Meteorological clutter suppression method based on distance-Doppler two-dimensional characteristics

Abstract

The embodiment of the invention relates to the technical field of data processing, and discloses a meteorological clutter suppression method based on distance-Doppler two-dimensional features, and the method comprises the steps: obtaining the coordinates of a training sample on a distance-Doppler two-dimensional plane, and taking the coordinates of the training sample as the center, cutting out a two-dimensional matrix according to a preset size; extracting image features corresponding to the training samples from the two-dimensional matrixes corresponding to the training samples; inputting the image features corresponding to the training samples into a support vector machine classifier, and performing iterative training on the support vector machine classifier to convergence based on a classification result of the training samples and labels of the training samples output by the support vector machine classifier; inputting the image features corresponding to the detection target into a support vector machine classifier, and obtaining a classification result of the detection target output by the support vector machine classifier; and if the classification result is meteorological clutter, rejecting the detection target. According to the method, low-altitude slow-moving meteorological clutters can be effectively eliminated, and false alarms are eliminated.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of data processing technology, and in particular to a method for suppressing meteorological clutter based on range-Doppler two-dimensional features. Background Art

[0002] Radar has the advantages of all-day and all-weather detection when detecting low-flying drone targets, and has a long detection distance and can obtain multi-dimensional information of the target. However, drones are typical low, slow and small targets. They fly at a low altitude, fly at a slow speed, and have a small radar scattering cross-sectional area. These characteristics make it difficult to distinguish the drone's echo from low-altitude meteorological clutter. During detection, if the detection threshold is set too low, a large number of clutter false alarms will be generated. If the detection threshold is set too high, it is easy to cause missed detection of targets. Therefore, how to effectively suppress meteorological clutter is a key issue in whether radar can accurately detect drone targets.

[0003] Commonly used clutter suppression methods include AMTI (Adaptive Moving Target Indication)-based methods and clutter map-based methods. The AMTI-based method mainly targets moving clutter with a narrow spectrum. First, the frequency to be compensated is calculated by estimating the center of the clutter spectrum, then motion compensation is performed on the clutter spectrum, the center of the spectrum is moved to zero frequency, and finally clutter is suppressed by the MTI filter. The clutter map-based method uses the time-domain stationary characteristics of clutter to divide the space scanned by the antenna into several clutter units, and then stores the clutter information according to the divided units after processing. This method can record and update the information of fixed ground clutter in the detection scene in real time, and eliminate fixed ground clutter by comparing the intensity of the echo in the current clutter unit with the historical clutter intensity recorded in the memory. However, the spectrum width of meteorological clutter is usually wide, and the spectrum is highly time-varying. The effect of using the above clutter suppression methods is not ideal. Summary of the invention

[0004] In view of this, the embodiment of the present application proposes a method for suppressing meteorological clutter based on range-Doppler two-dimensional features, which can effectively eliminate low-altitude slow-moving meteorological clutter, while ensuring effective detection of UAV targets, eliminating false alarms caused by meteorological clutter.

[0005] In order to achieve the above-mentioned purpose, an embodiment of the present application provides a method for suppressing meteorological clutter based on range-Doppler two-dimensional features, the method comprising the following steps: obtaining the coordinates of a training sample on a range-Doppler two-dimensional plane, and taking the coordinates of the training sample as the center, on the range-Doppler two-dimensional plane, cutting out a two-dimensional matrix according to a preset size; extracting image features corresponding to the training sample from the two-dimensional matrix corresponding to the training sample; wherein the image features include range-dimensional waveform entropy features, Doppler-dimensional waveform entropy features, image symmetry features, and energy weight features; inputting the image features corresponding to the training sample into a support vector machine classifier, and iteratively training the support vector machine classifier until convergence based on the classification results of the training sample output by the support vector machine classifier and the labels of the training samples; inputting the image features corresponding to the detection target into the support vector machine classifier, and obtaining the classification results of the detection target output by the support vector machine classifier; if the classification result of the detection target output by the support vector machine classifier is meteorological clutter, the detection target is eliminated.

[0006] In order to achieve the above-mentioned purpose, the embodiment of the present application also provides a meteorological clutter suppression system based on range-Doppler two-dimensional features, including: a positioning module, used to obtain the coordinates of the training sample on the range-Doppler two-dimensional plane, and take out a two-dimensional matrix according to a preset size on the range-Doppler two-dimensional plane with the coordinates of the training sample as the center; a feature extraction module, used to extract the image features corresponding to the training sample from the two-dimensional matrix corresponding to the training sample, wherein the image features include range-dimensional waveform entropy features, Doppler-dimensional waveform entropy features, image symmetry features and energy density features; a training module, used to input the image features corresponding to the training sample into a support vector machine classifier, and iteratively train the support vector machine classifier to converge based on the classification results of the training samples output by the support vector machine classifier and the labels of the training samples; a use module, used to input the image features corresponding to the detection target into the support vector machine classifier, obtain the classification results of the detection target output by the support vector machine classifier, and eliminate the detection target when the classification results of the detection target output by the support vector machine classifier are meteorological clutter.

[0007] In order to achieve the above-mentioned purpose, an embodiment of the present application also provides an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute a meteorological clutter suppression method based on range-Doppler two-dimensional features as described above.

[0008] In order to achieve the above objectives, an embodiment of the present application further provides a computer-readable storage medium storing a computer program, which, when executed by a processor, can implement a meteorological clutter suppression method based on range-Doppler two-dimensional features as described above.

[0009] The embodiment of the present application provides a method for suppressing meteorological clutter based on distance-Doppler two-dimensional features, constructs and trains a support vector machine classifier to perform the classification task of the detection target, and uses image features such as distance dimension waveform entropy features, Doppler dimension waveform entropy features, image symmetry features, and energy weight features as the basis for classification. Meteorological clutter has randomness and expansibility, and its distance dimension waveform entropy and Doppler dimension waveform entropy are both large, and the energy distribution does not show symmetry, and the energy is not as concentrated as that of a real target. Therefore, image features such as distance dimension waveform entropy features, Doppler dimension waveform entropy features, image symmetry features, and energy weight features can well characterize whether the detection target is meteorological clutter. When the support vector machine classifier determines that the classification result of the detection target is meteorological clutter, the detection target is immediately eliminated, thereby ensuring that while the drone target is effectively detected, the false alarm phenomenon caused by meteorological clutter is eliminated.

[0010] In some optional embodiments, the coordinates of the training sample on the range-Doppler two-dimensional plane are denoted as (x i ,y i ), i indicates that the training sample is the i-th training sample in the training sample set; taking the coordinates of the training sample as the center, on the range-Doppler two-dimensional plane, a two-dimensional matrix is ​​cut out according to a preset size, including: taking (x i ,y i ) is the center, and on the range-Doppler two-dimensional plane, a two-dimensional matrix S is cut out according to the size of the row and column respectively 2M+1 and 2N+1; where the starting point of the X axis is x i -N, the cutoff point of the X axis is x i +N, the starting point of the Y axis is y i -M, the cutoff point of the Y axis is y i +M, M and N are all integers greater than 0.

[0011] In some optional embodiments, the distance dimension waveform entropy feature and the Doppler dimension waveform entropy feature are extracted by the following steps:

[0012] Find the maximum amplitude of each column of S and get a one-dimensional vector D, D = [d0, d1…, d 2M ];

[0013] Find the maximum amplitude of each row of S and get a one-dimensional vector R, R = [r0, r1…, r 2M ];

[0014] The norm of each element in the one-dimensional vector D is normalized, and the distance dimension waveform entropy feature E is calculated based on the waveform entropy calculation formula and the value of each element after norm normalization. D ;

[0015] The norm of each element in the one-dimensional vector R is normalized, and the Doppler waveform entropy feature E is calculated based on the waveform entropy calculation formula and the value of each element after norm normalization. R ;

[0016] The waveform entropy calculation formula is:

[0017]

[0018] in, represents the value of the kth element in the one-dimensional vector D after norm normalization, Represents the value of the kth element in the one-dimensional vector R after norm normalization.

[0019] In some optional embodiments, the image symmetry feature is extracted by the following steps:

[0020] Flip S horizontally to get the two-dimensional matrix S hc ;

[0021] Flip S vertically to get the two-dimensional matrix S vc ;

[0022] Based on S, S hc and S vc The values ​​of each point in the image are calculated to obtain the image symmetry characteristics;

[0023] The formula for calculating the image symmetry feature is expressed as:

[0024]

[0025] Among them, S(m,n) represents the value of the midpoint (m,n) of S, S hc (m,n) represents S hc The value of the midpoint (m,n), S vc (m,n) represents s vc The value of the midpoint (m,n), T diff Represents the calculated image symmetry features.

[0026] In some optional embodiments, the energy density feature is extracted by the following steps:

[0027] Calculate the sum of the values ​​of each point in S, and calculate the energy density characteristic based on the value of the center point of S and the sum;

[0028] The formula for calculating the energy density characteristic is expressed as:

[0029]

[0030] Among them, S(M+1,N+1) represents the value of the center point of S, and CAR represents the calculated energy weight characteristic.

[0031] In some optional embodiments, the support vector machine classifier outputs the classification result of the detection target through the following formula:

[0032]

[0033] where sgn(·) represents the sign function, σ 2 represents the Gaussian kernel function, g, α and b are the model parameters of the support vector machine classifier, x represents the image feature corresponding to the detection target, f(x) = 1 means that the classification result of the detection target output by the support vector machine classifier is a real target, f(x) = -1, f(x) = 0 means that the classification result of the detection target output by the support vector machine classifier is meteorological clutter.

[0034] In some optional embodiments, the removing of detection targets is specifically: in the final target report, removing detection targets whose class results are meteorological clutter. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] One or more embodiments are exemplarily described by the pictures in the corresponding drawings, and these exemplary descriptions do not constitute limitations on the embodiments.

[0036] Figure 1 is a flow chart of a method for suppressing meteorological clutter based on range-Doppler two-dimensional features provided in one embodiment of the present application;

[0037] Figure 2 is a flow chart for classifying and distinguishing detection targets provided in one embodiment of the present application;

[0038] Figure 3 is a range-Doppler plane diagram of weather clutter and UAV targets provided in one embodiment of the present application;

[0039] Figure 4 In one embodiment of the present application, a schematic diagram of detection results of multiple frames before and after clutter suppression is provided;

[0040] Figure 5 is a structural schematic diagram of a meteorological clutter suppression system based on range-Doppler two-dimensional characteristics provided in another embodiment of the present application;

[0041] Figure 6It is a structural schematic diagram of an electronic device provided by another embodiment of the present application. DETAILED DESCRIPTION

[0042] To make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the embodiments of the present application will be described in detail below in conjunction with the accompanying drawings. However, it will be appreciated by those skilled in the art that in the present application, many technical details are proposed in order to enable the reader to better understand the present application. However, even without these technical details and various changes and modifications based on the following embodiments, the technical scheme claimed in the present application can also be implemented. The division of the following embodiments is for the convenience of description, and the specific implementation of the present application should not be construed as any limitation, and the various embodiments can be combined and referenced with each other under the premise of no contradiction.

[0043] An embodiment of the present application proposes a method for suppressing meteorological clutter based on range-Doppler two-dimensional features, which is applied to an electronic device, wherein the electronic device may be a terminal or a server. In this embodiment and the following embodiments, the electronic device is described by taking a server as an example. The implementation details of the method for suppressing meteorological clutter based on range-Doppler two-dimensional features proposed in this embodiment are specifically described below. The following content is only the implementation details provided for ease of understanding and is not necessary for implementing this solution.

[0044] The specific process of the meteorological clutter suppression method based on range-Doppler two-dimensional characteristics proposed in this embodiment can be as follows: Figure 1 As shown, including:

[0045] Step 101, obtain the coordinates of the training sample on the range-Doppler two-dimensional plane, and cut out a two-dimensional matrix according to a preset size on the range-Doppler two-dimensional plane with the coordinates of the training sample as the center.

[0046] In the specific implementation, the server first obtains the training sample set, test sample set and validation sample set of the support vector machine classifier. For each training sample in the training set, the server needs to obtain the coordinates of the training sample on the range-Doppler two-dimensional plane, and take the coordinates of the training sample as the center and cut out a two-dimensional matrix according to a preset size on the range-Doppler two-dimensional plane.

[0047] In one example, the server records the coordinates of the training sample on the range-Doppler two-dimensional plane as (x i ,y i ), i represents the i-th training sample in the training sample set. The server uses (x i ,y i) is the center, and on the range-Doppler two-dimensional plane, a two-dimensional matrix S is cut out according to the size of the row and column respectively 2M+1 and 2N+1. The starting point of the X axis is x i -N, the cutoff point of the X axis is x i +N, the starting point of the Y axis is y i -M, the cutoff point of the Y axis is y i +M, M and N are all integers greater than 0.

[0048] Step 102: extracting image features corresponding to the training samples from the two-dimensional matrix corresponding to the training samples, wherein the image features include distance dimension waveform entropy features, Doppler dimension waveform entropy features, image symmetry features, and energy density features.

[0049] In a specific implementation, after intercepting the two-dimensional matrix corresponding to the training sample, the server can extract the image features corresponding to the training sample from the two-dimensional matrix corresponding to the training sample, wherein the image features include distance dimension waveform entropy features, Doppler dimension waveform entropy features, image symmetry features and energy density features.

[0050] In one example, when extracting the range dimension waveform entropy feature and the Doppler dimension waveform entropy feature, the server needs to find the maximum amplitude of each column of the two-dimensional matrix S to obtain a one-dimensional vector D, D = [d0, d1…, d 2N ], and find the maximum amplitude of each row of the two-dimensional matrix S to obtain a one-dimensional vector R, R = [r0, r1…, r 2M ]. The one-dimensional vector D is the distance dimension vector, and the one-dimensional vector R is the Doppler dimension vector.

[0051] For the one-dimensional vector D, the server normalizes the norm of each element in the one-dimensional vector D, and calculates the distance dimension waveform entropy feature E based on the waveform entropy calculation formula and the value of each element after norm normalization. D .

[0052] For the one-dimensional vector R, the server normalizes the norm of each element in the one-dimensional vector R, and calculates the Doppler waveform entropy feature E based on the waveform entropy calculation formula and the value of each element after norm normalization. R .

[0053] The waveform entropy calculation formula is:

[0054]

[0055] in, represents the value of the kth element in the one-dimensional vector D after norm normalization, Represents the value of the kth element in the one-dimensional vector R after norm normalization.

[0056] In one example, the echo of a real target shows central symmetry on the range-Doppler plane, which is manifested in that the energy distribution of the upper and lower halves of the two-dimensional matrix is ​​similar, and the energy distribution of the left and right halves is similar. Meteorological clutter is random and extensible, and its energy distribution does not show such characteristics. Therefore, this type of feature can distinguish meteorological clutter from drone targets. When extracting the image symmetry feature, the server needs to flip the two-dimensional matrix S horizontally to obtain the two-dimensional matrix S hc , and vertically flip the two-dimensional matrix S to obtain the two-dimensional matrix S vc . Then based on S, S hc and S vc The value (energy) of each point in is used to calculate the image symmetry feature. The smaller the image symmetry feature, the stronger the central symmetry of the energy distribution of the two-dimensional matrix S.

[0057] The formula for calculating the image symmetry feature is expressed as:

[0058]

[0059] Among them, R(m,n) represents the value of the midpoint (m,n) of S, S hc (m,n) represents S hc The value of the midpoint (m,n), S vc (m,n) represents S vc The value of the midpoint (m,n), T diff Represents the calculated image symmetry features.

[0060] In one example, the center point position of the two-dimensional matrix S is the strongest value of the target. When the server extracts the energy weight feature, it needs to calculate the sum of the values ​​of each point in the two-dimensional matrix S, and calculate the energy weight feature based on the value of the center point of the two-dimensional matrix S and the sum. The larger the value of the energy weight feature, the more concentrated the energy.

[0061] The formula for calculating the energy density characteristic is expressed as:

[0062]

[0063] Among them, S(M+1,N+1) represents the value of the center point of S, and CAR represents the calculated energy weight characteristic.

[0064] Step 103: input the image features corresponding to the training samples into a support vector machine classifier, and iteratively train the support vector machine classifier based on the classification results of the training samples and the labels of the training samples output by the support vector machine classifier until convergence.

[0065] In a specific implementation, after extracting the image features corresponding to each training sample in the training sample set, the server can input the image features corresponding to the training samples into a support vector machine classifier, and based on the classification results of the training samples and the labels of the training samples output by the support vector machine classifier, iteratively train the support vector machine classifier until convergence to obtain the model parameters of the support vector machine classifier.

[0066] In an example, the server may also use the test sample set to perform a model performance test on the trained support vector machine classifier, and use the verification sample to verify relevant indicators of the trained support vector machine classifier.

[0067] Step 104: input the image features corresponding to the detection target into a support vector machine classifier, and obtain the classification result of the detection target output by the support vector machine classifier.

[0068] In the specific implementation, after completing the construction, training, testing and verification of the support vector machine classifier, we can enter the model use stage, that is, classify and distinguish the detection target. The specific process of classifying and distinguishing the detection target can be as follows Figure 2 As shown, the server needs to obtain the coordinates of the detection target on the range-Doppler two-dimensional plane, and take the coordinates of the detection target as the center, cut out a two-dimensional matrix according to the preset size on the range-Doppler two-dimensional plane, and then extract the image features corresponding to the detection target from the two-dimensional matrix corresponding to the detection target, including the range dimension waveform entropy feature, the Doppler dimension waveform entropy feature, the image symmetry feature and the energy density feature. After the extraction is completed, the server inputs the image features corresponding to the detection target into the support vector machine classifier to obtain the classification result of the detection target output by the support vector machine classifier.

[0069] In one example, the range-Doppler plane of weather clutter and UAV targets can be as follows: Figure 3 As shown, from Figure 3 The randomness and expansibility of meteorological clutter can be clearly seen in the figure.

[0070] In one example, the support vector machine classifier outputs the classification result of the detection target through the following formula:

[0071]

[0072] where sgn(·) represents the sign function, σ 2represents the Gaussian kernel function, g, α and b are the model parameters of the support vector machine classifier, x represents the image feature corresponding to the detection target, f(x) = 1 means that the classification result of the detection target output by the support vector machine classifier is a real target, f(x) = -1, f(x) = 0 means that the classification result of the detection target output by the support vector machine classifier is meteorological clutter.

[0073] Step 105: If the classification result of the detection target output by the support vector machine classifier is meteorological clutter, the detection target is eliminated.

[0074] In the specific implementation, if the classification result of the detection target output by the support vector machine classifier is meteorological clutter, the server will immediately remove the detection target, that is, in the final target report, the detection target whose classification result is meteorological clutter will be removed. If the classification result of the detection target output by the support vector machine classifier is a real target, the server will save the detection target and present it in the final target report.

[0075] In one example, Figure 4 The detection results of multiple frames before and after clutter suppression are shown. It can be seen that clutter suppression effectively eliminates the false alarm phenomenon caused by meteorological clutter.

[0076] In this embodiment, a support vector machine classifier is constructed and trained to classify the detection target, and image features such as distance dimension waveform entropy feature, Doppler dimension waveform entropy feature, image symmetry feature and energy weight feature are used as the basis for classification. Meteorological clutter has randomness and expansibility, and its distance dimension waveform entropy and Doppler dimension waveform entropy are both large, and the energy distribution will not show symmetry, and the energy will not be as concentrated as the real target. Therefore, image features such as distance dimension waveform entropy feature, Doppler dimension waveform entropy feature, image symmetry feature and energy weight feature can well characterize whether the detection target is meteorological clutter or a real target. When the support vector machine classifier determines that the classification result of the detection target is meteorological clutter, the detection target is eliminated, thereby ensuring that while the drone target is effectively detected, the false alarm phenomenon caused by meteorological clutter is eliminated.

[0077] The step division of the above methods is only for clear description. When implemented, they can be combined into one step or some steps can be split and decomposed into multiple steps. As long as they include the same logical relationship, they are all within the scope of protection of this application; adding insignificant modifications to the algorithm or process or introducing insignificant designs without changing the core design of the algorithm and process are all within the scope of protection of this application.

[0078] Another embodiment of the present application proposes a meteorological clutter suppression system based on range-Doppler two-dimensional features. The implementation details of the meteorological clutter suppression system based on range-Doppler two-dimensional features proposed in this embodiment are specifically described below. The following content is only for the convenience of understanding the implementation details provided, and is not necessary for the implementation of this solution. The structural schematic diagram of the meteorological clutter suppression system based on range-Doppler two-dimensional features proposed in this embodiment is as follows: Figure 5 As shown, including:

[0079] The positioning module 201 is used to obtain the coordinates of the training sample on the range-Doppler two-dimensional plane, and to cut out a two-dimensional matrix according to a preset size on the range-Doppler two-dimensional plane with the coordinates of the training sample as the center.

[0080] The feature extraction module 202 is used to extract image features corresponding to the training samples from the two-dimensional matrix corresponding to the training samples, wherein the image features include distance dimension waveform entropy features, Doppler dimension waveform entropy features, image symmetry features and energy density features.

[0081] The training module 203 is used to input the image features corresponding to the training samples into the support vector machine classifier, and iteratively train the support vector machine classifier until convergence based on the classification results of the training samples and the labels of the training samples output by the support vector machine classifier.

[0082] Module 204 is used to input the image features corresponding to the detection target into the support vector machine classifier, obtain the classification result of the detection target output by the support vector machine classifier, and eliminate the detection target when the classification result of the detection target output by the support vector machine classifier is meteorological clutter.

[0083] It is worth mentioning that all modules involved in this embodiment are logic modules. In practical applications, a logic unit can be a physical unit, a part of a physical unit, or a combination of multiple physical units. In addition, in order to highlight the innovative part of this application, this embodiment does not introduce units that are not closely related to solving the technical problems proposed by this application, but this does not mean that there are no other units in this embodiment.

[0084] It is not difficult to find that this embodiment is a system embodiment corresponding to the above method embodiment, and this embodiment can be implemented in conjunction with the above method embodiment. The relevant technical details and technical effects mentioned in the above embodiments are still valid in this embodiment, and in order to reduce repetition, they are not repeated here. Accordingly, the relevant technical details mentioned in this embodiment can also be applied in the above embodiments.

[0085] Another embodiment of the present application provides an electronic device, whose specific structure can be as follows: Figure 6 As shown, it includes: at least one processor 301; and a memory 302 that is communicatively connected to the at least one processor 301; wherein the memory 302 stores instructions that can be executed by the at least one processor 301, and the instructions are executed by the at least one processor 301 so that the at least one processor 301 can execute a meteorological clutter suppression method based on range-Doppler two-dimensional features described in the above-mentioned method embodiments.

[0086] Among them, the memory and the processor are connected in a bus manner, and the bus may include any number of interconnected buses and bridges, and the bus connects various circuits of one or more processors and memories together. The bus can also connect various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and will not be further described in this article. The bus interface provides an interface between the bus and the transceiver. The transceiver can be one element or multiple elements, such as multiple receivers and transmitters, providing a unit for communicating with various other devices on a transmission medium. The data processed by the processor is transmitted on a wireless medium through an antenna, and further, the antenna also receives data and transmits the data to the processor.

[0087] The processor is responsible for managing the bus and general processing, and can also provide various functions, including timing, peripheral interfaces, voltage regulation, power management, and other control functions. Memory can be used to store data used by the processor when performing operations.

[0088] Another embodiment of the present application relates to a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it can implement a meteorological clutter suppression method based on range-Doppler two-dimensional characteristics described in the above method embodiments.

[0089] That is, those skilled in the art can understand that all or part of the steps in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a program, and the program is stored in a storage medium, including a number of instructions to enable a device (which can be a single-chip microcomputer, chip, etc.) or a processor to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as: ROM), random access memory (Random Access Memory, referred to as: RAM), disk or optical disk and other media that can store program codes.

[0090] Those skilled in the art will appreciate that the above embodiments are specific embodiments for implementing the present application, and in actual applications, various changes may be made thereto in form and detail without departing from the spirit and scope of the present application.

Claims

1. A method for suppressing meteorological clutter based on range-Doppler two-dimensional characteristics, characterized in that: include: Obtain the coordinates of the training sample on the range-Doppler two-dimensional plane, and cut out a two-dimensional matrix according to a preset size on the range-Doppler two-dimensional plane with the coordinates of the training sample as the center; Extracting image features corresponding to the training samples from the two-dimensional matrix corresponding to the training samples; wherein the image features include distance dimension waveform entropy features, Doppler dimension waveform entropy features, image symmetry features and energy density features; The image features corresponding to the training samples are input into the support vector machine classifier, and based on the classification results of the training samples and the labels of the training samples output by the support vector machine classifier, the support vector machine classifier is iteratively trained until convergence; Input the image features corresponding to the detection target into the support vector machine classifier, and obtain the classification result of the detection target output by the support vector machine classifier; If the classification result of the detection target output by the support vector machine classifier is meteorological clutter, the detection target is eliminated.

2. The method for suppressing meteorological clutter based on range-Doppler two-dimensional characteristics according to claim 1, characterized in that: The coordinates of the training sample on the range-Doppler two-dimensional plane are (x i ,y i ), i means that the training sample is the i-th training sample in the training sample set; The method takes the coordinates of the training sample as the center and cuts out a two-dimensional matrix according to a preset size on the range-Doppler two-dimensional plane, including: With (x i ,y i ) is the center, and on the range-Doppler two-dimensional plane, a two-dimensional matrix S is cut out according to the size of the row and column respectively 2M+1 and 2N+1; where the starting point of the X axis is x i -N, the cutoff point of the X axis is x i +N, the starting point of the Y axis is y i -M, the cutoff point of the Y axis is y i +M, M and N are all integers greater than 0.

3. The method for suppressing meteorological clutter based on range-Doppler two-dimensional characteristics according to claim 2, characterized in that: The distance dimension waveform entropy feature and the Doppler dimension waveform entropy feature are extracted by the following steps: Find the maximum amplitude of each column of S and get a one-dimensional vector D, D = [d0, d1…, d 2N ]; Find the maximum amplitude of each row of S and get a one-dimensional vector R, R = [r0, r1…, r 2M ]; The norm of each element in the one-dimensional vector D is normalized, and the distance dimension waveform entropy feature E is calculated based on the waveform entropy calculation formula and the value of each element after norm normalization. D ; The norm of each element in the one-dimensional vector R is normalized, and the Doppler waveform entropy feature E is calculated based on the waveform entropy calculation formula and the value of each element after norm normalization. R ; The waveform entropy calculation formula is: in, represents the value of the kth element in the one-dimensional vector D after norm normalization, Represents the value of the kth element in the one-dimensional vector R after norm normalization.

4. The method for suppressing meteorological clutter based on range-Doppler two-dimensional characteristics according to claim 2, characterized in that: The image symmetry feature is extracted by the following steps: Flip S horizontally to get the two-dimensional matrix S hc ; Flip S vertically to get the two-dimensional matrix S vc ; Based on S, S hc and S vc The values ​​of each point in the image are calculated to obtain the image symmetry characteristics; The formula for calculating the image symmetry feature is expressed as: Among them, S(m,n) represents the value of the midpoint (m,n) of S, S hc (m,n) represents S hc The value of the midpoint (m,n), S vc (m,n) represents S vc The value of the midpoint (m,n), T diff Represents the calculated image symmetry features.

5. The method for suppressing meteorological clutter based on range-Doppler two-dimensional characteristics according to claim 2, characterized in that: The energy density feature is extracted by the following steps: Calculate the sum of the values ​​of each point in S, and calculate the energy density characteristic based on the value of the center point of S and the sum; The formula for calculating the energy density characteristic is expressed as: Among them, S(M+1,N+1) represents the value of the center point of S, and CAR represents the calculated energy weight characteristic.

6. A method for suppressing meteorological clutter based on range-Doppler two-dimensional features according to any one of claims 1 to 5, characterized in that: The support vector machine classifier outputs the classification result of the detection target through the following formula: where sgn(·) represents the sign function, σ 2 represents the Gaussian kernel function, g, α and b are the model parameters of the support vector machine classifier, x represents the image feature corresponding to the detection target, f(x) = 1 means that the classification result of the detection target output by the support vector machine classifier is a real target, f(x) = -1, f(x) = 0 means that the classification result of the detection target output by the support vector machine classifier is meteorological clutter.

7. A method for suppressing meteorological clutter based on range-Doppler two-dimensional features according to any one of claims 1 to 5, characterized in that: The elimination of detection targets specifically includes: in the final target report, elimination of detection targets whose class results are meteorological clutter.

8. A meteorological clutter suppression system based on range-Doppler two-dimensional characteristics, characterized in that: include: A positioning module is used to obtain the coordinates of the training sample on the range-Doppler two-dimensional plane, and to cut out a two-dimensional matrix according to a preset size on the range-Doppler two-dimensional plane with the coordinates of the training sample as the center; A feature extraction module, used to extract image features corresponding to the training samples from the two-dimensional matrix corresponding to the training samples, wherein the image features include distance dimension waveform entropy features, Doppler dimension waveform entropy features, image symmetry features and energy density features; A training module, used for inputting the image features corresponding to the training samples into the support vector machine classifier, and iteratively training the support vector machine classifier until convergence based on the classification results of the training samples and the labels of the training samples output by the support vector machine classifier; A module is used to input the image features corresponding to the detection target into a support vector machine classifier, obtain the classification result of the detection target output by the support vector machine classifier, and eliminate the detection target when the classification result of the detection target output by the support vector machine classifier is meteorological clutter.

9. An electronic device, characterized in that: include: at least one processor; as well as, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the meteorological clutter suppression method based on range-Doppler two-dimensional features as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the meteorological clutter suppression method based on range-Doppler two-dimensional features as claimed in any one of claims 1 to 7 is implemented.

Images