Radar geographic information and echo fusion processing sample selection method and device

Abstract

The invention relates to the technical field of signal processing, and provides a radar geographic information and echo fusion processing sample selection method and device. The method comprises the following steps: performing sample screening on historical data by using a first echo information evaluation index and a first geographic information evaluation index to obtain a first clutter residue and a second clutter residue; determining a first fusion weight and a second fusion weight according to the first clutter residue and the second clutter residue; and arranging the echo data from small to large according to the fusion evaluation index, and determining the front preset number of echo data as a training sample, thereby solving the problem that non-uniform clutters cannot be effectively suppressed in the face of a moving strong scatterer scene on the ground in the prior art.

Description

Technical Field

[0001] The present invention relates to the technical field of signal processing, and particularly to a method and device for selecting samples for radar geographic information and echo fusion processing. Background Art

[0002] Space-Time Adaptive Processing (STAP) plays an important role in airborne radar clutter suppression. The core of this technology lies in constructing the clutter covariance matrix of the unit to be detected. However, in practice, due to factors such as terrain undulation, weather changes, and artificial strong scatterers, the clutter distribution is non-uniform, resulting in a decrease in the number of training samples that meet the Independent and Identically Distributed (I.I.D) condition, and a deviation in the estimation of the clutter covariance matrix, thereby causing a reduction in the STAP clutter suppression performance.

[0003] In the prior art, some solutions achieve non-uniform clutter suppression through sparse recovery and estimate the covariance matrix from a small number of uniform samples. There are also some solutions that use non-uniform detection to achieve non-uniform clutter suppression and exclude outliers by analyzing the training samples. However, the solutions in the prior art only consider the geographic information or the mutual relationship between signals, and the performance of the corresponding algorithms is greatly affected by the clutter distribution. When facing the scenario where there are moving strong scatterers on the ground, the algorithm performance will decrease, the effect of non-uniform clutter suppression is poor, and the practicability is poor in complex scenarios, resulting in too few training samples that meet the independent and identically distributed condition in the selected training samples, and unable to meet the actual application requirements for constructing the clutter covariance matrix of the unit to be detected.

[0004] In view of this, overcoming the defects of the prior art is an urgent problem to be solved in this technical field. Summary of the Invention

[0005] The technical problem to be solved by the present invention is to provide a method and device for selecting samples for radar geographic information and echo fusion processing. The purpose is to provide a radar sample selection scheme based on the fusion of geographic information and echo information, select the echo data with a smaller fusion evaluation index as the training sample, which has high practicability in complex scenarios, and solves the problem that the prior art only considers the geographic information or the mutual relationship between signals, and the performance of the corresponding algorithms is greatly affected by the clutter distribution. When facing the scenario where there are moving strong scatterers on the ground, the effect of non-uniform clutter suppression is poor.

[0006] The present invention adopts the following technical solutions: In the first aspect, the present invention provides a method for selecting samples for radar geographic information and echo fusion processing, including: Use the first echo information evaluation index to screen the historical data to obtain the first clutter residue; use the first geographic information evaluation index to screen the historical data to obtain the second clutter residue; Determine the first fusion weight and the second fusion weight according to the first clutter residue and the second clutter residue; Determine the second echo information evaluation index and the second geographic information evaluation index of the echo data; wherein, the echo data and the historical data are at the same wave position; According to the second echo information evaluation index and the first fusion weight, and the second geographic information evaluation index and the second fusion weight, obtain a fusion evaluation index; arrange the echo data from small to large according to the fusion evaluation index, and determine the first preset number of echo data as training samples.

[0007] Further, before using the first geographic information evaluation index to screen the historical data to obtain the second clutter residue, it further includes: According to the carrier aircraft coordinate position, divide the clutter blocks on each range ring into multiple information points; determine the grazing angle of each information point relative to the carrier aircraft; input the surface coverage data and the grazing angle into the airborne radar clutter model to obtain the backscattering coefficient of each information point; use the information point as historical data, and use the historical data and the corresponding backscattering coefficient to construct a prior knowledge database; Determine the normalized Doppler frequency of the information points on each range ring, and divide the normalized Doppler frequency into multiple Doppler intervals; Taking the flight direction of the carrier aircraft as the boundary, divide the geographical environment into area A and area B; determine the first information point weight of the information points in each Doppler interval in area A, and determine the second information point weight of the information points in each Doppler interval in area B; Based on the prior knowledge database, use the first information point weight to construct a weighted vector for area A, and use the second information point weight to construct a weighted vector for area B; according to the weighted vector for area A and the weighted vector for area B, determine the first geographic information evaluation index.

[0008] Further, the determining the first information point weight of the information points in each Doppler interval in area A and the second information point weight of the information points in each Doppler interval in area B includes: In area A, the information points located at the same range gate and in the same Doppler interval are attributed to the same information point set to obtain at least one information point set in area A; in area B, the information points located at the same range gate and in the same Doppler interval are attributed to the same information point set to obtain at least one information point set in area B; For each of the sets of A-region information points, calculate the azimuth angle between each information point and the direction of the corresponding airborne radar array, and calculate the first mean value of the azimuth angles of all the information points in the set of A-region information points; for each of the sets of B-region information points, calculate the azimuth angle between each information point and the direction of the corresponding airborne radar array, and calculate the second mean value of the azimuth angles of all the information points in the set of B-region information points. According to the magnitude relationship between the first mean value and the corresponding second mean value, determine the first information point weight of the corresponding set of A-region information points and the second information point weight of the corresponding set of B-region information points, so as to obtain the first information point weights of all the sets of A-region information points and the second information point weights of all the sets of B-region information points; wherein, the information points corresponding to the first mean value and the corresponding second mean value are located in the same Doppler interval.

[0009] Further, the determining the first information point weight of the corresponding set of A-region information points and the second information point weight of the corresponding set of B-region information points according to the magnitude relationship between the first mean value and the corresponding second mean value includes: When the first mean value is equal to the corresponding second mean value, determine the first information point weight as one; determine the second information point weight as one; When the first mean value is not equal to the corresponding second mean value, determine the sum of the first mean value and the corresponding second mean value as the intermediate value; determine the ratio of the corresponding second mean value to the intermediate value as the first information point weight; determine the ratio of the corresponding first mean value to the intermediate value as the second information point weight.

[0010] Further, based on the prior knowledge database, construct a weighted vector for the A region using the first information point weight, and construct a weighted vector for the B region using the second information point weight; according to the weighted vector for the A region and the weighted vector for the B region, determining the first geographic information evaluation index includes: According to the backscattering coefficients of the historical data of various landform types in the prior knowledge database, represent the set of A-region information points with the normalized vectors of various landform types to obtain a normalized vector for the A region; represent the set of B-region information points with the normalized vectors of various landform types to obtain a normalized vector for the B region; Use the backscattering coefficient of the corresponding information point and the first information point weight of the set of A-region information points to weight the normalized vector for the A region to obtain a weighted vector for the A region; use the backscattering coefficient of the corresponding information point and the second information point weight to weight the normalized vector for the B region of the set of B-region information points to obtain a weighted vector for the B region; Determine the average value of Region A of the weighted vector of Region A; calculate the first distance between the weighted vector of Region A and the average value of Region A; determine the average value of Region B of the weighted vector of Region B; calculate the second distance between the weighted vector of Region B and the average value of Region B; determine the sum of the first distance and the second distance as the first geographic information evaluation index.

[0011] Furthermore, the expression for the normalized Doppler frequency is:

[0012] where is the flight speed of the carrier aircraft, is the wavelength, is the pulse repetition frequency, is the th angle between the th information point in the th distance ring and the array axis, is the elevation angle of the information point on the th distance ring;

[0013] where s k is the interval range, represents the number of divided Doppler intervals.

[0014] Furthermore, the expression for the first echo information evaluation index is:

[0015] where is the echo data vector of the th range gate, represents the conjugate transpose of the matrix, is the spatio-temporal dimensionality reduction matrix of the th Doppler channel, is the inverse matrix of the covariance matrix estimated using L such echo data.

[0016] Furthermore, the expression for the fusion evaluation index is:

[0017] where represents the fusion evaluation index, represents the second echo information evaluation index, represents the second geographic information evaluation index; represents the maximum value in the second echo information evaluation index, represents the maximum value in the second geographic information evaluation index; represents the first fusion weight, represents the second fusion weight.

[0018] In a second aspect, the present invention further provides a radar geographic information and echo fusion processing sample selection device, including: 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 processor for performing the radar geographic information and echo fusion processing sample selection method described in the first aspect.

[0019] In a third aspect, the present invention further provides a non-volatile computer storage medium, the computer storage medium stores computer-executable instructions, and the computer-executable instructions are executed by one or more processors for completing the radar geographic information and echo fusion processing sample selection method described in the first aspect.

[0020] In a fourth aspect, there is provided a computer program product containing instructions, when the instructions run on a computer or a processor, enabling the computer or the processor to execute the radar geographic information and echo fusion processing sample selection method as described in the first aspect.

[0021] In a fifth aspect, the present invention further provides a radar geographic information and echo fusion processing sample selection system, including the radar geographic information and echo fusion processing sample selection device as described in the second aspect, and using the radar geographic information and echo fusion processing sample selection method as described in the first aspect to complete the interaction of the radar geographic information and echo fusion processing sample selection device described in the second aspect.

[0022] Different from the prior art, the present invention has at least the following beneficial effects: The present invention uses evaluation indexes from two aspects of echo information and geographic information to screen historical data for samples, calculates corresponding fusion weights to construct a fusion evaluation index, expands the screening dimension of training samples through multi-dimensional information weighted fusion to achieve a more appropriate selection of the training sample set; arranges the echo data from small to large according to the fusion evaluation index, and determines the first preset number of echo data as training samples, with better non-uniform clutter suppression effect, solving the problem of poor non-uniform clutter suppression effect in the prior art when facing the scene where there are moving strong scatterers on the ground. Description of the Drawings

[0023] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the accompanying drawings required for use in the embodiments of the present invention. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0024] Figure 1 is a schematic flowchart of a method for selecting samples for radar geographic information and echo fusion processing provided by an embodiment of the present invention; Figure 2 is a schematic diagram of a specific example of a method for selecting samples for radar geographic information and echo fusion processing according to an embodiment of the present invention; Figure 3 is a schematic flowchart of step 10 provided by an embodiment of the present invention; Figure 4 is a schematic flowchart of step 103 provided by an embodiment of the present invention; Figure 5 is a schematic flowchart of step 104 provided by an embodiment of the present invention; Figure 6 is a schematic diagram of the architecture of a device for selecting samples for radar geographic information and echo fusion processing provided by an embodiment of the present invention. Detailed implementation manners

[0025] In order to make the objectives, technical solutions, and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0026] Unless otherwise required by the context, throughout the specification and claims, the term "comprising" is interpreted in an open inclusive sense, that is, "including, but not limited to". In the description of the specification, the terms "one embodiment", "some embodiments", "exemplary embodiments", "examples", "specific examples", or "some examples", etc., are intended to indicate that specific features, structures, materials, or characteristics related to the embodiment or example are included in at least one embodiment or example of the present disclosure. The schematic representations of the above terms are not necessarily referring to the same embodiment or example. In addition, the specific features, structures, materials, or characteristics may be included in any one or more embodiments or examples in any appropriate manner, that is, although they may be carried in the above-mentioned embodiments or examples due to reasons such as the order and position of appearance, they are not limited to being carried in a combined manner by one embodiment or example.

[0027] In the description of the present invention, it should be understood that the orientation or positional relationships indicated by the terms "center", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. are based on the orientation or positional relationships shown in the drawings. These are only for the convenience of describing the present disclosure and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operate in a specific orientation. Therefore, it should not be construed as a limitation to the present disclosure.

[0028] In the description of the present invention, the terms "first" and "second" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the embodiments of the present disclosure, unless otherwise specified, the meaning of "a plurality" is two or more. In addition, for example, in the description, for the same type of nouns, the method of adding "A" and "B" at the end is used to describe them as two independent individuals. In this case, the features defined with "A" and "B" are only used for the purpose of distinguishing the same type of individuals and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features.

[0029] In the description of some embodiments, expressions such as "coupled", "coupled to" and "connected" and their derivatives may be used. For example, in the description of some embodiments, the term "connected" may be used to indicate that two or more components have direct physical or electrical contact with each other. Also, for example, in the description of some embodiments, the term "coupled to" may be used to indicate that two or more components have direct physical or electrical contact. However, the term "connected" or "coupled" may also mean that two or more components do not have direct contact with each other, but still cooperate or interact with each other, such as "optical path coupling", "wireless connection", etc. The embodiments disclosed herein are not necessarily limited to the content of the present invention.

[0030] In the description of the present invention, the expression "A and / or B" (where A and B are used to formally represent specific feature contents) is involved, and the corresponding expression includes the following three combinations: only A, only B, and the combination of A and B.

[0031] As used in the present invention, "about", "substantially" or "approximately" includes the stated value and the average value within an acceptable deviation range of the specific value, where the acceptable deviation range is determined by those of ordinary skill in the art considering the measurement being discussed and the errors associated with the measurement of the specific quantity (i.e., the limitations of the measurement system).

[0032] In addition, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0033] Embodiment 1: To solve the above problems, as Figure 1 shown, an embodiment of the present invention provides a method for selecting samples for radar geographic information and echo fusion processing, including: Step 10: Use the first echo information evaluation index to screen the historical data to obtain the first clutter residue; use the first geographic information evaluation index to screen the historical data to obtain the second clutter residue.

[0034] Among them, the historical data is the historical echo data of the radar on a certain Doppler channel. The first echo information evaluation index and the first geographic information evaluation index are both corresponding evaluation index sets.

[0035] As Figure 2 shown, an embodiment of the present invention analyzes the historical data for a selected Doppler channel, uses the echo information evaluation index and the geographic information evaluation index to screen the historical data respectively. Obtain a training sample set selected based on the two evaluation indexes. Using the training samples of these two sets, two covariance matrices are estimated respectively, and using the space-time adaptive processing technology, the first clutter residue and the second clutter residue are obtained.

[0036] In one embodiment, the expression of the first echo information evaluation index is:

[0037] Among them, is the echo data vector of the th range gate, represents the conjugate transpose of the matrix, is the space-time dimensionality reduction matrix of the th Doppler channel, is the covariance matrix estimated using the L echo data, is the inverse matrix of the covariance matrix estimated using the L echo data; the expression of this covariance matrix is:

[0038] Step 20: Determine the first fusion weight and the second fusion weight according to the first clutter residue and the second clutter residue.

[0039] In one embodiment, the expressions for the first fusion weight and the second fusion weight are as follows:

[0040] Wherein, represents the first fusion weight, represents the second fusion weight.

[0041] Step 30: Determine the second echo information evaluation index and the second geographic information evaluation index of the echo data; wherein, the echo data and the historical data are at the same wave position.

[0042] As Figure 2 shown, for the echo data at the same wave position in the Doppler channel as the historical data, two sets of evaluation indexes, namely echo information and geographic information, are calculated respectively.

[0043] Step 40: Obtain a fusion evaluation index according to the second echo information evaluation index and the first fusion weight, and the second geographic information evaluation index and the second fusion weight; arrange the echo data in ascending order according to the fusion evaluation index, and determine the first preset number of echo data as training samples.

[0044] Among them, the preset number is selected by those skilled in the art according to the specific usage scenario and is not limited herein; in the embodiment of the present invention, the echo data with a smaller fusion evaluation index is taken as the training sample.

[0045] The second echo information evaluation index and the second geographic information evaluation index are normalized and then weighted and summed to obtain a fusion evaluation index. In one embodiment, the expression for the fusion evaluation index is:

[0046] Wherein, represents the fusion evaluation index, represents the second echo information evaluation index, represents the second geographic information evaluation index; represents the maximum value in the second echo information evaluation index, represents the maximum value in the second geographic information evaluation index; represents the first fusion weight, represents the second fusion weight.

[0047] The present invention uses two evaluation indicators, echo information and geographic information, to screen samples from historical data, calculate corresponding fusion weights to construct a fusion evaluation indicator, and expand the screening dimension of training samples through multi-dimensional information weighted fusion to achieve a more appropriate selection of the training sample set; arrange the echo data from smallest to largest according to the fusion evaluation indicator, and determine the first preset number of echo data as training samples, with a better effect of non-uniform clutter suppression, solving the problem of poor non-uniform clutter suppression effect in the prior art when facing the scene where there are moving strong scatterers on the ground.

[0048] The first geographic information evaluation indicator is calculated through the following steps: First, construct a prior knowledge database; second, implement information point mapping and divide regions, and then determine the information point set weights; then construct a weighted normalization vector, and finally select samples by calculating the geographic information evaluation indicator. Specifically, as Figure 3 shown, before using the first geographic information evaluation indicator to screen the historical data to obtain the second clutter residue in step 10, it further includes: Step 101: Divide the clutter blocks on each range ring into multiple information points according to the carrier aircraft coordinate position; determine the grazing angle of each information point relative to the carrier aircraft; input the surface coverage data and the grazing angle into the airborne radar clutter model to obtain the backscattering coefficient of each information point; use the information points as historical data, and construct a prior knowledge database using the historical data and the corresponding backscattering coefficients.

[0049] In one embodiment, in the process of constructing the prior knowledge database, first, according to the carrier aircraft coordinate position, combined with the 30m digital elevation model, divide the clutter blocks on each range ring into multiple information points with an accuracy of 30m; second, solve the grazing angle of each information point relative to the carrier aircraft; finally, according to the 30m fine surface coverage data, combined with the airborne radar clutter model, estimate the backscattering coefficient of each information point.

[0050] Step 102: Determine the normalized Doppler frequency of the information points on each range ring, and divide the normalized Doppler frequency into multiple Doppler intervals.

[0051] To save the amount of calculation and divide the Doppler intervals, since clutter is distributed differently at different Doppler frequencies, in an actual scenario, it is very likely that one Doppler interval is affected while another Doppler interval is not affected, which will affect the sorting situation when finally selecting training samples.

[0052] In one embodiment, the expression of the normalized Doppler frequency is:

[0053] where is the flight speed of the carrier aircraft, is the wavelength, is the pulse repetition frequency, is the th distance ring, and is the angle between the th information point in the th distance ring and the array axis, is the pitch angle of the information point on the

[0054] In one embodiment, the expression for the range of the plurality of Doppler intervals is:

[0055] wherein, s k is the range, represents the number of divided Doppler intervals.

[0056] Step 103: Taking the flight direction of the carrier aircraft as the boundary, divide the geographical environment into area A and area B; determine the first information point weight of the information points in each Doppler interval in area A, and determine the second information point weight of the information points in each Doppler interval in area B.

[0057] For an airborne radar, area A and area B are independent, so they need to be calculated separately; since a certain Doppler interval may exist in both area A and area B, it is necessary to distinguish information points according to the Doppler interval in area A and area B respectively, and determine the information point weight of each type of distinguished information point.

[0058] In an alternative embodiment, area A is located on the left side of the flight direction of the carrier aircraft, and area B is located on the right side of the flight direction of the carrier aircraft.

[0059] Step 104: Based on the prior knowledge database, construct a weighted vector for area A using the first information point weight, and construct a weighted vector for area B using the second information point weight; determine the first geographical information evaluation index according to the weighted vector of area A and the weighted vector of area B.

[0060] To illustrate the process of obtaining the first information point weight and the second information point weight, as Figure 4 shown, in step 103, the determining the first information point weight of the information points in each Doppler interval in area A and the determining the second information point weight of the information points in each Doppler interval in area B include: Step 1031: In area A, information points located at the same distance gate and within the same Doppler interval are grouped into the same information point set to obtain at least one information point set for area A; in area B, information points located at the same distance gate and within the same Doppler interval are grouped into the same information point set to obtain at least one information point set for area B.

[0061] Among them, information points located at the same distance gate and within the same Doppler interval refer to: information points located at the same distance gate and with normalized Doppler frequencies within the same Doppler interval.

[0062] Step 1032: For each of the information point sets in area A, calculate the azimuth angle between each information point and the direction of the corresponding airborne radar array, and calculate the first mean value of the azimuth angles of all information points in the information point set for area A; for each of the information point sets in area B, calculate the azimuth angle between each information point and the direction of the corresponding airborne radar array, and calculate the second mean value of the azimuth angles of all information points in the information point set for area B.

[0063] Step 1033: Based on the magnitude relationship between the first mean value and the corresponding second mean value, determine the first information point weight for the corresponding information point set in area A and the second information point weight for the corresponding information point set in area B, so as to obtain the first information point weights for all information point sets in area A and the second information point weights for all information point sets in area B; among them, the information points corresponding to the first mean value and the corresponding second mean value are within the same Doppler interval.

[0064] Specifically, step 1033 includes: When the first mean value is equal to the corresponding second mean value, determine the first information point weight as one; determine the second information point weight as one.

[0065] When the first mean value is not equal to the corresponding second mean value, determine the sum of the first mean value and the corresponding second mean value as the intermediate value; determine the ratio of the corresponding second mean value to the intermediate value as the first information point weight; determine the ratio of the corresponding first mean value to the intermediate value as the second information point weight.

[0066] In one embodiment, the expression can be:

[0067] Among them, is the first information point weight, is the second information point weight, is the first mean value, is the second mean value, is the intermediate value.

[0068] For airborne radars, the signal radiation intensities that may be received at different Doppler intervals vary depending on the pointing directions of each airborne radar array. Generally, the smaller the angle of the airborne radar array's pointing direction, the higher the intensity of the received radiation signal and the greater the impact. Conversely, the larger the angle of the airborne radar array's pointing direction, the lower the intensity of the received radiation signal and the smaller the impact. The present invention divides the Doppler intervals to distinguish between the intervals with higher radiation signal intensities and those with lower intensities, facilitating subsequent weighted processing using information point weights and focusing on the intervals with higher radiation signal intensities.

[0069] To illustrate the process of obtaining the weighted vector for Region A and the weighted vector for Region B, as Figure 5 shown, step 104 includes: Step 1041: Represent the set of information points in Region A using the normalized vectors of various landform types according to the backscattering coefficients of the historical data of various landform types in the prior knowledge database, obtaining the normalized vector for Region A; represent the set of information points in Region B using the normalized vectors of various landform types, obtaining the normalized vector for Region B.

[0070] Step 1042: Weight the normalized vector for Region A using the backscattering coefficient of the corresponding information point and the first information point weight of the set of information points in Region A to obtain the weighted vector for Region A; weight the normalized vector for Region B of the set of information points in Region B using the backscattering coefficient of the corresponding information point and the second information point weight to obtain the weighted vector for Region B.

[0071] During the process of constructing the corresponding weighted vectors, according to the prior knowledge database, the set of information points in Region A and the set of information points in Region B can be represented by the normalized vectors of landform types consisting of 8 elements, corresponding to the proportions of landform types such as farmland, forest, shrub grassland, wetland, artificial construction, water area, bare area, and glacier respectively. The expression is:

[0072] where, represents the weighted vector for Region A, represents the weighted vector for Region B, represents the th set of information points in Region A, or the th set of information points in Region B; j represents the j nd landform type.

[0073] Since the backscattering coefficients of various geomorphic types are different, and the influence of the proportion of different geomorphic types on the clutter non-uniformity degree is different, in order to better reflect the characteristics of surface information, the backscattering coefficient and the information point weight are used to weight the geomorphic type normalization vector, and its calculation formula is:

[0074] Among them, represents the weighted vector of area A, represents the weighted vector of area B, represents the number of information points belonging to the j-th geomorphic type in the set of information points with the same Doppler frequency and range gate in area A, represents the number of information points belonging to the j-th geomorphic type in the set of information points with the same Doppler frequency and range gate in area B, represents the number of the information point, represents the backscattering coefficient of the information points belonging to the j-th geomorphic type in the set of information points in area A, represents the backscattering coefficient of the information points belonging to the j-th geomorphic type in the set of information points in area B, represents the set composed of the information points with the same Doppler frequency and range gate and belonging to the j-th geomorphic type in area A, represents the set composed of the information points with the same Doppler frequency and range gate and belonging to the j-th geomorphic type in area B.

[0075] Step 1043: Determine the mean value of area A of the weighted vector of area A; calculate the first distance between the weighted vector of area A and the mean value of area A; determine the mean value of area B of the weighted vector of area B; calculate the second distance between the weighted vector of area B and the mean value of area B; determine the sum of the first distance and the second distance as the first geographic information evaluation index.

[0076] Among them, both the first distance and the second distance refer to the Euclidean distance.

[0077] In the process of calculating the geographic information evaluation index, in the selected Doppler channel, the corresponding expressions for calculating the geographic information evaluation indexes of area A and area B are as follows:

[0078] Among them, represents the Euclidean distance, represents the weighted vector of area A, represents the weighted vector of area B, is the mean value of area A, is the mean value of area B, and the corresponding expressions are:

[0079] The sample selection for radar geographic information and echo fusion processing in the embodiments of the present invention has good robustness in different clutter environments and has good training sample selection performance in complex environments containing ground discrete moving scatterers.

[0080] Embodiment 2: As Figure 6 shown, it is a schematic structural diagram of a device for sample selection of radar geographic information and echo fusion processing in the embodiments of the present invention. The device for sample selection of radar geographic information and echo fusion processing in this embodiment includes one or more processors 21 and a memory 22. Among them, Figure 6 one processor 21 is taken as an example here.

[0081] The processor 21 and the memory 22 can be connected through a bus or other means, Figure 6 taking the connection through a bus as an example here.

[0082] The memory 22, as a non-volatile computer-readable storage medium, can be used to store non-volatile software programs and non-volatile computer-executable programs, such as the method for sample selection of radar geographic information and echo fusion processing in this embodiment. The processor 21 executes the method for sample selection of radar geographic information and echo fusion processing by running the non-volatile software programs and instructions stored in the memory 22.

[0083] The memory 22 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage devices. In some embodiments, the memory 22 may optionally include a memory remotely provided with respect to the processor 21, and these remote memories can be connected to the processor 21 through a network. Examples of the above network include but are not limited to the Internet, an enterprise intranet, a local area network, a mobile communication network, and combinations thereof.

[0084] The program instructions / modules are stored in the memory 22 and, when executed by the one or more processors 21, execute the method for sample selection of radar geographic information and echo fusion processing in the above embodiments, for example, execute each step of the method for sample selection of radar geographic information and echo fusion processing in the embodiments of the present invention described above.

[0085] The embodiments of the present invention also provide a non-volatile computer storage medium, and the computer storage medium stores computer-executable instructions, which are executed by one or more processors, for example Figure 6A processor 21 can enable the above-mentioned one or more processors to execute the method for selecting radar geographic information and echo fusion processing samples in the specific implementation manner of the present invention. For example, it can execute each step of the method for selecting radar geographic information and echo fusion processing samples in the above-described embodiments of the present invention; it can also implement Figure 6 each of the above-mentioned modules and units; or execute the method for selecting radar geographic information and echo fusion processing samples in the specific implementation manner of the present invention. For example, it can execute each step of the method for selecting radar geographic information and echo fusion processing samples in the above-described embodiments of the present invention; it can also implement Figure 6 each of the above-mentioned modules and units.

[0086] It should be noted that the content such as information interaction and execution process among the modules and units in the above-mentioned device and system, due to being based on the same concept as the method embodiment of the present invention, the specific content can be referred to the description in the method embodiment of the present invention and will not be elaborated here.

[0087] Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the embodiments can be completed by instructing relevant hardware through a program, and this program can be stored in a computer-readable storage medium. The storage medium can include: read-only memory (ROM, Read Only Memory), random access memory (RAM, Random Access Memory), magnetic disk or optical disk, etc.

[0088] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, and improvements made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for selecting samples of radar geographic information and echo fusion processing, characterized in that Including: Using the first echo information evaluation index to screen the historical data to obtain the first clutter residue; Using the first geographic information evaluation index to screen the historical data to obtain the second clutter residue; Determining a first fusion weight and a second fusion weight according to the first clutter residue and the second clutter residue; Determining a second echo information evaluation index and a second geographic information evaluation index of the echo data; wherein, the echo data and the historical data are at the same wave position; Obtaining a fusion evaluation index according to the second echo information evaluation index and the first fusion weight, and the second geographic information evaluation index and the second fusion weight; arranging the echo data from small to large according to the fusion evaluation index, and determining the first preset number of echo data as training samples.

2. The method for selecting samples for radar geographic information and echo fusion processing according to claim 1, wherein Before using the first geographic information evaluation index to screen the historical data to obtain the second clutter residue, it further includes: Dividing the clutter blocks on each range ring into multiple information points according to the carrier aircraft coordinate position; determining the grazing angle of each information point relative to the carrier aircraft; inputting the surface coverage data and the grazing angle into the airborne radar clutter model to obtain the backscattering coefficient of each information point; using the information point as historical data, and constructing a prior knowledge database with the historical data and the corresponding backscattering coefficient; Determining the normalized Doppler frequency of the information points on each range ring, and dividing the normalized Doppler frequency into multiple Doppler intervals; Dividing the geographical environment into area A and area B with the flight direction of the carrier aircraft as the boundary; determining the first information point weight of the information points in each Doppler interval in area A, and determining the second information point weight of the information points in each Doppler interval in area B; Based on the prior knowledge database, constructing a weighted vector for area A using the first information point weight, and constructing a weighted vector for area B using the second information point weight; determining the first geographic information evaluation index according to the weighted vector for area A and the weighted vector for area B.

3. The method for selecting radar geographic information and echo fusion processing samples according to claim 2, wherein The determining the first information point weight of the information points in each Doppler interval in area A and the second information point weight of the information points in each Doppler interval in area B includes: In area A, grouping the information points located at the same range gate and in the same Doppler interval into the same information point set to obtain at least one information point set for area A; in area B, grouping the information points located at the same range gate and in the same Doppler interval into the same information point set to obtain at least one information point set for area B; For each of the information point sets for area A, calculating the azimuth angle between each information point and the corresponding airborne radar array pointing direction, and calculating the first mean value of the azimuth angles of all the information points in the information point set for area A; for each of the information point sets for area B, calculating the azimuth angle between each information point and the corresponding airborne radar array pointing direction, and calculating the second mean value of the azimuth angles of all the information points in the information point set for area B; Determine the first information point weight of the corresponding set of A-region information points and the second information point weight of the corresponding set of B-region information points according to the magnitude relationship between the first mean value and the corresponding second mean value, so as to obtain the first information point weights of all sets of A-region information points and the second information point weights of all sets of B-region information points; wherein, the information points corresponding to the first mean value and the corresponding second mean value are located in the same Doppler interval.

4. The method for selecting radar geographic information and echo fusion processing samples according to claim 3, wherein The determining the first information point weight of the corresponding set of A-region information points and the second information point weight of the corresponding set of B-region information points according to the magnitude relationship between the first mean value and the corresponding second mean value includes: When the first mean value is equal to the corresponding second mean value, determine the first information point weight as one; determine the second information point weight as one; When the first mean value is not equal to the corresponding second mean value, determine the sum of the first mean value and the corresponding second mean value as the intermediate value; determine the ratio of the corresponding second mean value to the intermediate value as the first information point weight; determine the ratio of the corresponding first mean value to the intermediate value as the second information point weight.

5. The method for selecting radar geographic information and echo fusion processing samples according to claim 3, characterized in that, Based on the prior knowledge database, construct an A-region weighted vector using the first information point weight, and construct a B-region weighted vector using the second information point weight; Determine the first geographic information evaluation index according to the A-region weighted vector and the B-region weighted vector, including: According to the backscattering coefficients of the historical data of various geomorphic types in the prior knowledge database, represent the set of A-region information points with the normalized vectors of various geomorphic types to obtain an A-region normalized vector; represent the set of B-region information points with the normalized vectors of various geomorphic types to obtain a B-region normalized vector; Use the backscattering coefficient of the corresponding information point and the first information point weight of the set of A-region information points to weight the A-region normalized vector to obtain an A-region weighted vector; use the backscattering coefficient of the corresponding information point and the second information point weight to weight the B-region normalized vector of the set of B-region information points to obtain a B-region weighted vector; Determine the A-region mean value of the A-region weighted vector; calculate the first distance between the A-region weighted vector and the A-region mean value; determine the B-region mean value of the B-region weighted vector; calculate the second distance between the B-region weighted vector and the B-region mean value; determine the sum of the first distance and the second distance as the first geographic information evaluation index.

6. The method for selecting radar geographic information and echo fusion processing samples according to claim 2, characterized in that The expression of the normalized Doppler frequency is: Among them, is the flight speed of the carrier aircraft, is the wavelength, is the pulse repetition frequency, is the th distance ring, and is the angle between the th information point and the array axis, is the angle between the array axis and the carrier aircraft direction, is the th elevation angle of the information point on the distance ring; The expression of the interval range of the multiple Doppler intervals is: Among them, s k is an interval range, indicating the number of divided Doppler intervals.

7. The method for selecting radar geographic information and echo fusion processing samples according to any one of claims 1-6, characterized in that The expression of the first echo information evaluation index is: wherein, is the th echo data vector from the range gate, is expressed as the conjugate transpose of a matrix, is the th space-time dimensionality reduction matrix for the Doppler channels, is the inverse matrix of the covariance matrix estimated using the L echo data.

8. The method for selecting samples for radar geographic information and echo fusion processing according to any one of claims 1-6, characterized in that, The expression of the fusion evaluation index is: Among them, represents the fusion evaluation index, represents the second echo information evaluation index, represents the second geographic information evaluation index; represents the maximum value in the second echo information evaluation index, represents the maximum value in the second geographic information evaluation index; represents the first fusion weight, represents the second fusion weight.

9. A device for selecting samples for radar geographic information and echo fusion processing, characterized in that The radar geographic information and echo fusion processing sample selection device includes at least one processor and a memory, the at least one processor and the memory are connected through a data bus, the memory stores instructions executable by the at least one processor, and after the instructions are executed by the processor, they are used to implement the radar geographic information and echo fusion processing sample selection method according to any one of claims 1-8.

10. A non-volatile computer storage medium, characterized in that, The computer storage medium stores computer-executable instructions, and the computer-executable instructions are executed by one or more processors to complete the radar geographic information and echo fusion processing sample selection method according to any one of claims 1-8.

Images