Spectrum broadening vegetation clutter suppression method based on feature recognition
By extracting features of vegetation clutter from the radar system and using a support vector machine classifier, the false alarm problem caused by the overlap of the spectrum of spectral broadened vegetation clutter and the target spectrum was solved, and effective detection of slow-moving targets was achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- CNGC INST NO 206 OF CHINA ARMS IND GRP
- Filing Date
- 2025-10-22
- Publication Date
- 2026-07-07
AI Technical Summary
When radar detects ground and low-altitude slow-moving targets, the broadened vegetation clutter overlaps with the target spectrum, resulting in too many false alarms, which existing methods cannot effectively distinguish.
By extracting the features of the target on the range-Doppler plane, a support vector machine classifier is used to determine whether the target is vegetation clutter and to eliminate false alarms.
It effectively suppresses spectral broadening vegetation clutter, reduces false alarms, and ensures effective detection of ground and low-altitude slow-moving targets.
Smart Images
Figure CN121703774B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of target recognition technology, specifically to a spectral broadening vegetation clutter suppression method based on feature recognition, applicable to radar detection of slow-moving targets on the ground and at low altitudes, for identifying and eliminating spectral broadening vegetation clutter in the scene. Background Technology
[0002] Radar offers advantages such as all-weather, all-day operation for detecting ground and low-altitude targets, along with long detection ranges and the ability to acquire multi-dimensional information about the targets. However, in windy conditions, the swaying vegetation in the scene causes the radar echo spectrum to broaden and exhibit time-varying characteristics. The broadened vegetation clutter spectrum overlaps significantly with the spectrum of small, slow-moving ground and low-altitude targets, such as people and drones. Simply using constant false alarm rate (CFAR) detection is insufficient to distinguish between targets and clutter, necessitating targeted clutter suppression.
[0003] Traditional multidimensional clutter mapping methods, based on the time-domain stationary nature of clutter, divide the space scanned by the antenna into several clutter cells, and then process and store the clutter information according to the divided cells. This approach can record and update information on fixed ground clutter in the detected scene in real time, effectively eliminating fixed ground clutter by comparing the intensity of the echo within the current clutter cell with the historical clutter intensity recorded in the memory. However, the spectral broadening of vegetation clutter exhibits strong time-varying characteristics, making the aforementioned clutter suppression methods less than ideal.
[0004] Analysis of the energy distribution characteristics of vegetation clutter and target echoes on the range-Doppler plane reveals that the spectrum of vegetation clutter exhibits significant symmetry relative to the zero channel. In contrast, the principal component of a real target, regardless of its proximity to or movement away from the radar, only appears on one side of the zero channel in the frequency domain. The echoes on the range-Doppler plane exhibit an approximately Gaussian shape, and their energy accounts for a larger proportion compared to clutter regions at the same range. Therefore, from a feature recognition perspective, vegetation clutter suppression is transformed into a binary classification problem of clutter and targets. By extracting multidimensional features, vegetation clutter and targets can be effectively distinguished, thus achieving clutter suppression.
[0005] It should be noted that the information disclosed in the background section above is only used to enhance the understanding of the background of the present invention, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention
[0006] This invention provides a feature-based method for suppressing spectral broadening vegetation clutter, which addresses the problem of excessive false alarms caused by ground-spectrum broadening vegetation clutter interfering with the effective detection of ground and low-altitude slow-moving targets when radar is detecting them.
[0007] Other features and advantages of the invention will become apparent from the following detailed description, or may be learned in part by practice of the invention.
[0008] According to a first aspect of the present invention, a method for suppressing spectral broadening vegetation clutter based on feature recognition is provided, the method comprising:
[0009] Obtain the target's coordinates on the range-Doppler plane and extract the one-dimensional spectral vector of the target's range cell;
[0010] Determine whether the target point is a peak point in the spectrum. If it is a peak point, extract the proportion of energy in the clutter support region on both sides of the zero channel and the proportion of the target point energy in the support region energy from the one-dimensional spectrum vector as features.
[0011] The features are input into a support vector machine classifier, and the support vector machine classifier determines whether the target is a slow-moving target or spectrally broadened vegetation clutter.
[0012] If it is not a peak point, it is directly identified as vegetation clutter; if the target is vegetation clutter, it is removed in subsequent target reports.
[0013] In some exemplary embodiments, obtaining the target's coordinates on the range-Doppler plane and extracting the one-dimensional spectral vector of the target's range cell specifically involves:
[0014] The coordinates of the target in the range-Doppler plane are obtained as follows: ,in, Represents the first of the matrix List, Represents the first of the matrix OK;
[0015] Extracting the target's distance cell from the range-Doppler 2D matrix. One-dimensional spectrum vector data of the column , N Indicates the length of the data.
[0016] In some exemplary embodiments, determining whether the target point is a peak point in the spectrum specifically involves:
[0017] If the amplitude of the target point is greater than the amplitude of the adjacent point to its left and greater than the amplitude of the adjacent point to its right, then the target point is determined to be a peak point.
[0018] In some exemplary embodiments, the proportion of energy extracted from the clutter support regions on both sides of the zero channel is specifically as follows:
[0019] The one-dimensional spectrum vector is shifted, and the data of the zero channel is moved to the center of the spectrum vector.
[0020]
[0021] Supporting regions for calculating the spectrum:
[0022] Based on the requirements for radar detection of low-speed targets, a point speed threshold is set. vel_th According to speed resolution dvel Calculate the support zone of low-speed targets on both sides of the zero channel, where the starting point of the support zone on the left side of the zero channel is... The cutoff point is located at The starting point of the support area on the right side of the zero channel is... The cutoff point is located at ;
[0023] Calculate the sum of the amplitudes of all points in the left support zone:
[0024]
[0025] Calculate the sum of the amplitudes of all points in the right support zone:
[0026]
[0027] Calculate the energy ratio of the two support regions:
[0028] .
[0029] In some exemplary embodiments, the proportion of the extracted target point energy to the support region energy is specifically as follows:
[0030] The position of the target point in the relocated spectrum vector is k Calculate the ratio of the amplitude at that point to the sum of the amplitudes at all points in the support zone:
[0031]
[0032] The larger this ratio, the more concentrated the energy.
[0033] In some exemplary embodiments, the step of inputting features into a support vector machine classifier to determine whether the detected target is a slow-moving target or spectrally broadened vegetation clutter specifically involves:
[0034] The feature vector formed by the extracted proportion of energy in the two support regions and the proportion of energy of the target point in the support region, along with the model parameters obtained during the training phase, are substituted into the following formula to calculate the classification result.
[0035]
[0036] in, Represents a symbolic function. , This represents the Gaussian kernel parameters, which are given during the training phase; This represents the feature vector formed by the two types of features extracted from the sample to be classified; parameters These are the model parameters, obtained during the training phase; where, m This represents the number of feature vectors selected from all training samples input into the support vector machine during the training phase. Indicates the selected first i 1 eigenvector Indicates the first i The weight coefficients of each eigenvector. Indicates the bias term; the output When the value is 1, the detected target point is judged as a slow-moving target; otherwise, the target point is judged as vegetation clutter.
[0037] According to a second aspect of the present invention, a spectral broadening vegetation clutter suppression system based on feature recognition is provided, comprising:
[0038] The spectrum extraction module is used to obtain the coordinates of the target on the range-Doppler plane and extract the one-dimensional spectrum vector of the range cell where the target is located;
[0039] The feature extraction module is used to determine whether the target point is a peak point in the spectrum. If it is a peak point, the proportion of energy of clutter support regions on both sides of the zero channel and the proportion of energy of the target point to the energy of the support region are extracted from the one-dimensional spectrum vector as features.
[0040] The classification module is used to input features into the support vector machine classifier to determine whether the detected target is a slow-moving target or spectrally broadened vegetation clutter.
[0041] If the target is not a peak point, it is directly identified as vegetation clutter; if the target is vegetation clutter, it is removed from the subsequent target report.
[0042] According to a third aspect of the present invention, a storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the feature recognition-based spectral broadening vegetation clutter suppression method described in the first aspect above.
[0043] According to a fourth aspect of the present invention, a computer program product is provided, on which a computer program is stored, wherein when the computer program is executed by a processor, it implements the feature recognition-based spectral broadening vegetation clutter suppression method described in the first aspect above.
[0044] According to a fifth aspect of the present invention, an electronic device is provided, comprising:
[0045] Processor; and
[0046] Memory for storing the executable instructions of the processor;
[0047] The processor is configured to implement the feature recognition-based spectral broadening vegetation clutter suppression method described in the first aspect above by executing the executable instructions.
[0048] The feature-based spectral broadening vegetation clutter suppression method provided in this invention solves the problem of excessive false alarms caused by ground-spectrum broadening vegetation clutter interfering with effective target detection when radar detects slow-moving targets at ground and low altitudes. First, the target's coordinates on the range-Doppler plane are obtained. A one-dimensional spectral vector of the target's range cell is extracted. Then, it is determined whether the target point is a peak point in the spectrum. If it is a peak point, features such as the proportion of energy in the clutter support zone on both sides of the zero channel and the proportion of the target point's energy to the support zone energy are extracted from the vector. These features are input into a support vector machine classifier to determine whether the detected target is a slow-moving target or spectral broadening vegetation clutter. If it is not a peak point, it is directly identified as vegetation clutter. If the target is vegetation clutter, it is removed from subsequent target reports.
[0049] This invention effectively eliminates false alarms caused by vegetation clutter that broadens the ground spectrum, ensuring effective detection of ground and low-altitude slow-moving targets.
[0050] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit the invention. Attached Figure Description
[0051] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention. It is obvious that the drawings described below are merely some embodiments of the invention, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort.
[0052] Figure 1 This is a flowchart of the spectral broadening vegetation clutter suppression method based on feature recognition of the present invention;
[0053] Figure 2 For the range-Doppler two-dimensional plane of vegetation clutter and slow target: (a) Spectrum of vegetation clutter; (b) Spectrum of slow target.
[0054] Figure 3 The diagram illustrates the composition of an electronic device according to an exemplary embodiment of the present invention. Detailed Implementation
[0055] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, they are provided so that the invention will be more comprehensive and complete, and will fully convey the concept of the exemplary embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
[0056] Furthermore, the accompanying drawings are merely illustrative of the invention and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted. Some block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.
[0057] To address the shortcomings and deficiencies of existing technologies, this example implementation provides a feature-based method for suppressing spectral broadening vegetation clutter. By extracting features from the spectrum of the distance cell containing the point that has passed the detection threshold on the range-Doppler two-dimensional plane, a support vector machine classifier is used to determine whether the target is a false alarm from vegetation clutter, thereby enabling the identification and removal of spectral broadening vegetation clutter in the scene.
[0058] refer to Figure 1 As shown, the specific steps may include:
[0059] Step S11: Obtain the coordinates of the target on the range-Doppler plane and extract the one-dimensional spectrum vector of the range cell where the target is located;
[0060] Step S12: Determine whether the target point is a peak point in the spectrum. If it is a peak point, extract the proportion of energy in the clutter support region on both sides of the zero channel and the proportion of energy in the support region of the target point from the one-dimensional spectrum vector as features.
[0061] Step S13: Input the features into the support vector machine classifier to determine whether the detected target is a slow-moving target or spectrally broadened vegetation clutter;
[0062] In step S14, if it is not a peak point, it is directly identified as vegetation clutter; if the target is vegetation clutter, it is removed in the subsequent target report.
[0063] The steps in this exemplary embodiment will now be described in more detail with reference to the accompanying drawings and embodiments.
[0064] In step S11, the coordinates of the target on the range-Doppler plane are obtained, and the one-dimensional spectrum vector of the range cell where the target is located is extracted.
[0065] Specifically, it includes the following:
[0066] Assuming a two-dimensional range-Doppler matrix containing the target has been obtained, after constant false alarm rate (CFAR) detection and point aggregation processing, the target's coordinates are: , Represents the first of the matrix List, Represents the first of the matrix OK.
[0067] Extracting the target's distance cell from the range-Doppler 2D matrix. One-dimensional spectrum vector data of the column , N Indicates the length of the data;
[0068] In step S12, it is determined whether the target point is a peak point in the spectrum. If it is a peak point, the proportion of energy in the clutter support region on both sides of the zero channel and the proportion of energy of the target point in the support region are extracted from the one-dimensional spectrum vector as features.
[0069] Specifically, it includes the following:
[0070] The spectrum is shifted according to the following formula;
[0071]
[0072] By moving the data from the zero channel, the data was moved to the center of the spectrum vector.
[0073] Supporting regions for calculating the spectrum:
[0074] Based on the requirements for radar detection of low-speed targets, a point speed threshold is set. vel_th According to speed resolution dvel Calculate the clutter support region range on both sides of the zero channel. The starting point of the support region on the left side of the zero channel is [location to be filled in]. The cutoff point is located at The starting point of the support area on the right side of the zero channel is... The cutoff point is located at .
[0075] Determine if the target point is a peak point
[0076] If the amplitude of the target point is greater than the amplitude of the point adjacent to the left of the target point... And it is greater than the amplitude of the adjacent point on the right. If so, the target point is determined to be a peak point.
[0077] Calculate the proportion of energy in the clutter support regions on both sides of the zero channel, including:
[0078] The sum of the amplitudes of all points in the left support zone:
[0079]
[0080] The sum of the amplitudes of all points in the right support zone:
[0081]
[0082] Calculate the energy ratio of the two support regions:
[0083]
[0084] Calculate the proportion of the target point energy to the support area energy.
[0085] The position of the target point in the relocated spectrum vector is k Calculate the ratio of the amplitude at that point to the sum of the amplitudes at all points in the support zone:
[0086]
[0087] The larger this ratio, the more concentrated the energy.
[0088] In step S13, the features are input into the support vector machine classifier to determine whether the detected target is a slow-moving target or spectrally broadened vegetation clutter.
[0089] Classification of spectral broadened vegetation clutter and slow-moving targets using a support vector machine classifier;
[0090] During the training phase, two types of features are extracted from all training samples as described above, and the features are fed into the support vector machine classifier for training to obtain the relevant parameters of the classification model.
[0091] During the testing phase, the samples to be classified are extracted with two types of features as described above. The extracted features and the model parameters obtained during the training phase are substituted into the following formula to calculate the classification result.
[0092]
[0093] in, Represents a symbolic function. , This represents the Gaussian kernel parameters, which are given during the training phase; This represents the feature vector formed by the two types of features extracted from the sample to be classified; parameters These are the model parameters, obtained during the training phase; where, m This represents the number of feature vectors selected from all training samples input into the support vector machine during the training phase. Indicates the selected first i 1 eigenvector Indicates the first i The weight coefficients of each eigenvector. This represents the bias term. The output... When the value is 1, the detected target point is judged as a slow-moving target; otherwise, the target point is judged as vegetation clutter.
[0094] In step S14, if it is not a peak point, it is directly identified as vegetation clutter; if the target is vegetation clutter, it is removed in the subsequent target report.
[0095] This invention provides a feature-based algorithm for suppressing spectral broadening vegetation clutter, which solves the problem of excessive false alarms caused by ground-spectrum broadened vegetation clutter interfering with effective target detection when radar detects slow-moving targets at ground and low altitudes. The algorithm first obtains the target's coordinates on the range-Doppler plane, extracts the one-dimensional spectral vector of the target's range cell, and then determines whether the target point is a peak point in the spectrum. If it is a peak point, features such as the proportion of energy in the clutter support zone on both sides of the zero channel and the proportion of the target point's energy in the support zone are extracted from the vector. These features are then input into a support vector machine classifier to determine whether the detected target is a slow-moving target or spectral broadened vegetation clutter. If it is not a peak point, it is directly identified as vegetation clutter. If the target is vegetation clutter, it is removed from subsequent target reports.
[0096] Figure 3 A schematic diagram of an electronic device suitable for implementing embodiments of the present invention is shown.
[0097] It should be noted that, Figure 3 The illustrated electronic device 1000 is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present invention.
[0098] like Figure 3 As shown, the electronic device 1000 includes a Central Processing Unit (CPU) 1001, which can perform various appropriate actions and processes based on programs stored in Read-Only Memory (ROM) 1002 or programs loaded from storage section 1008 into Random Access Memory (RAM) 1003. The RAM 1003 also stores various programs and data required for system operation. The CPU 1001, ROM 1002, and RAM 1003 are interconnected via a bus 1004. An Input / Output (I / O) interface 1005 is also connected to the bus 1004.
[0099] The following components are connected to I / O interface 1005: an input section 1006 including a keyboard, mouse, etc.; an output section 1007 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 1008 including a hard disk, etc.; and a communication section 1009 including a network interface card such as a LAN (Local Area Network) card, modem, etc. The communication section 1009 performs communication processing via a network such as the Internet. A drive 1010 is also connected to I / O interface 1005 as needed. Removable media 1011, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., are installed on drive 1010 as needed so that computer programs read from them can be installed into storage section 1008 as needed.
[0100] In particular, according to embodiments of the present invention, the processes described below with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a storage medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 1009, and / or installed from removable medium 1011. When the computer program is executed by central processing unit (CPU) 1001, it performs various functions defined in the system of this application.
[0101] It should be noted that the storage medium shown in the embodiments of the present invention can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, portable compact disc read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In the present invention, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, wherein computer-readable program code is carried. Such transmitted data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The computer-readable signal medium can also be any storage medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the storage medium can be transmitted using any suitable medium, including but not limited to wireless, wired, etc., or any suitable combination thereof.
[0102] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.
[0103] The units described in the embodiments of the present invention can be implemented in software or hardware, and the described units can also be located in a processor. The names of these units do not necessarily limit the specific unit itself.
[0104] It should be noted that, as another aspect, this application also provides a storage medium, which may be included in an electronic device or may exist independently without being assembled into the electronic device. The aforementioned storage medium carries one or more programs, which, when executed by an electronic device, cause the electronic device to perform the methods described in the following embodiments. For example, the electronic device may perform... Figure 1 The steps of the method shown.
[0105] In one embodiment, this application provides a computer program product including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.
[0106] Furthermore, the above figures are merely illustrative of the processes included in the method according to exemplary embodiments of the present invention, and are not intended to be limiting. It is readily understood that the processes shown in the above figures do not indicate or limit the temporal order of these processes. Additionally, it is readily understood that these processes may be executed synchronously or asynchronously, for example, in multiple modules.
[0107] Other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention herein. This application is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein. The specification and embodiments are to be considered exemplary only, and the true scope and spirit of the invention are indicated by the claims.
[0108] It should be understood that the present invention is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is defined only by the appended claims.
Claims
1. A spectral broadening vegetation clutter suppression method based on feature recognition, characterized in that, include: Obtain the target's coordinates on the range-Doppler plane and extract the one-dimensional spectral vector of the target's range cell; Determine whether the target point is a peak point in the spectrum. If it is a peak point, extract the proportion of energy in the clutter support region on both sides of the zero channel and the proportion of the target point energy in the support region energy from the one-dimensional spectrum vector as features. The features are input into a support vector machine classifier, and the support vector machine classifier determines whether the target is a slow-moving target or spectrally broadened vegetation clutter. If it is not a peak point, it is directly identified as vegetation clutter; If the target is vegetation clutter, it will be removed in subsequent target reports.
2. The method according to claim 1, characterized in that, The process of obtaining the target's coordinates on the range-Doppler plane and extracting the one-dimensional spectral vector of the target's range cell is as follows: The coordinates of the target in the range-Doppler plane are obtained as follows: ,in, Represents the first of the matrix List, Represents the first of the matrix OK; Extracting the target's distance cell from the range-Doppler 2D matrix. One-dimensional spectrum vector data of the column , N Indicates the length of the data.
3. The method according to claim 1, characterized in that, The determination of whether the target point is a peak point in the spectrum specifically involves: If the amplitude of the target point is greater than the amplitude of the adjacent point to its left and greater than the amplitude of the adjacent point to its right, then the target point is determined to be a peak point.
4. The method according to claim 2, characterized in that, The specific proportion of energy extracted from the clutter support regions on both sides of the zero channel is as follows: The one-dimensional spectrum vector is shifted, and the data of the zero channel is moved to the center of the spectrum vector. Supporting regions for calculating the spectrum: Based on the requirements for radar detection of low-speed targets, a point speed threshold is set. vel_th According to speed resolution dvel Calculate the support zone of low-speed targets on both sides of the zero channel, where the starting point of the support zone on the left side of the zero channel is... The cutoff point is located at The starting point of the support area on the right side of the zero channel is... The cutoff point is located at ; Calculate the sum of the amplitudes of all points in the left support zone: Calculate the sum of the amplitudes of all points in the right support zone: Calculate the energy ratio of the two support regions: 。 5. The method according to claim 4, characterized in that, The specific proportion of the energy extracted from the target point to the energy of the support region is as follows: The position of the target point in the relocated spectrum vector is k Calculate the ratio of the amplitude at that point to the sum of the amplitudes at all points in the support zone: The larger this ratio, the more concentrated the energy.
6. The method according to claim 5, characterized in that, The step of inputting features into a support vector machine classifier to determine whether the detected target is a slow-moving target or spectrally broadened vegetation clutter is as follows: The feature vector formed by the extracted proportion of energy in the two support regions and the proportion of energy of the target point in the support region, along with the model parameters obtained during the training phase, are substituted into the following formula to calculate the classification result. in, Represents a symbolic function. , This represents the Gaussian kernel parameters, which are given during the training phase; This represents the feature vector formed by the two types of features extracted from the sample to be classified; parameters These are the model parameters, obtained during the training phase; where, m This represents the number of feature vectors selected from all training samples input into the support vector machine during the training phase. Indicates the selected first i 1 eigenvector Indicates the first i The weight coefficients of each eigenvector. Indicates the bias term; the output When the value is 1, the detected target point is judged as a slow-moving target; otherwise, the target point is judged as vegetation clutter.
7. A spectral broadening vegetation clutter suppression system based on feature recognition, characterized in that, include: The spectrum extraction module is used to obtain the coordinates of the target on the range-Doppler plane and extract the one-dimensional spectrum vector of the range cell where the target is located; The feature extraction module is used to determine whether the target point is a peak point in the spectrum. If it is a peak point, the proportion of energy of clutter support regions on both sides of the zero channel and the proportion of energy of the target point to the energy of the support region are extracted from the one-dimensional spectrum vector as features. The classification module is used to input features into the support vector machine classifier to determine whether the detected target is a slow-moving target or spectrally broadened vegetation clutter. If the judgment module is not a peak point, it directly judges it as vegetation clutter. If the target is vegetation clutter, it will be removed in subsequent target reports.
8. A storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the spectral broadening vegetation clutter suppression method based on feature recognition as described in any one of claims 1 to 6.
9. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the spectral broadening vegetation clutter suppression method based on feature recognition as described in any one of claims 1 to 6.
10. An electronic device, characterized in that, include: processor; as well as Memory for storing the executable instructions of the processor; The processor is configured to execute the feature-recognition-based vegetation clutter suppression method according to any one of claims 1 to 6 by executing the executable instructions.