CN114966525A - Target direction estimation method based on artificial intelligence smart city sensor array - Google Patents
Target direction estimation method based on artificial intelligence smart city sensor array Download PDFInfo
- Publication number
- CN114966525A CN114966525A CN202210532902.4A CN202210532902A CN114966525A CN 114966525 A CN114966525 A CN 114966525A CN 202210532902 A CN202210532902 A CN 202210532902A CN 114966525 A CN114966525 A CN 114966525A
- Authority
- CN
- China
- Prior art keywords
- array
- distribution
- lnp
- matrix
- sensor array
- 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
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
- G01S3/00—Direction-finders for determining the direction from which infrasonic, sonic, ultrasonic, or electromagnetic waves, or particle emission, not having a directional significance, are being received
- G01S3/02—Direction-finders for determining the direction from which infrasonic, sonic, ultrasonic, or electromagnetic waves, or particle emission, not having a directional significance, are being received using radio waves
- G01S3/14—Systems for determining direction or deviation from predetermined direction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Analysis (AREA)
- Theoretical Computer Science (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Computational Mathematics (AREA)
- Databases & Information Systems (AREA)
- Algebra (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Probability & Statistics with Applications (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Remote Sensing (AREA)
- Operations Research (AREA)
- Bioinformatics & Computational Biology (AREA)
- Radar, Positioning & Navigation (AREA)
- Computing Systems (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The invention belongs to the technical field of artificial intelligence positioning processing, and particularly relates to a target azimuth estimation method based on an artificial intelligence smart city sensor array. The invention comprises the following steps: (1) building a uniform array by using the urban sensors, and confirming a data array L received by the sensor array; (2) and establishing prior distribution of each variable in the data array, carrying out layered prior distribution on data array signals, and the like. The target azimuth estimation method based on the artificial intelligent smart city sensor array provided by the invention fully considers the influence of various noises, utilizes the distribution characteristic of controlling multiple noises through Bernoulli distribution, is closer to the environment of an actual smart city through a Bayesian model, realizes accurate azimuth estimation, has ultrahigh distinguishing capability and multi-target resolving capability, and is more suitable for the estimation of the direction of arrival in the complex city environment.
Description
Technical Field
The invention belongs to the technical field of artificial intelligence positioning processing, and particularly relates to a target azimuth estimation method based on an artificial intelligence smart city sensor array.
Background
Because the influence of the environment of the smart city is complicated and changeable, the interference of people flow, heavy rain, strong wind, traffic flow and the like can be encountered during the operation of the sensor, and sometimes impulse noise exists, the direction-finding precision of the traditional method is reduced due to the complicated noise environment, and the condition that various noises are influenced simultaneously cannot be processed. In urban environment detection, an array formed by a plurality of sensors observes or receives a positioning signal to complete the direction estimation of a target. The traditional method is not enough to meet the requirement of high precision, has high-resolution orientation estimation, and also needs the number of information sources and the like as prior information.
Disclosure of Invention
The invention aims to provide a target direction estimation method based on an artificial intelligence smart city sensor array under the combined influence of multiple noises.
The purpose of the invention is realized as follows:
the target direction estimation method based on the artificial intelligent smart city sensor array comprises the following steps:
(1) building a uniform array by using the urban sensors, and confirming a data array L received by the sensor array;
(1.1) measuring the length Y of a receiving signal of the array and the grid number A of the traversing azimuth space;
(1.3) acquiring an expected signal matrix K detected by a sensor;
(1.4) acquiring a pulse noise occurrence state matrix M of each channel of the sensor array;
(1.5) acquiring a non-uniform noise matrix I of each array element of the sensor array;
(1.6) acquiring a pulse noise matrix R at each array element of the sensor array;
(1.7) confirming the data array received by the sensor array;
1 Y×Z is a Y multiplied by Z dimensional cell matrix; y is the dimension of the data array;
(2) establishing prior distribution of each variable in a data array, and carrying out layered prior distribution on data array signals;
(2.1) construction of the system at the y-th momentImpulse making noise U y And hidden variable matrix tau y Collecting the control impulse noise U of the z-th array element at the y-th time z,y And hidden variable matrix tau z,y ;
(2.2) detecting the non-uniform noise variance vector omicron of the artificial intelligence system array and the non-uniform noise variance vector omicron of the z-th array element detection z Shape parameter t z Inverse scale parameter u z Flow pattern matrix
(2.3) acquiring the variance matrix xi of the expected signal at the alpha scanning direction in the array a ;
(2.4) collecting data l received by the array at the y-th time y And data l received by the z-th array element at the y-th time z,y And data k transmitted at the y-th time y ;l y Forming a data matrix L;
(2.5) acquiring a state vector z of the noise at the y-th time y ;
(2.6) collecting the z-th array element at the y-th time m z,y The impulse noise of (2);
(2.7) constructing a layered prior distribution of the receiving signals of the sensor array at the y-th moment:
CN represents complex Gaussian distribution;
(2.8) constructing a hierarchical gamma distribution of the non-uniform noise variance vector omicron:
g represents a gamma distribution;
(2.9) variance matrix xi on desired Signal a Hidden variable matrix tau at time y y And controlling impulse noise U y And respectively constructing layered Gamma distribution:
wherein n is a 、σ z,y /3、π z,y 、p z,y To correspond to the shape parameter of the distribution, o a 、q z,y 、δ z,y To correspond to the inverse scale parameter of the distribution, σ 1 For constraining latent variable matrix elements tau y The variance vector of (2);
(2.10) construction of a noise State vector z for time y y The bernoulli distribution was constructed as:
γ y is z y A probability vector of occurrence;
(2.11) vs. gamma y Constructing a layered Beta distribution:
c z,y and d z,y Respectively Beta distribution parameters obeyed by the z-th array element at the y-th moment.
(2.12) solving the posterior probability of each variable:
(2.13) sequentially substituting the distribution matrix constructed in the step into the following formula to solve the posterior probability of each variable:
lnq(K)=<lnp(L|K,M,U,τ,ο)+lnp(L|ξ)> q(ν≠L) +CONST
lnq(ξ)=<lnp(L|ξ)+lnp(ξ)> q(ν≠L) +CONST
lnq(U)=<lnp(L|K,M,U,τ,ο)+lnp(U)> q(ν≠L) +CONST
lnq(K)=<lnp(L|K,M,U,τ,ο)+lnp(τ|α)> q(ν≠L) +CONST
lnq(ο)=<lnp(L|K,M,U,τ,ο)+lnp(ο)> q(ν≠L) +CONST
lnq(α)=<lnp(τ|α)+lnp(α)> q(ν≠L) +CONST
lnq(M)=<lnp(L|K,M,U,τ,ο)+lnp(M|γ)> q(ν≠L) +CONST
lnq(γ)=<lnp(M|γ)+lnp(γ)> q(ν≠L) +CONST
ν=(K,ξ,U,τ,α,ο,M,γ)
q () is the posterior probability of a variable, ln is logarithm, p (|) represents the probability of an element, q (v ≠ L) is the calculation of a part without the variable in the set, and CONST is a constant item;
(3) calculating the mean and variance of the system variables according to the probability distribution of the variables in the step (2);
(3.1) parameter initialization:
setting an initial iteration to be 1, initializing the maximum iteration times, and traversing the grid number A of the azimuth space to expect the shape parameter n of the signal distribution variance 0 Inverse scale parameter of variance of desired signal distribution omicron 0 Shape parameter p of noise variance distribution 0 、t 0 、π 0 Inverse scale parameter q of the noise variance distribution 0 ,u 0 ,δ 0 Control occurrence probability c 0 、d 0 ;
Q Δ =diag(z y ·ο y +(1 Y×Z +z y )·τ y ·U y )
Diag is a diagonal operation;
and (3.3) updating each distribution parameter:
(3.4) updating the mean values of the variables
(4) Updating iteration times and adding 1; judging whether the iteration termination condition is met, and jumping out of the iteration and outputting when the iteration termination condition is met
Toul is a termination threshold, xi is an expected signal variance, and te is an iteration number; if the iteration termination condition is not met, continuing the steps (3.2) - (3.4);
(5) carrying out azimuth estimation, and outputting an azimuth estimation result:
wherein | 1 ,‖·‖ ∞ Is an infinite norm operation on a matrix.
The invention has the beneficial effects that:
the target azimuth estimation method based on the artificial intelligent smart city sensor array provided by the invention fully considers the influence of various noises, utilizes the distribution characteristic of controlling multiple noises through Bernoulli distribution, is closer to the environment of an actual smart city through a Bayesian model, realizes accurate azimuth estimation, has ultrahigh distinguishing capability and multi-target resolving capability, and is more suitable for the estimation of the direction of arrival in the complex city environment.
Drawings
FIG. 1 is a flow chart of the present invention for orientation estimation;
FIG. 2 is a diagram of a model constructed according to the present invention;
FIG. 3 is a root mean square error comparison result of the sparse method based on impulse noise of the present invention and the traditional sparse method;
FIG. 4 is a detection probability result of the sparse method based on impulse noise, which is the method of the present invention and the conventional sparse method.
Detailed Description
The present invention is described in further detail below with reference to the attached drawing figures.
Referring to fig. 1 and 2, a target direction estimation method based on an artificial intelligence smart city sensor array includes the following steps:
(1) building a uniform array by using the urban sensors, and confirming a data array L received by the sensor array;
(1.1) measuring the length Y of a receiving signal of the array and the grid number A of the traversing azimuth space;
(1.3) acquiring an expected signal matrix K detected by a sensor;
(1.4) acquiring a pulse noise occurrence state matrix M of each channel of the sensor array;
(1.5) acquiring a non-uniform noise matrix I of each array element of the sensor array;
(1.6) acquiring a pulse noise matrix R at each array element of the sensor array;
(1.7) confirming the data array received by the sensor array;
1 Y×Z is a Y multiplied by Z dimensional cell matrix; y is the dimension of the data array;
(2) establishing prior distribution of each variable in a data array, and carrying out layered prior distribution on data array signals;
(2.1) constructing a proper system and controlling impulse noise U at the y-th moment y And hidden variable matrix tau y Collecting the control impulse noise U of the z-th array element at the y-th time z,y And hidden variable matrix tau z,y ;
(2.2) detecting the non-uniform noise variance vector omicron of the artificial intelligence system array and the non-uniform noise variance vector omicron of the z-th array element detection z Shape parameter t z Inverse scale parameter u z Flow pattern matrix
(2.3) acquisition of the desired signal at the a-th scan orientation in the arrayVariance matrix xi a ;
(2.4) collecting data l received by the array at the y-th time y And data l received by the z-th array element at the y-th time z,y And data k transmitted at the y-th time y ;l y Forming a data matrix L;
(2.5) acquiring a state vector z of the noise at the y-th time y ;
(2.6) collecting the z-th array element at the y-th time m z,y The impulse noise of (2);
(2.7) constructing a layered prior distribution of the receiving signals of the sensor array at the y-th moment:
CN represents complex Gaussian distribution;
(2.8) constructing a hierarchical gamma distribution of the non-uniform noise variance vector omicron:
g represents a gamma distribution;
(2.9) variance matrix xi on desired Signal a Hidden variable matrix tau at time y y And controlling impulse noise U y And respectively constructing layered Gamma distribution:
wherein n is a 、σ z,y /3、π z,y 、p z,y To correspond to the shape parameter of the distribution, o a 、q z,y 、δ z,y To correspond to the inverse scale parameter of the distribution, σ 1 For constraining latent variable matrix elements tau y The variance vector of (2);
(2.10) construction of a noise State vector z for time y y The bernoulli distribution was constructed as:
γ y is z y A probability vector of occurrence;
(2.11) vs. gamma y Constructing a layered Beta distribution:
c z,y and d z,y Respectively Beta distribution parameters obeyed by the z-th array element at the y-th moment.
(2.12) solving the posterior probability of each variable:
(2.13) sequentially substituting the distribution matrix constructed in the step into the following formula to solve the posterior probability of each variable:
lnq(K)=<lnp(L|K,M,U,τ,ο)+lnp(L|ξ)> q(ν≠L) +CONST
lnq(ξ)=<lnp(L|ξ)+lnp(ξ)> q(ν≠L) +CONST
lnq(U)=<lnp(L|K,M,U,τ,ο)+lnp(U)> q(ν≠L) +CONST
lnq(K)=<lnp(L|K,M,U,τ,ο)+lnp(τ|α)> q(ν≠L) +CONST
lnq(ο)=<lnp(L|K,M,U,τ,ο)+lnp(ο)> q(ν≠L) +CONST
lnq(α)=<lnp(τ|α)+lnp(α)> q(ν≠L) +CONST
lnq(M)=<lnp(L|K,M,U,τ,ο)+lnp(M|γ)> q(ν≠L) +CONST
lnq(γ)=<lnp(M|γ)+lnp(γ)> q(ν≠L) +CONST
ν=(K,ξ,U,τ,α,ο,M,γ)
q () is the posterior probability of a variable, ln is logarithm, < > represents expectation, p (|) represents the probability of an element in the set, q (ν ≠ L) is used for calculating the part of the set without the variable, and CONST is a constant item;
(3) calculating the mean and variance of the system variables according to the probability distribution of the variables in the step (2);
(3.1) parameter initialization:
setting an initial iteration to be 1, initializing the maximum iteration times, and traversing the grid number A of the azimuth space to expect the shape parameter n of the signal distribution variance 0 Inverse scale parameter of variance of desired signal distribution omicron 0 Shape parameter p of noise variance distribution 0 、t 0 、π 0 Inverse scale parameter q of the noise variance distribution 0 ,u 0 ,δ 0 Control occurrence probability c 0 、d 0 ;
Q Δ =diag(z y ·ο y +(1 Y×Z +z y )·τ y ·U y )
Diag is a diagonal operation;
and (3.3) updating each distribution parameter:
(3.4) updating the mean values of the variables
(4) Updating iteration times and adding 1; judging whether the iteration termination condition is met, and jumping out of the iteration and outputting when the iteration termination condition is met
Toul is a termination threshold, xi is an expected signal variance, and te is an iteration number; if the iteration termination condition is not met, continuing the steps (3.2) - (3.4);
(5) carrying out azimuth estimation, and outputting an azimuth estimation result:
wherein | 1 ,‖·‖ ∞ Is an infinite norm operation on a matrix.
The method has the distinguishing characteristics that the impulse noise and the influence of the impulse noise are fully considered, the constructed positioning model is more consistent with the actual noisy environment of the smart city, and a better estimation result can be obtained.
In the embodiment 1, data simulation is performed below, a single-frequency pulse signal matrix is used as an incident signal, the incident directions are respectively-45 ° and-30 °, the noise variance of each array element is randomly changed between [0.2 and 7], the generalized signal-to-noise ratio is changed in the range of [ -15 and 30], and a traditional sparse method, a sparse method based on pulse noise and the method provided by the invention are compared and analyzed.
Fig. 3 is a root mean square error variation curve of each method according to GSNR under impulse noise environment. Through comparison, the traditional sparse method can be found to be serious in failure; although the sparse method based on impulse noise also has a downward trend, when various noises occur alternately, a jumping trend occurs, which brings unstable estimation results; the method disclosed by the invention has the lowest RMSE and the most stable RMSE, obtains the best estimation result of the three methods, and has the minimum deviation.
Fig. 4 is a detection success probability curve of the three methods when the three methods change with GSNR under impulse noise environment, and the detection success is defined within 0.5 ° of the target deviation. Compared with the prior art, the target direction cannot be timely and accurately found under the background of pulse noise and non-uniform noise in the traditional sparse method; the probability of successful detection of the sparse method based on the impulse noise is increased, but the estimation result is unstable; the method has the highest success level of estimation on the target. Therefore, the effectiveness and the feasibility of the invention are fully verified by simulation experiments.
In conclusion, the invention provides the target orientation estimation method based on the artificial intelligence smart city sensor array under the combined influence of various noises, so that the high-precision DOA estimation under the mixed condition of the non-uniform noises and the impulse noises is realized, and the method is more suitable for practical application scenes. Compared with the existing similar method, the high-precision direction-of-arrival estimation method under the condition of pulse noise mixing has higher precision and stronger adaptability.
Claims (6)
1. The target direction estimation method based on the artificial intelligent smart city sensor array is characterized by comprising the following steps of:
(1) building a uniform array by using urban sensors, and confirming a data array L received by the sensor array;
(2) establishing prior distribution of each variable in a data array, and carrying out layered prior distribution on data array signals;
(3) calculating the mean and variance of the system variables according to the probability distribution of the variables in the step (2);
(4) updating iteration times and adding 1; judging whether the iteration termination condition is met, and jumping out of the iteration and outputting when the iteration termination condition is metIf the iteration termination condition is not met, continuing the step (3);
(5) and carrying out azimuth estimation and outputting an azimuth estimation result.
2. The target orientation estimation method based on artificial intelligence smart city sensor array as claimed in claim 1, wherein the step (1) comprises:
(1.1) measuring the length Y of a receiving signal of the array and the grid number A of the traversing azimuth space;
(1.3) acquiring an expected signal matrix K detected by a sensor;
(1.4) acquiring a pulse noise occurrence state matrix M of each channel of the sensor array;
(1.5) acquiring a non-uniform noise matrix I of each array element of the sensor array;
(1.6) acquiring a pulse noise matrix R at each array element of the sensor array;
(1.7) confirming the data array received by the sensor array;
1 Y×Z is a Y multiplied by Z dimensional cell matrix; y × Z is the dimension of the data array.
3. The target orientation estimation method based on artificial intelligence smart city sensor array as claimed in claim 1, wherein the step (2) comprises:
(2.1) constructing a proper system and controlling impulse noise U at the y-th moment y And hidden variable matrix tau y Collecting the control impulse noise U of the z-th array element at the y-th time z,y And hidden variable matrix tau z,y ;
(2.2) detecting the non-uniform noise variance vector omicron of the artificial intelligence system array and the non-uniform noise variance vector omicron of the z-th array element detection z Shape parameter t z Inverse scale parameter u z Flow pattern matrix
(2.3) acquiring the variance matrix xi of the expected signal at the alpha scanning direction in the array a ;
(2.4) collecting data l received by the array at the y-th time y And data l received by the z-th array element at the y-th time z,y And data k transmitted at the y-th time y ;l y Forming a data matrix L;
(2.5) acquiring a state vector z of the noise at the y-th time y ;
(2.6) collecting the z-th array element at the y-th time m z,y The impulse noise of (2);
(2.7) constructing a layered prior distribution of the receiving signals of the sensor array at the y-th moment:
CN represents complex Gaussian distribution;
(2.8) constructing a hierarchical gamma distribution of the non-uniform noise variance vector omicron:
g represents a gamma distribution;
(2.9) variance matrix xi on desired Signal a Hidden variable matrix tau at y time y And controlling impulse noise U y And respectively constructing layered Gamma distribution:
wherein n is a 、σ z,y /3、π z,y 、p z,y To correspond to the shape parameter of the distribution, o a 、q z,y 、δ z,y To correspond to the inverse scale parameter of the distribution, σ 1 For constraining latent variable matrix elements tau y The variance vector of (2);
(2.10) construction of a noise State vector z for time y y The bernoulli distribution was constructed as:
γ y is z y A probability vector of occurrence;
(2.11) vs. gamma y Constructing a layered Beta distribution:
c z,y and d z,y Respectively Beta distribution parameters obeyed by the z-th array element at the y-th moment.
(2.12) solving the posterior probability of each variable:
(2.13) sequentially substituting the distribution matrix constructed in the step into the following formula to solve the posterior probability of each variable:
Inq(K)=<lnp(L|K,M,U,τ,o)+lnp(L|ξ)> q(v≠L) +CONST
lnq(ξ)=<lnp(L|ξ)+lnp(ξ)> q(v≠L) +CONST
lnq(U)=<lnp(L|K,M,U,τ,o)+lnp(U)> q(v≠L) +CONST
lnq(K)=<lnp(L|K,M,U,τ,o)+lnp(τ|α)> q(v≠L) +CONST
lnq(o)=<lnp(L|K,M,U,τ,o)+lnp(o)> q(v≠L) +CONST
lnq(α)=<lnp(τ|α)+lnp(α)> q(v≠L) +CONST
lnq(M)=<lnp(L|K,M,U,τ,o)+lnp(M|γ)> q(v≠L) +CONST
lnq(γ)=<lnp(M|γ)+lnp(γ)> q(v≠L) +CONST
v=(K,ξ,U,τ,α,o,M,γ)
q () is the posterior probability of a variable, ln is logarithm, < > represents expectation, p (|) represents the probability of an element in the set, q (v ≠ L) is calculated for a part without the variable in the set, and CONST is a constant term;
4. the target orientation estimation method based on artificial intelligence smart city sensor array as claimed in claim 1, wherein the step (3) comprises:
(3.1) parameter initialization:
setting an initial iteration to be 1, initializing the maximum iteration times, and traversing the grid number A of the azimuth space to expect the shape parameter n of the signal distribution variance 0 Inverse scale parameter o of variance of desired signal distribution 0 Shape parameter p of noise variance distribution 0 、t 0 、π 0 Inverse scale parameter q of the noise variance distribution 0 ,u 0 ,δ 0 Control occurrence probability c 0 、d 0 ;
Q Δ =diag(z y ·o y +(1 Y×Z +z y )·τ y ·U y )
Diag is a diagonal operation;
and (3.3) updating each distribution parameter:
(3.4) updating the mean values of the variables
5. The target orientation estimation method based on artificial intelligence smart city sensor array as claimed in claim 1, wherein the step (4) comprises:
judging whether the iteration termination condition is met, and jumping out of the iteration and outputting when the iteration termination condition is met
Toul is a termination threshold, xi is an expected signal variance, and te is an iteration number; and (5) if the iteration termination condition is not met, continuing the steps (3.2) - (3.4).
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210532902.4A CN114966525A (en) | 2022-05-15 | 2022-05-15 | Target direction estimation method based on artificial intelligence smart city sensor array |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210532902.4A CN114966525A (en) | 2022-05-15 | 2022-05-15 | Target direction estimation method based on artificial intelligence smart city sensor array |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114966525A true CN114966525A (en) | 2022-08-30 |
Family
ID=82983034
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210532902.4A Pending CN114966525A (en) | 2022-05-15 | 2022-05-15 | Target direction estimation method based on artificial intelligence smart city sensor array |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114966525A (en) |
-
2022
- 2022-05-15 CN CN202210532902.4A patent/CN114966525A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109086700B (en) | Radar one-dimensional range profile target identification method based on deep convolutional neural network | |
Du et al. | Secondary radar signal processing based on deep residual separable neural network | |
CN110888105B (en) | DOA estimation method based on convolutional neural network and received signal strength | |
CN114595732B (en) | Radar radiation source sorting method based on depth clustering | |
CN114449452A (en) | Indoor positioning algorithm for heterogeneous equipment | |
CN111401565A (en) | DOA estimation method based on machine learning algorithm XGboost | |
CN109884625B (en) | Radar correlation imaging method based on convolutional neural network | |
CN111257845A (en) | Approximate message transfer-based non-grid target angle estimation method | |
CN115685096B (en) | Secondary radar side lobe suppression method based on logistic regression | |
CN111913155A (en) | Two-dimensional DOA estimation method based on array radar | |
CN111175692A (en) | Discrete sparse Bayesian DOA estimation method based on layered synthesis Lasso prior model | |
CN109061556B (en) | Sparse iteration angle of arrival estimation method based on elastic network | |
CN108631817B (en) | Method for predicting frequency hopping signal frequency band based on time-frequency analysis and radial neural network | |
CN111859241B (en) | Unsupervised sound source orientation method based on sound transfer function learning | |
CN107682822B (en) | Compressed sensing outdoor positioning method based on electromagnetic field intensity | |
CN111505575B (en) | Sensor selection method aiming at TDOA (time difference of arrival) location based on conversion TOA (time of arrival) model | |
CN114966525A (en) | Target direction estimation method based on artificial intelligence smart city sensor array | |
CN113759303A (en) | Non-grid DOA (angle of arrival) estimation method based on particle swarm optimization | |
CN110568406B (en) | Positioning method based on acoustic energy under condition of unknown energy attenuation factor | |
CN112710982A (en) | Method, system, medium, equipment and application for estimating wave arrival angle of antenna array | |
CN112699992A (en) | Hybrid source positioning method based on convolutional neural network | |
CN115015832A (en) | Large-scale array amplitude-phase error and target direction joint estimation method under non-uniform noise | |
CN110850366B (en) | Positioning method based on received signal strength under mixed line-of-sight and non-line-of-sight environment | |
CN115372925A (en) | Array robust adaptive beam forming method based on deep learning | |
CN115015831B (en) | Large-scale array target azimuth estimation method under combined influence of impulse noise and non-uniform noise |
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 |