CN112731332A - Millimeter wave-based static target existence identification method and system - Google Patents
Millimeter wave-based static target existence identification method and system Download PDFInfo
- Publication number
- CN112731332A CN112731332A CN202110040979.5A CN202110040979A CN112731332A CN 112731332 A CN112731332 A CN 112731332A CN 202110040979 A CN202110040979 A CN 202110040979A CN 112731332 A CN112731332 A CN 112731332A
- Authority
- CN
- China
- Prior art keywords
- static
- millimeter wave
- wave sensing
- data
- sensing signals
- 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.)
- Pending
Links
- 230000003068 static effect Effects 0.000 title claims abstract description 200
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000012544 monitoring process Methods 0.000 claims abstract description 74
- 238000013528 artificial neural network Methods 0.000 claims abstract description 32
- 238000003909 pattern recognition Methods 0.000 claims abstract description 16
- 238000001914 filtration Methods 0.000 claims description 17
- 230000006870 function Effects 0.000 claims description 13
- 230000008030 elimination Effects 0.000 claims description 11
- 238000003379 elimination reaction Methods 0.000 claims description 11
- 230000007613 environmental effect Effects 0.000 claims description 11
- 238000007781 pre-processing Methods 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 8
- 230000000306 recurrent effect Effects 0.000 claims description 7
- 238000006073 displacement reaction Methods 0.000 claims description 4
- 230000000694 effects Effects 0.000 claims description 4
- 239000011159 matrix material Substances 0.000 claims description 4
- 230000005540 biological transmission Effects 0.000 claims description 3
- 238000005314 correlation function Methods 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 230000007787 long-term memory Effects 0.000 claims description 2
- 230000006403 short-term memory Effects 0.000 claims description 2
- 238000001514 detection method Methods 0.000 description 13
- 238000012790 confirmation Methods 0.000 description 4
- 230000015654 memory Effects 0.000 description 4
- 238000005192 partition Methods 0.000 description 4
- 230000036544 posture Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 238000012423 maintenance Methods 0.000 description 2
- 238000002203 pretreatment Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 230000007958 sleep Effects 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
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
- 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
- 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
- G01S13/04—Systems determining presence of a 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
- G01S13/06—Systems determining position data of a 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
- G06F18/24147—Distances to closest patterns, e.g. nearest neighbour classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Abstract
The invention provides a static target existence identification method and a system based on millimeter waves, wherein the method comprises the following steps: emitting linear frequency modulation continuous millimeter waves into a monitoring space through one or more millimeter wave sensing devices, and receiving millimeter wave sensing signals reflected in the monitoring space in real time; the millimeter wave sensing signals comprise initial sensing signals and sensing signals to be identified; constructing a spatial environment static model based on the preprocessed initial sensing signals; identifying and analyzing the spatial position of the static target by adopting a neural network based on the preprocessed to-be-identified sensing signal; importing the spatial position of the static target to be identified and spatial environment static model data into a pattern recognition classification learning device, outputting a static human body or an environment static object, and determining the static human body existing in the monitored space; and transmitting the spatial position information of the static human body in the monitoring space to a monitoring server or a user side in real time. The method improves the identification accuracy of the static human body, reduces the misjudgment rate and does not infringe the personal privacy.
Description
Technical Field
The invention relates to the technical field of communication and monitoring of the Internet of things, in particular to a static target existence identification method and system based on millimeter waves.
Background
The millimeter wave refers to an electromagnetic wave with a wavelength of 1-10 mm, and is located in a wavelength range where microwave and far-infrared wave are overlapped, so that the millimeter wave has the characteristics of two wave spectrums. Compared with light waves, the millimeter waves are less influenced by natural light and a thermal radiation source; the device has extremely wide bandwidth, the frequency range of millimeter waves is 30GHz-300GHz, and the device has the characteristics of high precision and high resolution; the beam of the millimeter wave is narrow, and the beam of the millimeter wave is much narrower than that of the microwave under the same antenna size, so that small targets which are closer to each other can be distinguished or the details of the targets can be observed more clearly. The propagation of millimeter waves is much less affected by weather than laser light and can be considered to be all-weather. Compared with microwaves, millimeter wave components are much smaller in size and easier to miniaturize.
At present, the accurate judgment of the far-field static human body has wide rigidity requirements in the application fields of intelligent homes, intelligent offices, intelligent hotels, intelligent household appliances and the like. For example, when a human body is in a static posture such as lying or sleeping, dozing, or standing on a desk, the intelligent system needs to accurately determine whether the human body still exists in the detection space, and if it is determined that the human body leaves the detection space, the intelligent system turns off lights, air conditioners, televisions and other electrical appliances according to the corresponding application scenes, so as to achieve the purpose of effectively saving energy. And otherwise, when the human body is still confirmed to be in the detection space, the various electric appliances are still in the state of being used by the user. In the prior art, monitoring technologies for recognizing the existence of a static human body generally adopt infrared induction, ultrasonic detection, microwave detection and the like, and have the problems of low recognition rate, high misjudgment rate, poor user experience and the like. Although a camera may be used for monitoring, the use of a camera is prone to personal privacy violations.
Disclosure of Invention
In view of the above-mentioned shortcomings of the prior art, the present invention aims to: the millimeter wave technology is adopted, a space environment static object model is constructed in advance, static object data in a monitoring space are stored in advance, then a neural network algorithm is adopted to analyze the position of a static object to be identified in the monitoring space, and a static human body in the monitoring space is determined through a pattern recognition classification learning device. The method improves the identification accuracy of the static human body, reduces the misjudgment rate and does not infringe the personal privacy.
A static target existence identification method based on millimeter waves comprises the following steps:
emitting linear frequency modulation continuous millimeter waves into a monitoring space through one or more millimeter wave sensing devices, and receiving millimeter wave sensing signals reflected in the monitoring space in real time; the millimeter wave sensing signals comprise initial millimeter wave sensing signals and millimeter wave sensing signals to be identified;
preprocessing the received millimeter wave sensing signals, analyzing and calculating initial physical values of the static targets according to the preprocessed initial millimeter wave sensing signals, and constructing a static model of the space environment based on the initial physical values;
analyzing and calculating a real-time physical value of the static target according to the preprocessed millimeter wave sensing signals to be recognized, and recognizing and analyzing the spatial position of the static target by adopting a neural network based on the real-time physical value;
importing the spatial position of the static target to be identified and spatial environment static model data into a pattern recognition classification learning device, outputting a static human body or an environment static object, and determining the static human body existing in the monitored space;
and transmitting the spatial position information of the static human body in the monitoring space to a monitoring server or a user side in real time.
Further, the initial physical value includes a distance and an angle of a static object of the environment in the monitoring space and a signal intensity amplitude of the initial millimeter wave sensing signal, and the real-time physical value includes a distance and an angle of a static human body or the static object of the environment in the monitoring space and a signal intensity amplitude of the millimeter wave sensing signal to be identified.
Further, the analyzing and calculating a real-time physical value of the static target according to the preprocessed millimeter wave sensing signal to be recognized, and recognizing and analyzing the spatial position of the static target by using a neural network based on the real-time physical value specifically includes:
performing Doppler operation on the preprocessed millimeter wave sensing signals to be recognized to obtain real-time physical values of static targets, and performing obstacle elimination on static objects in the monitored space environment and the static targets without Doppler effect;
calculating the polar coordinates of the static target based on the real-time physical value of the static target, and constructing an array matrix according to the polar coordinate set of the static target and the corresponding amplitude value;
and when the Doppler displacement of the static target is zero, analyzing the spatial position of the static target by adopting a neural network according to the polar coordinates of the static target.
Further, the method for constructing the static model of the space environment comprises the following steps:
scanning a static monitoring space for N times through millimeter wave sensing equipment; acquiring distance, angle and amplitude data corresponding to each scanning, wherein the amplitude is a two-dimensional correlation function of the distance and the angle;
comparing whether the amplitude data at the moment k and the amplitude data at the moment k +1 are within the tolerance range of the tolerance delta;
if the comparison data of the k +1 moment at the same distance and angle is smaller than the tolerance delta, the reflection point cloud of the static object of the real space environment is obtained;
and repeating N times of data comparison on each real reflection point cloud, determining all real reflection point cloud sets of the static objects of the space environment, and storing data and coordinates of all environment static object point cloud sets.
Further, the neural network adopts a long-short term memory recurrent neural network LSTM, and the learning process of the LSTM neural network is as follows:
s101: acquiring a learning type data vector Xk at the moment k, using the learning type data vector Xk as an input layer, and determining an input weight vector U by a weight value W;
s102: determining a vector function Sk ═ f (Uk · Xk + W · Sk-1) of the hidden layer at the moment k; wherein Uk represents an input weight vector at the moment k, and Sk-1 represents a vector function of a hidden layer at the moment k-1;
s103: setting an output weight vector V, and determining a vector function Ok of an output layer at the moment k as g (V & Sk);
s104: after the learning of the data at time k is completed, steps S101 to S103 are executed in a loop.
Further, the pattern recognition classification learner adopts a KNN classifier, and the recognition process of the KNN classifier is as follows:
acquiring a data set in a subset space, and calculating data samples based on an Euclidean distance function;
acquiring k nearest training samples in the data samples, and performing weighted average on the k samples based on the distance;
and selecting the category with the most occurrence in the k samples, taking the obtained weighted average as a corresponding category, and outputting the identified category as the corresponding posture.
Further, the preprocessing the received millimeter wave sensing signal specifically includes:
converting the millimeter wave sensing signal from an analog signal to a digital signal, performing inverse Fourier transform on the millimeter wave sensing signal, and converting the frequency domain digital signal into a time domain digital signal; and sequentially carrying out digital filtering processing, spatial multipath interference elimination and spatial noise processing on the time domain digital signal.
Further, performing signal digital filtering on the time domain digital signal specifically includes:
s201: setting digital filtering parameters, and carrying out anti-interference mean digital filtering on the time domain digital signals of the millimeter wave sensing signals;
s202: predicting data at the K +1 th moment by the data at the K th moment, and estimating a prediction error at the K +1 th moment by the prediction error at the K th moment;
s203: calculating Kalman gain according to the data at the K moment and the prediction data at the K +1 moment, calculating the optimal estimation value of the data, and calculating the prediction error of the current moment K;
s204: step S202 and step S203 are looped.
Further, the spatial multi-path interference cancellation is performed on the time domain digital signal, which specifically includes:
s301: acquiring a time domain digital signal S of millimeter waves received after transmission at the current moment KKCalculating the weight Q of the current time KK；
S302: acquiring time domain digital signal S of millimeter wave transmitted at K moment and received by K +1K+1Calculating the weight Q at the time K +1K+1；：
S303: generating a multipath interference cancellation amount: Δ S ═ SK·QK-SK+1·QK+1And calculating effective data after interference cancellation: s ═ SK-ΔS；
S304: and (6) looping the steps S301 to S303 until all data converge.
A millimeter wave based static target presence identification system comprising:
the millimeter wave sensing equipment is used for transmitting linear frequency modulation continuous millimeter waves into the monitoring space and receiving millimeter wave sensing signals reflected in the monitoring space in real time; preprocessing received millimeter wave sensing signals, wherein the millimeter wave sensing signals comprise initial millimeter wave sensing signals and millimeter wave sensing signals to be identified;
the environment static model building module is used for analyzing and calculating an initial physical value of the static target according to the preprocessed initial millimeter wave sensing signal and building a space environment static model based on the initial physical value;
the recognition analysis module is used for analyzing and calculating a real-time physical value of the static target according to the preprocessed millimeter wave sensing signals to be recognized and recognizing and analyzing the spatial position of the static target by adopting a neural network based on the real-time physical value;
the target existence confirming module is used for importing the spatial position of the static target to be identified and spatial environment static object model data into the pattern recognition classification learning device, outputting a static human body or an environmental static object, and determining the static human body existing in the monitored space;
and the monitoring server or the user side is used for monitoring the monitoring space in real time.
Compared with the prior art, the invention has the following advantages:
the invention provides a static target existence recognition method and system based on millimeter waves, which can be applied to intelligent homes, intelligent hotels, intelligent offices and the like, a space environment static model is constructed in advance by adopting millimeter wave technology, static target data in a monitoring space are stored in advance, then the position of a static target to be recognized in the monitoring space is analyzed by adopting a neural network algorithm, and a static human body existing in the monitoring space is determined by a pattern recognition classification learner. The method improves the identification accuracy of the static human body, reduces the misjudgment rate and does not infringe the personal privacy.
Drawings
Fig. 1 is a flowchart illustrating an identification method for identifying existence of a static target based on millimeter waves according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating a process of determining a spatial position of a static target in a monitored space according to an embodiment of the present invention;
FIG. 3 is a flow chart of a method for constructing a spatial environment static model according to an embodiment of the present invention;
FIG. 4 is a flowchart illustrating the learning process of the medium-and-long term memory recurrent neural network LSTM according to an embodiment of the present invention;
fig. 5 is a flow chart of the KNN classifier according to an embodiment of the present invention;
FIG. 6 is a flowchart illustrating digital filtering of a time-domain digital signal according to an embodiment of the present invention;
fig. 7 is a flowchart illustrating spatial multi-path interference cancellation for time-domain digital signals according to an embodiment of the present invention;
fig. 8 is a system block diagram of a millimeter wave-based static target presence recognition system according to a second embodiment of the present invention.
Detailed Description
Embodiments of the present invention will be described in detail below with reference to the accompanying drawings. The following examples are only for illustrating the technical solutions of the present invention more clearly, and therefore are only examples, and the protection scope of the present invention is not limited thereby.
The first embodiment is as follows:
referring to fig. 1, a static target existence recognition method based on millimeter waves includes the following steps:
emitting linear frequency modulation continuous millimeter waves into a monitoring space through one or more millimeter wave sensing devices, and receiving millimeter wave sensing signals reflected in the monitoring space in real time; the millimeter wave sensing signals comprise initial millimeter wave sensing signals and millimeter wave sensing signals to be identified. Specifically, the monitoring space is freely selected by a user, and can be an intelligent home space, an intelligent hotel space, an intelligent office space and the like; the arrangement number of the millimeter wave sensing devices can be specifically determined according to the size of the monitoring space, whether a partition wall exists or not, for example, in a house, because the walls partition the rooms, the living rooms, the kitchens and the like, the millimeter wave sensing devices are required to be arranged in the rooms, the living rooms, the kitchens and the like respectively; if the device is used for an open office, only one millimeter wave sensing device is needed to meet the requirement.
Preprocessing the received millimeter wave sensing signals, analyzing and calculating initial physical values of the static targets according to the preprocessed initial millimeter wave sensing signals, and constructing a static model of the space environment based on the initial physical values. Specifically, the pretreatment method comprises the following steps: converting the millimeter wave sensing signal from an analog signal to a digital signal, performing inverse Fourier transform on the millimeter wave sensing signal, and converting the frequency domain digital signal into a time domain digital signal; the digital filtering processing, the space multipath interference elimination and the secondary elimination of the possible environmental noise and harmonic noise are carried out on the time domain digital signal in sequence. The initial physical values include the distance, angle, and signal strength amplitude RSS of the initial millimeter wave sensing signal of the environmental still in the monitored space, so that the data of the still object in the monitored space is stored in advance. The environmental still includes walls, ceilings, furniture, large household appliances, televisions, computers and the like.
And analyzing and calculating a real-time physical value of the static target according to the preprocessed millimeter wave sensing signals to be recognized, and recognizing and analyzing the spatial position of the static target by adopting a neural network based on the real-time physical value. Specifically, the real-time physical value includes a distance and an angle of a static human body or a static object in the monitored space and a signal intensity amplitude RSS of the millimeter wave sensing signal to be recognized, and a detailed method for recognizing and analyzing the spatial position of the static target by using a neural network based on the real-time physical value is described below.
And importing the spatial position of the static target to be identified and spatial environment static model data into a pattern recognition classification learning device, outputting a static human body or an environment static object, and determining the static human body existing in the monitored space. Specifically, the KNN pattern recognition classification learner is used for accurately distinguishing the environmental still object from the static human body, so that the human body is determined to be in the detection space. The static human body existing in the monitoring space is determined, and the determination step aims to improve the identification accuracy of the static human body and reduce the misjudgment rate.
And transmitting the spatial position information of the static human body in the monitoring space to a monitoring server or a user side in real time.
The millimeter wave-based static target existence identification method can be applied to identification and existence confirmation of static human bodies in places such as smart homes, smart hotels, smart offices and the like, firstly, reflected digital signals of a monitoring space after denoising and filtering are obtained, a space environment static object model is constructed in advance based on initial emitted digital signals, static object data in the monitoring space are stored in advance, then, the position of a static object to be identified in the monitoring space is analyzed by adopting a neural network algorithm, and the static human body existing in the monitoring space is determined by a pattern recognition classification learner. Through the secondary static human body existence confirmation of the classification learner, the identification accuracy of the static human body existence can be effectively improved, the misjudgment rate is reduced, and meanwhile, the individual privacy is not invaded.
The static target existence identification method can be applied to the following scenes: when a human body is in static postures such as sleeping, napping, or standing on desk, the intelligent system needs to accurately judge whether the human body still exists in the detection space, and if the human body is confirmed to leave the detection area, light, an air conditioner, a television and other electrical appliances are turned off according to corresponding application scenes, so that the aim of effectively saving energy is fulfilled. And otherwise, when the human body is still confirmed to be in the detection space, the various electric appliances are still in the state of being used by the user. Two examples are specifically described below:
in the application scene of intelligent office, no matter independent office or open office space, after the millimeter wave sensor detects and confirms that the human body really leaves the detection area, no human body existence is detected within five minutes (the time can be set by a user), the system puts the light, the air conditioner and other electric appliances into an energy-saving state (such as dimming the light, standby the air conditioner and the like), and if the human body existence is not detected within ten minutes (the time can be set by the user), the system completely turns off the light, the air conditioner and other electric appliances. When the human body is detected to return to the detection area, the system can recover the normal use of the electrical appliances such as light, air conditioners and the like. If the office staff are at a desk and still, the millimeter wave sensor still detects the existence of the human body, and the normal use state of the office appliance is kept.
In the application scene of the intelligent hotel, accurate identification of the static human body is vital to energy-saving management of guest rooms. When the millimeter wave sensor detects and confirms that the guest of the guest room leaves the room, no human body is detected within five minutes (the time can be set by a user), the system puts the electrical appliances of the guest room such as the light, the air conditioner, the television and the like into an energy-saving state (for example, the light is dimmed, the set temperature of the air conditioner is increased in summer, the set temperature of the air conditioner is decreased in winter and the like to save energy), and if no human body is detected within ten minutes (the time can be set by the user), the system completely turns off the light, the air conditioner, the television and other electrical appliances of the guest room. When the human body is detected to return to the detection area, the system can recover the normal use of the electrical appliances of the guest room such as light, an air conditioner, a television and the like. When the tenant still lies in the room for rest or sleeps for dozing, the millimeter wave sensor detects that the human body is still in the room, and the electrical appliances of the guest room such as light, an air conditioner, a television and the like can be kept in the setting state of the tenant.
Referring to fig. 2, the analyzing and calculating a real-time physical value of the static target according to the preprocessed millimeter wave sensing signal to be recognized, and recognizing and analyzing a spatial position of the static target by using a neural network based on the real-time physical value specifically includes:
performing Doppler operation on the preprocessed millimeter wave sensing signals to be recognized to obtain real-time physical values of static targets, and performing obstacle elimination on static objects in the monitored space environment and the static targets without Doppler effect;
calculating the polar coordinates of the static target based on the real-time physical value of the static target, and constructing an array matrix according to the polar coordinate set of the static target and the corresponding amplitude value;
and when the Doppler displacement of the static target is zero, analyzing the spatial position of the static target by adopting a neural network according to the polar coordinates of the static target.
Specifically, Doppler operation is carried out on the effective point cloud set data, and the static objects and other objects which are not in Doppler effect and stored by the system are eliminated. And calculating the polar coordinates of the one or more human body targets according to the distance and angle data obtained by preprocessing. In the post-statics elimination space, all amplitudes (RSS) and corresponding sets of polar coordinates form an array matrix. The long-short term memory recurrent neural network (LSTM) under the Recurrent Neural Network (RNN) is used for machine learning to obtain one or more spatial positions of the human body. And recording the point cloud data of the human body with the Doppler displacement becoming zero and recording the space position of the human body according to the result.
Referring to fig. 3, the method for constructing the static environment model of the space environment is as follows:
scanning a static monitoring space for N times through millimeter wave sensing equipment; acquiring distance, angle and amplitude data corresponding to each scanning, wherein the amplitude is a two-dimensional correlation function of the distance and the angle;
comparing whether the amplitude data at the moment k and the amplitude data at the moment k +1 are within the tolerance range of the tolerance delta;
if the comparison data of the k +1 moment at the same distance and angle is smaller than the tolerance delta, the reflection point cloud of the static object of the real space environment is obtained;
and repeating N times of data comparison on each real reflection point cloud, determining all real reflection point cloud sets of the static objects of the space environment, and storing data and coordinates of all environment static object point cloud sets.
Therefore, the static object data in the monitoring space can be stored in advance, the influence of the static object of the environment on the static object identification when the static human body is identified is prevented, the identification accuracy of the static human body in the monitoring space is improved, and the misjudgment rate is reduced.
Referring to fig. 4, the neural network adopts a long-short term memory recurrent neural network LSTM, and the learning process of the LSTM neural network is as follows:
s101: acquiring a learning type data vector Xk at the moment k, using the learning type data vector Xk as an input layer, and determining an input weight vector U by a weight value W;
s102: determining a vector function Sk ═ f (Uk · Xk + W · Sk-1) of the hidden layer at the moment k; wherein Uk represents an input weight vector at the moment k, and Sk-1 represents a vector function of a hidden layer at the moment k-1;
s103: setting an output weight vector V, and determining a vector function Ok of an output layer at the moment k as g (V & Sk);
s104: after the learning of the data at time k is completed, steps S101 to S103 are executed in a loop.
Therefore, the position of the static target to be identified in the monitoring space can be effectively analyzed through the long-term and short-term memory recurrent neural network LSTM, the spatial position identification accuracy is high, and the identification result is stable.
Referring to fig. 5, the pattern recognition classification learner employs a KNN classifier, and the recognition process of the KNN classifier is as follows:
acquiring a data set in a subset space, and calculating data samples based on an Euclidean distance function;
acquiring k nearest training samples in the data samples, and performing weighted average on the k samples based on the distance;
and selecting the category with the most occurrence in the k samples, taking the obtained weighted average as a corresponding category, and outputting the identified category as the corresponding posture.
Therefore, the static human body in the monitoring space is secondarily determined through the KNN classifier, so that the identification accuracy of the static human body can be further effectively improved, the misjudgment rate is reduced, and meanwhile, the individual privacy is not invaded.
Referring to fig. 6, the signal digital filtering on the time domain digital signal specifically includes:
s201: setting digital filtering parameters, and carrying out anti-interference mean digital filtering on the time domain digital signals of the millimeter wave sensing signals;
s202: predicting data at the K +1 th moment by the data at the K th moment, and estimating a prediction error at the K +1 th moment by the prediction error at the K th moment;
s203: calculating Kalman gain according to the data at the K moment and the prediction data at the K +1 moment, calculating the optimal estimation value of the data, and calculating the prediction error of the current moment K;
s204: step S202 and step S203 are looped.
In this way, the interference signal in the millimeter wave monitoring signal can be preliminarily filtered.
Referring to fig. 7, the spatial multipath interference cancellation for the time domain digital signal specifically includes:
s301: acquiring a time domain digital signal S of millimeter waves received after transmission at the current moment KKCalculating the weight Q of the current time KK；
S302: acquiring time domain digital signal S of millimeter wave transmitted at K moment and received by K +1K+1Calculating the weight Q at the time K +1K+1；：
S303: generating a multipath interference cancellation amount: Δ S ═ SK·QK-SK+1·QK+1And calculating effective data after interference cancellation: s ═ SK-ΔS；
S304: and (6) looping the steps S301 to S303 until all data converge.
Thus, the interference signal in the millimeter wave monitoring signal can be effectively eliminated.
In the above method for identifying existence of a static target based on millimeter waves, the method for performing spatial noise processing on the time domain digital signal of the millimeter wave monitoring signal is as follows:
carrying out autocorrelation digital noise signal monitoring and cross-correlation digital noise signal monitoring on the 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 signal, introducing the digital noise signal into a delayer, introducing the output signal of the delayer and the antecedent noise signal into a multiplier, introducing the output signal of the multiplier into an integrator, introducing the output signal of the integrator into a digital FIR filter, and outputting a digital noise function.
In this way, the noise signal in the millimeter wave monitor signal can be effectively eliminated. For millimeter wave signals collected in a monitoring space, the preprocessing of the millimeter wave signals is sequentially subjected to the digital filtering, the spatial multipath interference elimination, the spatial 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 then powerful data support is provided for subsequent target identification and target state analysis, the sensitivity and the agility of target identification are ensured, the accuracy and the reliability of a target monitoring result are improved, and the anti-interference capability is strong.
Example two:
referring to fig. 8, a millimeter wave based static target presence recognition system includes:
the millimeter wave sensing equipment is used for transmitting linear frequency modulation continuous millimeter waves into the monitoring space and receiving millimeter wave sensing signals reflected in the monitoring space in real time; preprocessing received millimeter wave sensing signals, wherein the millimeter wave sensing signals comprise initial millimeter wave sensing signals and millimeter wave sensing signals to be identified. Specifically, the monitoring space is freely selected by a user, and can be an intelligent home space, an intelligent hotel space, an intelligent office space and the like; the arrangement number of the millimeter wave sensing devices can be specifically determined according to the size of the monitoring space, whether a partition wall exists or not, for example, in a house, because the walls partition the rooms, the living rooms, the kitchens and the like, the millimeter wave sensing devices are required to be arranged in the rooms, the living rooms, the kitchens and the like respectively; if the device is used for an open office, only one millimeter wave sensing device is needed to meet the requirement. The pretreatment method comprises the following steps: converting the millimeter wave sensing signal from an analog signal to a digital signal, performing inverse Fourier transform on the millimeter wave sensing signal, and converting the frequency domain digital signal into a time domain digital signal; the digital filtering processing, the space multipath interference elimination and the secondary elimination of the possible environmental noise and harmonic noise are carried out on the time domain digital signal in sequence.
And the environment static model building module is used for analyzing and calculating an initial physical value of the static target according to the preprocessed initial millimeter wave sensing signal and building a space environment static model based on the initial physical value. Specifically, the initial physical values include the distance, angle, and signal strength amplitude RSS of the initial millimeter wave sensing signal of the environmental still in the monitored space, so that the still object data in the monitored space is stored in advance. The environmental still includes walls, ceilings, furniture, large household appliances, televisions, computers and the like.
And the recognition analysis module is used for analyzing and calculating a real-time physical value of the static target according to the preprocessed millimeter wave sensing signals to be recognized and recognizing and analyzing the spatial position of the static target by adopting a neural network based on the real-time physical value. Specifically, the real-time physical value includes a distance and an angle of a static human body or a static object in the monitored space and a signal intensity amplitude RSS of the millimeter wave sensing signal to be recognized, and the detailed method for recognizing and analyzing the spatial position of the static target by using the neural network based on the real-time physical value is as described above.
And the target existence confirming module is used for importing the spatial position of the static target to be identified and the spatial environment static object model data into the pattern recognition classification learning device, outputting a static human body or an environmental static object, and determining the static human body existing in the monitored space. Specifically, the KNN pattern recognition classification learner is used for accurately distinguishing the environmental still object from the static human body, so that the human body is determined to be in the detection space. The static human body existing in the monitoring space is determined, and the determination step aims to improve the identification accuracy of the static human body and reduce the misjudgment rate.
And the monitoring server or the user side is used for monitoring the monitoring space in real time. The system also comprises a user maintenance platform used for operation management and maintenance of the system data.
The millimeter wave-based static target existence recognition system can be applied to recognition and existence confirmation of static human bodies in places such as smart homes, smart hotels, smart offices and the like, firstly, reflected digital signals of a monitoring space after denoising and filtering are obtained, a space environment static object model is constructed in advance based on initial emitted digital signals, static object data in the monitoring space are stored in advance, then, the position of a static object to be recognized in the monitoring space is analyzed by adopting a neural network algorithm, and the static human body existing in the monitoring space is determined through a pattern recognition classification learner. Through the secondary static human body existence confirmation of the classification learner, the identification accuracy of the static human body existence can be effectively improved, the misjudgment rate is reduced, and meanwhile, the individual privacy is not invaded.
Finally, the above embodiments are only used for illustrating the technical solutions of the present invention and not for limiting, although the present invention is described in detail with reference to the embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions can be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all of them should be covered in the protection scope of the present invention.
Claims (10)
1. A static target existence identification method based on millimeter waves is characterized by comprising the following steps:
emitting linear frequency modulation continuous millimeter waves into a monitoring space through one or more millimeter wave sensing devices, and receiving millimeter wave sensing signals reflected in the monitoring space in real time; the millimeter wave sensing signals comprise initial millimeter wave sensing signals and millimeter wave sensing signals to be identified;
preprocessing the received millimeter wave sensing signals, analyzing and calculating initial physical values of the static targets according to the preprocessed initial millimeter wave sensing signals, and constructing a static model of the space environment based on the initial physical values;
analyzing and calculating a real-time physical value of the static target according to the preprocessed millimeter wave sensing signals to be recognized, and recognizing and analyzing the spatial position of the static target by adopting a neural network based on the real-time physical value;
importing the spatial position of the static target to be identified and spatial environment static model data into a pattern recognition classification learning device, outputting a static human body or an environment static object, and determining the static human body existing in the monitored space;
and transmitting the spatial position information of the static human body in the monitoring space to a monitoring server or a user side in real time.
2. The millimeter wave-based static target presence recognition method according to claim 1, wherein the initial physical values comprise distances and angles of static objects in the monitoring space and signal strength amplitudes of initial millimeter wave sensing signals, and the real-time physical values comprise distances and angles of static human bodies or static objects in the monitoring space and signal strength amplitudes of millimeter wave sensing signals to be recognized.
3. The millimeter wave-based static target existence recognition method according to claim 2, wherein the analyzing and calculating a real-time physical value of the static target according to the preprocessed millimeter wave sensing signal to be recognized, and recognizing and analyzing a spatial position of the static target by using a neural network based on the real-time physical value specifically comprises:
performing Doppler operation on the preprocessed millimeter wave sensing signals to be recognized to obtain real-time physical values of static targets, and performing obstacle elimination on static objects in the monitored space environment and the static targets without Doppler effect;
calculating the polar coordinates of the static target based on the real-time physical value of the static target, and constructing an array matrix according to the polar coordinate set of the static target and the corresponding amplitude value;
and when the Doppler displacement of the static target is zero, analyzing the spatial position of the static target by adopting a neural network according to the polar coordinates of the static target.
4. The millimeter wave-based static object existence recognition method according to claim 2, wherein the spatial environment static object model is constructed by the following method:
scanning a static monitoring space for N times through millimeter wave sensing equipment; acquiring distance, angle and amplitude data corresponding to each scanning, wherein the amplitude is a two-dimensional correlation function of the distance and the angle;
comparing whether the amplitude data at the moment k and the amplitude data at the moment k +1 are within the tolerance range of the tolerance delta;
if the comparison data of the k +1 moment at the same distance and angle is smaller than the tolerance delta, the reflection point cloud of the static object of the real space environment is obtained;
and repeating N times of data comparison on each real reflection point cloud, determining all real reflection point cloud sets of the static objects of the space environment, and storing data and coordinates of all environment static object point cloud sets.
5. The millimeter wave based static object presence recognition method according to claim 1, wherein the neural network employs a long and short term memory recurrent neural network LSTM, the learning process of the LSTM neural network is as follows:
s101: acquiring a learning type data vector Xk at the moment k, using the learning type data vector Xk as an input layer, and determining an input weight vector U by a weight value W;
s102: determining a vector function Sk ═ f (Uk · Xk + W · Sk-1) of the hidden layer at the moment k; wherein Uk represents an input weight vector at the moment k, and Sk-1 represents a vector function of a hidden layer at the moment k-1;
s103: setting an output weight vector V, and determining a vector function Ok of an output layer at the moment k as g (V & Sk);
s104: after the learning of the data at time k is completed, steps S101 to S103 are executed in a loop.
6. The millimeter wave based static object presence recognition method according to claim 1, wherein the pattern recognition classification learner employs a KNN classifier, and the KNN classifier performs the following recognition process:
acquiring a data set in a subset space, and calculating data samples based on an Euclidean distance function;
acquiring k nearest training samples in the data samples, and performing weighted average on the k samples based on the distance;
and selecting the category with the most occurrence in the k samples, taking the obtained weighted average as a corresponding category, and outputting the identified category as the corresponding posture.
7. The millimeter wave-based static object presence recognition method according to claim 1, wherein the preprocessing the received millimeter wave sensing signal specifically comprises:
converting the millimeter wave sensing signal from an analog signal to a digital signal, performing inverse Fourier transform on the millimeter wave sensing signal, and converting the frequency domain digital signal into a time domain digital signal; and sequentially carrying out digital filtering processing, spatial multipath interference elimination and spatial noise processing on the time domain digital signal.
8. The millimeter wave-based static object presence recognition method according to claim 7, wherein the signal digital filtering is performed on the time domain digital signal, and specifically comprises:
s201: setting digital filtering parameters, and carrying out anti-interference mean digital filtering on the time domain digital signals of the millimeter wave sensing signals;
s202: predicting data at the K +1 th moment by the data at the K th moment, and estimating a prediction error at the K +1 th moment by the prediction error at the K th moment;
s203: calculating Kalman gain according to the data at the K moment and the prediction data at the K +1 moment, calculating the optimal estimation value of the data, and calculating the prediction error of the current moment K;
s204: step S202 and step S203 are looped.
9. The millimeter wave-based static object existence recognition method according to claim 7, wherein the spatial multi-path interference cancellation is performed on the time domain digital signal, and specifically comprises:
s301: acquiring a time domain digital signal S of millimeter waves received after transmission at the current moment KKCalculating the weight Q of the current time KK；
S302: acquiring time domain digital signal S of millimeter wave transmitted at K moment and received by K +1K+1Calculating the weight Q at the time K +1K+1；：
S303: generating a multipath interference cancellation amount: Δ S ═ SK·QK-SK+1·QK+1And calculating effective data after interference cancellation: s ═ SK-ΔS；
S304: and (6) looping the steps S301 to S303 until all data converge.
10. A millimeter wave based static target presence identification system, comprising:
the millimeter wave sensing equipment is used for transmitting linear frequency modulation continuous millimeter waves into the monitoring space and receiving millimeter wave sensing signals reflected in the monitoring space in real time; preprocessing received millimeter wave sensing signals, wherein the millimeter wave sensing signals comprise initial millimeter wave sensing signals and millimeter wave sensing signals to be identified;
the environment static model building module is used for analyzing and calculating an initial physical value of the static target according to the preprocessed initial millimeter wave sensing signal and building a space environment static model based on the initial physical value;
the recognition analysis module is used for analyzing and calculating a real-time physical value of the static target according to the preprocessed millimeter wave sensing signals to be recognized and recognizing and analyzing the spatial position of the static target by adopting a neural network based on the real-time physical value;
the target existence confirming module is used for importing the spatial position of the static target to be identified and spatial environment static object model data into the pattern recognition classification learning device, outputting a static human body or an environmental static object, and determining the static human body existing in the monitored space;
and the monitoring server or the user side is used for monitoring the monitoring space in real time.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110040979.5A CN112731332A (en) | 2021-01-13 | 2021-01-13 | Millimeter wave-based static target existence identification method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110040979.5A CN112731332A (en) | 2021-01-13 | 2021-01-13 | Millimeter wave-based static target existence identification method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112731332A true CN112731332A (en) | 2021-04-30 |
Family
ID=75592829
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110040979.5A Pending CN112731332A (en) | 2021-01-13 | 2021-01-13 | Millimeter wave-based static target existence identification method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112731332A (en) |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001349942A (en) * | 2000-06-12 | 2001-12-21 | Toto Ltd | Human body detecting device |
| US6438491B1 (en) * | 1999-08-06 | 2002-08-20 | Telanon, Inc. | Methods and apparatus for stationary object detection |
| US20030122703A1 (en) * | 2001-12-11 | 2003-07-03 | Masayuki Kishida | Radar data processing apparatus and data processing method |
| CN110045370A (en) * | 2019-05-10 | 2019-07-23 | 成都宋元科技有限公司 | Human perception method and its system based on millimetre-wave radar |
| US20190227156A1 (en) * | 2018-01-22 | 2019-07-25 | Infineon Technologies Ag | System and method for human behavior modelling and power control using a millimeter-wave radar sensor |
| CN110118966A (en) * | 2019-05-28 | 2019-08-13 | 长沙莫之比智能科技有限公司 | Personnel's detection and number system based on millimetre-wave radar |
| US20190317191A1 (en) * | 2018-04-11 | 2019-10-17 | Infineon Technologies Ag | Human Detection and Identification in a Setting Using Millimiter-Wave Radar |
| US20200081118A1 (en) * | 2018-09-07 | 2020-03-12 | Baidu Online Network Technology (Beijing) Co., Ltd. | Method and apparatus for determining static state of obstacle |
| US20200116850A1 (en) * | 2018-10-16 | 2020-04-16 | Infineon Technologies Ag | Estimating Angle of Human Target Using mmWave Radar |
| CN111289967A (en) * | 2020-03-31 | 2020-06-16 | 四川长虹电器股份有限公司 | Personnel detection tracking and counting algorithm based on millimeter wave radar |
| CN111474537A (en) * | 2020-04-20 | 2020-07-31 | 广州桑瑞科技有限公司 | Radar personnel monitoring and measuring system and method |
| CN111856422A (en) * | 2020-07-03 | 2020-10-30 | 西安电子科技大学 | Lip language identification method based on broadband multichannel millimeter wave radar |
| CN111999726A (en) * | 2020-09-27 | 2020-11-27 | 四川长虹电器股份有限公司 | Personnel positioning method based on millimeter wave radar |
-
2021
- 2021-01-13 CN CN202110040979.5A patent/CN112731332A/en active Pending
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6438491B1 (en) * | 1999-08-06 | 2002-08-20 | Telanon, Inc. | Methods and apparatus for stationary object detection |
| JP2001349942A (en) * | 2000-06-12 | 2001-12-21 | Toto Ltd | Human body detecting device |
| US20030122703A1 (en) * | 2001-12-11 | 2003-07-03 | Masayuki Kishida | Radar data processing apparatus and data processing method |
| US20190227156A1 (en) * | 2018-01-22 | 2019-07-25 | Infineon Technologies Ag | System and method for human behavior modelling and power control using a millimeter-wave radar sensor |
| US20190317191A1 (en) * | 2018-04-11 | 2019-10-17 | Infineon Technologies Ag | Human Detection and Identification in a Setting Using Millimiter-Wave Radar |
| US20200081118A1 (en) * | 2018-09-07 | 2020-03-12 | Baidu Online Network Technology (Beijing) Co., Ltd. | Method and apparatus for determining static state of obstacle |
| US20200116850A1 (en) * | 2018-10-16 | 2020-04-16 | Infineon Technologies Ag | Estimating Angle of Human Target Using mmWave Radar |
| CN110045370A (en) * | 2019-05-10 | 2019-07-23 | 成都宋元科技有限公司 | Human perception method and its system based on millimetre-wave radar |
| CN110118966A (en) * | 2019-05-28 | 2019-08-13 | 长沙莫之比智能科技有限公司 | Personnel's detection and number system based on millimetre-wave radar |
| CN111289967A (en) * | 2020-03-31 | 2020-06-16 | 四川长虹电器股份有限公司 | Personnel detection tracking and counting algorithm based on millimeter wave radar |
| CN111474537A (en) * | 2020-04-20 | 2020-07-31 | 广州桑瑞科技有限公司 | Radar personnel monitoring and measuring system and method |
| CN111856422A (en) * | 2020-07-03 | 2020-10-30 | 西安电子科技大学 | Lip language identification method based on broadband multichannel millimeter wave radar |
| CN111999726A (en) * | 2020-09-27 | 2020-11-27 | 四川长虹电器股份有限公司 | Personnel positioning method based on millimeter wave radar |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zhao et al. | mid: Tracking and identifying people with millimeter wave radar | |
| Virmani et al. | Position and orientation agnostic gesture recognition using WiFi | |
| CN108629380B (en) | Cross-scene wireless signal sensing method based on transfer learning | |
| CN102105816B (en) | Use the threat agents that active electromagnetic waves identification is potential | |
| Liang et al. | Opportunistic sensing in wireless sensor networks: theory and application | |
| CN112859063B (en) | Millimeter wave-based multi-human body target identification and counting method | |
| Zhang et al. | Sozu: Self-powered radio tags for building-scale activity sensing | |
| CN107422318A (en) | A kind of take sensor and its detection method based on Doppler technology | |
| CN112998668A (en) | Millimeter wave-based non-contact far-field multi-human-body respiration heart rate monitoring method | |
| CN113655471A (en) | Method, apparatus and system on chip for radar-enabled sensor fusion | |
| CN110687816A (en) | Intelligent household control system and method based on millimeter wave radar | |
| Kim et al. | Robust detection of presence of individuals in an indoor environment using IR-UWB radar | |
| Korany et al. | Multiple people identification through walls using off-the-shelf WiFi | |
| WO2022109712A1 (en) | Filtering channel responses for motion detection | |
| Wang et al. | {MAVL}: Multiresolution analysis of voice localization | |
| Li et al. | Using Wi-Fi signals to characterize human gait for identification and activity monitoring | |
| Oguchi et al. | Human positioning estimation method using received signal strength indicator (RSSI) in a wireless sensor network | |
| CN108344996B (en) | Panel switch based on microwave radar gesture recognition technology and control method thereof | |
| CN111712730A (en) | Monitoring living facilities by multi-channel radar | |
| EP3467539A1 (en) | Radar detection method and system for identifying moving objects | |
| Cardillo et al. | Embedded heating, ventilation, and air-conditioning control systems: From traditional technologies toward radar advanced sensing | |
| CN111856592A (en) | Indoor living body monitoring device and method | |
| CN113591760B (en) | Gait monitoring method of far-field multiple human bodies based on millimeter waves | |
| CN112634566B (en) | Intelligent electronic fence construction method and system based on millimeter waves | |
| CN112731332A (en) | Millimeter wave-based static target existence identification method and system |
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 |