A single-target and multi-target classification method and device
By calculating the target entropy of the received signal of the array, it quickly judges the single multi-objective, avoids feature decomposition, solves the problem of large calculations in the prior art, and improves direction finding efficiency and engineering practicality.
Patent Information
- Application Number
- CN202110590422.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-05-28
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2041-05-28
AI Technical Summary
The existing single-multi-objective classification method requires feature decomposition when performing target single-multi-objective classification, resulting in large amounts of calculations and thus reducing direction finding efficiency.
By obtaining the received signal of the array, performing vector normalization processing to obtain the target signal vector, calculating the target entropy of the target signal vector, and determining the target type based on the target entropy, avoiding feature decomposition, and quickly completing single-multi-objective classification.
It improves direction finding efficiency, reduces the amount of calculation, can quickly judge single or multiple goals, and is suitable for any array, improving the practical value of engineering.
Smart Images

Figure CN113255528B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of signal processing technology, and in particular to a single-target and multi-target classification method and device. Background Art
[0002] Direction finding technology refers to estimating the direction of the target wave by analyzing and processing the array received signal. After the target is detected, the number of targets and the direction of the wave need to be estimated in sequence. In the existing single-target and multi-target classification methods, it is necessary to perform feature decomposition on the target signal when performing single-target and multi-target classification. In practice, it is found that single-target and multi-target classification generally requires feature decomposition. In the scenario of a single target, the amount of calculation is large, which leads to a decrease in direction finding efficiency. Summary of the invention
[0003] The purpose of the embodiments of the present application is to provide a single-target and multi-target classification method and device, which can quickly complete the single-target and multi-target classification without the need for feature decomposition, thereby facilitating the improvement of direction finding efficiency.
[0004] A first aspect of an embodiment of the present application provides a single-target and multi-target classification method, including:
[0005] Obtain array receiving signal;
[0006] Performing vector normalization processing on the array received signal to obtain a target signal vector;
[0007] Calculating a target entropy of the target signal vector;
[0008] A target type is determined according to the target entropy, where the target type is a single target or multiple targets.
[0009] In the above implementation process, the array receiving signal is first obtained, and the array receiving signal is vector normalized to obtain the target signal vector; then the target entropy of the target signal vector is calculated; finally, the target type is determined according to the target entropy. The target type is single target or multiple targets, which can quickly complete the single and multiple target classification without feature decomposition, thereby helping to improve the direction finding efficiency.
[0010] Furthermore, the formula for performing vector normalization processing on the array received signal is:
[0011]
[0012] in, is the target signal vector, x(n) is the array received signal, and ||x(n)||2 represents the calculation of the 2-norm of the array received signal.
[0013] Further, the calculating the target entropy of the target signal vector includes:
[0014] Calculating a target correlation of the target signal vector;
[0015] According to the target correlation, the target entropy is calculated.
[0016] In the above implementation process, single-target and multi-target judgment can be achieved by calculating the entropy of the target signal vector, with less calculation.
[0017] Furthermore, the formula for calculating the target entropy is:
[0018]
[0019] Where E is the target entropy, p n is the target correlation, and N is the number of snapshots.
[0020] Further, determining the target type according to the target entropy includes:
[0021] Determining whether the target entropy is less than a preset threshold;
[0022] If it is less than, the target type is determined to be a single target;
[0023] If it is greater than or equal to, the target type is determined to be multi-target.
[0024] In the above implementation process, the target entropy is compared with the preset threshold to obtain a judgment result. If the target entropy is less than the preset threshold, it is a single target; otherwise, it is multiple targets.
[0025] A second aspect of an embodiment of the present application provides a single-target or multi-target classification device, the single-target or multi-target classification device comprising:
[0026] A signal acquisition unit, used for acquiring array receiving signals;
[0027] A normalization unit, used for performing vector normalization processing on the array received signal to obtain a target signal vector;
[0028] A calculation unit, used for calculating the target entropy of the target signal vector;
[0029] A classification unit is used to determine a target type according to the target entropy, where the target type is a single target or multiple targets.
[0030] In the above implementation process, the signal acquisition unit first acquires the array receiving signal, and the normalization unit performs vector normalization processing on the array receiving signal to obtain the target signal vector; then the calculation unit calculates the target entropy of the target signal vector; finally, the classification unit determines the target type according to the target entropy, and the target type is single target or multiple targets. It can quickly complete the single and multiple target classification without feature decomposition, which is beneficial to improve the direction finding efficiency.
[0031] Furthermore, the calculation unit comprises:
[0032] A first calculation subunit, configured to calculate a target correlation of the target signal vector;
[0033] The second calculation subunit is used to calculate the target entropy according to the target correlation.
[0034] In the above implementation process, single-target and multi-target judgment can be achieved by calculating the entropy of the target signal vector, with less calculation.
[0035] Furthermore, the classification unit includes:
[0036] A judging subunit, used to judge whether the target entropy is less than a preset threshold;
[0037] The determination subunit is used to determine that the target type is a single target when it is determined that the target entropy is less than the preset threshold; and to determine that the target type is multiple targets when it is determined that the target entropy is greater than or equal to the preset threshold.
[0038] In the above implementation process, the target entropy is compared with the preset threshold to obtain a judgment result. If the target entropy is less than the preset threshold, it is a single target; otherwise, it is multiple targets.
[0039] A third aspect of an embodiment of the present application provides an electronic device, including a memory and a processor, wherein the memory is used to store a computer program, and the processor runs the computer program to enable the electronic device to perform the single-target or multi-target classification method described in any one of the first aspect of the embodiments of the present application.
[0040] A fourth aspect of an embodiment of the present application provides a computer-readable storage medium storing computer program instructions. When the computer program instructions are read and executed by a processor, the single-target or multi-target classification method described in any one of the first aspect of the embodiment of the present application is executed. BRIEF DESCRIPTION OF THE DRAWINGS
[0041] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.
[0042] Figure 1 A schematic diagram of a flow chart of a single-target and multi-target classification method provided in Example 1 of the present application;
[0043] Figure 2 A schematic diagram of a flow chart of a single-target and multi-target classification method provided in Example 2 of the present application;
[0044] Figure 3 A schematic diagram of the structure of a single-multiple target classification device provided in Example 3 of the present application;
[0045] Figure 4 A schematic diagram of the structure of a single-multiple target classification device provided in Embodiment 4 of the present application;
[0046] Figure 5 A schematic diagram of the relationship between the judgment accuracy and the signal-to-noise ratio provided in Example 2 of the present application. DETAILED DESCRIPTION
[0047] The technical solutions in the embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application.
[0048] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.
[0049] Example 1
[0050] Please see Figure 1 , Figure 1 A flowchart of a single-target and multi-target classification method is provided for an embodiment of the present application. The single-target and multi-target classification method includes:
[0051] S101, obtaining array receiving signals.
[0052] In the embodiment of the present application, an array reception signal can be obtained through an array antenna.
[0053] In the embodiment of the present application, it is assumed that K incident angles in space are θ kThe target transmitted signal is received by the array antenna to obtain the array received signal. The signal model of the array received signal x(n) can be expressed as:
[0054] x(n)=As(n)+w(n);
[0055] Wherein, k = 1, 2, ..., K, n = 1, 2, ..., L, ..., N;
[0056] The array receives the signal x(n) = [x1(n), x2(n),…, x M (n)] T ; Target transmission signal s(n) = [s1(n), s2(n),…, s K (n)] T ; Array popularity matrix A = [a(θ1), a(θ2), …, a(θ K )]; array receiving noise w(n)=[w1(n),w2(n),…,w M (n)] T .
[0057] In the above formula, the array antenna is composed of M isotropic antennas, where M>K, and the wavelength of the signal is λ.
[0058] In the above formula, the array popularity matrix A and the incident angle θ k Regarding, s(n) is the signal reaching the array antenna, and x(n) is the signal received by the array antenna.
[0059] In the embodiments of the present application, the target refers to the object to be detected, which may be a reflection or emission of electromagnetic waves. In the field of radar, it is generally an object that reflects electromagnetic waves. In the field of passive detection, the target generally emits electromagnetic waves. Because the target emits electromagnetic waves, it can also be called a signal source.
[0060] In the embodiment of the present application, the processing object of the method is the array received signal x(n), which can be directly received and processed by the array antenna, and the processing is based on the signal model of the above x(n).
[0061] After step S101, the following steps are also included:
[0062] S102: Perform vector normalization processing on the array received signal to obtain a target signal vector.
[0063] In the embodiment of the present application, in order to avoid the influence of the specificity of different snapshot data, it is necessary to perform signal vector normalization processing on the array received signal.
[0064] In the embodiment of the present application, there are multiple calculation methods for signal vector normalization. Specifically, a power normalization processing method can be adopted, which is not limited in the embodiment of the present application.
[0065] S103. Calculate the target entropy of the target signal vector.
[0066] In the embodiment of the present application, entropy can describe the degree of disorder of the system. By calculating the target entropy of the target signal vector, the degree of disorder of the high-dimensional signal vector (i.e., the target signal vector) can be described. In practical applications, compared with a single target, the entropy of the high-dimensional signal vector received by the array in the case of multiple targets is greater.
[0067] In the embodiment of the present application, single-target and multi-target judgment can be achieved by calculating the entropy of the target signal vector.
[0068] S104. Determine the target type according to the target entropy, where the target type is single target or multiple targets.
[0069] In the embodiment of the present application, the method proposes a single-multiple target judgment method applicable to any array, which can judge whether there is only one target.
[0070] In the embodiment of the present application, the method has a small amount of calculation. When it is determined that it is a single target, a direction finding algorithm with a small amount of calculation, such as the amplitude ratio method, can be used to complete the direction finding of the single target.
[0071] In the embodiment of the present application, from the perspective of the entire direction finding process, for a single target, this method can avoid eigenvalue decomposition, has a small amount of calculation, and has great engineering practical value.
[0072] In the embodiment of the present application, the method is implemented to complete the direction finding of a single target without performing eigenvalue decomposition.
[0073] In the embodiment of the present application, the problem solved by the method is how to determine whether there is one target or multiple targets based on the array received signal. It should be noted that although the signal model of the array received signal in the embodiment of the present application describes a one-dimensional array, the method is applicable not only to any one-dimensional array, but also to any two-dimensional and three-dimensional arrays.
[0074] In the embodiment of the present application, the execution subject of the method can be a computing device such as a computer or a server, and no limitation is made in this embodiment.
[0075] In the embodiment of the present application, the execution subject of the method can also be a smart device such as a smart phone, a tablet computer, etc., and there is no limitation on this in the present embodiment.
[0076] It can be seen that the implementation of the single-target and multi-target classification method described in this embodiment can quickly complete the single-target and multi-target classification without the need for feature decomposition, thereby helping to improve the direction finding efficiency.
[0077] Example 2
[0078] Please see Figure 2 , Figure 2 A schematic diagram of a single-target and multi-target classification method provided in an embodiment of the present application. Figure 2 As shown, the single-multi-target classification method includes:
[0079] S201, obtaining array receiving signals.
[0080] S202: Perform vector normalization processing on the array received signal to obtain a target signal vector.
[0081] As an optional implementation, a power normalization method may be used to perform vector normalization processing on the array received signal. Specifically, the formula for performing vector normalization processing on the array received signal is:
[0082]
[0083] in, is the target signal vector, x(n) is the array received signal, and ||x(n)||2 represents the calculation of the 2-norm of the array received signal.
[0084] S203: Calculate the target correlation of the target signal vector.
[0085] As an optional implementation, calculating the target correlation of the target signal vector includes:
[0086] Calculate the initial correlation of the target signal vector;
[0087] The initial correlation is fused to obtain the target correlation.
[0088] In the above implementation, there are multiple ways to measure the correlation between signal vectors. Specifically, cosine similarity can be used for measurement, which is not limited in the embodiments of the present application.
[0089] As a further optional implementation, the formula for calculating the initial correlation is:
[0090]
[0091] Wherein, i=1, 2, ..., N, N is the number of snapshots;
[0092] Among them, p' n is the initial correlation between the target signal vector and the i-th snapshot signal vector, To normalize the array receiving signal, represents the conjugate transpose of the received signal of the calculation array.
[0093] In the embodiment of the present application, in order to calculate the entropy of the signal vector, the correlation between the signal vectors must first be calculated.
[0094] In the above embodiment, when i=1, the above formula for calculating the initial correlation can be used to obtain p' n =p'1,p'2,..,p' N , when i ranges from 1 to N, we can get N groups p'1, p'2, .., p' N , then we can get N groups p'1,p'2,..,p' N Perform fusion processing to obtain the final target correlation p n =p1,p2,..,p N .
[0095] In the above embodiment, for N groups p'1, p'2, .., p' N When performing the fusion processing, the average value, weighted average, etc. can be adopted, which is not limited in the embodiments of the present application.
[0096] In the above implementation, for example, when calculating the fused p1, the average of N p'1s is calculated to obtain p1.
[0097] In the above implementation, the fusion processing of the initial correlation can improve the accuracy of the target correlation, which is beneficial to improve the accuracy of single-target and multi-target resolution.
[0098] After step S203, the following steps are also included:
[0099] S204. Calculate target entropy according to target correlation.
[0100] As an optional implementation, the formula for calculating the target entropy is:
[0101]
[0102] Among them, E is the target entropy, p n is the target correlation, and N is the number of snapshots.
[0103] Among them, the number of snapshots is the number of time domain samples, which is the number of samples sampled.
[0104] In the embodiment of the present application, the above steps S203 to S204 are implemented to calculate the target entropy of the target signal vector.
[0105] S205, determining whether the target entropy is less than a preset threshold, if yes, executing step S206; if no, executing step S207.
[0106] S206: Determine that the target type is a single target, and end this process.
[0107] S207: Determine that the target type is multi-target, and end this process.
[0108] In the embodiment of the present application, E is compared with a preset threshold ε to obtain a judgment result. If E<ε, the target type is a single target; otherwise, the target type is a multi-target.
[0109] As an optional implementation, after the judgment is completed, if it is a single target, the direction can be found by using the amplitude comparison method or other methods.
[0110] In the embodiment of the present application, when the target type is a single target, the amplitude ratio method can be used for direction finding, and the entire direction finding process can be completed without feature decomposition. Compared with the existing direction finding scheme, this method can quickly realize single target judgment and direction finding of any array, and is particularly suitable for scenarios with a higher probability of a single target appearing, and has great engineering application value.
[0111] In the embodiment of the present application, by implementing the above steps S205 to S207, the target type can be determined according to the target entropy, and the target type is a single target or multiple targets.
[0112] In the simulation experiment, an 8-element uniform linear array is used, and the element spacing is half a wavelength. The number of signal snapshots is 200. The number of simulation experiments is 1000, of which there is a 40% probability that there is only one target from -10°, a 30% probability that there are two targets from -10° and 0°, and a 30% probability that there are three targets from -10°, 0°, and 10°. The relationship between the judgment accuracy and the signal-to-noise ratio is shown in Figure 5 As shown, Figure 5 This is a schematic diagram of the relationship between the judgment accuracy and the signal-to-noise ratio. Figure 5 As shown, the horizontal axis of the line graph is the signal-to-noise ratio (SNR), and the vertical axis is the correct judgment rate. Figure 5 It can be seen that when the signal-to-noise ratio is high, a higher decision accuracy can be obtained.
[0113] It can be seen that the implementation of the single-target and multi-target classification method described in this embodiment can quickly complete the single-target and multi-target classification without the need for feature decomposition, thereby helping to improve the direction finding efficiency.
[0114] Example 3
[0115] Please see Figure 3 , Figure 3This is a schematic diagram of the structure of a single-target and multi-target classification device provided in an embodiment of the present application. Figure 3 As shown, the single-multi-target classification device includes:
[0116] A signal acquisition unit 310 is used to acquire an array receiving signal;
[0117] A normalization unit 320 is used to perform vector normalization processing on the array received signal to obtain a target signal vector;
[0118] A calculation unit 330, configured to calculate a target entropy of a target signal vector;
[0119] The classification unit 340 is used to determine the target type according to the target entropy, and the target type is a single target or multiple targets.
[0120] In the embodiments of the present application, the explanation of the single-multi-target classification device can refer to the description in Embodiment 1 or Embodiment 2, and no further details will be given in this embodiment.
[0121] It can be seen that the single-target and multi-target classification device described in this embodiment can quickly complete the single-target and multi-target classification without the need for feature decomposition, thereby helping to improve the direction finding efficiency.
[0122] Example 4
[0123] Please also read Figure 4 , Figure 4 is a schematic diagram of the structure of a single-target multi-target classification device provided in an embodiment of the present application. Figure 4 The single and multi-target classification device shown is composed of Figure 3 The single and multi-objective classification device shown is optimized. Figure 4 As shown, the calculation unit 330 includes:
[0124] A first calculation subunit 331, configured to calculate a target correlation of a target signal vector;
[0125] The second calculation subunit 332 is used to calculate the target entropy according to the target correlation.
[0126] As an optional implementation, the formula for performing vector normalization processing on the array received signal is:
[0127]
[0128] in, is the target signal vector, x(n) is the array received signal, and ||x(n)||2 represents the calculation of the 2-norm of the array received signal.
[0129] As an optional implementation, the classification unit 340 includes:
[0130] A judging subunit 341 is used to judge whether the target entropy is less than a preset threshold;
[0131] The determination subunit 342 is used to determine that the target type is a single target when it is determined that the target entropy is less than a preset threshold; and to determine that the target type is multiple targets when it is determined that the target entropy is greater than or equal to the preset threshold.
[0132] As an optional implementation, the formula for calculating the target entropy is:
[0133]
[0134] Among them, E is the target entropy, p n is the target correlation, and N is the number of snapshots.
[0135] In the embodiments of the present application, the explanation of the single-target multi-target classification device can refer to the description in Embodiment 1 or Embodiment 2, which will not be further elaborated in this embodiment.
[0136] It can be seen that the single-target and multi-target classification device described in this embodiment can quickly complete the single-target and multi-target classification without the need for feature decomposition, thereby helping to improve the direction finding efficiency.
[0137] An embodiment of the present application provides an electronic device, including a memory and a processor, wherein the memory is used to store a computer program, and the processor runs the computer program to enable the electronic device to perform any single- or multi-target classification method in Embodiment 1 or Embodiment 2 of the present application.
[0138] An embodiment of the present application provides a computer-readable storage medium storing computer program instructions. When the computer program instructions are read and executed by a processor, any single-target or multi-target classification method in Embodiment 1 or Embodiment 2 of the present application is executed.
[0139] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely schematic. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the devices, methods and computer program products according to multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of a code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.
[0140] In addition, the functional modules in the various embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.
[0141] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.
[0142] The above description is only an embodiment of the present application and is not intended to limit the scope of protection of the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the scope of protection of the present application. It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings.
[0143] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.
[0144] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.
Claims
1. A single-multi-target classification method, characterized in that: include: Acquire array receiving signals through array antennas; Performing vector normalization processing on the array received signal to obtain a target signal vector; Calculating a target entropy of the target signal vector; Determine a target type according to the target entropy, where the target type is a single target or multiple targets; Wherein, calculating the target entropy of the target signal vector includes: Calculating a target correlation of the target signal vector; Calculating target entropy according to the target correlation; Wherein, the formula for calculating the target entropy is: ; Where E is the target entropy, p n is the target correlation, N is the number of snapshots; Wherein, determining the target type according to the target entropy, the target type being a single target or multiple targets, includes: Determining whether the target entropy is less than a preset threshold; If it is less than, the target type is determined to be a single target; If it is greater than or equal to, the target type is determined to be multiple targets; in the field of radar, the target is an object that reflects electromagnetic waves, and in the field of passive detection, the target is an object that emits electromagnetic waves; The signal model of the array receiving signal is: x(n)=As(n)+w(n); Among them, x(n) is the array received signal, A is the array popularity matrix, s(n) is the target transmitted signal, and w(n) is the array received noise.
2. The single-target and multi-target classification method according to claim 1, characterized in that: The formula for performing vector normalization processing on the array received signal is: ; in, is the target signal vector, x(n) is the array received signal, It indicates calculating the 2-norm of the array received signal.
3. A single-target and multi-target classification device, characterized in that: The single-multi-target classification device comprises: A signal acquisition unit, used to acquire an array receiving signal through an array antenna; A normalization unit, used for performing vector normalization processing on the array received signal to obtain a target signal vector; A calculation unit, used for calculating the target entropy of the target signal vector; A classification unit, used to determine a target type according to the target entropy, wherein the target type is a single target or multiple targets; Wherein, the computing unit comprises: A first calculation subunit, configured to calculate a target correlation of the target signal vector; A second calculation subunit, configured to calculate a target entropy according to the target correlation; Wherein, the formula for calculating the target entropy is: ; Where E is the target entropy, p n is the target correlation, N is the number of snapshots; Wherein, the classification unit includes: A judging subunit, used to judge whether the target entropy is less than a preset threshold; A determination subunit, configured to determine the target type as a single target when it is determined that the target entropy is less than the preset threshold; and to determine the target type as multiple targets when it is determined that the target entropy is greater than or equal to the preset threshold; wherein, in the field of radar, the target is an object that reflects electromagnetic waves, and in the field of passive detection, the target is an object that emits electromagnetic waves; The signal model of the array receiving signal is: x(n)=As(n)+w(n); Among them, x(n) is the array received signal, A is the array popularity matrix, s(n) is the target transmitted signal, and w(n) is the array received noise.
4. An electronic device, characterized in that: The electronic device comprises a memory and a processor, the memory is used to store a computer program, and the processor runs the computer program to enable the electronic device to perform the single-target and multi-target classification method according to any one of claims 1 to 2.
5. A readable storage medium, characterized in that: The readable storage medium stores computer program instructions, and when the computer program instructions are read and executed by a processor, the single-target or multi-target classification method according to any one of claims 1 to 2 is executed.
