CN113514811B - Radar target attribute scattering center extraction method and device - Google Patents

Radar target attribute scattering center extraction method and device Download PDF

Info

Publication number
CN113514811B
CN113514811B CN202110997643.8A CN202110997643A CN113514811B CN 113514811 B CN113514811 B CN 113514811B CN 202110997643 A CN202110997643 A CN 202110997643A CN 113514811 B CN113514811 B CN 113514811B
Authority
CN
China
Prior art keywords
echo
scattering center
attribute
argument
matrix
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202110997643.8A
Other languages
Chinese (zh)
Other versions
CN113514811A (en
Inventor
田鹤
董纯柱
袁莉
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Institute of Environmental Features
Original Assignee
Beijing Institute of Environmental Features
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Beijing Institute of Environmental Features filed Critical Beijing Institute of Environmental Features
Priority to CN202110997643.8A priority Critical patent/CN113514811B/en
Publication of CN113514811A publication Critical patent/CN113514811A/en
Application granted granted Critical
Publication of CN113514811B publication Critical patent/CN113514811B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Radar Systems Or Details Thereof (AREA)

Abstract

The invention relates to a radar target attribute scattering center extraction method and a device, wherein the method comprises the following steps: acquiring SAR complex images; dividing each scattering center of the target, and performing inverse Fourier transform on the complex image to obtain radar echo data corresponding to each scattering center; performing, for each scattering center, corresponding radar echo data: complex decomposition is carried out to obtain an echo module value correlation matrix and an echo argument correlation matrix; carrying out optimization solution on an optimization problem formed by the echo model related quantity matrix and the dimensionality reduction combined dictionary to obtain an estimated value of the echo model related attribute parameter; carrying out optimization solution on an optimization problem formed by the echo argument correlation matrix and the dimensionality reduction combined dictionary to obtain an estimated value of echo argument correlation attribute parameters; and obtaining attribute parameter sets corresponding to all scattering centers. The method can realize rapid extraction of the scattering centers of the multiple target attributes, and improves the extraction efficiency and accuracy of the physical attribute characteristics of the radar target.

Description

Radar target attribute scattering center extraction method and device
Technical Field
The present invention relates to the field of radar target feature extraction and recognition technologies, and in particular, to a method and apparatus for extracting a radar target attribute scattering center, a computer device, and a computer readable storage medium.
Background
The target characteristics of SAR (synthetic aperture radar) signals are the basis for target recognition, and the target characteristics are the results of the interaction between the electromagnetic waves emitted by the radar and the target, and are included in the target scattering echo signals. Target recognition techniques based on SAR signals require extracting relevant features of the target from the signal, including target outline size features, strong scattering point features, contour features, etc. In the attribute scattering center model, the scattering response of the scattering center under electromagnetic wave excitation is a function of the measurement frequency and the observation angle, and through accurate and stable estimation of the attribute scattering center parameters, some information related to the physical structure characteristics of the target can be extracted, so that the method is an important basis for realizing radar target identification.
At present, the model structure of the attribute scattering center is complex, the parameter dimension is higher, the complexity of model parameter estimation is greatly increased, and the accuracy of a calculation result is low, so that the method is not beneficial to practical application.
Disclosure of Invention
The invention aims at overcoming at least one part of the defects, and provides a radar target attribute scattering center rapid extraction technology based on complex decomposition so as to reduce the calculation difficulty and further solve the problems of large calculation amount and poor precision caused by high dimension of target attribute parameters in practical application.
In order to achieve the above object, the present invention provides a method for extracting a radar target attribute scattering center, including:
acquiring SAR complex images;
dividing each scattering center of the target based on the SAR complex images, and performing inverse Fourier transform on the complex images corresponding to each scattering center to obtain radar echo data corresponding to each scattering center;
the following operations are performed on the radar echo data corresponding to each scattering center:
complex decomposition is carried out on radar echo data corresponding to the scattering center, so that an echo model value correlation matrix and an echo argument correlation matrix are obtained; carrying out optimization solution on an optimization problem formed by the echo module value correlation matrix and the dimension reduction combined dictionary to obtain an estimated value of the echo module value correlation attribute parameter; carrying out optimization solution on an optimization problem formed by the echo argument correlation matrix and the dimensionality reduction combined dictionary to obtain an estimated value of echo argument correlation attribute parameters; acquiring an attribute parameter set corresponding to the scattering center based on the echo module value related attribute parameter and the echo argument related attribute parameter estimated value;
and obtaining attribute parameter sets corresponding to all scattering centers, and realizing rapid extraction of the target attribute scattering centers.
Optionally, complex decomposition is performed on radar echo data corresponding to the scattering center to obtain an echo model value correlation matrix and an echo argument correlation matrix, which include:
setting the scattering center as the ith scattering center, wherein i is more than or equal to 1 and less than or equal to N, and N represents the total number of the scattering centers of the target;
radar echo data corresponding to the ith scattering center
Figure BDA0003234384700000021
Complex decomposition is performed, and the expression is: />
Figure BDA0003234384700000022
Wherein f represents a discrete radar broadband frequency vector with a length of N f ，f c The radar center frequency, c is the speed of light;
Figure BDA0003234384700000023
represents a discrete observation azimuth vector of length +.>
Figure BDA0003234384700000024
Figure BDA0003234384700000025
Representing an attribute parameter set corresponding to the ith scattering center, wherein the attribute parameters in the set comprise: a is that i Indicating scattering intensity, alpha i Represents an orientation dependent factor, L i Indicating scattering center length, +.>
Figure BDA0003234384700000026
Representing the initial azimuth angle gamma i Representing a frequency dependent factor, x i 、y i Respectively representing the horizontal and vertical coordinate positions of the ith scattering center;
according to the complex decomposition expression, an expression of an echo module value correlation matrix is obtained:
Figure BDA0003234384700000031
the attribute parameter set expression corresponding to the echo module value correlation matrix is as follows:
Figure BDA0003234384700000032
according to the complex decomposition expression, an echo argument correlation matrix expression is obtained:
Figure BDA0003234384700000033
the attribute parameter set expression corresponding to the echo argument matrix is as follows:
θ p ＝{α i ,x i ,y i }。
optionally, performing optimization solution on an optimization problem formed by the echo module value correlation quantity matrix and the dimension reduction joint dictionary to obtain an estimated value of the echo module value correlation attribute parameter, including:
establishing a parameter solving optimization model corresponding to the echo module value correlation quantity matrix, wherein the expression is as follows:
Figure BDA0003234384700000034
wherein delta f To solve for theta f The corresponding sparse coefficient vector has the size of
Figure BDA0003234384700000035
N α 、N L 、/>
Figure BDA0003234384700000036
N γ Respectively the attribute parameters alpha i 、L i 、/>
Figure BDA0003234384700000037
γ i The number of meshes divided in the corresponding parameter space, +.>
Figure BDA0003234384700000038
Delta is f Lambda of the estimated value of (a) f Representing regularization parameters corresponding to the parameter solving optimization model corresponding to the echo module value correlation quantity matrix;
establishing a dimension reduction joint dictionary corresponding to the echo module value correlation matrix, wherein the expression is as follows:
Figure BDA0003234384700000039
Figure BDA00032343847000000310
wherein D is f (θ f ) The dimension-reducing joint dictionary corresponding to the echo module value correlation quantity matrix is represented and has the size of
Figure BDA00032343847000000311
Figure BDA00032343847000000312
Representation D f (θ f ) Is a first row vector of (a); />
Using the formula
Figure BDA0003234384700000041
Estimating the property parameters of the ith scattering center
Figure BDA0003234384700000042
Optionally, performing optimization solution on an optimization problem formed by the echo argument correlation matrix and the dimension reduction joint dictionary to obtain an estimated value of the echo argument correlation attribute parameter, including:
establishing a parameter solving optimization model corresponding to the echo argument matrix, wherein the expression is as follows:
Figure BDA0003234384700000043
wherein delta p To solve for theta p The corresponding sparse coefficient vector is of the size N x N y ×1，N x 、N y Respectively the attribute parameters x i 、y i The number of grids divided in the parameter space,
Figure BDA0003234384700000044
delta is p Lambda of the estimated value of (a) p Parameter solving optimization model corresponding to echo argument matrixCorresponding regularization parameters;
establishing a dimensionality reduction joint dictionary corresponding to the echo argument matrix, wherein the expression is as follows:
Figure BDA0003234384700000045
Figure BDA0003234384700000046
wherein D is p (θ p ) The dimension-reducing joint dictionary corresponding to the echo argument matrix is represented and has the size of
Figure BDA0003234384700000047
d p (x 1 ,y 1 ) Representation D p (θ p ) Is a first row vector of (a);
using the formula
Figure BDA0003234384700000048
And the obtained alpha i Estimating the attribute parameter { x } of the ith scattering center i ,y i }。
The invention also provides a radar target attribute scattering center extraction device, which comprises:
the image module is used for acquiring SAR complex images;
the echo module is used for dividing each scattering center of the target based on the SAR complex images, and performing inverse Fourier transform on the complex images corresponding to each scattering center to obtain radar echo data corresponding to each scattering center;
the estimation module is used for executing the following operations on the radar echo data corresponding to each scattering center:
complex decomposition is carried out on radar echo data corresponding to the scattering center, so that an echo model value correlation matrix and an echo argument correlation matrix are obtained;
carrying out optimization solution on an optimization problem formed by the echo module value correlation matrix and the dimension reduction combined dictionary to obtain an estimated value of the echo module value correlation attribute parameter;
carrying out optimization solution on an optimization problem formed by the echo argument correlation matrix and the dimensionality reduction combined dictionary to obtain an estimated value of echo argument correlation attribute parameters;
acquiring an attribute parameter set corresponding to the scattering center based on the echo module value related attribute parameter and the echo argument related attribute parameter estimated value;
and the result module is used for obtaining attribute parameter sets corresponding to all scattering centers and realizing rapid extraction of the target attribute scattering centers.
Optionally, the estimating module is configured to perform complex decomposition on radar echo data corresponding to the scattering center to obtain an echo module value correlation matrix and an echo argument correlation matrix, and includes performing the following operations:
setting the scattering center as the ith scattering center, wherein i is more than or equal to 1 and less than or equal to N, and N represents the total number of the scattering centers of the target;
radar echo data corresponding to the ith scattering center
Figure BDA0003234384700000051
Complex decomposition is performed, and the expression is:
Figure BDA0003234384700000052
wherein f represents a discrete radar broadband frequency vector with a length of N f ，f c The radar center frequency, c is the speed of light;
Figure BDA0003234384700000053
represents a discrete observation azimuth vector of length +.>
Figure BDA0003234384700000054
Figure BDA0003234384700000055
Representing an attribute parameter set corresponding to the ith scattering center, wherein the attribute parameters in the set comprise: a is that i Indicating scattering intensity, alpha i Represents an orientation dependent factor, L i Indicating scattering center length, +.>
Figure BDA0003234384700000061
Representing the initial azimuth angle gamma i Representing a frequency dependent factor, x i 、y i Respectively representing the horizontal and vertical coordinate positions of the ith scattering center;
according to the complex decomposition expression, an expression of an echo module value correlation matrix is obtained:
Figure BDA0003234384700000062
the attribute parameter set expression corresponding to the echo module value correlation matrix is as follows:
Figure BDA0003234384700000063
according to the complex decomposition expression, an echo argument correlation matrix expression is obtained:
Figure BDA0003234384700000064
the attribute parameter set expression corresponding to the echo argument matrix is as follows:
θ p ＝{α i ,x i ,y i }。
optionally, the estimating module is configured to perform optimization solution on an optimization problem formed by the echo module value correlation matrix and the dimension-reduction joint dictionary to obtain an estimated value of the echo module value correlation attribute parameter, and includes performing the following operations:
establishing a parameter solving optimization model corresponding to the echo module value correlation quantity matrix, wherein the expression is as follows:
Figure BDA0003234384700000065
wherein delta f To solve for theta f The corresponding sparse coefficient vector has the size of
Figure BDA0003234384700000066
N α 、N L 、/>
Figure BDA0003234384700000067
N γ Respectively the attribute parameters alpha i 、L i 、/>
Figure BDA0003234384700000068
γ i The number of meshes divided in the corresponding parameter space, +.>
Figure BDA0003234384700000069
Delta is f Lambda of the estimated value of (a) f Representing regularization parameters corresponding to the parameter solving optimization model corresponding to the echo module value correlation quantity matrix;
establishing a dimension reduction joint dictionary corresponding to the echo module value correlation matrix, wherein the expression is as follows:
Figure BDA00032343847000000610
Figure BDA00032343847000000611
/>
wherein D is f (θ f ) The dimension-reducing joint dictionary corresponding to the echo module value correlation quantity matrix is represented and has the size of
Figure BDA0003234384700000071
Figure BDA0003234384700000072
Representation D f (θ f ) Is a first row vector of (a);
using the formula
Figure BDA0003234384700000073
Estimating the property parameters of the ith scattering center
Figure BDA0003234384700000074
Optionally, the estimating module is configured to perform optimization solution on an optimization problem formed by the echo argument correlation matrix and the dimension-reduction joint dictionary, to obtain an estimated value of the echo argument correlation attribute parameter, and includes performing the following operations:
establishing a parameter solving optimization model corresponding to the echo argument matrix, wherein the expression is as follows:
Figure BDA0003234384700000075
wherein delta p To solve for theta p The corresponding sparse coefficient vector is of the size N x N y ×1，N x 、N y Respectively the attribute parameters x i 、y i The number of grids divided in the parameter space,
Figure BDA0003234384700000076
delta is p Lambda of the estimated value of (a) p Representing regularization parameters corresponding to the parameter solving optimization model corresponding to the echo argument matrix;
establishing a dimensionality reduction joint dictionary corresponding to the echo argument matrix, wherein the expression is as follows:
Figure BDA0003234384700000077
Figure BDA0003234384700000078
wherein the method comprises the steps of，D p (θ p ) The dimension-reducing joint dictionary corresponding to the echo argument matrix is represented and has the size of
Figure BDA0003234384700000079
d p (x 1 ,y 1 ) Representation D p (θ p ) Is a first row vector of (a);
using the formula
Figure BDA00032343847000000710
And the obtained alpha i Estimating the attribute parameter { x } of the ith scattering center i ,y i }。
The invention also provides a computer device, which comprises a memory and a processor, wherein the memory stores a computer program, and the processor realizes the steps of the radar target attribute scattering center extraction method according to any one of the above steps when executing the computer program.
The invention also provides a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of the radar target attribute scattering center extraction method of any of the above.
The technical scheme of the invention has the following advantages: the invention provides a radar target attribute scattering center extraction method and device, computer equipment and a computer readable storage medium.
Drawings
Fig. 1 is a schematic diagram of steps of a method for extracting a radar target attribute scattering center according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of the extraction result of a scattering center corresponding to measurement data of a target darkroom in an embodiment of the present invention;
fig. 3 is a schematic structural diagram of a radar target attribute scattering center extraction device according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
As described above, the complexity of model parameter estimation increases greatly due to the complex structure of the model of the attribute scattering center and the high dimension of the parameters. The method for extracting the characteristic of the attribute scattering center and estimating the parameter is researched quickly and efficiently, and has very important value for radar target identification. In order to solve the problems of large operand and poor precision caused by higher dimension of target attribute parameters in practical application, the invention provides a method for complex decomposition of radar echo data, namely complex domain modulus and argument decomposition of the radar echo data, which reduces dimension of attribute parameter estimation and further improves operation efficiency and accuracy.
As shown in fig. 1, a method for extracting a radar target attribute scattering center provided by an embodiment of the present invention includes:
step 100, acquiring SAR complex images;
102, dividing each scattering center of a target based on the acquired SAR complex images, and performing inverse Fourier transform on the complex images corresponding to each scattering center obtained by dividing to obtain radar echo data corresponding to each scattering center;
step 104, executing the following operations on the radar echo data corresponding to each scattering center:
complex decomposition is carried out on radar echo data corresponding to the scattering center, so that an echo model value correlation matrix and an echo argument correlation matrix are obtained; complex decomposition, namely decomposing SAR echo data into a modulus-related component and a argument-related component;
carrying out optimization solution on an optimization problem formed by the echo model related quantity matrix and the dimensionality reduction combined dictionary to obtain an estimated value of the echo model related attribute parameter;
carrying out optimization solution on an optimization problem formed by the echo argument correlation matrix and the dimensionality reduction combined dictionary to obtain an estimated value of echo argument correlation attribute parameters;
acquiring an attribute parameter set corresponding to the scattering center based on the estimated value of the echo model value related attribute parameter and the estimated value of the echo argument related attribute parameter;
and 106, after the radar echo data corresponding to all the scattering centers are processed, acquiring attribute parameter sets corresponding to all the scattering centers, and realizing rapid extraction of the target attribute scattering centers.
According to the method for extracting the radar target attribute scattering center, rapid extraction of the radar target attribute scattering center is achieved based on complex decomposition, complex domain module value and argument decomposition are carried out on radar echo data, an echo module value related quantity matrix and an echo argument related quantity matrix are obtained, further effective expression of a dimension-reducing combined dictionary of the radar target attribute parameter is obtained, the dimension of the dimension-reducing combined dictionary is reduced by 1 order of magnitude compared with a high-dimension dictionary corresponding to an original echo, the dimension of the dimension-reducing combined dictionary is reduced, estimated values of the echo module value related attribute parameter and the echo argument related attribute parameter are obtained through optimization solving, the attribute parameter estimated dimension is reduced, operation efficiency and accuracy are improved, and technical support can be provided for breakthrough of radar target identification key technology.
Further, in step 104, complex decomposition is performed on the radar echo data corresponding to the scattering center to obtain an echo model correlation matrix and an echo argument correlation matrix, which include:
setting the scattering center as the ith scattering center, wherein i is more than or equal to 1 and less than or equal to N, and N represents the total number of the scattering centers of the separated targets;
radar echo data corresponding to the ith scattering center
Figure BDA0003234384700000101
Complex decomposition is performed, and the expression is:
Figure BDA0003234384700000102
wherein f represents a discrete radar broadband frequency vector with a length of N f ，f c The radar center frequency, c is the speed of light;
Figure BDA0003234384700000103
represents a discrete observation azimuth vector of length +.>
Figure BDA0003234384700000104
Figure BDA0003234384700000105
Representing an attribute parameter set corresponding to the ith scattering center, wherein the attribute parameters in the set comprise: a is that i Indicating scattering intensity, alpha i Represents an orientation dependent factor, L i Indicating scattering center length, +.>
Figure BDA0003234384700000106
Representing the initial azimuth angle gamma i Representing a frequency dependent factor, x i 、y i Respectively representing the horizontal and vertical coordinate positions of the ith scattering center;
according to the complex decomposition expression, an expression of an echo module value correlation matrix is obtained:
Figure BDA0003234384700000107
the attribute parameter set expression corresponding to the echo module value correlation matrix is as follows:
Figure BDA0003234384700000108
according to the complex decomposition expression, an echo argument correlation matrix expression is obtained:
Figure BDA0003234384700000109
the attribute parameter set expression corresponding to the echo argument matrix is as follows:
θ p ＝{α i ,x i ,y i }。
by adopting the technical scheme, complex decomposition of radar echo data can be realized, namely complex domain module value and argument decomposition are carried out on the radar echo data, and the attribute parameter sets corresponding to the decomposed echo module value correlation quantity matrix and echo argument correlation quantity matrix are solved respectively, so that the operation difficulty can be reduced, and the operation efficiency is improved.
Further, in step 104, an optimization problem formed by the echo model correlation matrix and the dimension-reduction joint dictionary is solved in an optimization manner to obtain an estimated value of the echo model correlation attribute parameter, which includes:
establishing a parameter solving optimization model corresponding to the echo module value correlation quantity matrix, wherein the expression is as follows:
Figure BDA0003234384700000111
wherein delta f To solve for theta f The corresponding sparse coefficient vector has the size of
Figure BDA0003234384700000112
N α 、N L 、/>
Figure BDA0003234384700000113
N γ Respectively the attribute parameters alpha i 、L i 、/>
Figure BDA0003234384700000114
γ i The number of meshes divided in their respective parameter space, +.>
Figure BDA0003234384700000115
Delta is f Lambda of the estimated value of (a) f Representing regularization parameters corresponding to the parameter solution optimization model corresponding to the echo module value correlation quantity matrix;
establishing a dimensionality reduction joint dictionary corresponding to the echo module value correlation quantity matrix, wherein the expression is as follows:
Figure BDA0003234384700000116
/>
Figure BDA0003234384700000117
Figure BDA0003234384700000118
wherein D is f (θ f ) The size of the dimension-reducing combined dictionary corresponding to the echo module value correlation matrix is as follows
Figure BDA0003234384700000119
α 1 ,L 1 ,/>
Figure BDA00032343847000001110
γ 1 Representing the corresponding attribute parameter of the first scattering center in the target,
Figure BDA00032343847000001111
representation D f (θ f ) Is the first row vector of +.>
Figure BDA00032343847000001112
Representation D f (θ f ) N (th) α Individual row vectors, and so on, large row vectorsLittle->
Figure BDA00032343847000001113
Using the formula
Figure BDA0003234384700000121
Estimating the property parameters of the ith scattering center
Figure BDA0003234384700000122
Obtaining the attribute parameter related to the echo mode value>
Figure BDA0003234384700000123
Is used for the estimation of the estimated value of (a).
Specifically, the estimation process includes:
first, for attribute parameter alpha i 、L i 、
Figure BDA0003234384700000124
γ i The corresponding parameter space is gridded and then formulated
Figure BDA0003234384700000125
Estimating θ f The position of the non-zero value in (a) represents the parameter (azimuth dependent factor alpha i Length of scattering center L i Initial azimuth->
Figure BDA0003234384700000126
Frequency dependent factor gamma i ) A non-zero value representing A i 。
By adopting the technical scheme, the echo mode value related attribute parameters can be obtained quickly
Figure BDA0003234384700000127
Is used for the estimation of the estimated value of (a). Of course, the attribute parameter +.>
Figure BDA0003234384700000128
Is used for the estimation of the estimated value of (a).
Further, in step 104, an optimization problem formed by the echo argument correlation matrix and the dimension-reduction joint dictionary is solved in an optimization manner to obtain an estimated value of the echo argument correlation attribute parameter, which includes:
establishing a parameter solving optimization model corresponding to the echo argument matrix, wherein the expression is as follows:
Figure BDA0003234384700000129
wherein delta p To solve for theta p The corresponding sparse coefficient vector is of the size N x N y ×1，N x 、N y Respectively the attribute parameters x i 、y i The number of grids divided in the parameter space,
Figure BDA00032343847000001210
delta is p Lambda of the estimated value of (a) p Representing regularization parameters corresponding to the parameter solving optimization model corresponding to the echo radial angle correlation quantity matrix;
establishing a dimensionality reduction joint dictionary corresponding to the echo argument matrix, wherein the expression is as follows:
Figure BDA00032343847000001211
Figure BDA0003234384700000131
/>
Figure BDA0003234384700000132
wherein D is p (θ p ) The size of the dimension-reducing combined dictionary corresponding to the echo argument correlation matrix is as follows
Figure BDA0003234384700000133
d p (x 1 ,y 1 ) Representation D p (θ p ) Is the first row vector of +.>
Figure BDA0003234384700000134
Representation D p (θ p ) N (th) x A row vector, and so on, the size of the row vector is +.>
Figure BDA0003234384700000135
Using the formula
Figure BDA0003234384700000136
And estimating the property parameter of the ith scattering center +.>
Figure BDA0003234384700000137
Alpha obtained at that time i Estimating the attribute parameter { x } of the ith scattering center i ,y i Obtaining echo argument related attribute parameter { x } i ,y i An estimated value of { alpha }, which determines the echo argument related attribute parameter i ,x i ,y i An estimate of }.
By adopting the technical scheme, the echo radial angle related attribute parameter { alpha } can be obtained rapidly i ,x i ,y i An estimate of }. Of course, other ways of determining the attribute parameter { alpha } in the prior art may be used i ,x i ,y i An estimate of }.
By the method, the attribute parameter set corresponding to the ith scattering center is obtained based on the echo model value related attribute parameter and the echo argument related attribute parameter
Figure BDA0003234384700000138
In step 106, the set of attribute parameters corresponding to all scattering centers of the target is θ= [ θ ] 1 T ,θ 2 T ,...,θ i T ,...,θ N T ]And (5) completing rapid extraction of the radar target attribute scattering center.
As shown in fig. 2, the method for extracting the scattering center of the radar target attribute (the method is short for the invention) is also adopted to obtain the scattering center extraction result corresponding to the measurement data of the target darkroom, the observation target shown in fig. 2 is a tank model, the radar wave band is an X wave band, and the real length of a gun barrel of the tank model is 0.420m; from the extraction result, the extraction result of the scattering center position corresponding to the gun barrel is identical with the imaging result, the corresponding estimated value of the attribute parameter is 0.5, and the type of the scattering center is a cylindrical scattering center; the estimated value of the attribute parameter is 0.475m, which is close to the structural parameter of a real cylindrical gun barrel component, and the estimated accuracy is better than 85%.
By adopting darkroom measurement data corresponding to FIG. 2, and respectively adopting a traditional dictionary construction method and the method for carrying out attribute parameter inversion on the target gun barrel scattering center, the calculation performance under two conditions is shown in the following table 1, and the method can effectively reduce the calculation time and improve the calculation efficiency.
Table 1 comparison of the operational performances
Traditional dictionary construction method The method of the invention
Calculation time(s) 135s 61s
As shown in fig. 3, the present invention further provides a radar target attribute scattering center extraction device, which includes an image module 300, an echo module 302, an estimation module 304, and a result module 306, wherein:
the image module 300 is used for acquiring SAR complex images;
the echo module 302 is configured to segment each scattering center of the target based on the SAR complex image, and perform inverse fourier transform on the complex image corresponding to each scattering center to obtain radar echo data corresponding to each scattering center;
the estimation module 304 is configured to perform the following operations on the radar echo data corresponding to each scattering center:
complex decomposition is carried out on radar echo data corresponding to the scattering center, so that an echo model value correlation matrix and an echo argument correlation matrix are obtained;
carrying out optimization solution on an optimization problem formed by the echo model related quantity matrix and the dimensionality reduction combined dictionary to obtain an estimated value of the echo model related attribute parameter;
carrying out optimization solution on an optimization problem formed by the echo argument correlation matrix and the dimensionality reduction combined dictionary to obtain an estimated value of echo argument correlation attribute parameters;
acquiring an attribute parameter set corresponding to the scattering center based on the echo model value related attribute parameter and the echo argument related attribute parameter estimation value;
the result module 306 is configured to obtain attribute parameter sets corresponding to all scattering centers, so as to implement rapid extraction of the target attribute scattering centers.
In an embodiment of the present invention, the image module 300 may be used to implement the above-mentioned step 100, the echo module 302 may be used to implement the above-mentioned step 102, the estimation module 304 may be used to implement the above-mentioned step 104, and the result module 306 may be used to implement the above-mentioned step 106.
Further, the estimation module 304 is configured to perform complex decomposition on radar echo data corresponding to the scattering center to obtain an echo model correlation matrix and an echo argument correlation matrix, which includes performing the following operations:
setting the scattering center as the ith scattering center, wherein i is more than or equal to 1 and less than or equal to N, and N represents the total number of the scattering centers of the target;
radar echo data corresponding to the ith scattering center
Figure BDA0003234384700000151
Complex decomposition is performed, and the expression is:
Figure BDA0003234384700000152
wherein f represents a discrete radar broadband frequency vector with a length of N f ，f c The radar center frequency, c is the speed of light;
Figure BDA0003234384700000153
represents a discrete observation azimuth vector of length +.>
Figure BDA0003234384700000154
Figure BDA0003234384700000155
Representing an attribute parameter set corresponding to the ith scattering center, wherein the attribute parameters in the set comprise: a is that i Indicating scattering intensity, alpha i Represents an orientation dependent factor, L i Indicating scattering center length, +.>
Figure BDA0003234384700000156
Representing the initial azimuth angle gamma i Representing a frequency dependent factor, x i 、y i Respectively representing the horizontal and vertical coordinate positions of the ith scattering center;
according to the complex decomposition expression, an expression of an echo module value correlation matrix is obtained:
Figure BDA0003234384700000157
the attribute parameter set expression corresponding to the echo module value correlation quantity matrix is as follows:
Figure BDA0003234384700000158
according to the complex decomposition expression, an echo argument correlation matrix expression is obtained:
Figure BDA0003234384700000161
the attribute parameter set expression corresponding to the echo argument matrix is as follows:
θ p ＝{α i ,x i ,y i }。
further, the estimating module 304 is configured to perform an optimization solution on an optimization problem formed by the echo module correlation matrix and the dimension-reduction joint dictionary, to obtain an estimated value of the echo module correlation attribute parameter, and includes performing the following operations:
establishing a parameter solving optimization model corresponding to the echo module value correlation quantity matrix, wherein the expression is as follows:
Figure BDA0003234384700000162
wherein delta f To solve for theta f The corresponding sparse coefficient vector has the size of
Figure BDA0003234384700000163
N α 、N L 、/>
Figure BDA0003234384700000164
N γ Respectively the attribute parameters alpha i 、L i 、/>
Figure BDA0003234384700000165
γ i The number of meshes divided in the corresponding parameter space, +.>
Figure BDA0003234384700000166
Delta is f Lambda of the estimated value of (a) f Representing regularization parameters corresponding to the parameter solution optimization model corresponding to the echo module value correlation quantity matrix;
establishing a dimensionality reduction joint dictionary corresponding to the echo module value correlation quantity matrix, wherein the expression is as follows:
Figure BDA0003234384700000167
Figure BDA0003234384700000168
wherein D is f (θ f ) The size of the dimension-reducing combined dictionary corresponding to the echo module value correlation matrix is as follows
Figure BDA0003234384700000169
Figure BDA00032343847000001610
Representation D f (θ f ) Is a first row vector of (a);
using the formula
Figure BDA00032343847000001611
Estimating the property parameters of the ith scattering center
Figure BDA00032343847000001612
Further, the estimating module 304 is configured to perform an optimization solution on an optimization problem formed by the echo argument correlation matrix and the dimension-reduction joint dictionary, to obtain an estimated value of the echo argument correlation attribute parameter, and includes performing the following operations:
establishing a parameter solving optimization model corresponding to the echo argument matrix, wherein the expression is as follows:
Figure BDA0003234384700000171
wherein delta p To solve for theta p The corresponding sparse coefficient vector is of the size N x N y ×1，N x 、N y Respectively the attribute parameters x i 、y i The number of grids divided in the parameter space,
Figure BDA0003234384700000172
delta is p Lambda of the estimated value of (a) p Representing regularization parameters corresponding to the parameter solving optimization model corresponding to the echo radial angle correlation quantity matrix;
establishing a dimensionality reduction joint dictionary corresponding to the echo argument matrix, wherein the expression is as follows:
Figure BDA0003234384700000173
Figure BDA0003234384700000174
wherein D is p (θ p ) The size of the dimension-reducing combined dictionary corresponding to the echo argument correlation matrix is as follows
Figure BDA0003234384700000176
d p (x 1 ,y 1 ) Representation D p (θ p ) Is a first row vector of (a);
using the formula
Figure BDA0003234384700000175
And the obtained alpha i Estimating the attribute parameter { x } of the ith scattering center i ,y i }。
The contents of information interaction and execution process between the modules of the radar target attribute scattering center extraction device are based on the same conception as the embodiment of the method of the present invention, and specific contents can be referred to the description in the embodiment of the method of the present invention, and are not repeated here.
In the above embodiments, the hardware module may be mechanically or electrically implemented. For example, a hardware module may include permanently dedicated circuitry or logic (e.g., a dedicated processor, FPGA, or ASIC) to perform the corresponding operations. The hardware modules may also include programmable logic or circuitry (e.g., a general-purpose processor or other programmable processor) that may be temporarily configured by software to perform the corresponding operations. The particular implementation (mechanical, or dedicated permanent, or temporarily set) may be determined based on cost and time considerations.
In particular, in some preferred embodiments of the present invention, there is also provided a computer device, including a memory and a processor, where the memory stores a computer program, and the processor implements the steps of the radar target attribute scattering center extraction method in any of the above embodiments when the computer program is executed.
In other preferred embodiments of the present invention, there is also provided a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the radar target attribute scattering center extraction method of any of the above embodiments.
Those skilled in the art will appreciate that implementing all or part of the above-described embodiment method may be implemented by a computer program to instruct related hardware, where the computer program may be stored in a non-volatile computer readable storage medium, and the computer program may include the above-described embodiment of the radar target attribute scattering center extraction method when executed, and will not be repeated herein.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims (10)

1. The radar target attribute scattering center extraction method is characterized by comprising the following steps of:
acquiring SAR complex images;
dividing each scattering center of the target based on the SAR complex images, and performing inverse Fourier transform on the complex images corresponding to each scattering center to obtain radar echo data corresponding to each scattering center;
the following operations are performed on the radar echo data corresponding to each scattering center:
complex decomposition is carried out on radar echo data corresponding to the scattering center, so that an echo model value correlation matrix and an echo argument correlation matrix are obtained; carrying out optimization solution on an optimization problem formed by the echo module value correlation matrix and the dimension reduction combined dictionary to obtain an estimated value of the echo module value correlation attribute parameter; carrying out optimization solution on an optimization problem formed by the echo argument correlation matrix and the dimensionality reduction combined dictionary to obtain an estimated value of echo argument correlation attribute parameters; acquiring an attribute parameter set corresponding to the scattering center based on the echo module value related attribute parameter and the echo argument related attribute parameter estimated value;
and obtaining attribute parameter sets corresponding to all scattering centers, and realizing rapid extraction of the target attribute scattering centers.
2. The radar target attribute scattering center extraction method according to claim 1, wherein:
the complex decomposition is carried out on the radar echo data corresponding to the scattering center to obtain an echo module value correlation quantity matrix and an echo argument correlation quantity matrix, and the complex decomposition comprises the following steps:
setting the scattering center as the ith scattering center, wherein i is more than or equal to 1 and less than or equal to N, and N represents the total number of the scattering centers of the target;
radar echo data corresponding to the ith scattering center
Figure FDA0003234384690000011
Complex decomposition is performed, and the expression is:
Figure FDA0003234384690000021
wherein f represents a discrete radar broadband frequency vector with a length of N f ，f c The radar center frequency, c is the speed of light;
Figure FDA0003234384690000022
represents a discrete observation azimuth vector of length +.>
Figure FDA0003234384690000023
Figure FDA0003234384690000024
Representing an attribute parameter set corresponding to the ith scattering center, wherein the attribute parameters in the set comprise: a is that i Indicating scattering intensity, alpha i Represents an orientation dependent factor, L i Indicating scattering center length, +.>
Figure FDA0003234384690000025
Representing the initial azimuth angle gamma i Representing a frequency dependent factor, x i 、y i Respectively representing the horizontal and vertical coordinate positions of the ith scattering center;
according to the complex decomposition expression, an expression of an echo module value correlation matrix is obtained:
Figure FDA0003234384690000026
the attribute parameter set expression corresponding to the echo module value correlation matrix is as follows:
Figure FDA0003234384690000027
according to the complex decomposition expression, an echo argument correlation matrix expression is obtained:
Figure FDA0003234384690000028
the attribute parameter set expression corresponding to the echo argument matrix is as follows:
θ p ＝{α i ,x i ,y i }。
3. the radar target attribute scattering center extraction method according to claim 2, wherein:
carrying out optimization solving on an optimization problem formed by the echo module value correlation quantity matrix and the dimensionality reduction combined dictionary to obtain an estimated value of the echo module value correlation attribute parameter, wherein the method comprises the following steps:
establishing a parameter solving optimization model corresponding to the echo module value correlation quantity matrix, wherein the expression is as follows:
Figure FDA0003234384690000031
wherein delta f To solve for theta f The corresponding sparse coefficient vector has the size of
Figure FDA0003234384690000032
N α 、N L 、/>
Figure FDA0003234384690000033
N γ Respectively the attribute parameters alpha i 、L i 、/>
Figure FDA0003234384690000034
γ i The number of meshes divided in the corresponding parameter space, +.>
Figure FDA0003234384690000035
Delta is f Lambda of the estimated value of (a) f Regularization corresponding to parameter solving optimization model corresponding to echo module value correlation quantity matrixParameters;
establishing a dimension reduction joint dictionary corresponding to the echo module value correlation matrix, wherein the expression is as follows:
Figure FDA0003234384690000036
Figure FDA0003234384690000037
wherein D is f (θ f ) The dimension-reducing joint dictionary corresponding to the echo module value correlation quantity matrix is represented and has the size of
Figure FDA0003234384690000038
Figure FDA0003234384690000039
Representation D f (θ f ) Is a first row vector of (a);
using the formula
Figure FDA00032343846900000310
Estimating the property parameters of the ith scattering center
Figure FDA00032343846900000311
4. A radar target attribute scattering center extraction method according to claim 3, wherein:
carrying out optimization solving on an optimization problem formed by the echo argument correlation matrix and the dimensionality reduction combined dictionary to obtain an estimated value of the echo argument correlation attribute parameter, wherein the method comprises the following steps:
establishing a parameter solving optimization model corresponding to the echo argument matrix, wherein the expression is as follows:
Figure FDA00032343846900000312
wherein delta p To solve for theta p The corresponding sparse coefficient vector is of the size N x N y ×1，N x 、N y Respectively the attribute parameters x i 、y i The number of grids divided in the parameter space,
Figure FDA00032343846900000313
delta is p Lambda of the estimated value of (a) p Representing regularization parameters corresponding to the parameter solving optimization model corresponding to the echo argument matrix;
establishing a dimensionality reduction joint dictionary corresponding to the echo argument matrix, wherein the expression is as follows:
Figure FDA0003234384690000041
Figure FDA0003234384690000042
wherein D is p (θ p ) The dimension-reducing joint dictionary corresponding to the echo argument matrix is represented and has the size of
Figure FDA0003234384690000044
d p (x 1 ,y 1 ) Representation D p (θ p ) Is a first row vector of (a); />
Using the formula
Figure FDA0003234384690000043
And the obtained alpha i Estimating the attribute parameter { x } of the ith scattering center i ,y i }。
5. The radar target property scattering center extraction device of claim 1, comprising:
the image module is used for acquiring SAR complex images;
the echo module is used for dividing each scattering center of the target based on the SAR complex images, and performing inverse Fourier transform on the complex images corresponding to each scattering center to obtain radar echo data corresponding to each scattering center;
the estimation module is used for executing the following operations on the radar echo data corresponding to each scattering center:
complex decomposition is carried out on radar echo data corresponding to the scattering center, so that an echo model value correlation matrix and an echo argument correlation matrix are obtained;
carrying out optimization solution on an optimization problem formed by the echo module value correlation matrix and the dimension reduction combined dictionary to obtain an estimated value of the echo module value correlation attribute parameter;
carrying out optimization solution on an optimization problem formed by the echo argument correlation matrix and the dimensionality reduction combined dictionary to obtain an estimated value of echo argument correlation attribute parameters;
acquiring an attribute parameter set corresponding to the scattering center based on the echo module value related attribute parameter and the echo argument related attribute parameter estimated value;
and the result module is used for obtaining attribute parameter sets corresponding to all scattering centers and realizing rapid extraction of the target attribute scattering centers.
6. The radar target attribute scattering center extraction apparatus of claim 5, wherein:
the estimation module is used for carrying out complex decomposition on radar echo data corresponding to the scattering center to obtain an echo module value correlation matrix and an echo argument correlation matrix, and comprises the following operations:
setting the scattering center as the ith scattering center, wherein i is more than or equal to 1 and less than or equal to N, and N represents the total number of the scattering centers of the target;
radar echo data corresponding to the ith scattering center
Figure FDA0003234384690000051
Complex decomposition is performed, and the expression is:
Figure FDA0003234384690000052
wherein f represents a discrete radar broadband frequency vector with a length of N f ，f c The radar center frequency, c is the speed of light;
Figure FDA0003234384690000053
represents a discrete observation azimuth vector of length +.>
Figure FDA0003234384690000054
Figure FDA0003234384690000055
Representing an attribute parameter set corresponding to the ith scattering center, wherein the attribute parameters in the set comprise: a is that i Indicating scattering intensity, alpha i Represents an orientation dependent factor, L i Indicating scattering center length, +.>
Figure FDA0003234384690000056
Representing the initial azimuth angle gamma i Representing a frequency dependent factor, x i 、y i Respectively representing the horizontal and vertical coordinate positions of the ith scattering center;
according to the complex decomposition expression, an expression of an echo module value correlation matrix is obtained:
Figure FDA0003234384690000057
the attribute parameter set expression corresponding to the echo module value correlation matrix is as follows:
Figure FDA0003234384690000058
according to the complex decomposition expression, an echo argument correlation matrix expression is obtained:
Figure FDA0003234384690000061
the attribute parameter set expression corresponding to the echo argument matrix is as follows:
θ p ＝{α i ,x i ,y i }。
7. the radar target attribute scattering center extraction apparatus of claim 6, wherein:
the estimation module is used for carrying out optimization solution on the optimization problem formed by the echo module value correlation quantity matrix and the dimension reduction combined dictionary to obtain an estimated value of the echo module value correlation attribute parameter, and comprises the following operations:
establishing a parameter solving optimization model corresponding to the echo module value correlation quantity matrix, wherein the expression is as follows:
Figure FDA0003234384690000062
wherein delta f To solve for theta f The corresponding sparse coefficient vector has the size of
Figure FDA0003234384690000063
N α 、N L 、/>
Figure FDA0003234384690000064
N γ Respectively the attribute parameters alpha i 、L i 、/>
Figure FDA0003234384690000065
γ i Grid divided in corresponding parameter spaceNumber of (I) and (II)>
Figure FDA0003234384690000066
Delta is f Lambda of the estimated value of (a) f Representing regularization parameters corresponding to the parameter solving optimization model corresponding to the echo module value correlation quantity matrix;
establishing a dimension reduction joint dictionary corresponding to the echo module value correlation matrix, wherein the expression is as follows:
Figure FDA0003234384690000067
Figure FDA0003234384690000068
wherein D is f (θ f ) The dimension-reducing joint dictionary corresponding to the echo module value correlation quantity matrix is represented and has the size of
Figure FDA0003234384690000069
Figure FDA00032343846900000610
Representation D f (θ f ) Is a first row vector of (a);
using the formula
Figure FDA00032343846900000611
Estimating the property parameters of the ith scattering center
Figure FDA00032343846900000612
8. The radar target attribute scattering center extraction apparatus of claim 7, wherein:
the estimation module is used for carrying out optimization solution on the optimization problem formed by the echo argument correlation matrix and the dimensionality reduction joint dictionary to obtain an estimated value of the echo argument correlation attribute parameter, and comprises the following steps:
establishing a parameter solving optimization model corresponding to the echo argument matrix, wherein the expression is as follows:
Figure FDA0003234384690000071
wherein delta p To solve for theta p The corresponding sparse coefficient vector is of the size N x N y ×1，N x 、N y Respectively the attribute parameters x i 、y i The number of grids divided in the parameter space,
Figure FDA0003234384690000072
delta is p Lambda of the estimated value of (a) p Representing regularization parameters corresponding to the parameter solving optimization model corresponding to the echo argument matrix;
establishing a dimensionality reduction joint dictionary corresponding to the echo argument matrix, wherein the expression is as follows:
Figure FDA0003234384690000073
Figure FDA0003234384690000074
wherein D is p (θ p ) The dimension-reducing joint dictionary corresponding to the echo argument matrix is represented and has the size of
Figure FDA0003234384690000075
d p (x 1 ,y 1 ) Representation D p (θ p ) Is a first row vector of (a);
using the formula
Figure FDA0003234384690000076
And the obtained alpha i Estimating the attribute parameter { x } of the ith scattering center i ,y i }。
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the radar target property scattering center extraction method of any one of claims 1 to 4 when the computer program is executed.
10. A computer readable storage medium having stored thereon a computer program, characterized in that the computer program when executed by a processor implements the steps of the radar target property scattering center extraction method of any of claims 1 to 4.
CN202110997643.8A 2021-08-27 2021-08-27 Radar target attribute scattering center extraction method and device Active CN113514811B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110997643.8A CN113514811B (en) 2021-08-27 2021-08-27 Radar target attribute scattering center extraction method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110997643.8A CN113514811B (en) 2021-08-27 2021-08-27 Radar target attribute scattering center extraction method and device

Publications (2)

Publication Number Publication Date
CN113514811A CN113514811A (en) 2021-10-19
CN113514811B true CN113514811B (en) 2023-05-12

Family

ID=78062991

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110997643.8A Active CN113514811B (en) 2021-08-27 2021-08-27 Radar target attribute scattering center extraction method and device

Country Status (1)

Country Link
CN (1) CN113514811B (en)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103529447A (en) * 2012-07-02 2014-01-22 中国科学院对地观测与数字地球科学中心 Polarization four-component decomposition method for city area
CN109444842A (en) * 2019-01-04 2019-03-08 北京环境特性研究所 A kind of electromagnetic characteristic of scattering data reconstruction method and device
CN111781573A (en) * 2020-07-10 2020-10-16 中国人民解放军空军工程大学 Scattering center model parameter estimation method based on improved 3D-ESPRIT algorithm

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8330642B2 (en) * 2007-07-09 2012-12-11 Carnegie Mellon University Imaging by time reversal beamforming

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103529447A (en) * 2012-07-02 2014-01-22 中国科学院对地观测与数字地球科学中心 Polarization four-component decomposition method for city area
CN109444842A (en) * 2019-01-04 2019-03-08 北京环境特性研究所 A kind of electromagnetic characteristic of scattering data reconstruction method and device
CN111781573A (en) * 2020-07-10 2020-10-16 中国人民解放军空军工程大学 Scattering center model parameter estimation method based on improved 3D-ESPRIT algorithm

Also Published As

Publication number Publication date
CN113514811A (en) 2021-10-19

Similar Documents

Publication Publication Date Title
US10977526B2 (en) Method and apparatus for SAR image recognition based on multi-scale features and broad learning
CN109766835B (en) SAR target recognition method for generating countermeasure network based on multi-parameter optimization
CN104933678B (en) A kind of image super-resolution rebuilding method based on image pixel intensities
CN107229918B (en) SAR image target detection method based on full convolution neural network
CN109343060B (en) ISAR imaging method and system based on deep learning time-frequency analysis
CN109507666B (en) ISAR sparse band imaging method based on off-network variational Bayesian algorithm
CN107831473B (en) Distance-instantaneous Doppler image sequence noise reduction method based on Gaussian process regression
CN112052762A (en) Small sample ISAR image target identification method based on Gaussian prototype
CN109991602A (en) ISAR image resolution enhancement method based on depth residual error network
Qin et al. ISAR resolution enhancement using residual network
CN108776339B (en) Single-bit synthetic aperture radar imaging method based on block sparse iteration threshold processing
CN111352108B (en) Fast SAR echo signal simulation method based on FFBP reverse processing
Pan et al. Deep learning-based 2-D frequency estimation of multiple sinusoidals
CN116012364A (en) SAR image change detection method and device
CN109444844B (en) Method and device for extracting target scattering center features
CN109658340B (en) SAR image rapid denoising method based on RSVD and histogram preservation
CN113514811B (en) Radar target attribute scattering center extraction method and device
CN114779185A (en) Radar signal anti-interference low-loss recovery method of coding and decoding convolutional neural network
Wang et al. Low probability of intercept radar waveform recognition based on dictionary leaming
CN112215832B (en) SAR trail image quality evaluation and self-adaptive detection parameter adjustment method
CN115830462B (en) SAR image reconstruction method and device based on cyclic consistency countermeasure network
CN109766899B (en) Physical feature extraction and SVM SAR image vehicle target recognition method
CN116577748A (en) Scattering center parameter extraction method based on microwave photon signals
CN112215942B (en) Method and system for reconstructing partial tomographic three-dimensional image of refrigeration electron microscope
CN114966687A (en) Sparse ISAR imaging method and system based on low rank and non-local self-similarity

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant