 2021-10-25 | 2024-04-16 | 南京慧尔视智能科技有限公司 | Target detection method, device and system |
| CN116449330B (en) * | 2023-06-20 | 2023-10-13 | 精华隆智慧感知科技（深圳）股份有限公司 | Indoor people number estimation method and device, computer equipment and storage medium |
| CN117031136B (en) * | 2023-09-22 | 2024-03-29 | 北京中成康富科技股份有限公司 | Detection method, device, equipment and storage medium of millimeter wave therapeutic instrument |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111481184A (en) * | 2020-04-24 | 2020-08-04 | 华侨大学 | Multi-target respiration heart rate monitoring method and system based on millimeter wave radar technology |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109581361A (en) * | 2018-11-22 | 2019-04-05 | 九牧厨卫股份有限公司 | A kind of detection method, detection device, terminal and detection system |
| CN111175741B (en) * | 2020-01-10 | 2022-03-18 | 浙江大学 | Single-frequency continuous millimeter wave Doppler sensing microwave wall safety space early warning method |
-
2020
- 2020-12-16 CN CN202011488371.0A patent/CN112731380B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111481184A (en) * | 2020-04-24 | 2020-08-04 | 华侨大学 | Multi-target respiration heart rate monitoring method and system based on millimeter wave radar technology |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112731380A (en) | 2021-04-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112731380B (en) | Human body intelligent monitoring method and monitoring equipment based on millimeter waves | |
| US7358888B2 (en) | System and method for intrusion detection using a time domain radar array | |
| US11435443B2 (en) | Integration of tracking with classifier in mmwave radar | |
| CN112998668B (en) | Millimeter wave-based non-contact far-field multi-human-body respiration heart rate monitoring method | |
| US11041947B2 (en) | Radar detection methods and systems for identifying moving objects | |
| IL265930A (en) | Detection apparatus and method | |
| Giannì et al. | Obstacle detection system involving fusion of multiple sensor technologies | |
| CN112634566B (en) | Intelligent electronic fence construction method and system based on millimeter waves | |
| CN114325623A (en) | Method for measuring human body limb movement information based on millimeter wave radar | |
| Jose et al. | Millimetre wave radar spectra simulation and interpretation for outdoor slam | |
| Kocur et al. | Through wall tracking of moving targets by M-sequence UWB radar | |
| Iqbal et al. | Indoor motion classification using passive RF sensing incorporating deep learning | |
| Kocur et al. | Imaging method: A strong tool for moving target tracking by a multistatic UWB radar system | |
| KR102322480B1 (en) | Position Detecting System and Method of Ultra Wide Band Using the Optimized Detection Threshold at Objects Size and Motion Strenth | |
| Darlis et al. | Autonomous Human and Animal Classification Using Synthetic 2D Tensor Data Based on Dual-Receiver mmWave Radar System | |
| CN115605775A (en) | Method for identifying and classifying objects and motor vehicle | |
| Zande | 3D Point Cloud Object Detection for Millimeter Wave Radar: a Synthesis Study | |
| Kriukova et al. | Motion Zone Estimation for Adaptive Radar-System Parameters Selection | |
| Park et al. | Bi-directional LSTM-based Overhead Target Classification for Automotive Radar Systems | |
| CN117572423B (en) | Doppler aperture same transceiver array radar | |
| WO2022249881A1 (en) | Electronic device, method for controlling electronic device, and program | |
| Haritha et al. | Investigation on Indoor Detection and Tracking of People using IWR1642 mmWave Sensor | |
| Cheredachuk et al. | Adaptive Algorithm for Radar-System Parameters Tuning by means of Motion Zone Estimation | |
| Streck et al. | Comparison of two different radar concepts for pedestrian protection on bus stops | |
| Cheredarchuk et al. | Adaptive radar system configuration tuning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |