Sensing target identification method and device, sensing receiving end and medium

Abstract

The invention discloses a sensing target identification method and device, a sensing receiving end and a medium, and relates to the field of wireless communication. According to the specific implementation scheme, the method comprises the following steps: sensing a sensing environment to obtain a sensing signal; acquiring a sensing periodic diagram corresponding to the sensing signal; determining a plurality of extreme points from the perceptual periodogram; screening the plurality of extreme points to obtain a target extreme point; clustering each target extreme point to obtain a target cluster; and according to the cluster center of the target cluster, identifying a sensing target in the sensing environment. Therefore, a plurality of extreme points in the perceptual periodogram can be screened to filter noise extreme points, extreme points corresponding to false perceptual targets and the like, the accuracy of perceptual target recognition can be improved, the reserved target extreme points are clustered, and the accuracy of perceptual target recognition is improved. According to the invention, the extreme points belonging to the same real sensing target can be clustered into the same cluster, and the accuracy of the number identification of the sensing target is improved.

Description

Technical Field

[0001] The present application relates to the field of wireless communication technology, and in particular to a method, device, a sensing receiving terminal and a medium for identifying a sensing target. Background Art

[0002] Currently in the synaesthesia integrated system, after receiving the perception signal, the perception receiving end can use the periodogram method to obtain the perception periodogram corresponding to the perception signal, and identify the perception target in the synaesthesia environment based on the perception periodogram.

[0003] For complex channels, there will be a large number of extreme points in the perception periodogram. Directly identifying the perception targets based on these extreme points may cause the number of identified perception targets to be much larger than the actual number of perception targets, that is, resulting in low accuracy in perception target recognition. Summary of the invention

[0004] The present application provides a method, device, a sensing receiving terminal and a medium for sensing a target.

[0005] According to one aspect of the present application, a method for identifying a perception target is provided, the method being executed by a perception receiving end, the method comprising: perceiving a synaesthesia environment to obtain a first perception signal, and acquiring a perception periodogram corresponding to the first perception signal; wherein the perception periodogram is used to indicate the correspondence between a perception parameter and a signal amplitude; determining a plurality of extreme value points from the perception periodogram, and screening the plurality of extreme value points based on the signal amplitudes of the plurality of extreme value points to obtain target extreme value points; clustering each of the target extreme value points to obtain at least one target cluster; and identifying the perception target in the synaesthesia environment according to the cluster center of the target cluster.

[0006] Optionally, the perceptual periodogram includes two dimensions, and determining a plurality of extreme points from the perceptual periodogram includes: for any point p in the perceptual periodogram ij , when the p ij The signal amplitude is greater than that located at the p ij When the signal amplitude of multiple surrounding points is ij As the extreme point; wherein 0≤i≤N i -1, 0≤j≤N j -1, N i is the number of indices in the first dimension of the two dimensions in the perceptual periodogram, N j is the number of indices in the second dimension of the two dimensions in the perceptual periodogram.

[0007] Optionally, the plurality of surrounding points satisfy any one of the following: when the p ijWhen the plurality of surrounding points are not located at the boundary of the perceptual periodogram, the plurality of surrounding points include the points corresponding to the p ij adjacent adjacent points; when the p ij is located at the first boundary of the perceptual periodogram, and the p ij When the plurality of surrounding points are not located at the vertex of the perceptual period graph, the plurality of surrounding points include the points corresponding to the p ij adjacent adjacent points and boundary points on the second boundary of the perceptual periodogram; wherein the second boundary is parallel to the first boundary, and the boundary points are adjacent to the p ij The index of one of the two dimensions is the same; when the p ij When located at the first vertex of the perceptual period graph, the plurality of surrounding points include ij adjacent adjacent points and the second vertex of the perceptual period graph; wherein the second vertex and the p ij The index of one of the two dimensions is the same.

[0008] Optionally, the screening of the multiple extreme value points based on the signal amplitudes of the multiple extreme value points to obtain a target extreme value point includes: selecting multiple second extreme value points other than the first extreme value point from the multiple extreme value points based on the signal amplitudes of the multiple extreme value points; determining a first amplitude threshold according to the average of the signal amplitudes of the multiple second extreme value points, and screening the multiple second extreme value points according to the first amplitude threshold to obtain a third extreme value point; wherein the signal amplitude of the third extreme value point is greater than the first amplitude threshold; normalizing the signal amplitude of each of the third extreme value points to obtain a normalized amplitude of each of the third extreme value points; and screening each of the third extreme value points according to a set second amplitude threshold to obtain a target extreme value point; wherein the normalized amplitude of the target extreme point is greater than the second amplitude threshold.

[0009] Optionally, the selecting a plurality of second extreme points other than the first extreme point from the plurality of extreme points based on the signal amplitudes of the plurality of extreme points comprises: for any extreme point, determining the difference between the signal amplitudes of a plurality of surrounding points located around the any extreme point; when the difference between the signal amplitudes of the plurality of surrounding points satisfies a first set condition, taking the any extreme point as the first extreme point; selecting a plurality of second extreme points other than the first extreme point from the plurality of extreme points; wherein the first set condition comprises: the number of first differences is equal to a first set number, and the number of second differences is equal to a second set number; wherein the first difference refers to a difference among the plurality of differences that is greater than a set difference threshold, the second difference refers to a difference among the plurality of differences that is less than the set difference threshold, and the first set number is greater than the second set number.

[0010] Optionally, the selecting a plurality of second extreme points other than the first extreme point from the plurality of extreme points based on the signal amplitudes of the plurality of extreme points comprises: for any extreme point, determining the rate of change of the signal amplitudes of the plurality of surrounding points respectively according to the signal amplitude of the any extreme point and the signal amplitudes of the plurality of surrounding points located around the any extreme point; when the rate of change of the signal amplitudes of the plurality of surrounding points satisfies a second set condition, taking the any extreme point as the first extreme point; selecting a plurality of second extreme points other than the first extreme point from the plurality of extreme points; wherein the second set condition comprises: the number of the first change rates is equal to the third set number, and the number of the second change rates is equal to the fourth set number; wherein the first change rate refers to a change rate among the plurality of change rates that is greater than a set ratio threshold, the second change rate refers to a change rate among the plurality of change rates that is less than the set ratio threshold, and the third set number is equal to the fourth set number.

[0011] Optionally, for any extreme point, the change rates of the signal amplitudes of the multiple surrounding points are determined respectively according to the signal amplitude of the any extreme point and the signal amplitudes of the multiple surrounding points located around the any extreme point, including: for any surrounding point, according to the first index of the any surrounding point in any dimension in the perception period diagram, determining the first perception parameter between the any extreme point and the perception receiving end; according to the second index of the any extreme point in any dimension in the perception period diagram, determining the second perception parameter between the any extreme point and the perception receiving end; determining the third difference between the first perception parameter and the second perception parameter, and determining the fourth difference between the signal amplitude of the any extreme point and the signal amplitude of the any surrounding point; and determining the change rate of the signal amplitude of the any surrounding point according to the ratio of the fourth difference to the third difference.

[0012] Optionally, clustering each of the target extreme value points to obtain at least one target cluster includes: for any target extreme value point, determining a third perceptual parameter between any target extreme value point and the perceptual receiving end according to the index of any target extreme value point under the first dimension in the perceptual period diagram; determining a fourth perceptual parameter of any target extreme value point relative to the perceptual receiving end according to the index of any target extreme value point under the second dimension in the perceptual period diagram; clustering each of the target extreme value points according to the third perceptual parameter, fourth perceptual parameter and signal amplitude corresponding to each of the target extreme value points to obtain the at least one target cluster.

[0013] Optionally, clustering each of the target extreme points according to the third perception parameter, the fourth perception parameter and the signal amplitude corresponding to each of the target extreme points to obtain the at least one target cluster includes: counting the first number of the third perception parameter and the second number of the fourth perception parameter; clustering each of the target extreme points in turn according to multiple K values ​​to obtain a clustering result corresponding to each K value; wherein the clustering result includes corresponding K value initial clusters, the third perception parameters of each target extreme point in the same initial cluster are similar, the fourth perception parameters of each target extreme point in the same initial cluster are similar, and the signal amplitudes of each target extreme point in the same initial cluster are similar; the K value is less than or equal to the maximum value of the first number and the second number; determining the target clustering result from the multiple clustering results, and taking each initial cluster in the target clustering result as the target cluster.

[0014] Optionally, identifying the perceptual targets in the synaesthesia environment according to the cluster centers of the target clusters includes: determining the number of perceptual targets in the synaesthesia environment according to the number of the target clusters; and identifying each of the perceptual targets according to the third perceptual parameter and the fourth perceptual parameter of the cluster center of each of the target clusters.

[0015] Optionally, obtaining the perception period graph corresponding to the first perception signal includes: obtaining a second perception signal sent by a perception sending end; and determining the perception period graph according to the first perception signal and the second perception signal.

[0016] Optionally, the perception sending end and the perception receiving end are located in the same communication device, and acquiring the second perception signal sent by the perception sending end includes: acquiring the second perception signal from the same communication device.

[0017] Optionally, the perception sending end and the perception receiving end are located in different communication devices, and obtaining the second perception signal sent by the perception sending end includes: obtaining the first pilot data of the perception sending end; extracting the second pilot data from the first perception signal; and restoring the first perception signal based on the first pilot data and the second pilot symbol to obtain the second perception signal.

[0018] According to another aspect of the present application, a perception receiving terminal is provided, comprising:

[0019] Memory, transceiver, processor:

[0020] A memory for storing computer programs; a transceiver for transmitting and receiving data under the control of the processor; a processor for reading the computer program in the memory and performing the following operations: perceiving a synaesthesia environment to obtain a first perception signal, and obtaining a perception periodogram corresponding to the first perception signal; wherein the perception periodogram is used to indicate the correspondence between perception parameters and signal amplitudes; determining a plurality of extreme value points from the perception periodogram, and screening the plurality of extreme value points based on the signal amplitudes of the plurality of extreme value points to obtain target extreme value points; clustering each of the target extreme value points to obtain at least one target cluster; and identifying a perception target in the synaesthesia environment according to the cluster center of the target cluster.

[0021] Optionally, the perceptual periodogram includes two dimensions, and the processor performs the step of determining a plurality of extreme points from the perceptual periodogram, specifically: for any point p in the perceptual periodogram ij , when the p ij The signal amplitude is greater than that located at the p ij When the signal amplitude of multiple surrounding points is ij As the extreme point; wherein 0≤i≤N i -1, 0≤j≤N j -1, N i is the number of indices in the first dimension of the two dimensions in the perceptual periodogram, N j is the number of indices in the second dimension of the two dimensions in the perceptual periodogram.

[0022] Optionally, the plurality of surrounding points satisfy any one of the following: when the p ij When the plurality of surrounding points are not located at the boundary of the perceptual periodogram, the plurality of surrounding points include the points corresponding to the p ij adjacent adjacent points; when the p ij is located at the first boundary of the perceptual periodogram, and the p ij When the plurality of surrounding points are not located at the vertex of the perceptual period graph, the plurality of surrounding points include the points corresponding to the p ij adjacent adjacent points and boundary points on the second boundary of the perceptual periodogram; wherein the second boundary is parallel to the first boundary, and the boundary points are adjacent to the p ij The index of one of the two dimensions is the same; when the p ij When located at the first vertex of the perceptual period graph, the plurality of surrounding points include ij adjacent adjacent points and the second vertex of the perceptual period graph; wherein the second vertex and the p ij The index of one of the two dimensions is the same.

[0023] Optionally, the processor performs screening of the multiple extreme value points based on the signal amplitudes of the multiple extreme value points to obtain a target extreme value point, specifically: based on the signal amplitudes of the multiple extreme value points, selecting multiple second extreme value points other than the first extreme value point from the multiple extreme value points; determining a first amplitude threshold according to the average of the signal amplitudes of the multiple second extreme value points, and screening the multiple second extreme value points according to the first amplitude threshold to obtain a third extreme value point; wherein the signal amplitude of the third extreme value point is greater than the first amplitude threshold; normalizing the signal amplitude of each of the third extreme value points to obtain a normalized amplitude of each of the third extreme value points; screening each of the third extreme value points according to a set second amplitude threshold to obtain a target extreme value point; wherein the normalized amplitude of the target extreme point is greater than the second amplitude threshold.

[0024] Optionally, the processor executes, based on the signal amplitudes of the multiple extreme points, selecting multiple second extreme points other than the first extreme point from the multiple extreme points, specifically: for any extreme point, determining the difference between the signal amplitudes of multiple surrounding points located around the any extreme point; when the difference between the signal amplitudes of the multiple surrounding points satisfies a first set condition, taking the any extreme point as the first extreme point; selecting multiple second extreme points other than the first extreme point from the multiple extreme points; wherein the first set condition includes: the number of first differences is equal to a first set number, and the number of second differences is equal to a second set number; wherein the first difference refers to a difference among the multiple differences that is greater than a set difference threshold, the second difference refers to a difference among the multiple differences that is less than the set difference threshold, and the first set number is greater than the second set number.

[0025] Optionally, the processor executes, based on the signal amplitudes of the multiple extreme points, selecting multiple second extreme points other than the first extreme point from the multiple extreme points, specifically: for any extreme point, according to the signal amplitude of any extreme point and the signal amplitudes of multiple surrounding points located around the any extreme point, respectively determine the change rate of the signal amplitude of the multiple surrounding points; when the change rate of the signal amplitude of the multiple surrounding points meets the second set condition, use the any extreme point as the first extreme point of the abnormality; select multiple second extreme points other than the first extreme point from the multiple extreme points; wherein the second set condition includes: the number of first change rates is equal to the third set number, and the number of second change rates is equal to the fourth set number; wherein the first change rate refers to the change rate of the multiple change rates that is greater than the set ratio threshold, the second change rate refers to the change rate of the multiple change rates that is less than the set ratio threshold, and the third set number is equal to the fourth set number.

[0026] Optionally, the processor executes, for any extreme point, determining the change rates of the signal amplitudes of the multiple surrounding points respectively according to the signal amplitude of the any extreme point and the signal amplitudes of the multiple surrounding points located around the any extreme point, specifically: for any surrounding point, determining the first perception parameter between the any surrounding point and the perception receiving end according to the first index of the any surrounding point in any dimension in the perception period diagram; determining the second perception parameter between the any extreme point and the perception receiving end according to the second index of the any extreme point in any dimension in the perception period diagram; determining the third difference between the first perception parameter and the second perception parameter, and determining the fourth difference between the signal amplitude of the any extreme point and the signal amplitude of the any surrounding point; determining the change rate of the signal amplitude of the any surrounding point according to the ratio of the fourth difference to the third difference.

[0027] Optionally, the processor performs clustering of each of the target extreme value points to obtain at least one target cluster, specifically: for any target extreme value point, according to the index of any target extreme value point under the first dimension in the perception period diagram, determine the third perception parameter between any target extreme value point and the perception receiving end; according to the index of any target extreme value point under the second dimension in the perception period diagram, determine the fourth perception parameter of any target extreme value point relative to the perception receiving end; according to the third perception parameter, fourth perception parameter and signal amplitude corresponding to each of the target extreme value points, cluster each of the target extreme value points to obtain the at least one target cluster.

[0028] Optionally, the processor performs clustering of each of the target extreme points according to the third perception parameter, the fourth perception parameter and the signal amplitude corresponding to each of the target extreme points to obtain the at least one target cluster, specifically: counting the first number of the third perception parameter and the second number of the fourth perception parameter; clustering each of the target extreme points in turn according to multiple K values ​​to obtain a clustering result corresponding to each K value; wherein the clustering result includes corresponding K value initial clusters, the third perception parameters of each target extreme point in the same initial cluster are similar, and the fourth perception parameters of each target extreme point in the same initial cluster are similar, and the signal amplitudes of each target extreme point in the same initial cluster are similar; the K value is less than or equal to the maximum value of the first number and the second number; determining the target clustering result from the multiple clustering results, and taking each initial cluster in the target clustering result as the target cluster.

[0029] Optionally, the processor executes identifying the perceptual targets in the synaesthesia environment according to the cluster centers of the target clusters, specifically: determining the number of perceptual targets in the synaesthesia environment according to the number of the target clusters; and identifying each of the perceptual targets according to the third perceptual parameter and the fourth perceptual parameter of the cluster center of each of the target clusters.

[0030] Optionally, the processor executes acquiring the perception period graph corresponding to the first perception signal, specifically: acquiring a second perception signal sent by a perception sending end; and determining the perception period graph according to the first perception signal and the second perception signal.

[0031] Optionally, the perception sending end and the perception receiving end are located in the same communication device, and the processor executes acquiring the second perception signal sent by the perception sending end, specifically: acquiring the second perception signal from the same communication device.

[0032] Optionally, the perception sending end and the perception receiving end are located in different communication devices, and the processor executes the acquisition of the second perception signal sent by the perception sending end, specifically: acquiring the first pilot data of the perception sending end; extracting the second pilot data from the first perception signal; and restoring the first perception signal based on the first pilot data and the second pilot symbol to obtain the second perception signal.

[0033] According to another aspect of the present application, a device for identifying a perception target is provided, which is applied to a perception receiving end, and includes:

[0034] A sensing unit, used to sense the synaesthesia environment and obtain a first sensing signal;

[0035] An acquisition unit, configured to acquire a perceptual periodogram corresponding to the first perceptual signal; wherein the perceptual periodogram is used to indicate a corresponding relationship between a perceptual parameter and a signal amplitude;

[0036] A processing unit, configured to determine a plurality of extreme value points from the perceptual periodogram, and screen the plurality of extreme value points based on signal amplitudes of the plurality of extreme value points to obtain a target extreme value point;

[0037] A clustering unit, used for clustering each of the target extreme value points to obtain at least one target cluster;

[0038] The identification unit is used to identify the perception target in the synaesthesia environment according to the cluster center of the target cluster.

[0039] Optionally, the perceptual periodogram includes two dimensions, and the processing unit is specifically configured to: for any point p in the perceptual periodogram ij , when the p ijThe signal amplitude is greater than that located at the p ij When the signal amplitude of multiple surrounding points is ij As the extreme point; wherein 0≤i≤N i -1, 0≤j≤N j -1, N i is the number of indices in the first dimension of the two dimensions in the perceptual periodogram, N j is the number of indices in the second dimension of the two dimensions in the perceptual periodogram.

[0040] Optionally, the plurality of surrounding points satisfy any one of the following: when the p ij When the plurality of surrounding points are not located at the boundary of the perceptual periodogram, the plurality of surrounding points include the points corresponding to the p ij adjacent adjacent points; when the p ij is located at the first boundary of the perceptual periodogram, and the p ij When the plurality of surrounding points are not located at the vertex of the perceptual period graph, the plurality of surrounding points include the points corresponding to the p ij adjacent adjacent points and boundary points on the second boundary of the perceptual periodogram; wherein the second boundary is parallel to the first boundary, and the boundary points are adjacent to the p ij The index of one of the two dimensions is the same; when the p ij When located at the first vertex of the perceptual period graph, the plurality of surrounding points include ij adjacent adjacent points and the second vertex of the perceptual period graph; wherein the second vertex and the p ij The index of one of the two dimensions is the same.

[0041] Optionally, the processing unit is specifically used to: select multiple second extreme value points other than the first extreme value point from the multiple extreme value points based on the signal amplitudes of the multiple extreme value points; determine a first amplitude threshold according to the average of the signal amplitudes of the multiple second extreme value points, and screen the multiple second extreme value points according to the first amplitude threshold to obtain a third extreme value point; wherein the signal amplitude of the third extreme value point is greater than the first amplitude threshold; normalize the signal amplitude of each of the third extreme value points to obtain a normalized amplitude of each of the third extreme value points; and screen each of the third extreme value points according to a set second amplitude threshold to obtain a target extreme value point; wherein the normalized amplitude of the target extreme point is greater than the second amplitude threshold.

[0042] Optionally, the processing unit is specifically used to: for any extreme point, determine the difference between the signal amplitudes of multiple surrounding points located around the any extreme point; when the difference between the signal amplitudes of the multiple surrounding points satisfies a first set condition, take the any extreme point as the first extreme point; select multiple second extreme points other than the first extreme point from the multiple extreme points; wherein the first set condition includes: the number of first differences is equal to the first set number, and the number of second differences is equal to the second set number; wherein the first difference refers to a difference among the multiple differences that is greater than a set difference threshold, the second difference refers to a difference among the multiple differences that is less than the set difference threshold, and the first set number is greater than the second set number.

[0043] Optionally, the processing unit is specifically used to: for any extreme point, determine the change rate of the signal amplitude of the multiple surrounding points respectively according to the signal amplitude of the any extreme point and the signal amplitude of the multiple surrounding points located around the any extreme point; when the change rate of the signal amplitude of the multiple surrounding points meets the second setting condition, take the any extreme point as the first extreme point; select multiple second extreme points other than the first extreme point from the multiple extreme points; wherein the second setting condition includes: the number of first change rates is equal to the third setting number, and the number of second change rates is equal to the fourth setting number; wherein the first change rate refers to the change rate among the multiple change rates that is greater than the set proportion threshold, the second change rate refers to the change rate among the multiple change rates that is less than the set proportion threshold, and the third setting number is equal to the fourth setting number.

[0044] Optionally, the processing unit is specifically used to: for any surrounding point, determine a first perception parameter between any surrounding point and the perception receiving end according to a first index of any surrounding point in any dimension in the perception period diagram; determine a second perception parameter between any extreme point and the perception receiving end according to a second index of any extreme point in any dimension in the perception period diagram; determine a third difference between the first perception parameter and the second perception parameter, and determine a fourth difference between the signal amplitude of any extreme point and the signal amplitude of any surrounding point; determine the rate of change of the signal amplitude of any surrounding point according to the ratio of the fourth difference to the third difference.

[0045] Optionally, the clustering unit is specifically used to: for any target extreme value point, determine the third perception parameter between any target extreme value point and the perception receiving end according to the index of any target extreme value point under the first dimension in the perception period diagram; determine the fourth perception parameter of any target extreme value point relative to the perception receiving end according to the index of any target extreme value point under the second dimension in the perception period diagram; cluster each target extreme value point according to the third perception parameter, fourth perception parameter and signal amplitude corresponding to each target extreme value point to obtain the at least one target cluster.

[0046] Optionally, the clustering unit is specifically used to: count the first number of the third perception parameters and the second number of the fourth perception parameters; cluster the target extreme points according to multiple K values ​​in turn to obtain a clustering result corresponding to each K value; wherein the clustering result includes corresponding K value initial clusters, the third perception parameters of the target extreme points in the same initial cluster are similar, and the fourth perception parameters of the target extreme points in the same initial cluster are similar, and the signal amplitudes of the target extreme points in the same initial cluster are similar; the K value is less than or equal to the maximum value of the first number and the second number; determine the target clustering result from the multiple clustering results, and use the initial clusters in the target clustering result as the target cluster.

[0047] Optionally, the identification unit is specifically used to: determine the number of perception targets in the synaesthesia environment according to the number of the target clusters; and identify each of the perception targets according to the third perception parameter and the fourth perception parameter of the cluster center of each of the target clusters.

[0048] Optionally, the acquisition unit is specifically used to: acquire a second perception signal sent by a perception sending end; and determine the perception periodogram according to the first perception signal and the second perception signal.

[0049] Optionally, the perception sending end and the perception receiving end are located in different communication devices, and the acquisition unit is specifically used to: obtain the first pilot data of the perception sending end; extract the second pilot data from the first perception signal; and restore the first perception signal based on the first pilot data and the second pilot symbol to obtain the second perception signal.

[0050] Optionally, the perception sending end and the perception receiving end are located in the same communication device, and the acquisition unit is specifically used to: acquire the second perception signal from the same communication device.

[0051] According to another aspect of the present application, a processor-readable storage medium is provided, characterized in that the processor-readable storage medium stores a computer program, and the computer program is used to enable the processor to execute the method for identifying the perceived target described in the above embodiment.

[0052] According to another aspect of the present application, a computer program product is provided, including a computer program, which, when executed by a processor, implements the method for identifying a perceived target described in the above embodiment of the present application.

[0053] The recognition method, device, perception receiving end and medium of the perception target provided by the embodiment of the present application, by perceiving the synaesthesia environment, obtain a first perception signal, and obtain the perception periodogram corresponding to the first perception signal; determine multiple extreme value points from the perception periodogram, and screen the multiple extreme value points based on the signal amplitude of the multiple extreme value points to obtain the target extreme value point; cluster each target extreme value point to obtain at least one target cluster; and identify the perception target in the synaesthesia environment according to the cluster center of the target cluster. Thus, it is possible to screen multiple extreme value points in the perception periodogram to filter out noise extreme value points, extreme value points corresponding to false perception targets, etc., which can improve the accuracy of perception target recognition, and cluster the retained target extreme value points, which can achieve the clustering of extreme value points belonging to the same real perception target into the same cluster, thereby identifying the number of perception targets according to the number of clusters obtained by clustering, which can improve the accuracy of the number of perception target recognition.

[0054] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present application.

[0056] Figure 1 It is a schematic diagram of the perceptual periodogram (two-dimensional distance-speed periodogram);

[0057] Figure 2 This is a schematic diagram of the perceptual periodogram after being processed by the extreme value method;

[0058] Figure 3 A schematic diagram of a flow chart of a method for identifying a perceived target provided in an embodiment of the present application;

[0059] Figure 4 A flowchart of another method for identifying a perceived target provided in an embodiment of the present application;

[0060] Figure 5A flowchart of another method for identifying a perceived target provided in an embodiment of the present application;

[0061] Figure 6 A flowchart of another method for identifying a perceived target provided in an embodiment of the present application;

[0062] Figure 7 A flowchart of another method for identifying a perceived target provided in an embodiment of the present application;

[0063] Figure 8 A flowchart of another method for identifying a perceived target provided in an embodiment of the present application;

[0064] Fig. 9 A schematic diagram of the structure of a sensing receiving terminal provided in an embodiment of the present application;

[0065] Fig.10 A schematic diagram of the structure of a target recognition device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0066] In the embodiments of the present application, the term "and / or" describes the association relationship of the associated objects, indicating that three relationships may exist. For example, A and / or B may represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the associated objects before and after are in an "or" relationship.

[0067] In the embodiments of the present application, the term "plurality" refers to two or more than two, and other quantifiers are similar.

[0068] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0069] The periodogram method is a typical perception and reception algorithm in the current synaesthesia integrated system. Due to its simple calculation and easy implementation, it is a strong competitor for the perception and reception algorithm of the fifth-generation mobile communication technology (Beyound 5G, referred to as B5G) and the future 6G.

[0070] After receiving the perception signal, the perception receiving end can use the periodogram method to obtain the perception periodogram corresponding to the perception signal (such as a two-dimensional distance-speed periodogram, a two-dimensional distance-angle periodogram), for example, by performing corresponding inverse fast Fourier transform (IFFT) or fast Fourier transform (FFT) on different dimensions to obtain the perception periodogram. In general, IFFT can be performed on the frequency domain to obtain distance information, FFT can be performed on the time domain to obtain speed information, and FFT can be performed on the spatial domain to obtain angle information.

[0071] The perceptual periodogram is a two-dimensional distance-speed periodogram for exemplary explanation. Each point in the perceptual periodogram contains three elements, namely, distance (i.e., the distance or relative distance between the perceptual target and the perceptual receiving end), speed (i.e., the relative speed or relative radial speed between the perceptual target and the perceptual receiving end), and signal amplitude. Assume that the number of IFFT points corresponding to the distance dimension of the perceptual periodogram is N IFFT , the number of FFT points corresponding to the velocity dimension is N FFT , then the point p with distance index i and speed index j ij The corresponding signal amplitude is A ij , 0≤i≤N IFFT -1, 0≤j≤N FFT -1, the point p ij The corresponding distance R i (i.e. point p ij The relative distance to the sensing receiver) and the speed v j (i.e. point p ij The relative speed or relative radial speed between the sensing receiving end is:

[0072]

[0073]

[0074] Where c represents the speed of light (3*10 8 , in meters per second), Δf represents the subcarrier spacing (120,000, in Hertz Hz), T s (1.0417*10 -5 , in seconds) represents the duration of an orthogonal frequency division multiplexing (OFDM) symbol, and λ represents the wavelength (0.03, in meters).

[0075] As an example, a perceptual periodogram can be Figure 1As shown, Figure 1 The perceptual periodogram shown is a periodogram obtained after passing through a tapped delay line (TDL) channel and being processed by the periodogram method. The horizontal axis of the perceptual periodogram corresponds to the distance dimension, and the vertical axis corresponds to the speed dimension. Different colors in the perceptual periodogram correspond to signal amplitudes at different points.

[0076] Depend on Figure 1 It can be seen that the human eye can clearly see that there are 5 bright spots, corresponding to the 5 real perception targets of the initial configuration, but the computer cannot directly distinguish these 5 bright spots from other points like the human eye. Figure 1 In total, we can find the extreme points Figure 2 The 18 extreme points shown, especially the intersection of the horizontal axis and the vertical axis of every two real perceived targets, will have new bright spots (extreme points), which are false perceived targets caused by the side lobes of the real perceived targets. In addition to the false perceived targets caused by the side lobes at the intersections, there will also be extreme points in the side lobes where the real perceived targets do not intersect with other real perceived targets, which is another false perceived target caused by the side lobes.

[0077] in, Figure 2 The “*” in represents the extreme value point obtained by the extreme value method at the perception receiving end, and “○” represents the real perception target.

[0078] In addition, for complex channels, such as the Clustered Delay Line (CDL) channel, when a cluster (a set of multipaths with similar arrival angles, departure angles, and delays) exists as a perception target, since a cluster's multipath set contains multiple sub-paths, a real perception target will generate multiple corresponding extreme points in the perception periodogram. These extreme points are different from the false perception targets caused by side lobes, and are all extreme points corresponding to real perception targets. However, the existence of these extreme points will cause the number of estimated perception targets to be much larger than the number of real perception targets, which will also cause trouble in the identification of real perception targets.

[0079] In summary, the related technology has at least the following disadvantages:

[0080] 1. After obtaining the perceptual periodogram using the periodogram method, the computer cannot directly distinguish the real perceptual target from the false perceptual target caused by the side lobes of the real perceptual target like the human eye;

[0081] 2. When performing multi-target recognition in a complex synaesthesia environment, a real perceived target may have multiple corresponding extreme points, further causing inaccurate multi-target recognition.

[0082] Therefore, in order to solve at least one of the above-mentioned problems, an embodiment of the present application provides a method, device, perception receiving end and medium for identifying a perception target, wherein the method and the device are based on the same application concept. Since the principles of solving the problems by the method and the device are similar, the implementation of the device and the method can refer to each other, and the repeated parts will not be repeated.

[0083] The following is a description of the method, device, receiving terminal and medium for identifying a sensing target provided by the present application with reference to the accompanying drawings. Before describing the embodiments of the present application in detail, for ease of understanding, the commonly used technical terms are first introduced:

[0084] The synaesthesia environment refers to the perception environment, that is, the set of all scatterers that the perception signal experiences on the way from the perception sending end to the perception receiving end. For example, taking the identification of perception targets under smart transportation as an example, the synaesthesia environment can include vehicles, pedestrians, road infrastructure, obstacles, animals and other objects in road traffic that may affect the perception signal.

[0085] It should be noted that the method for identifying a perception target provided in the present disclosure can be applicable to a synaesthesia channel or a communication channel, and can also be applicable to a synaesthesia environment. This application only uses the method applied to a synaesthesia environment as an example.

[0086] Clustering refers to dividing a data set into different classes or clusters (referred to as clusters in this application) according to a specific standard (such as distance), so that the similarities between data objects in the same cluster (or clusters) are as large as possible, and the differences between data objects in different clusters (or clusters) are as large as possible. That is, after clustering, data objects belonging to the same class are gathered together as much as possible, and data objects of different classes are separated as much as possible.

[0087] The center of a cluster (or clustering) refers to the most representative point in the cluster, which can make any object in the cluster closer to the center of the cluster than the centers of other clusters. For example, the center of a cluster can be the average value or center point of all the points in the cluster.

[0088] Target clustering refers to the clusters or clusters obtained by clustering each target extreme point.

[0089] The cluster center refers to the center of the target cluster (also called the centroid, center of gravity or center point).

[0090] The number of indexes under the first dimension refers to the total number of indexes contained in the first dimension of the perceptual periodogram. For example, when the first dimension is the distance dimension, the number of indexes under the first dimension refers to the total number of distance indexes contained in the distance dimension of the perceptual periodogram, that is, the number of IFFT points N corresponding to the distance dimension in the perceptual periodogram.IFFT .like Figure 1 As shown, the number of indices in the horizontal distance dimension is 1024, and the distance size of each horizontal grid (i.e., the distance length between two adjacent distance indices) △R is Meters, the horizontal distance range is [0,1.2207*1024=1250 meters].

[0091] The number of indexes under the second dimension refers to the total number of indexes contained in the second dimension of the perceptual periodogram. For example, when the second dimension is the speed dimension, the number of indexes under the second dimension refers to the total number of speed indexes contained in the speed dimension of the perceptual periodogram, that is, the number of FFT points N corresponding to the speed dimension in the perceptual periodogram. FFT .like Figure 1 As shown, the number of indexes in the vertical velocity dimension is 140, and the velocity magnitude of each vertical grid (i.e., the velocity magnitude between two adjacent velocity indexes) △v is Meters / second. Since the longitudinal velocity value is signed with positive and negative signs, that is, the velocity dimension has 70 positive velocity indexes and 70 negative velocity indexes, the velocity value range is [-10.2854*70 meters / second, 10.2854*70 meters / second] = [-720 meters / second, 720 meters / second].

[0092] It should be noted that the two-dimensional perceptual periodogram is rectangular and includes four boundaries, and the intersection of two adjacent boundaries is the vertex of the perceptual periodogram.

[0093] Boundary points refer to points located on the boundary of the perceptual periodogram.

[0094] The initial cluster refers to an initial cluster obtained by clustering multiple target extreme value points according to the K value. Correspondingly, the target cluster may be a cluster selected from the initial cluster and finally used to identify the perceived target.

[0095] Figure 3 A flowchart of a method for identifying a perceived target provided in an embodiment of the present application.

[0096] The method for identifying a perception target in the embodiment of the present application may be executed by a perception receiving end.

[0097] It should be noted that in different application scenarios, the perception receiving end may be different. For example, in a smart transportation scenario, the perception receiving end may be an access network device, a roadside unit, a vehicle, etc. In a smart factory scenario, the perception receiving end may be a fixed device, a movable device, etc. in the smart factory. The embodiments of the present application do not limit this.

[0098] Herein, the access network device is taken as an example as a base station. The base station may include multiple cells that provide services for the terminal device. Depending on the specific application scenario, the base station may also be called an access point, or may be a device in the access network that communicates with the wireless terminal device through one or more sectors on the air interface, or other names. The access network device may be used to interchange received air frames with Internet Protocol (IP) packets, and serve as a router between the wireless terminal device and the rest of the access network, wherein the rest of the access network may include an Internet Protocol (IP) communication network. The access network device may also coordinate the attribute management of the air interface. For example, the access network device involved in the embodiments of the present application may be an access network device (Base TransceiverStation, BTS) in the Global System for Mobile communications (GSM) or Code Division Multiple Access (CDMA), or an access network device (NodeB) in Wide-band Code Division Multiple Access (WCDMA), or an evolutionary access network device (eNB or e-NodeB) in the long term evolution (LTE) system, a 5G base station (gNB) in the 5G network architecture (next generation system), or a home evolved Node B (HeNB), a relay node, a home base station (femto), a pico base station (pico), etc., which is not limited in the embodiments of the present application. In some network structures, the access network device may include a centralized unit (CU) node and a distributed unit (DU) node, and the centralized unit and the distributed unit may also be arranged geographically separately.

[0099] The terminal device may be a device that provides voice and / or data connectivity to a user, a handheld device with a wireless connection function, or other processing devices connected to a wireless modem. In different systems, the names of the terminal devices may also be different. For example, in a 5G system, the terminal device may be called a user equipment (UE). The wireless terminal device may communicate with one or more core networks (CN) via a radio access network (RAN). The wireless terminal device may be a mobile terminal device, such as a mobile phone (or "cellular" phone) and a computer with a mobile terminal device. For example, it may be a portable, pocket-sized, handheld, computer-built-in or vehicle-mounted mobile device that exchanges language and / or data with a wireless access network. For example, personal communication service (PCS) phones, cordless phones, session initiation protocol (SIP) phones, wireless local loop (WLL) stations, personal digital assistants (PDA) and other devices. The wireless terminal device may also be referred to as a system, a subscriber unit, a subscriber station, a mobile station, a mobile station, a remote station, an access point, a remote terminal device, an access terminal device, a user terminal device, a user agent, and a user device, but is not limited in the embodiments of the present application.

[0100] like Figure 3 As shown, the method for identifying the perceived target may include the following steps:

[0101] Step S301, sensing the synaesthesia environment, obtaining a first perception signal, and acquiring a perception periodogram corresponding to the first perception signal.

[0102] In the embodiment of the present application, the perceptual periodogram is used to indicate the corresponding relationship between the perceptual parameter and the signal amplitude. The perceptual parameter may include but is not limited to distance (i.e., the relative distance between a point in the perceptual periodogram and the perceptual receiving end), speed (i.e., the relative speed or relative radial speed between a point in the perceptual periodogram and the perceptual receiving end), and angle (i.e., the relative angle between a point in the perceptual periodogram and the perceptual receiving end).

[0103] As an example, taking the perceptual periodogram as a one-dimensional periodogram, the perceptual periodogram can be used to indicate the corresponding relationship between a perceptual parameter of one dimension (such as one of distance, speed, and angle) and a signal amplitude.

[0104] As another example, the perceptual periodogram is taken as a two-dimensional periodogram, and the perceptual periodogram can be used to indicate the correspondence between the perceptual parameters and the signal amplitude in two dimensions. For example, the perceptual periodogram can be a distance-speed periodogram (i.e., the two dimensions are the distance dimension and the speed dimension), a distance-angle periodogram (i.e., the two dimensions are the distance dimension and the angle dimension), and a ZOA (Zenith of Arrival, vertical angle of arrival)-AOA (Angle of Arrival, horizontal angle of arrival) periodogram (i.e., the two dimensions are the vertical angle of arrival dimension and the horizontal angle of arrival dimension).

[0105] In an embodiment of the present application, the perception receiving end can perceive the synaesthesia environment, obtain a perception signal (referred to as a first perception signal in the present application), and use a periodogram method to obtain a perception periodogram corresponding to the first perception signal.

[0106] Step S302, determining a plurality of extreme value points from the perceptual periodogram, and screening the plurality of extreme value points based on signal amplitudes of the plurality of extreme value points to obtain a target extreme value point.

[0107] In an embodiment of the present application, multiple extreme value points can be identified or determined from the perceptual periodogram, and based on the signal amplitudes of the multiple extreme value points, the multiple extreme value points are screened to obtain the retained target extreme value points.

[0108] For example, based on the signal amplitudes of multiple extreme points, it is possible to screen out extreme points caused by side lobes where the real perceived target does not intersect with other real perceived targets, noise extreme points, extreme points caused by side lobes where the real perceived target intersects with other real perceived targets, and the like.

[0109] Step S303: clustering each target extreme point to obtain at least one target cluster.

[0110] In an embodiment of the present application, each target extreme point can be clustered based on a clustering algorithm (including but not limited to a k-means clustering algorithm, a density-based clustering algorithm (Density-Based Spatial Clustering of Applications with Noise, DBSCAN for short), etc.) to obtain at least one target cluster.

[0111] Step S304: identifying the perceived target in the synaesthesia environment according to the cluster center of the target cluster.

[0112] It should be noted that the perception targets may be different in different application scenarios. For example, in smart transportation scenarios, the perception targets may be vehicles, pedestrians, animals (such as pets), objects (such as roadblocks, garbage, etc.), etc. In smart factory scenarios, the perception targets may be movable robots / robotic arms, products, other equipment, etc.

[0113] In the embodiment of the present application, the perception target in the synaesthesia environment can be identified according to the cluster center of each target cluster.

[0114] As an example, the number of perceptual targets in the synaesthesia environment can be determined according to the number of target clusters, that is, the number of perceptual targets is equal to the number of target clusters, and each perceptual target can be identified according to the perceptual parameter corresponding to the cluster center of each target cluster.

[0115] The method for identifying the perceived target of the embodiment of the present application is to perceive the synaesthesia environment to obtain a first perceived signal, and obtain a perceived periodogram corresponding to the first perceived signal; determine multiple extreme points from the perceived periodogram, and screen the multiple extreme points based on the signal amplitudes of the multiple extreme points to obtain target extreme points; cluster each target extreme point to obtain at least one target cluster; and identify the perceived target in the synaesthesia environment according to the cluster center of the target cluster. Thus, it is possible to screen multiple extreme points in the perceived periodogram to filter out noise extreme points, extreme points corresponding to false perceived targets, etc., which can improve the accuracy of perceived target recognition, and cluster the retained target extreme points to cluster the extreme points belonging to the same real perceived target into the same cluster, thereby identifying the number of perceived targets according to the number of clusters obtained by clustering, which can improve the accuracy of the number of perceived targets.

[0116] Figure 4 A flowchart of another method for identifying a perceived target provided in an embodiment of the present application.

[0117] like Figure 4As shown, the method for identifying the perception target can be executed by the perception receiving end, and may include the following steps:

[0118] Step 401, perceive the synaesthesia environment, obtain a first perception signal, and acquire a perception periodogram corresponding to the first perception signal.

[0119] The perceptual periodogram includes two dimensions, and is used to indicate the corresponding relationship between the perceptual parameters and the signal amplitude in the two dimensions.

[0120] For example, when the two dimensions are the distance dimension and the angle dimension, the perceptual periodogram is used to indicate the corresponding relationship between the distance, angle and signal amplitude.

[0121] Step S401 can be implemented in any way in the embodiments of the present application, and the embodiments of the present application do not limit this and will not be described in detail.

[0122] Step S402: for any point p in the perceptual periodic graph ij , when p ij The signal amplitude is greater than that at p ij When the signal amplitude of multiple surrounding points is ij as an extreme point.

[0123] Where 0≤i≤N i -1, 0≤j≤N j -1,N i is the number of indices in the first of the two dimensions in the perceptual periodogram, N j is the number of indices under the second of the two dimensions in the perceptual periodogram.

[0124] In the embodiment of the present application, for any point p in the perception period graph, ij First, we can determine the ij Multiple surrounding points around.

[0125] As an example, when p ij When it is not at the boundary of the perceptual periodogram, that is, 1≤i≤N i -2, 1≤j≤N j -2, at the p ij The surrounding points include the ij Adjacent adjacent points.

[0126] For example, in the p ij The surrounding points include: (i-1)j 、p (i+1)j 、p i(j-1) 、p i(j+1) These four adjacent points.

[0127] As another example, when p ij Located at the boundary of the perceptual periodogram (referred to as the first boundary in this application), and p ij When not at the vertex of the perceptual period graph, it is at the p ij The surrounding points include the ij adjacent adjacent points and boundary points on the second boundary of the perceptual periodic graph; wherein the second boundary is parallel to the first boundary, and the boundary point is adjacent to p ij The index of one of the two dimensions is the same.

[0128] For example, when i = 0 and 1 ≤ j ≤ N j -2, at p ij The surrounding points include: (i+1)j 、p i(j-1) 、p i(j+1) These three adjacent points, and jump to the boundary i=N relative to i=0 i Points on -1

[0129] As another example, when p ij When it is located at the vertex of the perceptual period graph (referred to as the first vertex in this application), it is located at the p ij The surrounding points include the ij adjacent adjacent points and the second vertex of the perceptual period graph; wherein the second vertex is related to p ij The index of one of the two dimensions is the same.

[0130] For example, when i=0 and j=0, the ij The surrounding points include: (i+1)j 、p i(j+1) These two adjacent points, and jump to the boundary i=N relative to i=0 i Points on -1 and jump to the boundary j=N relative to j=0 j Points on -1

[0131] In the embodiment of the present application, it can be determined that p ij Is the signal amplitude greater than the signal amplitude of multiple surrounding points? ij When the signal amplitude of each point is greater than the signal amplitude of multiple surrounding points, the p ij As the extreme point, at this p ij When the signal amplitude of the p is less than or equal to the signal amplitude of multiple surrounding points, it is not necessary to ij as an extreme point.

[0132] Step S403 , screening multiple extreme value points based on the signal amplitudes of the multiple extreme value points to obtain a target extreme value point.

[0133] Step S404: clustering each target extreme point to obtain at least one target cluster.

[0134] Step S405 , identifying the perceived target in the synaesthesia environment according to the cluster center of the target cluster.

[0135] Steps S403 to S405 may be implemented in any manner in the embodiments of the present application, and the embodiments of the present application do not limit this and will not be described in detail.

[0136] The method for identifying the perception target of the embodiment of the present application can accurately identify each extreme point from the perception periodogram according to the signal amplitude of each point in the perception periodogram.

[0137] Figure 5 A flowchart of another method for identifying a perceived target provided in an embodiment of the present application.

[0138] like Figure 5 As shown, the method for identifying the perception target can be executed by the perception receiving end, and may include the following steps:

[0139] Step S501, sensing a synaesthesia environment, obtaining a first sensing signal, and acquiring a sensing periodogram corresponding to the first sensing signal.

[0140] The perceptual periodogram is used to indicate the corresponding relationship between the perceptual parameters and the signal amplitude.

[0141] Step S502, determining a plurality of extreme value points from the perceptual periodogram.

[0142] Steps S501 to S502 may be implemented in any manner in the embodiments of the present application, and the embodiments of the present application do not limit this and will not be described in detail.

[0143] Step S503: selecting a plurality of second extreme value points other than the first extreme value point from the plurality of extreme value points based on the signal amplitudes of the plurality of extreme value points.

[0144] In the embodiment of the present application, based on the signal amplitudes of the multiple extreme value points, the abnormal first extreme value points can be eliminated from the multiple extreme value points to obtain the retained multiple second extreme value points.

[0145] In a possible implementation of the embodiment of the present application, the first extreme point is identified, for example, as follows: for any one of the multiple extreme points, the difference between the signal amplitudes of the multiple surrounding points located around the extreme point can be calculated. For example, for any two surrounding points, the difference between the signal amplitudes of the two surrounding points, the absolute value of the difference, the square of the difference, etc. can be used as the difference between the signal amplitudes of the two surrounding points. Afterwards, it can be determined whether the difference between the signal amplitudes of the multiple surrounding points meets the first set condition. If the difference between the signal amplitudes of the multiple surrounding points meets the first set condition, the extreme point is taken as an abnormal first extreme point. If the difference between the signal amplitudes of the multiple surrounding points does not meet the first set condition, there is no need to take the extreme point as an abnormal first extreme point.

[0146] Among them, the first set condition may include: the number of first differences is equal to the first set number, and the number of second differences is equal to the second set number; wherein the first difference refers to a difference in the signal amplitudes of multiple surrounding points that is greater than a set difference threshold, and the second difference refers to a difference in the signal amplitudes of multiple surrounding points that is less than a set difference threshold, and the first set number is greater than the second set number.

[0147] For example, the difference threshold is set to σ1, the number of surrounding points is 4, and the perceptual periodogram includes two dimensions. The signal amplitudes of the four surrounding points of any extreme point can be subtracted two by two, and the absolute value is taken to obtain There are 6 differences, among which two values ​​of the 6 differences are differences in the same dimension, and the other four values ​​are differences in different dimensions. Two values ​​of the 6 differences are much smaller than the other 4 values. Therefore, it can be judged whether there are 4 (the first set number) differences greater than σ1 and 2 (the second set number) differences less than σ1 among the 6 differences. If so, any extreme point is taken as the first extreme point. If not (for example, 3 differences are greater than σ1 and 3 differences are less than σ1), there is no need to take any extreme point as the first extreme point.

[0148] In another possible implementation of the embodiment of the present application, the method for identifying the first extreme point is, for example, as follows: for any extreme point among multiple extreme points, the rate of change of the signal amplitudes of the multiple surrounding points can be determined respectively based on the signal amplitude of the any extreme point and the signal amplitudes of the multiple surrounding points located around the any extreme point.

[0149] As an example, for any one of the multiple surrounding points, the first perception parameter between the surrounding point and the perception receiving end can be determined according to the first index of the surrounding point in any dimension in the perception period map. For example, when the any dimension is a distance dimension, the first perception parameter can be a relative distance, and the above formula (1) can be used to calculate the relative distance between the surrounding point and the perception receiving end according to the first index of the surrounding point in the distance dimension in the perception period map. For another example, when the any dimension is a speed dimension, the first perception parameter can be a relative speed (or relative radial speed), and the above formula (2) can be used to calculate the relative speed (or relative radial speed) between the surrounding point and the perception receiving end according to the first index of the surrounding point in the speed dimension in the perception period map.

[0150] Furthermore, the second perception parameter between the extreme point and the perception receiving end can be determined according to the second index of the extreme point under any dimension in the perception period diagram, so that the third difference between the first perception parameter and the second perception parameter (such as the difference, the absolute value of the difference, etc.) can be calculated, and the fourth difference between the signal amplitude of the extreme point and the signal amplitude of the above-mentioned surrounding points (such as the difference, the absolute value of the difference, etc.) can be calculated, and then the rate of change of the signal amplitude of any surrounding point can be determined according to the ratio of the fourth difference to the third difference.

[0151] For example, take the extreme point as point p ij , the surrounding points are point p (i-1)j For an example, click p (i-1)j The rate of change of the signal amplitude can be: ij -A (i-1)j | / |S i -S i-1 |; Among them, A ij Represents point p ij The signal amplitude, A (i-1)j Represents point p (i-1)j The signal amplitude, S i Represents the point p (i-1)j The perceptual parameter corresponding to the index in the first dimension of the perceptual periodogram, S i-1 Represents the point p (i-1)j The perceptual parameters corresponding to the indices under the first dimension in the perceptual periodogram.

[0152] In the present application, it is possible to determine whether the rate of change of the signal amplitude of multiple surrounding points meets the second setting condition. If the rate of change of the signal amplitude of multiple surrounding points meets the second setting condition, the extreme point is taken as the abnormal first extreme point. If the rate of change of the signal amplitude of multiple surrounding points does not meet the second setting condition, there is no need to take the extreme point as the abnormal first extreme point.

[0153] Among them, the second setting condition may include: the number of first change rates is equal to the third setting number, and the number of second change rates is equal to the fourth setting number; wherein the first change rate refers to the change rate of the signal amplitude of multiple surrounding points that is greater than the set proportional threshold, the second change rate refers to the change rate of the signal amplitude of multiple surrounding points that is less than the set proportional threshold, and the third setting number is equal to the fourth setting number.

[0154] For example, the mark sets the difference threshold to σ2, and the number of surrounding points is 4. The perceptual periodogram includes two dimensions for example. The rate of change between the signal amplitude of any extreme point and the signal amplitude of the four surrounding points can be calculated to obtain four change rates, of which two change rates have larger values ​​and the other two change rates have smaller values. Therefore, it can be determined whether there are 2 (the third set number) change rates greater than σ2 and 2 (the fourth set number) change rates less than σ2 among the four change rates. If so, any extreme point is taken as the first extreme point. If not (for example, 1 change rate is greater than σ2 and 3 change rates are less than σ2), there is no need to take any extreme point as the first extreme point.

[0155] Step S504: determining a first amplitude threshold according to the average of the signal amplitudes of the plurality of second extreme value points.

[0156] In an embodiment of the present application, a first amplitude threshold can be determined based on the average of the signal amplitudes of multiple second extreme points, wherein the first amplitude threshold is positively correlated with the average, that is, the larger the average, the larger the first amplitude threshold, and conversely, the smaller the average, the smaller the first amplitude threshold.

[0157] As an example, the mean of the signal amplitudes marking multiple second extreme value points is The first amplitude threshold is σ3, then:

[0158]

[0159] Among them, α is a threshold coefficient, which can be configured or adjusted according to the false alarm probability of performance statistics.

[0160] Step S505 , screening multiple second extreme value points according to the first amplitude threshold to obtain a third extreme value point; wherein the signal amplitude of the third extreme value point is greater than the first amplitude threshold.

[0161] It should be noted that the signal amplitude of the extreme point caused or caused by noise is very low, much lower than other extreme points. Therefore, in the present application, the second extreme point with relatively low signal amplitude can be eliminated.

[0162] That is, in the embodiment of the present application, for any second extreme point, it can be determined whether the signal amplitude of the second extreme point is greater than the first amplitude threshold. If the signal amplitude of the second extreme point is less than or equal to the first amplitude threshold, the second extreme point can be used as a noise extreme point and filtered. If the signal amplitude of the second extreme point is greater than the first amplitude threshold, the second extreme point can be used as a retained third extreme point.

[0163] Step S506, normalizing the signal amplitude of each third extreme value point to obtain a normalized amplitude of each third extreme value point.

[0164] In the embodiment of the present application, the signal amplitudes of the retained third extreme value points may be normalized to obtain normalized amplitudes of the third extreme value points.

[0165] As an example, for any third extreme value point, the ratio of the signal amplitude of the third extreme value point to the sum of the signal amplitudes of all the third extreme value points can be used as the normalized amplitude of the third extreme value point.

[0166] Step S507, screening the third extreme value points according to the second amplitude threshold to obtain a target extreme value point; wherein the normalized amplitude of the target extreme value point is greater than the second amplitude threshold.

[0167] In the embodiment of the present application, the second amplitude threshold is a preset amplitude threshold, for example, the second amplitude threshold can be set according to manual experience. For example, the second amplitude threshold is marked as σ4.

[0168] In an embodiment of the present application, for any third extreme value point, it can be determined whether the normalized amplitude of the third extreme value point is greater than the second amplitude threshold. If the normalized amplitude of the third extreme value point is less than or equal to the second amplitude threshold, the third extreme value point can be removed. If the normalized amplitude of the third extreme value point is greater than the second amplitude threshold, the third extreme value point can be used as the target extreme value point to be retained.

[0169] Step S508: clustering each target extreme value point to obtain at least one target cluster.

[0170] Step S509: identifying the perceived target in the synaesthesia environment according to the cluster center of the target cluster.

[0171] Steps S508 to S509 may be implemented in any manner in the embodiments of the present application, and the embodiments of the present application do not limit this and will not be described in detail.

[0172] The method for identifying a perceived target in the embodiment of the present application can achieve effective screening of extreme points to improve the accuracy of perceived target identification.

[0173] Figure 6 A flowchart of another method for identifying a perceived target provided in an embodiment of the present application.

[0174] like Figure 6 As shown, the method for identifying the perception target can be executed by the perception receiving end, and may include the following steps:

[0175] Step S601, sensing the synaesthesia environment, obtaining a first perception signal, and acquiring a perception periodogram corresponding to the first perception signal.

[0176] The perceptual periodogram is used to indicate the corresponding relationship between the perceptual parameters and the signal amplitude.

[0177] Step S602, determining a plurality of extreme value points from the perceptual periodogram, and screening the plurality of extreme value points based on signal amplitudes of the plurality of extreme value points to obtain a target extreme value point.

[0178] Steps S601 to S602 may be implemented in any manner in the embodiments of the present application, and the embodiments of the present application do not limit this and will not be described in detail.

[0179] Step S603: for any target extreme value point, according to the index of any target extreme value point under the first dimension in the perception period graph, determine the third perception parameter between any target extreme value point and the perception receiving end.

[0180] In an embodiment of the present application, for any target extreme value point, a third perception parameter between the target extreme value point and the perception receiving end can be determined according to the index of the target extreme value point under the first dimension in the perception period graph.

[0181] Step S604: determining a fourth perception parameter of any target extreme value point relative to the perception receiving end according to the index of any target extreme value point in the second dimension in the perception periodogram.

[0182] In an embodiment of the present application, the fourth perception parameter of any target extreme point relative to the perception receiving end can be determined according to the index of the above-mentioned target extreme point under the second dimension in the perception period graph.

[0183] As an example, taking the first dimension as the distance dimension and the second dimension as the speed dimension, the third perception parameter may be the relative distance and the fourth perception parameter may be the relative speed (or relative radial speed). The above formula (1) may be used to calculate the relative distance between the target extreme point and the perception receiving end according to the index of the target extreme point in the distance dimension in the perception periodogram. The above formula (2) may be used to calculate the relative speed (or relative radial speed) between the target extreme point and the perception receiving end according to the index of the target extreme point in the speed dimension in the perception periodogram.

[0184] Step S605: clustering the target extreme value points according to the third perception parameter, the fourth perception parameter and the signal amplitude corresponding to each target extreme value point to obtain at least one target cluster.

[0185] In the embodiment of the present application, each target extreme value point can be clustered according to the third perception parameter, the fourth perception parameter and the signal amplitude corresponding to each target extreme value point to obtain at least one target cluster.

[0186] Among them, the third perception parameters of each target extreme value point in the same target cluster are similar, that is, the similarity between the third perception parameters of each target extreme value point is greater than the first similarity threshold, and the fourth perception parameters of each target extreme value point in the same target cluster are similar, that is, the similarity between the fourth perception parameters of each target extreme value point is greater than the second similarity threshold, and the signal amplitudes of each target extreme value point in the same target cluster are similar, that is, the similarity between the signal amplitudes of each target extreme value point is greater than the third similarity threshold. Among them, there is no restriction on the size relationship between the first similarity threshold, the second similarity threshold and the third similarity threshold.

[0187] Step S606: identifying the perceived target in the synaesthesia environment according to the cluster center of the target cluster.

[0188] In an embodiment of the present application, the number of perceived targets in the synaesthesia environment can be determined based on the number of target clusters, that is, the number of perceived targets is equal to the number of target clusters, and each perceived target can also be identified based on the third perception parameter and the fourth perception parameter of the cluster center of each target cluster.

[0189] The method for identifying the perception target of the embodiment of the present application clusters each target extreme point based on the third perception parameter, the fourth perception parameter and the signal amplitude corresponding to each target extreme point, which can improve the accuracy and reliability of the clustering results.

[0190] Figure 7 A flowchart of another method for identifying a perceived target provided in an embodiment of the present application.

[0191] like Figure 7As shown, the method for identifying the perception target can be executed by the perception receiving end, and may include the following steps:

[0192] Step S701, perceive the synaesthesia environment, obtain a first perception signal, and acquire a perception periodogram corresponding to the first perception signal.

[0193] The perceptual periodogram is used to indicate the corresponding relationship between the perceptual parameters and the signal amplitude.

[0194] Step S702, determining a plurality of extreme value points from the perceptual periodogram, and screening the plurality of extreme value points based on signal amplitudes of the plurality of extreme value points to obtain a target extreme value point.

[0195] Step S703: for any target extreme value point, according to the index of any target extreme value point under the first dimension in the perception period graph, determine the third perception parameter between any target extreme value point and the perception receiving end.

[0196] Step S704: Determine a fourth perception parameter of any target extreme value point relative to the perception receiving end according to the index of any target extreme value point in the second dimension in the perception periodogram.

[0197] Steps S701 to S704 may be implemented in any manner in the embodiments of the present application, and the embodiments of the present application do not limit this and will not be described in detail.

[0198] Step S705, counting the first quantity of the third perception parameter and the second quantity of the fourth perception parameter.

[0199] In an embodiment of the present application, the number of non-repeating values ​​in each third perception parameter can be counted (recorded as the fifth number in the present application), and the number of non-repeating values ​​in each fourth perception parameter can be counted (recorded as the sixth number in the present application).

[0200] Step S706: clustering the target extreme value points in turn according to multiple K values ​​to obtain a clustering result corresponding to each K value.

[0201] In an embodiment of the present application, each target extreme point can be clustered according to multiple K values ​​to obtain a clustering result corresponding to each K value, wherein each clustering result includes a corresponding K value initial cluster, the third perception parameters of each target extreme point in the same initial cluster are similar, and the fourth perception parameters of each target extreme point in the same initial cluster are similar, and the signal amplitudes of each target extreme point in the same initial cluster are similar; wherein the K value is less than or equal to the maximum value of the second number and the first number.

[0202] Step S707 , determining a target clustering result from the multiple clustering results, and taking each initial cluster in the target clustering result as a target cluster.

[0203] In an embodiment of the present application, the clustering effect of each clustering result can be determined, and based on the clustering effects of multiple clustering results, a target clustering result with the best clustering effect can be determined from multiple clustering results. For example, the clustering result corresponding to the optimal K value can be obtained based on the elbow method and used as the target clustering result.

[0204] Step S708: identifying the perceived target in the synaesthesia environment according to the cluster center of the target cluster.

[0205] Step S708 can be implemented in any of the embodiments of the present application. The embodiments of the present application do not limit this and will not be described in detail.

[0206] The method for identifying perceptual targets in an embodiment of the present application can implement a clustering-based approach to determine the optimal number of clusters (the number of clusters included in the target clustering results) when the number of real perceptual targets in the synaesthesia environment is unknown, thereby determining the number of real perceptual targets in the synaesthesia environment based on the optimal number of clusters.

[0207] Figure 8 A flowchart of another method for identifying a perceived target provided in an embodiment of the present application.

[0208] like Figure 8 As shown, the method for identifying the perception target can be executed by the perception receiving end, and may include the following steps:

[0209] Step S801, sensing the synaesthesia environment, obtaining a first sensing signal, and acquiring a second sensing signal sent by a sensing sending end.

[0210] In an embodiment of the present application, the perception receiving end may perceive the synaesthesia environment, obtain a first perception signal, and acquire a second perception signal sent by the perception receiving end.

[0211] As a possible implementation manner, a manner of acquiring the second perception signal is, for example, as follows: when the perception sending end and the perception receiving end are located in the same communication device, the perception receiving end may acquire the second perception signal from the same communication device.

[0212] As another possible implementation method, the second perception signal is obtained in, for example, when the perception sending end and the perception receiving end are located in different communication devices, the perception receiving end can obtain the first pilot data of the perception sending end, and extract the second pilot data from the first perception signal, so that the first perception signal can be restored according to the change relationship between the first pilot data and the second pilot data to obtain the second perception signal.

[0213] Step S802: determining a perception periodogram according to the first perception signal and the second perception signal.

[0214] In an embodiment of the present disclosure, a perceptual periodogram may be determined according to the first perceptual signal and the second perceptual signal, wherein the perceptual periodogram is used to indicate a corresponding relationship between a perceptual parameter and a signal amplitude.

[0215] As an example, a divider operation may be performed on the first perception signal and the second perception signal, and then a perception reception algorithm may be performed to obtain a perception periodogram, wherein the divider operation refers to dividing the first perception signal by the second perception signal.

[0216] Step S803, determining a plurality of extreme value points from the perceptual periodogram, and screening the plurality of extreme value points based on signal amplitudes of the plurality of extreme value points to obtain a target extreme value point.

[0217] Step S804: clustering each target extreme point to obtain at least one target cluster.

[0218] Step S805 , identifying the perceived target in the synaesthesia environment according to the cluster center of the target cluster.

[0219] Steps S803 to S805 may be implemented in any manner in the embodiments of the present application, and the embodiments of the present application do not limit this and will not be described in detail.

[0220] In summary, it is possible to obtain from the perception periodogram the extreme points (referred to as the second extreme points in this application) after removing the extreme points (referred to as the first extreme points in this application) caused by the side lobes where the real perception target does not intersect with other real perception targets; then, use a double threshold coarse judgment to remove the extreme points caused by noise and the extreme points caused by the side lobes where the real perception target intersects with other real perception targets; finally, use a clustering algorithm to obtain the optimal number of multiple targets and multiple perception targets and their perception parameters.

[0221] The following example illustrates the interaction between the perception transmitter and the perception receiver in different scenarios and perception modes to achieve the recognition of multiple perception targets, where the recognition results of the perception targets can be used for synaesthesia system regulation and planning.

[0222] Application scenario 1: Smart transportation-active perception, that is, the perception receiving end and the perception sending end are located in the same communication device.

[0223] In smart transportation scenarios, there is a great demand for both perception and communication, which is very suitable for the synaesthesia integrated system. In addition, there are a large number of vehicles, pedestrians, and other animals or objects such as pets, roadblocks, garbage, etc. in smart transportation scenarios, which is a typical multi-target perception scenario.

[0224] When the base station or roadside unit uses the perception signals it sends for active perception, it can obtain the perception information of multiple perception targets in the synaesthesia environment, thereby realizing real-time monitoring of the road environment, and using the perception information of multiple perception targets to command and dispatch road operations, or reconstruct environmental maps, providing basic information for third-party applications.

[0225] The specific process is as follows:

[0226] 1. The sensing transmitter (such as a base station or a roadside unit) is configured with time-frequency resources suitable for both communication and sensing functions, and sends sensing signals (also called communication signals or interawareness integrated signals) through time division, frequency division or space division multiplexing for sensing;

[0227] 2. After the sensing signal passes through the channel, it is received by the sensing receiving end, where the sensing receiving end for active sensing is the sensing sending end that sends the sensing signal;

[0228] 3. After the perception receiving end performs a divider operation on the received perception signal (referred to as the first perception signal in this application) and the perception signal sent by the perception sending end (referred to as the second perception signal in this application), the perception receiving algorithm can be processed to obtain a perception periodogram;

[0229] Wherein, when the perception receiving end and the perception transmitting end are on the same side, the perception signal sent by the perception transmitting end is known to the perception receiving end; the divider operation refers to dividing the received perception signal by the transmitted perception signal;

[0230] 4. The sensing receiving end identifies multiple sensing targets in the sensing cycle diagram using the sensing target identification method provided in the present application, and reports these sensing targets and their sensing parameters to the network side;

[0231] 5. The network side instructs and dispatches vehicles and pedestrians on the road based on the reported perception information, or uses the reported perception information to reconstruct environmental maps and other further applications or services.

[0232] Similarly, vehicles on the road can also act as perception subjects for active perception. The difference is that after the vehicle obtains the perception information of multiple perception targets, it can be directly used for its own route planning, obstacle avoidance, etc. If it wants to provide perception information to the upper layer, it needs to further upload the perception information to the network side through communication.

[0233] Application scenario 2: Smart transportation-passive perception, that is, the perception receiving end and the perception sending end are located in different communication devices.

[0234] Vehicles use the perception signals sent by base stations or roadside units for passive perception, and obtain perception information of multiple perception targets in the synaesthesia environment for their own route planning or obstacle avoidance. At the same time, the perception information can be uploaded to the network side through communication, thereby providing basic information for road operation command and dispatch, or environmental map reconstruction.

[0235] The specific process is as follows:

[0236] 1. The sensing transmitter (such as a base station or a roadside unit) is configured with time-frequency resources suitable for both communication and sensing functions, and sends sensing signals (also called communication signals or interawareness integrated signals) through time division, frequency division or space division multiplexing for sensing;

[0237] 2. After the sensing signal passes through the channel, it is received by the sensing receiving end, wherein the sensing receiving end is not located on the same side as the sensing receiving end that originally sent the sensing signal, but is a new device (such as a vehicle, another base station or another roadside unit);

[0238] 3. The sensing receiving end demodulates the received sensing signal, and then performs a divider operation on the sensing signal sent by the sensing transmitting end, and then performs sensing receiving algorithm processing to obtain a sensing periodogram; wherein, when the sensing receiving end and the sensing transmitting end are on different sides, the transmitted sensing signal can be restored through the pilot data;

[0239] 4. The perception receiving end uses the perception target recognition method provided in the present application to identify multiple perception targets in the perception cycle diagram. The perception receiving end performs its own route planning or obstacle avoidance based on these perception information. In addition, if the network side notifies the perception receiving end that the perception information needs to be uploaded in the early stage, the perception receiving end also needs to report these perception targets and their perception parameters to the network side through communication;

[0240] 5. The network side instructs and dispatches vehicles and pedestrians on the road based on the reported perception information, or uses the reported perception information to reconstruct the environment map and other further applications or services. The dispatch at this time is the dispatch obtained by integrating the perception information reported by multiple perception receiving terminals, so it is more comprehensive and long-term than the vehicle's own planning considerations.

[0241] Similarly, the base station or roadside unit can also serve as a perception receiver, receiving the perception signal sent by the perception transmitter (such as a vehicle) for passive perception. The difference is that when the vehicle serves as a perception transmitter, the number of antennas, time-frequency resources, etc. may not be as many as when the base station or roadside unit serves as a perception transmitter, so the perception effect may not be as good as the latter.

[0242] Application scenario three: Smart factory - active perception and passive perception.

[0243] In smart factories, a similar process to smart transportation can be used to identify sensing targets and obtain sensing information. The difference is that the sensing requirements of smart factories are far greater than communication. Therefore, the network side needs to allocate more resources to the sensing transmitter and the sensing receiver, such as more time-frequency resources or more antennas.

[0244] In a smart factory, the perceived targets to be identified may include movable robots / robotic arms, products, other equipment, etc. Since the scenario is mainly based on perception services, the network side needs to configure the frequency of reporting perception information. Under normal circumstances, the perception frequency is reduced, such as reporting the perception information of products once a day; but in the case of special or abnormal situations, such as the robot suddenly losing control (such as the speed in the perception parameters exceeds the limit, and the speed of the factory equipment is generally limited or stationary), it needs to be reported to the network side in a timely manner. After identifying multiple perception targets, a certain obstacle discrimination threshold needs to be set to further identify the out-of-control perception target, and the perception information corresponding to the out-of-control perception target should be uploaded to the network side in a timely manner to facilitate the network side to handle exceptions.

[0245] It should be noted that the recognition principle of multiple perception targets is the same in various scenarios and perception modes. To facilitate subsequent distinction, the extreme point caused by the side lobe where the real perception target does not intersect with other real perception targets (referred to as the first extreme point in this application) is recorded as side lobe extreme point 1, and the extreme point caused by the side lobe where the real perception target intersects with other real perception targets is recorded as side lobe extreme point 2.

[0246] In any of the above embodiments or scenarios, the recognition process of the perception target may include the following steps:

[0247] 1. After the perception receiving end uses the periodogram method to obtain the perception periodogram (such as a two-dimensional periodogram), the improved extreme value method is used to obtain all extreme value points in the perception periodogram after removing the side lobe extreme value point 1.

[0248] The sub-steps are as follows:

[0249] 1) Assume that the initial value of the extreme value counter k = 0;

[0250] 2) Traverse all points in the perception periodic graph and determine any point p in the perception periodic graph ij Is it an extreme point, that is, p ij The signal amplitude A ij Is it greater than the signal amplitude of the surrounding points? If so, then p ij is the extreme point, otherwise, p ij It is not an extreme point;

[0251] In particular, at p ij The number of surrounding points is 4.

[0252] When 1≤i≤N i -2, 1≤j≤N j -2, that is, p ij When it is not at the boundary of the perceptual periodogram, it is at p ij The four surrounding points are p (i-1)j 、p (i+1)j 、p i(j-1) 、p i(j+1) ;

[0253] When i=0 or i=N i -1 or j=0 or j≤N j -1, that is, p ij When it is located at the boundary of the perceptual periodic graph and is not one of the four vertices, it is located at p ij The four surrounding points include three adjacent points and one point that jumps to the relative boundary. For example, when i = 0 and 1 ≤ j ≤ N j -2, at p ij The four surrounding points are p (i+1)j 、p i(j-1) 、p i(j+1) These three normal surrounding points and This one jumps to a point on the boundary opposite to i=0;

[0254] When p ij When located at the four vertices of the perceptual periodic diagram, at p ij The four surrounding points are two normal adjacent points and two points that jump to the opposite boundary. For example, when i = 0 and j = 0, the point at p ij The four surrounding points are p (i+1)j 、p i(j+1) These two normal adjacent points and These two jump to points on the opposite boundary from i=0 and j=0.

[0255] 3) When determining p ij After it is an extreme point, further determine p ij Whether it is an extreme point caused by the side lobe where the real perceived target does not intersect with other real perceived targets (i.e., side lobe extreme point 1), if not, then the extreme point is retained, otherwise, it is removed.

[0256] The specific determination method is: Since the side lobe extreme point 1 will only appear in the first dimension S of the perception periodicity diagram i or the first dimension S j The signal amplitude is basically the same in one dimension, but it decreases sharply in the other dimension, that is, the signal amplitude of two of the four surrounding points around the sidelobe extreme point 1 is much larger than that of the other two points. ijAfter it is an extreme point, we can subtract the four points around it two by two and take the absolute value to get There are differences, two of which are differences in the same dimension, and the other four are differences in different dimensions, so two of them are much smaller than the other four. At this time, a sidelobe difference threshold σ1 can be set to determine whether the first set condition is met based on the difference between the signal amplitudes of the four surrounding points (6 differences). If so, the extreme point is the sidelobe extreme point 1, and the extreme point is removed from all extreme points; otherwise, the extreme point is not the sidelobe extreme point 1 and is retained in all extreme points.

[0257] Optionally, the surrounding points of the side lobe extreme point 1 can be selected in S i or S j The rate of change of the signal amplitude in the dimension (the rate of change of the signal amplitude may be more obvious and easier to distinguish than the difference between the signal amplitudes), determine p ij Is it the side lobe extreme point 1? The specific method is to determine p ij After the extreme point is reached, calculate the rate of change of the signal amplitude between it and the four surrounding points, take the absolute value, and use point p as the ij and p (i-1)j For example, the rate of change of the signal amplitude of the two is |A ij -A (i-1)j | / |S i -S i-1 |, a total of four signal amplitude change rates can be obtained, of which two signal amplitude change rates are particularly large, and the other two are particularly small. At this time, a sidelobe change rate threshold σ2 can also be set, and the magnitude of the change rates of the four signal amplitudes obtained can be used to determine whether the second set condition is met. If so, the extreme point is the sidelobe extreme point 1, and the extreme point is removed from all extreme points; otherwise, the extreme point is not the sidelobe extreme point 1, and is retained in all extreme points.

[0258] 4) After executing steps 2) and 3), if p ij is the extreme point to be retained, then let k = k + 1, and store p ij In S i The perceptual parameters of the dimension, in S j The perceptual parameters of the dimension and A ij Otherwise, remove p ij , k remains unchanged.

[0259] Assuming that K1 extreme value points (referred to as the second extreme value points in this application) that meet the requirements are finally obtained, K1 is equal to the traversed k value.

[0260] 2. Set a double threshold, make a rough judgment on the extreme point (i.e., the second extreme point) obtained in step 1, and remove the noise extreme point and the side lobe extreme point 2.

[0261] The sub-steps are as follows:

[0262] This step is used to remove extreme points caused by noise and side lobe extreme point 2. The signal amplitude of the former is very low, far less than that of other extreme points, and the signal amplitude of the latter is generally lower than the signal amplitude of the extreme point corresponding to the real perception target. This step can remove a large number of useless extreme points and reduce system consumption.

[0263] 1) A rough amplitude judgment threshold σ3 can be set. Among them, α is the threshold coefficient, which can be configured or adjusted according to the false alarm probability of performance statistics. is the mean value of the signal amplitude of the K1 extreme value points obtained in step 1 above. After traversing the K1 extreme value points, the extreme value points whose signal amplitude is greater than σ3 are retained, otherwise, they are removed. Assume that K2 extreme value points (referred to as the third extreme value point in this application) that meet the requirements are finally obtained (this step can remove most of the extreme value points caused by noise).

[0264] 2) Set a new amplitude rough judgment threshold σ4, where σ4 can be configured as an empirical value. According to the K2 extreme value points obtained in the previous step, calculate the ratio of the signal amplitude of each extreme value point to the sum of the signal amplitudes of all extreme value points, denoted as γ. If γ>σ4, retain the extreme value point, otherwise, remove it. Assume that K3 extreme value points that meet the requirements are finally obtained (denoted as target extreme value points in this application).

[0265] It should be noted that, since a large number of noise extreme points have been removed, the ratio of the signal amplitude of a single point to the sum of the signal amplitudes of all points is no longer a very small value, and becomes easy to distinguish; since the signal amplitude of the extreme points caused by the side lobes at the intersection of the horizontal and vertical axes of the two real perception targets is much lower than the signal amplitude of the extreme points corresponding to the real perception targets, it is also easier to distinguish them by ratio.

[0266] 3. Using the clustering method, multiple extreme points corresponding to a real perception target are clustered into one, so as to obtain the optimal number of multiple perception targets and the corresponding multiple perception targets and their perception parameters.

[0267] The sub-steps are as follows:

[0268] The K3 extreme points obtained in the previous step are clustered. The clustering algorithm can use classic clustering algorithms such as k-means and DBSCAN. The clustering algorithm first needs to determine the number of clusters (or the number of clusters, denoted as K4), but since the number of actual perception targets is unknown, it is necessary to determine it through different clustering effects.

[0269] 1) Assume that the K3 extreme points obtained in the previous step are in S i The perceptual parameters of the dimension are Ki , 0≤K i ≤K3, K3 extreme points in S j The perceptual parameters of the dimension are K j , 0≤K j ≤K3, the value range of the number of clusters K4 is [0,max(K i ,K j )] and K4 is an integer, where max(K i ,K j ) represents taking K i and K j The maximum value in .

[0270] 2) Then clustering is performed according to different K4 values, and which clustering result is the best according to the clustering effect. For example, the k-means clustering algorithm can obtain the optimal clustering number K4 through the elbow method. The optimal clustering number K4 is used as the number of finally estimated perception targets, and the multiple cluster centers or centroids in the clustering results corresponding to the optimal clustering number K4 are used as the optimal multiple estimated perception targets, and the multiple perception targets in S are obtained. i The index or perception parameter of the dimension, and the acquisition of multiple perception targets in S j The index or perception parameter of the dimension (used for subsequent perception parameter estimation, such as distance-speed estimation).

[0271] It should be noted that if the number of real perceived targets is known a priori, the number of clusters can be directly set equal to the number of real perceived targets and clustering can be performed without multiple clustering. However, this situation is generally only used for simulation testing and is not suitable for actual environment perception.

[0272] It should also be noted that the present application is also applicable to the recognition of a perceptual target whose perceptual periodogram is a one-dimensional periodogram. Unlike a two-dimensional periodogram, each point in a one-dimensional periodogram has only one perceptual parameter and its corresponding signal amplitude. For the recognition of the perceptual target of a one-dimensional periodogram, assuming that the horizontal axis is the perceptual parameter of a certain dimension and the vertical axis is the signal amplitude, which is a curve, the dimension can be one of the distance, speed, or angle. The overall recognition process is similar to the recognition process of a two-dimensional periodogram, so it will not be repeated here.

[0273] In summary, the method for identifying perceptual targets suitable for the synaesthesia system proposed in this application can enable the perceptual receiving end to effectively remove false perceptual targets and identify multiple optimal estimated perceptual targets after the perceptual receiving end executes the perceptual algorithm processing, and these perceptual targets can be used to regulate the synaesthesia system or provide information for further other applications.

[0274] The technical solution provided in the embodiment of the present application can be applicable to a variety of systems, especially 5G systems. For example, the applicable system can be a global system of mobile communication (Global System of Mobile communication, referred to as GSM) system, code division multiple access (Code Division Multiple Access, referred to as CDMA) system, wideband code division multiple access (Wideband Code Division Multiple Access, referred to as WCDMA) general packet radio service (General Packet Radio Service, referred to as GPRS) system, long term evolution (long term evolution, referred to as LTE) system, LTE frequency division duplex (Frequency Division Duplex, referred to as FDD) system, LTE time division duplex (time division duplex, referred to as TDD) system, advanced long term evolution (Long Term Evolution Advanced, referred to as LTE-A) system, Universal Mobile Telecommunication System (Universal Mobile Telecommunication System, referred to as UMTS), Worldwide interoperability for Microwave Access (Worldwide interoperability for Microwave Access, referred to as WiMAX) system, 5G new air interface (NewRadio, referred to as NR) system, etc. These various systems include terminals and network equipment. The system may also include a core network part, such as an evolved packet system (EPS), a 5G system (5GS), etc.

[0275] In order to implement the above embodiments, the present application also proposes a perception receiving end.

[0276] Fig. 9 A schematic diagram of the structure of a perception receiving terminal provided in an embodiment of the present application.

[0277] like Fig. 9 As shown, the perception receiving end may include: a transceiver 900 , a processor 910 , and a memory 920 .

[0278] Among them, the memory 920 is used to store computer programs; the transceiver 900 is used to send and receive data under the control of the processor 910; the processor 910 is used to read the computer program in the memory 920 and perform the following operations: perceive the synaesthesia environment, obtain a first perception signal, and obtain a perception periodogram corresponding to the first perception signal; wherein the perception periodogram is used to indicate the correspondence between the perception parameter and the signal amplitude; determine multiple extreme points from the perception periodogram, and based on the signal amplitudes of the multiple extreme points, screen the multiple extreme points to obtain target extreme points; cluster each target extreme point to obtain at least one target cluster; and identify the perception target in the synaesthesia environment according to the cluster center of the target cluster.

[0279] The transceiver 900 is used to receive and send data under the control of the processor 910 .

[0280] Among them, Fig. 9 In the embodiment, the bus architecture may include any number of interconnected buses and bridges, specifically one or more processors represented by processor 910 and various circuits of memory represented by memory 920 are linked together. The bus architecture may also link together various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. The bus interface provides an interface. The transceiver 900 may be a plurality of components, namely, a transmitter and a receiver, providing a unit for communicating with various other devices on a transmission medium, which transmission medium may include a wireless channel, a wired channel, an optical cable, and other transmission media. The processor 910 is responsible for managing the bus architecture and general processing, and the memory 920 may store data used by the processor 910 when performing operations.

[0281] The processor 910 may be a CPU, an ASIC, an FPGA or a CPLD, and the processor 910 may also adopt a multi-core architecture.

[0282] In a possible implementation form of the present application, the perceptual periodogram includes two dimensions, and the processor 910 performs the process of determining multiple extreme points from the perceptual periodogram, specifically: for any point p in the perceptual periodogram ij , when p ij The signal amplitude is greater than that at p ij When the signal amplitude of multiple surrounding points is ij As the extreme point; where 0≤i≤N i -1, 0≤j≤N j -1,N i is the number of indices in the first of the two dimensions in the perceptual periodogram, N j is the number of indices under the second of the two dimensions in the perceptual periodogram.

[0283] In a possible implementation form of the present application, multiple surrounding points satisfy any of the following conditions: ij When it is not at the boundary of the perceptual periodogram, multiple surrounding points including p ij Adjacent adjacent points; when p ij Located at the first boundary of the perceptual periodogram, and p ij When not at the vertex of the perceptual period graph, multiple surrounding points include ij adjacent adjacent points and boundary points on the second boundary of the perceptual periodic graph; wherein the second boundary is parallel to the first boundary, and the boundary points are adjacent to p ij The index of one of the two dimensions is the same; when p ij When located at the first vertex of the perceptual period graph, multiple surrounding points include ij adjacent adjacent points and the second vertex of the perceptual period graph; wherein the second vertex is related to p ij The index of one of the two dimensions is the same.

[0284] In a possible implementation form of the present application, the processor 910 performs screening of multiple extreme value points based on the signal amplitudes of the multiple extreme value points to obtain a target extreme value point, specifically: based on the signal amplitudes of the multiple extreme value points, multiple second extreme value points other than the first extreme value point are selected from the multiple extreme value points; according to the average of the signal amplitudes of the multiple second extreme value points, a first amplitude threshold is determined, and according to the first amplitude threshold, the multiple second extreme value points are screened to obtain a third extreme value point; wherein the signal amplitude of the third extreme value point is greater than the first amplitude threshold; the signal amplitude of each third extreme value point is normalized to obtain a normalized amplitude of each third extreme value point; according to the set second amplitude threshold, each third extreme value point is screened to obtain a target extreme value point; wherein the normalized amplitude of the target extreme value point is greater than the second amplitude threshold.

[0285] In a possible implementation form of the present application, the processor 910 executes based on the signal amplitudes of multiple extreme points, and selects multiple second extreme points other than the first extreme point from the multiple extreme points, specifically: for any extreme point, determine the difference between the signal amplitudes of multiple surrounding points located around any extreme point; when the difference between the signal amplitudes of multiple surrounding points meets the first set condition, take any extreme point as the first extreme point; select multiple second extreme points other than the first extreme point from the multiple extreme points; wherein the first set condition includes: the number of first differences is equal to the first set number, and the number of second differences is equal to the second set number; wherein the first difference refers to a difference among the multiple differences that is greater than a set difference threshold, the second difference refers to a difference among the multiple differences that is less than the set difference threshold, and the first set number is greater than the second set number.

[0286] In a possible implementation form of the present application, the processor 910 executes, based on the signal amplitudes of the multiple extreme points, selecting multiple second extreme points other than the first extreme point from the multiple extreme points, specifically: for any extreme point, according to the signal amplitude of any extreme point and the signal amplitudes of multiple surrounding points located around any extreme point, respectively determine the change rate of the signal amplitude of the multiple surrounding points; when the change rate of the signal amplitude of the multiple surrounding points meets the second set condition, any extreme point is used as the first extreme point; and multiple second extreme points other than the first extreme point are selected from the multiple extreme points; wherein the second set condition includes: the number of first change rates is equal to the third set number, and the number of second change rates is equal to the fourth set number; wherein the first change rate refers to the change rate of the multiple change rates that is greater than the set ratio threshold, the second change rate refers to the change rate of the multiple change rates that is less than the set ratio threshold, and the third set number is equal to the fourth set number.

[0287] In a possible implementation form of the present application, the processor 910 executes, for any extreme point, according to the signal amplitude of any extreme point and the signal amplitudes of multiple surrounding points located around any extreme point, respectively determining the change rate of the signal amplitudes of multiple surrounding points, specifically: for any surrounding point, according to the first index of any surrounding point in any dimension in the perception period diagram, determining the first perception parameter between any surrounding point and the perception receiving end; according to the second index of any extreme point in any dimension in the perception period diagram, determining the second perception parameter between any extreme point and the perception receiving end; determining the third difference between the first perception parameter and the second perception parameter, and determining the fourth difference between the signal amplitude of any extreme point and the signal amplitude of any surrounding point; determining the change rate of the signal amplitude of any surrounding point according to the ratio of the fourth difference to the third difference.

[0288] In a possible implementation form of the present application, the processor 910 performs clustering of each target extreme value point to obtain at least one target cluster, specifically: for any target extreme value point, according to the index of any target extreme value point under the first dimension in the perception period diagram, determine the third perception parameter between any target extreme value point and the perception receiving end; according to the index of any target extreme value point under the second dimension in the perception period diagram, determine the fourth perception parameter of any target extreme value point relative to the perception receiving end; according to the third perception parameter, fourth perception parameter and signal amplitude corresponding to each target extreme value point, cluster each target extreme value point to obtain at least one target cluster.

[0289] In a possible implementation form of the present application, the processor 910 performs clustering of each target extreme point according to the third perception parameter, the fourth perception parameter and the signal amplitude corresponding to each target extreme point to obtain at least one target cluster, specifically: counting the first number of the third perception parameter and the second number of the fourth perception parameter; clustering each target extreme point in turn according to multiple K values ​​to obtain a clustering result corresponding to each K value; wherein the clustering result includes corresponding K value initial clusters, the third perception parameters of each target extreme point in the same initial cluster are similar, and the fourth perception parameters of each target extreme point in the same initial cluster are similar, and the signal amplitudes of each target extreme point in the same initial cluster are similar; the K value is less than or equal to the maximum value of the first number and the second number; determining the target clustering result from multiple clustering results, and taking each initial cluster in the target clustering result as the target cluster.

[0290] In a possible implementation form of the present application, the processor 910 executes identification of perceptual targets in the synaesthesia environment according to the cluster centers of the target clusters, specifically: determining the number of perceptual targets in the synaesthesia environment according to the number of target clusters; and identifying each perceptual target according to the third perceptual parameter and the fourth perceptual parameter of the cluster center of each target cluster.

[0291] In a possible implementation form of the present application, the processor 910 executes acquiring a perception period graph corresponding to the first perception signal, specifically: acquiring a second perception signal sent by a perception sending end; and determining a perception period graph according to the first perception signal and the second perception signal.

[0292] In a possible implementation form of the present application, the perception sending end and the perception receiving end are located in the same communication device, and the processor 910 executes obtaining a second perception signal sent by the perception sending end, specifically: obtaining the second perception signal from the same communication device.

[0293] In a possible implementation form of the present application, the perception sending end and the perception receiving end are located in different communication devices, and the processor 910 executes the acquisition of the second perception signal sent by the perception sending end, specifically: acquiring the first pilot data of the perception sending end; extracting the second pilot data from the first perception signal; based on the first pilot data and the second pilot symbol, restoring the first perception signal to obtain the second perception signal.

[0294] It should be noted that the sensing receiving end provided in the embodiment of the present application can achieve the above Figures 3 to 8 All the method steps implemented in the method embodiment can achieve the same technical effect, and the parts and beneficial effects of this embodiment that are the same as those in the method embodiment will not be described in detail here.

[0295] With the above Figures 3 to 8Corresponding to the method for identifying a perceived target provided in the embodiment, the present application also provides a device for identifying a perceived target. Figures 3 to 8 The method for identifying the perceived target provided in the embodiment corresponds to the method, so the implementation method of the method for identifying the perceived target is also applicable to the device for identifying the perceived target provided in the embodiment of the present application, and will not be described in detail in the embodiment of the present application.

[0296] Fig.10 A schematic diagram of the structure of a target perception recognition device provided in an embodiment of the present application.

[0297] like Fig.10 As shown, the perception target recognition device 1000 is applied to a perception receiving end and may include: a perception unit 1010 , an acquisition unit 1020 , a processing unit 1030 , a clustering unit 1040 and a recognition unit 1050 .

[0298] The sensing unit 1010 is used to sense the synaesthesia environment and obtain a first sensing signal.

[0299] The acquisition unit 1020 is configured to acquire a perceptual periodogram corresponding to the first perceptual signal; wherein the perceptual periodogram is used to indicate a corresponding relationship between a perceptual parameter and a signal amplitude.

[0300] The processing unit 1030 is used to determine multiple extreme value points from the perception periodogram, and screen the multiple extreme value points based on the signal amplitudes of the multiple extreme value points to obtain the target extreme value point.

[0301] The clustering unit 1040 is used to cluster each target extreme value point to obtain at least one target cluster.

[0302] The identification unit 1050 is used to identify the perceived target in the synaesthesia environment according to the cluster center of the target cluster.

[0303] Further, in a possible implementation form of the present application, the perceptual periodogram includes two dimensions, and the processing unit 1030 is specifically configured to: for any point p in the perceptual periodogram ij , when p ij The signal amplitude is greater than that at p ij When the signal amplitude of multiple surrounding points is ij As the extreme point; where 0≤i≤N i -1, 0≤j≤N j -1,N i is the number of indices in the first of the two dimensions in the perceptual periodogram, N j is the number of indices under the second of the two dimensions in the perceptual periodogram.

[0304] Further, in another possible implementation form of the present application, the plurality of surrounding points satisfy any one of the following conditions: ij When it is not at the boundary of the perceptual periodogram, multiple surrounding points including p ij Adjacent adjacent points; when p ij Located at the first boundary of the perceptual periodogram, and p ij When not at the vertex of the perceptual period graph, multiple surrounding points include ij adjacent adjacent points and boundary points on the second boundary of the perceptual periodic graph; wherein the second boundary is parallel to the first boundary, and the boundary points are adjacent to p ij The index of one of the two dimensions is the same; when p ij When located at the first vertex of the perceptual period graph, multiple surrounding points include ij adjacent adjacent points and the second vertex of the perceptual period graph; wherein the second vertex is related to p ij The index of one of the two dimensions is the same.

[0305] Further, in another possible implementation form of the present application, the processing unit 1030 is specifically used to: select multiple second extreme value points other than the first extreme value point from the multiple extreme value points based on the signal amplitudes of the multiple extreme value points; determine the first amplitude threshold according to the average of the signal amplitudes of the multiple second extreme value points, and screen the multiple second extreme value points according to the first amplitude threshold to obtain a third extreme value point; wherein the signal amplitude of the third extreme value point is greater than the first amplitude threshold; normalize the signal amplitude of each third extreme value point to obtain a normalized amplitude of each third extreme value point; screen each third extreme value point according to the set second amplitude threshold to obtain a target extreme value point; wherein the normalized amplitude of the target extreme value point is greater than the second amplitude threshold.

[0306] Further, in another possible implementation form of the present application, the processing unit 1030 is specifically used to: for any extreme point, determine the difference between the signal amplitudes of multiple surrounding points located around any extreme point; when the difference between the signal amplitudes of multiple surrounding points meets the first set condition, take any extreme point as the first extreme point; select multiple second extreme points other than the first extreme point from the multiple extreme points; wherein the first set condition includes: the number of first differences is equal to the first set number, and the number of second differences is equal to the second set number; wherein the first difference refers to a difference among the multiple differences that is greater than a set difference threshold, the second difference refers to a difference among the multiple differences that is less than the set difference threshold, and the first set number is greater than the second set number.

[0307] Further, in another possible implementation form of the present application, the processing unit 1030 is specifically used to: for any extreme point, determine the change rate of the signal amplitude of multiple surrounding points respectively according to the signal amplitude of any extreme point and the signal amplitude of multiple surrounding points located around any extreme point; when the change rate of the signal amplitude of multiple surrounding points meets the second setting condition, take any extreme point as the first extreme point; select multiple second extreme points other than the first extreme point from the multiple extreme points; wherein the second setting condition includes: the number of first change rates is equal to the third setting number, and the number of second change rates is equal to the fourth setting number; wherein the first change rate refers to the change rate of the multiple change rates that is greater than the set ratio threshold, the second change rate refers to the change rate of the multiple change rates that is less than the set ratio threshold, and the third setting number is equal to the fourth setting number.

[0308] Furthermore, in another possible implementation form of the present application, the processing unit 1030 is specifically used to: for any surrounding point, determine a first perception parameter between any surrounding point and the perception receiving end according to the first index of any surrounding point in any dimension in the perception period diagram; determine a second perception parameter between any extreme point and the perception receiving end according to the second index of any extreme point in any dimension in the perception period diagram; determine a third difference between the first perception parameter and the second perception parameter, and determine a fourth difference between the signal amplitude of any extreme point and the signal amplitude of any surrounding point; determine the rate of change of the signal amplitude of any surrounding point according to the ratio of the fourth difference to the third difference.

[0309] Furthermore, in another possible implementation form of the present application, the clustering unit 1040 is specifically used to: for any target extreme value point, determine the third perception parameter between any target extreme value point and the perception receiving end according to the index of any target extreme value point under the first dimension in the perception period diagram; determine the fourth perception parameter of any target extreme value point relative to the perception receiving end according to the index of any target extreme value point under the second dimension in the perception period diagram; cluster each target extreme value point according to the third perception parameter, fourth perception parameter and signal amplitude corresponding to each target extreme value point to obtain at least one target cluster.

[0310] Furthermore, in another possible implementation form of the present application, the clustering unit 1040 is specifically used to: count the first number of the third perception parameter and the second number of the fourth perception parameter; cluster each target extreme point according to multiple K values ​​in turn to obtain a clustering result corresponding to each K value; wherein the clustering result includes corresponding K value initial clusters, the third perception parameters of each target extreme point in the same initial cluster are similar, and the fourth perception parameters of each target extreme point in the same initial cluster are similar, and the signal amplitudes of each target extreme point in the same initial cluster are similar; the K value is less than or equal to the maximum value of the first number and the second number; determine the target clustering result from multiple clustering results, and use each initial cluster in the target clustering result as the target cluster.

[0311] Furthermore, in another possible implementation form of the present application, the identification unit 1050 is specifically used to: determine the number of perceived targets in the synaesthesia environment according to the number of target clusters; and identify each perceived target according to the third perception parameter and the fourth perception parameter of the cluster center of each target cluster.

[0312] Furthermore, in another possible implementation form of the present application, the acquisition unit 1020 is specifically used to: acquire a second perception signal sent by the perception sending end; and determine a perception periodicity diagram according to the first perception signal and the second perception signal.

[0313] Furthermore, in another possible implementation form of the present application, the perception sending end and the perception receiving end are located in different communication devices, and the acquisition unit 1020 is specifically used to: obtain the first pilot data of the perception sending end; extract the second pilot data from the first perception signal; and restore the first perception signal based on the first pilot data and the second pilot symbol to obtain the second perception signal.

[0314] Furthermore, in another possible implementation form of the present application, the perception sending end and the perception receiving end are located in the same communication device, and the acquisition unit 1020 is specifically used to: acquire the second perception signal from the same communication device.

[0315] It should be noted that the above-mentioned recognition device for sensing targets provided in the embodiment of the present application can achieve the above-mentioned Figures 3 to 8 All the method steps implemented in the method embodiment can achieve the same technical effect, and the parts and beneficial effects of this embodiment that are the same as those in the method embodiment will not be described in detail here.

[0316] It should be noted that each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0317] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a processor-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) or a processor (processor) to perform all or part of the steps of each embodiment method of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store program code.

[0318] In order to implement the above embodiments, the present application also proposes a processor-readable storage medium.

[0319] The processor-readable storage medium stores a computer program for causing the processor to execute the present application. Figures 3 to 8 A method for identifying a perception target according to any embodiment.

[0320] Among them, the processor-readable storage medium can be any available medium or data storage device that can be accessed by the processor, including but not limited to magnetic storage (such as floppy disks, hard disks, magnetic tapes, magneto-optical disks (MO), etc.), optical storage (such as CD, DVD, BD, HVD, etc.), and semiconductor storage (such as ROM, EPROM, EEPROM, non-volatile memory (NANDFLASH), solid-state drive (SSD)), etc.

[0321] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage and optical storage, etc.) that contain computer-usable program code.

[0322] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer executable instructions. These computer executable instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0323] These processor executable instructions may also be stored in a processor readable memory that can direct a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the processor readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0324] These processor-executable instructions may also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable device to implement the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0325] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A method for identifying a perception target, characterized in that: Applied to the sensing receiving end, including: Perceiving a synaesthesia environment, obtaining a first perception signal, and acquiring a perception periodogram corresponding to the first perception signal; wherein the perception periodogram is used to indicate a corresponding relationship between a perception parameter and a signal amplitude; Determine a plurality of extreme value points from the perceptual periodogram, and screen the plurality of extreme value points based on signal amplitudes of the plurality of extreme value points to obtain a target extreme value point; Clustering each of the target extreme value points to obtain at least one target cluster; According to the cluster center of the target cluster, a perception target in the synaesthesia environment is identified.

2. The method according to claim 1, characterized in that The perceptual periodogram includes two dimensions, The step of determining a plurality of extreme points from the perceptual periodogram comprises: For any point p in the perceptual periodogram ij , when the p ij The signal amplitude is greater than that located at the p ij When the signal amplitude of multiple surrounding points is ij as said extreme point; Where 0≤i≤N i -1, 0≤j≤N j -1, N i is the number of indices in the first dimension of the two dimensions in the perceptual periodogram, N j is the number of indices in the second dimension of the two dimensions in the perceptual periodogram.

3. The method according to claim 2, characterized in that The multiple surrounding points satisfy any of the following conditions: When the p ij When the plurality of surrounding points are not located at the boundary of the perceptual periodogram, the plurality of surrounding points include the points corresponding to the p ij adjacent adjacent points; When the p ij is located at the first boundary of the perceptual periodogram, and the p ij When the plurality of surrounding points are not located at the vertex of the perceptual period graph, the plurality of surrounding points include the points corresponding to the p ij adjacent adjacent points and boundary points on the second boundary of the perceptual periodogram; wherein the second boundary is parallel to the first boundary, and the boundary points are adjacent to the p ij The index of one of the two dimensions is the same; When the p ij When located at the first vertex of the perceptual period graph, the plurality of surrounding points include ij adjacent adjacent points and the second vertex of the perceptual period graph; wherein the second vertex and the p ij The index of one of the two dimensions is the same.

4. The method according to claim 1, characterized in that: The screening of the plurality of extreme value points based on the signal amplitudes of the plurality of extreme value points to obtain a target extreme value point includes: Based on the signal amplitudes of the plurality of extreme value points, selecting a plurality of second extreme value points other than the first extreme value point from the plurality of extreme value points; Determine a first amplitude threshold according to the average of the signal amplitudes of the plurality of second extreme value points, and screen the plurality of second extreme value points according to the first amplitude threshold to obtain a third extreme value point; wherein the signal amplitude of the third extreme value point is greater than the first amplitude threshold; Normalizing the signal amplitude of each of the third extreme value points to obtain a normalized amplitude of each of the third extreme value points; According to the set second amplitude threshold, each of the third extreme value points is screened to obtain a target extreme value point; wherein the normalized amplitude of the target extreme value point is greater than the second amplitude threshold.

5. The method according to claim 4, characterized in that The selecting a plurality of second extreme value points other than the first extreme value point from the plurality of extreme value points based on the signal amplitudes of the plurality of extreme value points comprises: For any extreme point, determining the difference between the signal amplitudes of a plurality of surrounding points located around the any extreme point; When the difference between the signal amplitudes of the plurality of surrounding points satisfies a first set condition, taking any one of the extreme value points as a first extreme value point; Selecting a plurality of second extreme value points other than the first extreme value point from the plurality of extreme value points; Among them, the first set condition includes: the number of first differences is equal to the first set number, and the number of second differences is equal to the second set number; wherein, the first difference refers to a difference among the multiple differences that is greater than the set difference threshold, the second difference refers to a difference among the multiple differences that is less than the set difference threshold, and the first set number is greater than the second set number.

6. The method according to claim 4, characterized in that The selecting a plurality of second extreme value points other than the first extreme value point from the plurality of extreme value points based on the signal amplitudes of the plurality of extreme value points comprises: For any extreme point, according to the signal amplitude of the extreme point and the signal amplitudes of multiple surrounding points located around the extreme point, respectively determine the change rates of the signal amplitudes of the multiple surrounding points; When the change rate of the signal amplitude of the plurality of surrounding points meets the second set condition, taking any extreme point as the first extreme point; Selecting a plurality of second extreme value points other than the first extreme value point from the plurality of extreme value points; Among them, the second setting condition includes: the number of first change rates is equal to the third setting number, and the number of second change rates is equal to the fourth setting number; wherein, the first change rate refers to the change rate among the multiple change rates that is greater than the set proportion threshold, the second change rate refers to the change rate among the multiple change rates that is less than the set proportion threshold, and the third setting number is equal to the fourth setting number.

7. The method according to claim 6, characterized in that The step of determining, for any extreme point, the change rates of the signal amplitudes of the plurality of surrounding points respectively according to the signal amplitude of the any extreme point and the signal amplitudes of the plurality of surrounding points located around the any extreme point, comprises: For any surrounding point, determining a first perception parameter between the any surrounding point and the perception receiving end according to a first index of the any surrounding point in any dimension in the perception periodogram; Determining a second perception parameter between any extreme value point and the perception receiving end according to a second index of any extreme value point in any dimension in the perception periodogram; determining a third difference between the first perception parameter and the second perception parameter, and determining a fourth difference between the signal amplitude of any extreme point and the signal amplitude of any surrounding point; The change rate of the signal amplitude of any surrounding point is determined according to the ratio of the fourth difference to the third difference.

8. The method according to claim 1, characterized in that The clustering of the target extreme value points to obtain at least one target cluster includes: For any target extreme value point, determining a third perception parameter between the any target extreme value point and the perception receiving end according to the index of the any target extreme value point under the first dimension in the perception period graph; Determining a fourth perception parameter of any target extreme value point relative to the perception receiving end according to an index of any target extreme value point under the second dimension in the perception periodogram; The target extreme value points are clustered according to the third perception parameter, the fourth perception parameter and the signal amplitude corresponding to each of the target extreme value points to obtain the at least one target cluster.

9. The method according to claim 8, characterized in that The clustering of the target extreme value points according to the third perception parameter, the fourth perception parameter and the signal amplitude corresponding to each of the target extreme value points to obtain the at least one target cluster includes: Counting a first quantity of the third perception parameter and a second quantity of the fourth perception parameter; Clustering the target extreme value points in sequence according to multiple K values ​​to obtain a clustering result corresponding to each K value; wherein the clustering result includes a corresponding K value initial cluster, the third perception parameters of the target extreme value points in the same initial cluster are similar, the fourth perception parameters of the target extreme value points in the same initial cluster are similar, and the signal amplitudes of the target extreme value points in the same initial cluster are similar; the K value is less than or equal to the maximum value of the first number and the second number; A target clustering result is determined from the plurality of clustering results, and each initial cluster in the target clustering result is used as the target cluster.

10. The method according to claim 8, characterized in that The step of identifying the perceived target in the synaesthesia environment according to the cluster center of the target cluster includes: Determining the number of perceived targets in the synaesthesia environment according to the number of the target clusters; Each of the perceived targets is identified according to the third perception parameter of the cluster center of each of the target clusters and the fourth perception parameter.

11. The method according to any one of claims 1 to 10, characterized in that The acquiring the perception periodogram corresponding to the first perception signal includes: Acquire a second perception signal sent by a perception sending end; The perceptual periodogram is determined according to the first perceptual signal and the second perceptual signal.

12. The method according to claim 11, characterized in that: The perception sending end and the perception receiving end are located in the same communication device, and obtaining a second perception signal sent by the perception sending end includes: The second perception signal is obtained from the same communication device.

13. The method according to claim 11, characterized in that The perception sending end and the perception receiving end are located in different communication devices, and obtaining a second perception signal sent by the perception sending end includes: Acquire first pilot data of the sensing sending end; extracting second pilot data from the first perception signal; The first perception signal is restored based on the first pilot data and the second pilot symbol to obtain the second perception signal.

14. A sensing receiving terminal, characterized in that: Including memory, transceiver, processor; A memory for storing a computer program; a transceiver for transmitting and receiving data under the control of the processor; and a processor for reading the computer program in the memory and performing the following operations: Perceiving a synaesthesia environment, obtaining a first perception signal, and acquiring a perception periodogram corresponding to the first perception signal; wherein the perception periodogram is used to indicate a corresponding relationship between a perception parameter and a signal amplitude; Determine a plurality of extreme value points from the perceptual periodogram, and screen the plurality of extreme value points based on signal amplitudes of the plurality of extreme value points to obtain a target extreme value point; Clustering each of the target extreme value points to obtain at least one target cluster; According to the cluster center of the target cluster, a perception target in the synaesthesia environment is identified.

15. The sensing receiving terminal according to claim 14, characterized in that: The perceptual periodogram includes two dimensions, and the processor performs the following steps to determine a plurality of extreme points from the perceptual periodogram: For any point p in the perceptual periodogram ij , when the p ij The signal amplitude is greater than that located at the p ij When the signal amplitude of multiple surrounding points is ij as said extreme point; Where 0≤i≤N i -1, 0≤j≤N j -1, N i is the number of indices in the first dimension of the two dimensions in the perceptual periodogram, N j is the number of indices in the second dimension of the two dimensions in the perceptual periodogram.

16. The sensing receiving terminal according to claim 15, characterized in that: The multiple surrounding points satisfy any of the following conditions: When the p ij When the plurality of surrounding points are not located at the boundary of the perceptual periodogram, the plurality of surrounding points include the points corresponding to the p ij adjacent adjacent points; When the p ij is located at the first boundary of the perceptual periodogram, and the p ij When the plurality of surrounding points are not located at the vertex of the perceptual period graph, the plurality of surrounding points include the points corresponding to the p ij adjacent adjacent points and boundary points on the second boundary of the perceptual periodogram; wherein the second boundary is parallel to the first boundary, and the boundary points are adjacent to the p ij The index of one of the two dimensions is the same; When the p ij When located at the first vertex of the perceptual period graph, the plurality of surrounding points include ij adjacent adjacent points and the second vertex of the perceptual period graph; wherein the second vertex and the p ij The index of one of the two dimensions is the same.

17. The sensing receiving terminal according to claim 14, characterized in that: The processor performs screening of the multiple extreme value points based on the signal amplitudes of the multiple extreme value points to obtain a target extreme value point, specifically: Based on the signal amplitudes of the plurality of extreme value points, selecting a plurality of second extreme value points other than the first extreme value point from the plurality of extreme value points; Determine a first amplitude threshold according to the average of the signal amplitudes of the plurality of second extreme value points, and screen the plurality of second extreme value points according to the first amplitude threshold to obtain a third extreme value point; wherein the signal amplitude of the third extreme value point is greater than the first amplitude threshold; Normalizing the signal amplitude of each of the third extreme value points to obtain a normalized amplitude of each of the third extreme value points; According to the set second amplitude threshold, each of the third extreme value points is screened to obtain a target extreme value point; wherein the normalized amplitude of the target extreme value point is greater than the second amplitude threshold.

18. The sensing receiving terminal according to claim 17, characterized in that: The processor performs the following steps of selecting a plurality of second extreme value points other than the first extreme value point from the plurality of extreme value points based on the signal amplitudes of the plurality of extreme value points: For any extreme point, determining the difference between the signal amplitudes of a plurality of surrounding points located around the any extreme point; When the difference between the signal amplitudes of the plurality of surrounding points satisfies a first set condition, taking any one of the extreme value points as a first extreme value point; Selecting a plurality of second extreme value points other than the first extreme value point from the plurality of extreme value points; Among them, the first set condition includes: the number of first differences is equal to the first set number, and the number of second differences is equal to the second set number; wherein, the first difference refers to a difference among the multiple differences that is greater than the set difference threshold, the second difference refers to a difference among the multiple differences that is less than the set difference threshold, and the first set number is greater than the second set number.

19. The sensing receiving terminal according to claim 17, characterized in that: The processor performs the following steps of selecting a plurality of second extreme value points other than the first extreme value point from the plurality of extreme value points based on the signal amplitudes of the plurality of extreme value points: For any extreme point, according to the signal amplitude of the extreme point and the signal amplitudes of multiple surrounding points located around the extreme point, respectively determine the change rates of the signal amplitudes of the multiple surrounding points; When the change rate of the signal amplitude of the plurality of surrounding points meets the second set condition, taking any extreme point as the first extreme point; Selecting a plurality of second extreme value points other than the first extreme value point from the plurality of extreme value points; Among them, the second setting condition includes: the number of first change rates is equal to the third setting number, and the number of second change rates is equal to the fourth setting number; wherein, the first change rate refers to the change rate among the multiple change rates that is greater than the set proportion threshold, the second change rate refers to the change rate among the multiple change rates that is less than the set proportion threshold, and the third setting number is equal to the fourth setting number.

20. The sensing receiving terminal according to claim 19, characterized in that: The processor performs, for any extreme point, determining the change rate of the signal amplitude of the plurality of surrounding points respectively according to the signal amplitude of the any extreme point and the signal amplitude of the plurality of surrounding points located around the any extreme point, specifically: For any surrounding point, determining a first perception parameter between the any surrounding point and the perception receiving end according to a first index of the any surrounding point in any dimension in the perception periodogram; Determining a second perception parameter between any extreme value point and the perception receiving end according to a second index of any extreme value point in any dimension in the perception periodogram; determining a third difference between the first perception parameter and the second perception parameter, and determining a fourth difference between the signal amplitude of any extreme point and the signal amplitude of any surrounding point; The change rate of the signal amplitude of any surrounding point is determined according to the ratio of the fourth difference to the third difference.

21. The sensing receiving terminal according to claim 14, characterized in that: The processor performs clustering of the target extreme value points to obtain at least one target cluster, specifically: For any target extreme value point, determining a third perception parameter between the any target extreme value point and the perception receiving end according to the index of the any target extreme value point under the first dimension in the perception period graph; Determining a fourth perception parameter of any target extreme value point relative to the perception receiving end according to an index of any target extreme value point under the second dimension in the perception periodogram; The target extreme value points are clustered according to the third perception parameter, the fourth perception parameter and the signal amplitude corresponding to each of the target extreme value points to obtain the at least one target cluster.

22. The sensing receiving terminal according to claim 21, characterized in that: The processor performs clustering of each of the target extreme value points according to the third perception parameter, the fourth perception parameter, and the signal amplitude corresponding to each of the target extreme value points to obtain the at least one target cluster, specifically: Counting a first quantity of the third perception parameter and a second quantity of the fourth perception parameter; Clustering the target extreme value points in sequence according to multiple K values ​​to obtain a clustering result corresponding to each K value; wherein the clustering result includes a corresponding K value initial cluster, the third perception parameters of the target extreme value points in the same initial cluster are similar, the fourth perception parameters of the target extreme value points in the same initial cluster are similar, and the signal amplitudes of the target extreme value points in the same initial cluster are similar; the K value is less than or equal to the maximum value of the first number and the second number; A target clustering result is determined from the plurality of clustering results, and each initial cluster in the target clustering result is used as the target cluster.

23. The sensing receiving terminal according to claim 21, characterized in that: The processor executes, according to the cluster center of the target cluster, identifying the perception target in the synaesthesia environment, specifically: Determining the number of perceived targets in the synaesthesia environment according to the number of the target clusters; Each of the perceived targets is identified according to the third perception parameter of the cluster center of each of the target clusters and the fourth perception parameter.

24. The sensing receiving terminal according to any one of claims 14 to 23, characterized in that: The processor executes acquiring a perception periodogram corresponding to the first perception signal, specifically: Acquire a second perception signal sent by a perception sending end; The perceptual periodogram is determined according to the first perceptual signal and the second perceptual signal.

25. The sensing receiving terminal according to claim 24, characterized in that: The perception sending end and the perception receiving end are located in the same communication device, and the processor executes acquiring a second perception signal sent by the perception sending end, specifically: The second perception signal is obtained from the same communication device.

26. The sensing receiving terminal according to claim 24, characterized in that: The perception sending end and the perception receiving end are located in different communication devices, and the processor executes the acquisition of a second perception signal sent by the perception sending end, specifically: Acquire first pilot data of the sensing sending end; extracting second pilot data from the first perception signal; The first perception signal is restored based on the first pilot data and the second pilot symbol to obtain the second perception signal.

27. A device for identifying a sensing target, characterized in that: Applied to the sensing receiving end, including: A sensing unit, used to sense the synaesthesia environment and obtain a first sensing signal; An acquisition unit, configured to acquire a perceptual periodogram corresponding to the first perceptual signal; wherein the perceptual periodogram is used to indicate a corresponding relationship between a perceptual parameter and a signal amplitude; A processing unit, configured to determine a plurality of extreme value points from the perceptual periodogram, and screen the plurality of extreme value points based on signal amplitudes of the plurality of extreme value points to obtain a target extreme value point; A clustering unit, used for clustering each of the target extreme value points to obtain at least one target cluster; The identification unit is used to identify the perception target in the synaesthesia environment according to the cluster center of the target cluster.

28. A processor-readable storage medium, characterized in that: The processor-readable storage medium stores a computer program, and the computer program is used to enable the processor to execute the method according to any one of claims 1 to 13.

Images