Structural recognition method, device, computing equipment and storage medium for ball-head cone target

Abstract

The embodiments of the present invention relate to the field of data processing technology, and in particular to a method, device, computing device and storage medium for structural recognition of a spherical head cone target. The method comprises: obtaining each scattered echo signal measured in a dual polarization mode of the spherical head cone target to be identified; determining the target scattering center polarization ratio feature according to each scattered echo signal measured in the dual polarization mode; inputting the target scattering center polarization ratio feature into a pre-trained classification model to obtain a structural recognition result of the spherical head cone target. This solution can effectively improve the recognition accuracy of the spherical head cone target.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of data processing technology, and in particular to a method, device, computing equipment and storage medium for structural recognition of a ball-head cone target. Background Art

[0002] In modern radar application scenarios, accurately distinguishing between true and false targets is an important aspect. The appearances of true and false targets are very similar, with only slight differences. Only by accurately identifying the detailed structures of true and false targets can the true target be effectively identified.

[0003] In the related art, the recognition algorithms for ball-head cone targets with similar shapes and structures mostly extract the features of different targets from the echo data through methods such as coherent matrix decomposition and feature vector analysis, and use these features to train the classification model. However, the existing recognition algorithms are prone to confusion of target features when facing ball-head cone targets with similar structures, which affects the recognition accuracy. Therefore, the accuracy of the existing recognition algorithms for ball-head cone targets with similar shapes and structures is relatively low.

[0004] Therefore, a new structural recognition method for spherical head cone targets is urgently needed. Summary of the invention

[0005] In order to improve the recognition accuracy of a spherical-conical target, an embodiment of the present invention provides a method, an apparatus, a computing device and a storage medium for structural recognition of a spherical-conical target.

[0006] In a first aspect, an embodiment of the present invention provides a method for structural recognition of a ball-head cone target, comprising:

[0007] Acquire each scattered echo signal measured by the spherical cone target to be identified in the dual polarization mode;

[0008] Determine the target scattering center polarization ratio characteristics according to each scattered echo signal measured in the dual polarization mode;

[0009] The target scattering center polarization ratio feature is input into a pre-trained classification model to obtain a structural recognition result of the spherical head cone target.

[0010] In one possible design, the dual polarization mode is a horizontal transmission and horizontal reception polarization mode and a vertical transmission and vertical reception polarization mode.

[0011] In a possible design, determining the target scattering center polarization ratio feature according to each scattered echo signal measured in the dual-polarization mode includes:

[0012] Perform frequency domain analysis on the scattered echo signal corresponding to each polarization mode to obtain the one-dimensional image history data corresponding to each polarization mode;

[0013] Determine the target part of the spherical cone target to be identified;

[0014] From the one-dimensional image history data corresponding to each polarization mode, the time domain signals corresponding to the local scattering center of the target in various polarization modes are extracted respectively;

[0015] According to the time domain signals corresponding to the local scattering centers of the targets under various polarization modes, the polarization ratio characteristics of the target scattering centers are determined.

[0016] In a possible design, extracting the time domain signals corresponding to the local scattering centers of the target in various polarization modes from the one-dimensional image history data corresponding to each polarization mode includes:

[0017] Determine the distance range corresponding to the local scattering center of the target in each polarization mode according to the one-dimensional image history data and the local scattering characteristics of the target;

[0018] According to the distance range and one-dimensional image history data corresponding to the local scattering center of the target in each polarization mode, the time domain signal corresponding to the local scattering center of the target in each polarization mode is determined.

[0019] In a possible design, determining the target scattering center polarization ratio feature according to the time domain signal corresponding to the target local scattering center in various polarization modes includes:

[0020] The time domain signals corresponding to the local scattering centers of the target in various polarization modes are divided to obtain the polarization ratio characteristics of the target scattering centers.

[0021] In a possible design, the target portion is the tail of the spherical cone target.

[0022] In one possible design, the classification model is constructed as follows:

[0023] Determine the azimuth range, broadband sweep range, dual polarization mode and structural type of spherical cone targets for radar measurement;

[0024] Acquire sample echo signals of the spherical head cone target of each structural type in the dual polarization mode according to the preset angle interval, the preset frequency interval, the azimuth angle range, and the broadband sweep frequency range;

[0025] According to the sample echo signals of the spherical head cone target of each structural type in the dual polarization mode, the sample scattering center polarization ratio characteristics of the spherical head cone target of each structural type are determined;

[0026] Downsampling the sample scattering center polarization ratio feature;

[0027] The downsampled sample scattering center polarization ratio features are input into the support vector machine to obtain the classification model.

[0028] In a second aspect, an embodiment of the present invention further provides a structure recognition device for a ball-head cone target, comprising:

[0029] An acquisition unit, used for acquiring each scattered echo signal measured by the spherical cone target to be identified in a dual polarization mode;

[0030] A determination unit, used to determine a target scattering center polarization ratio characteristic according to each scattered echo signal measured in a dual polarization mode;

[0031] The recognition unit is used to input the target scattering center polarization ratio feature into a pre-trained classification model to obtain a structural recognition result of the spherical head cone target.

[0032] In a third aspect, an embodiment of the present invention further provides a computing device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the method described in any embodiment of this specification is implemented.

[0033] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed in a computer, enables the computer to execute the method described in any embodiment of this specification.

[0034] The embodiment of the present invention provides a method, device, computing device and storage medium for structural recognition of a spherical head cone target. First, each scattered echo signal of the spherical head cone target to be identified measured in a dual polarization mode is obtained, and then the target scattering center polarization ratio feature is determined according to each scattered echo signal measured in the dual polarization mode. By inputting the target scattering center polarization ratio feature into a classification model generated by pre-training, the structural recognition result of the spherical head cone target can be obtained. In this solution, the target scattering center polarization ratio feature can be used to effectively improve the recognition accuracy of the spherical head cone target. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0036] Figure 1 It is a flow chart of a method for structural recognition of a ball-head cone target provided by one embodiment of the present invention;

[0037] Figure 2It is a one-dimensional image history diagram of a spherical cone target under HH polarization provided by one embodiment of the present invention;

[0038] Figure 3 It is a right-angle bottom ball head cone target model diagram provided by an embodiment of the present invention;

[0039] Figure 4 This is a diagram of a target model of a circular arc bottom ball head cone provided by an embodiment of the present invention;

[0040] Figure 5 It is a time domain signal diagram corresponding to the tail scattering center of a right-angle bottom spherical head cone target provided by an embodiment of the present invention;

[0041] Figure 6 It is a time domain signal diagram corresponding to the tail scattering center of a circular arc bottom spherical head cone target provided by an embodiment of the present invention;

[0042] Figure 7 This is a comparison diagram of the characteristic of the sample scattering center polarization ratio of two spherical head cone targets at different azimuth angles provided by an embodiment of the present invention;

[0043] Figure 8 is a classification result diagram provided by an embodiment of the present invention;

[0044] Fig. 9 is a hardware architecture diagram of an electronic device provided by an embodiment of the present invention;

[0045] Fig.10 It is a structural diagram of a structure recognition device for a ball-head cone target provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0046] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0047] As mentioned above, in the related art, the recognition algorithms for ball-head cone targets with similar shapes and structures mostly extract the features of different targets from the echo data through methods such as coherent matrix decomposition and feature vector analysis, and use these features to train the classification model. These methods require a large amount of data support as training samples in practical applications. However, when facing ball-head cone targets with similar structures, the existing recognition algorithms are prone to confusion of target features, affecting the recognition accuracy. Therefore, the accuracy of the existing recognition algorithms for ball-head cone targets with similar shapes and structures is relatively low.

[0048] In order to solve the above technical problems, the inventors may consider using prior knowledge of the scattering mechanism and utilizing the fact that the target scattering center polarization ratio characteristics of spherical head cone targets with different structures have obvious differences to identify the structure of the spherical head cone target, thereby improving the recognition accuracy of the spherical head cone target.

[0049] The specific implementation of the above concept is described below.

[0050] Please refer to Figure 1 The embodiment of the present invention provides a method for structural recognition of a ball-head cone target, the method comprising:

[0051] Step 100: Acquire scattered echo signals of the spherical cone target to be identified measured in a dual-polarization mode;

[0052] Step 102: determining a target scattering center polarization ratio characteristic according to each scattered echo signal measured in a dual-polarization mode;

[0053] Step 104: Input the target scattering center polarization ratio feature into the pre-trained classification model to obtain the structural recognition result of the spherical head cone target.

[0054] In the embodiment of the present invention, each scattered echo signal of the ball-head cone target to be identified measured in the dual polarization mode is first obtained, and then the target scattering center polarization ratio feature is determined according to each scattered echo signal measured in the dual polarization mode. By inputting the target scattering center polarization ratio feature into a classification model generated by pre-training, the structural recognition result of the ball-head cone target can be obtained. In this solution, the target scattering center polarization ratio feature can be used to effectively improve the recognition accuracy of the ball-head cone target.

[0055] Described below Figure 1 How the various steps are performed.

[0056] For step 100:

[0057] In the embodiment of the present invention, the dual polarization mode is a horizontal transmission and horizontal reception polarization mode and a vertical transmission and vertical reception polarization mode.

[0058] It should be noted that the dual polarization mode refers to a polarization mode plus another polarization mode, such as a horizontal transmission and horizontal reception polarization mode (HH polarization) and a horizontal transmission and vertical reception polarization mode (HV polarization).

[0059] In an embodiment of the present invention, based on a study of the scattering characteristics of spherical head cone targets with different structures, the target scattering center polarization ratio characteristics obtained for spherical head cone targets with different structures in the dual polarization modes of horizontal transmission and horizontal reception polarization mode (HH polarization) and vertical transmission and vertical reception polarization mode (VV polarization) have obvious differences. Therefore, by obtaining the scattered echo signal measured for the spherical head cone target to be identified in this dual polarization mode, the obtained target scattering center polarization ratio characteristics can have a significant effect on the structural identification of the spherical head cone target, thereby improving the accuracy of identifying the structure of the spherical head cone target.

[0060] For example, the scattered echo signals of the spherical cone target to be identified measured in this dual-polarization mode are s hh (f,t) and s vv (f,t), where s hh (f,t) and s vv (f, t) represent the scattered echo signals measured under HH polarization and VV polarization, respectively, and s hh (f,t) and s vv (f, t) are power values, expressed as complex numbers.

[0061] Regarding step 102:

[0062] In some implementations, step 102 may include steps S1-S4:

[0063] Step S1, performing frequency domain analysis on the scattered echo signal corresponding to each polarization mode to obtain one-dimensional image history data corresponding to each polarization mode;

[0064] Step S2, determining the target part of the ball-head cone target to be identified;

[0065] Step S3, respectively extracting the time domain signals corresponding to the local scattering centers of the target in various polarization modes from the one-dimensional image history data corresponding to each polarization mode;

[0066] Step S4, determining the polarization ratio characteristics of the target scattering center according to the time domain signals corresponding to the target local scattering centers under various polarization modes.

[0067] For example, the scattered echo signal s measured under HH polarization and VV polarization in step 100 hh (f,t) and s vv (f, t) are respectively subjected to inverse fast Fourier transform in the frequency dimension to obtain the one-dimensional image history data s corresponding to each polarization mode hh (r,t) and s vv (r, t); In this embodiment, the target part is the tail of the spherical cone target, so from each one-dimensional image history data s hh (r,t) and svv (r, t), the time domain signal s corresponding to the tail scattering center under various polarization modes can be extracted respectively. hh_sc (t) and s vv_sc (t), and then according to the time domain signal s corresponding to the tail scattering center in various polarization modes hh_sc (t) and s vv_sc (t), the polarization ratio characteristics of the target scattering center can be determined.

[0068] It should be noted that the target part can be the tail of the spherical head cone target or the head of the spherical head cone target. The specific needs need to be determined according to the local position of the different structures of the spherical head cone target. Therefore, there is no specific limitation on the target part.

[0069] In some implementations, step S3 may include:

[0070] According to the one-dimensional image history data and the local scattering characteristics of the target, the distance range corresponding to the local scattering center of the target in each polarization mode is determined;

[0071] According to the distance range and one-dimensional image history data corresponding to the local scattering center of the target in each polarization mode, the time domain signal corresponding to the local scattering center of the target in each polarization mode is determined.

[0072] For example, if Figure 2 The figure shows a one-dimensional image history diagram generated by one-dimensional image history data of the spherical head cone target to be identified under HH polarization. It can be seen that there are two intersecting curves in the figure, and these two curves are the distance distribution of the tail and head scattering centers in the one-dimensional image. According to the scattering characteristics of each part of the spherical head cone target, when the azimuth angle is between 0-80 degrees, the distance of the tail scattering center of the spherical head cone target in the one-dimensional image history diagram is higher than that of the head, and according to the study of the scattering characteristics of the spherical head cone target, the target scattering center polarization ratio feature generated by the time domain signal corresponding to the tail scattering center with an azimuth angle between 0-80 degrees is better in classification and identification. Therefore, the target part confirmed in this embodiment is the tail, and it can be based on Figure 2 It is determined that the distance range corresponding to the tail scattering center of the spherical head cone target to be identified between 0-80 degrees azimuth under HH polarization is 0 to negative 0.8. Then, according to the distance range corresponding to the tail scattering center under each polarization mode and the one-dimensional image history data, the time domain signal corresponding to the tail scattering center under each polarization mode can be extracted.

[0073] In some embodiments, since the scattering center is a point with higher scattering intensity in the range image, by determining the maximum value and extracting the peak point in its corresponding distance range, data on the time domain variation of the scattering center intensity (i.e., the time domain signal corresponding to the scattering center) can be obtained.

[0074] It should be noted that there are at least two methods for determining the distance range. One is to determine the distance range based on the fact that the distance of the tail scattering center in the one-dimensional image history diagram is higher than the distance of the head scattering center when the azimuth angle is between 0-80 degrees as described above. The other is to determine the distance range based on the fact that the distance line of the tail scattering center in the one-dimensional image history diagram has a double image.

[0075] In some implementations, step S4 may include:

[0076] The time domain signals corresponding to the local scattering centers of the target in various polarization modes are divided to obtain the polarization ratio characteristics of the target scattering centers.

[0077] For example, assume that the time domain signal corresponding to the tail scattering center measured under HH polarization and VV polarization obtained in step S3 is s hh_sc (t) and s vv_sc (t), then we can take s hh_sc (t) / s vv_sc The ratio of (t) is determined as the polarization ratio characteristic of the target scattering center.

[0078] Regarding step 104:

[0079] Next, the construction method of the classification model is explained in detail.

[0080] In some embodiments, the classification model is constructed as follows:

[0081] Determine the azimuth range, broadband sweep range, dual polarization mode and structural type of spherical cone targets for radar measurement;

[0082] According to the preset angle interval, the preset frequency interval, the azimuth angle range, and the broadband sweep frequency range, the sample echo signal of the spherical head cone target of each structural type in the dual polarization mode is obtained;

[0083] According to the sample echo signals of the spherical head cone target of each structural type in the dual polarization mode, the sample scattering center polarization ratio characteristics of the spherical head cone target of each structural type are determined;

[0084] Downsampling the polarization ratio characteristics of the sample scattering center;

[0085] The downsampled sample scattering center polarization ratio features are input into the support vector machine to obtain the classification model.

[0086] For example, it can be determined that the azimuth range of radar measurement is 0° to 180°, the broadband sweep frequency range is 9 to 11 GHz, the dual polarization modes are HH polarization and VV polarization, and the structural types of spherical head cone targets are right-angle bottom spherical head cone targets and arc bottom spherical head cone targets. Figure 3and Figure 4 , which are the right-angle bottom ball head cone target model diagram and the arc bottom ball head cone target model diagram respectively.

[0087] Using a single-station radar with a broadband sweep frequency range of 9 to 11 GHz, echo measurements are performed on the two types of spherical head cone targets from various angles according to a preset angular interval of 0.1°. Then, sample echo signals of the right-angle bottom spherical head cone target and the arc bottom spherical head cone target in dual polarization mode are generated according to the preset frequency interval. 1hh (f,t),s 1vv (f,t),s 2hh (f,t) and s 2vv (f, t), where 1 represents a right angle base and 2 represents a circular arc base.

[0088] Then, according to the method of step 102, s 1hh (f,t),s 1vv (f,t),s 2hh (f,t) and s 2vv (f, t) are respectively subjected to fast Fourier transform in frequency dimension and converted into one-dimensional image history data s 1hh (r,t),s 1vv (r,t),s 2hh (r,t) and s 2vv (r, t), then, according to the one-dimensional image history data and the scattering characteristics of the tail, determine the distance range corresponding to the tail scattering center of each spherical head cone target in each polarization mode. Then, according to the distance range corresponding to the tail scattering center of each spherical head cone target in each polarization mode and the one-dimensional image history data, determine the time domain signal corresponding to the tail scattering center of each spherical head cone target in each polarization mode, that is, s 1hh_sc (t), s 1vv_sc (t), s 2hh_sc (t) and s 2vv_sc (t). Figure 5 It is the time domain signal diagram corresponding to the tail scattering center of the right-angle bottom spherical nose cone target. In the figure, the dotted line is the time domain signal under HH polarization, and the solid line is the time domain signal under VV polarization; Figure 6 The time domain signal diagram corresponding to the tail scattering center of the arc-bottom spherical nose cone target. In the figure, the dotted line is the time domain signal under HH polarization, and the solid line is the time domain signal under VV polarization. Figure 5 and Figure 6 It can be seen that the time domain signals corresponding to the tail scattering centers of the two spherical head cone targets under HH polarization and VV polarization are significantly different.

[0089] According to the time domain signal s of the right-angle bottom spherical cone target under HH polarization and VV polarization 1hh_sc (t) and s 1vv_sc(t), the sample scattering center polarization ratio characteristic S of the right-angle bottom spherical head cone target can be calculated according to the following formula 1_pr (t):

[0090]

[0091] Similarly, according to the time domain signal s of the arc bottom spherical head cone target under HH polarization and VV polarization 2hh_sc (t) and s 2vv_sc (t), the sample scattering center polarization ratio characteristic S of the arc-bottom spherical head cone target can be calculated according to the following formula 2_pr (t):

[0092]

[0093] like Figure 7 The figure is a comparison diagram of the polarization ratio characteristics of the sample scattering center of two spherical head cone targets at different azimuths. The dotted line corresponds to the arc base, and the solid line corresponds to the right-angle base. The polarization ratio characteristics of the sample scattering center of the two spherical head cone targets are obviously different.

[0094] It can be seen that the sample scattering center polarization ratio feature extracted by the embodiment of the present invention has a good effect on the classification and recognition of spherical head cone targets with different structures. Therefore, in order to reduce the training samples and reduce the training time of the support vector machine, the sample scattering center polarization ratio feature S of the right-angle bottom spherical head cone target can be extracted. 1_pr (t) and the sample scattering center polarization ratio characteristic S of the arc-bottom spherical head cone target 2_pr (t) is downsampled, and then the downsampled sample scattering center polarization ratio feature is input into the support vector machine to generate a classification decision threshold and obtain a classification model.

[0095] Specifically, the target scattering center polarization ratio feature of the spherical head cone target to be identified in the dual polarization mode obtained in step 102 is input into the classification model constructed according to the above construction method, and the structural recognition result of the spherical head cone target can be obtained.

[0096] like Figure 8 As shown, it is the classification result of inputting the un-downsampled test set into the classification model. In summary, it can be seen that this scheme can effectively improve the structural recognition accuracy of the ball-head cone target, and thus can improve the recognition accuracy of the ball-head cone target.

[0097] like Fig. 9 , Fig.10 As shown, an embodiment of the present invention provides a structure recognition device for a ball-head cone target. The device embodiment can be implemented by software, or by hardware or a combination of software and hardware. From the hardware level, Fig. 9As shown, it is a hardware architecture diagram of a computing device where a structure recognition device for a ball-head cone target provided by an embodiment of the present invention is located. Fig. 9 In addition to the processor, memory, network interface, and non-volatile memory shown in the figure, the computing device in which the device is located in the embodiment may also generally include other hardware, such as a forwarding chip responsible for processing messages, etc. Taking software implementation as an example, Fig.10 As shown, as a device in a logical sense, the CPU of the computing device in which it is located reads the corresponding computer program in the non-volatile memory into the internal memory and runs it.

[0098] like Fig.10 As shown, the present embodiment provides a structure recognition device for a ball-head cone target, comprising:

[0099] An acquisition unit 1001 is used to acquire each scattered echo signal measured by a spherical cone target to be identified in a dual polarization mode;

[0100] A determination unit 1002 is used to determine a target scattering center polarization ratio feature according to each scattered echo signal measured in a dual polarization mode;

[0101] The recognition unit 1003 is used to input the target scattering center polarization ratio feature into the pre-trained classification model to obtain the structural recognition result of the spherical head cone target.

[0102] In one embodiment of the present invention, in the acquisition unit 1001, the dual polarization mode is a horizontal transmission and horizontal reception polarization mode and a vertical transmission and vertical reception polarization mode.

[0103] In one embodiment of the present invention, the determining unit 1002 is configured to execute:

[0104] Perform frequency domain analysis on the scattered echo signal corresponding to each polarization mode to obtain the one-dimensional image history data corresponding to each polarization mode;

[0105] Determine the target part of the spherical cone target to be identified;

[0106] From the one-dimensional image history data corresponding to each polarization mode, the time domain signals corresponding to the local scattering center of the target in various polarization modes are extracted respectively;

[0107] According to the time domain signals corresponding to the local scattering centers of the targets under various polarization modes, the polarization ratio characteristics of the target scattering centers are determined.

[0108] In one embodiment of the present invention, when the determination unit 1002 extracts the time domain signals corresponding to the local scattering centers of the target in various polarization modes from the one-dimensional image history data corresponding to each polarization mode, it is configured to perform:

[0109] According to the one-dimensional image history data and the local scattering characteristics of the target, the distance range corresponding to the local scattering center of the target in each polarization mode is determined;

[0110] According to the distance range and one-dimensional image history data corresponding to the local scattering center of the target in each polarization mode, the time domain signal corresponding to the local scattering center of the target in each polarization mode is determined.

[0111] In one embodiment of the present invention, when determining the target scattering center polarization ratio feature according to the time domain signal corresponding to the target local scattering center under various polarization modes, the determining unit 1002 is used to perform:

[0112] The time domain signals corresponding to the local scattering centers of the target in various polarization modes are divided to obtain the polarization ratio characteristics of the target scattering centers.

[0113] In one embodiment of the present invention, in the determination unit 1002, the target part is the tail of the spherical cone target.

[0114] In one embodiment of the present invention, in the recognition unit 1003, the classification model is constructed in the following manner, including:

[0115] Determine the azimuth range, broadband sweep range, dual polarization mode and structural type of spherical cone targets for radar measurement;

[0116] According to the preset angle interval, the preset frequency interval, the azimuth angle range, and the broadband sweep frequency range, the sample echo signal of the spherical head cone target of each structural type in the dual polarization mode is obtained;

[0117] According to the sample echo signals of the spherical head cone target of each structural type in the dual polarization mode, the sample scattering center polarization ratio characteristics of the spherical head cone target of each structural type are determined;

[0118] Downsampling the polarization ratio characteristics of the sample scattering center;

[0119] The downsampled sample scattering center polarization ratio features are input into the support vector machine to obtain the classification model.

[0120] It is to be understood that the structure illustrated in the embodiment of the present invention does not constitute a specific limitation on the structure recognition device of a ball-head cone target. In other embodiments of the present invention, a structure recognition device of a ball-head cone target may include more or fewer components than shown in the figure, or combine some components, or split some components, or arrange the components differently. The components shown in the figure may be implemented in hardware, software, or a combination of software and hardware.

[0121] The information interaction, execution process and other contents between the modules in the above-mentioned device are based on the same concept as the embodiment of the method of the present invention. For the specific contents, please refer to the description in the embodiment of the method of the present invention, and no further description is given here.

[0122] An embodiment of the present invention further provides a computing device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, a method for structural recognition of a ball-head-cone target in any embodiment of the present invention is implemented.

[0123] An embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the processor executes a method for structural recognition of a ball-head-cone target in any embodiment of the present invention.

[0124] Specifically, a system or device equipped with a storage medium can be provided, on which software program code that implements the functions of any of the above-mentioned embodiments is stored, and a computer (or CPU or MPU) of the system or device can read and execute the program code stored in the storage medium.

[0125] In this case, the program code itself read from the storage medium can realize the function of any one of the above-mentioned embodiments, and thus the program code and the storage medium storing the program code constitute a part of the present invention.

[0126] The storage medium embodiments for providing the program code include a floppy disk, a hard disk, a magneto-optical disk, an optical disk (such as CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RAM, DVD-RW, DVD+RW), a magnetic tape, a non-volatile memory card, and a ROM. Alternatively, the program code can be downloaded from a server computer by a communication network.

[0127] In addition, it should be clear that the functions of any of the above embodiments can be implemented not only by executing the program code read by the computer, but also by enabling an operating system operating on the computer to complete part or all of the actual operations based on instructions from the program code.

[0128] In addition, it can be understood that the program code read from the storage medium is written to a memory provided in an expansion board inserted into the computer or to a memory provided in an expansion module connected to the computer, and then based on the instructions of the program code, a CPU installed on the expansion board or expansion module is enabled to perform part or all of the actual operations, thereby realizing the functions of any of the above-mentioned embodiments.

[0129] It should be noted that, in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "comprise a ..." do not exclude the presence of other identical factors in the process, method, article or device including the elements.

[0130] A person of ordinary skill in the art can understand that all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiments; and the aforementioned storage medium includes: ROM, RAM, magnetic disk or optical disk, etc., various media that can store program codes.

[0131] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for structural recognition of a ball-head cone target, characterized in that: include: Acquire each scattered echo signal measured by the spherical cone target to be identified in the dual polarization mode; Determine the target scattering center polarization ratio characteristics according to each scattered echo signal measured in the dual polarization mode; Inputting the target scattering center polarization ratio feature into a pre-trained classification model to obtain a structural recognition result of a spherical cone target; The step of determining the target scattering center polarization ratio characteristic according to each scattered echo signal measured in the dual polarization mode includes: Perform frequency domain analysis on the scattered echo signal corresponding to each polarization mode to obtain the one-dimensional image history data corresponding to each polarization mode; Determine the target part of the spherical cone target to be identified; From the one-dimensional image history data corresponding to each polarization mode, the time domain signals corresponding to the local scattering center of the target in various polarization modes are extracted respectively; According to the time domain signals corresponding to the local scattering centers of the targets under various polarization modes, the polarization ratio characteristics of the target scattering centers are determined.

2. The method according to claim 1, characterized in that The dual polarization mode is a horizontal transmission and horizontal reception polarization mode and a vertical transmission and vertical reception polarization mode.

3. The method according to claim 1, characterized in that The step of extracting the time domain signals corresponding to the local scattering centers of the target in various polarization modes from the one-dimensional image history data corresponding to each polarization mode includes: Determine the distance range corresponding to the local scattering center of the target in each polarization mode according to the one-dimensional image history data and the local scattering characteristics of the target; According to the distance range and one-dimensional image history data corresponding to the local scattering center of the target in each polarization mode, the time domain signal corresponding to the local scattering center of the target in each polarization mode is determined.

4. The method according to claim 1, characterized in that: Determining the target scattering center polarization ratio feature according to the time domain signal corresponding to the target local scattering center under various polarization modes includes: The time domain signals corresponding to the local scattering centers of the target in various polarization modes are divided to obtain the polarization ratio characteristics of the target scattering centers.

5. The method according to any one of claims 1 to 4, characterized in that: The target part is the tail of the spherical cone target.

6. The method according to claim 1, characterized in that The classification model is constructed in the following way: Determine the azimuth range, broadband sweep range, dual polarization mode and structural type of spherical cone targets for radar measurement; Acquire sample echo signals of the spherical head cone target of each structural type in the dual polarization mode according to the preset angle interval, the preset frequency interval, the azimuth angle range, and the broadband sweep frequency range; According to the sample echo signals of the spherical head cone target of each structural type in the dual polarization mode, the sample scattering center polarization ratio characteristics of the spherical head cone target of each structural type are determined; Downsampling the sample scattering center polarization ratio feature; The downsampled sample scattering center polarization ratio features are input into the support vector machine to obtain the classification model.

7. A structure recognition device for a ball-head cone target, used to implement the method according to any one of claims 1 to 6, characterized in that: include: An acquisition unit, used for acquiring each scattered echo signal measured by the spherical cone target to be identified in a dual polarization mode; A determination unit, used to determine a target scattering center polarization ratio characteristic according to each scattered echo signal measured in a dual polarization mode; The recognition unit is used to input the target scattering center polarization ratio feature into a pre-trained classification model to obtain a structural recognition result of the spherical head cone target.

8. A computing device, comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the method according to any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium having a computer program stored thereon, which, when executed in a computer, causes the computer to execute the method according to any one of claims 1 to 6.

Images