A radar target identification method, device, equipment and storage medium

Abstract

The application discloses a radar target identification method, device and equipment and a storage medium, and the method comprises the following steps: acquiring radar data of at least one identification point; determining algorithm parameters corresponding to each identification point according to the radar data of the at least one identification point; and determining the identified radar target according to the algorithm output result by combining a set algorithm according to the algorithm parameters. The radar target identification method provided by the application can adaptively adjust the size of the algorithm parameters according to the radar data of each identification point, solve the problem of target merging or splitting caused by fixed algorithm parameters in the prior art, and can be applied to identification of different types and different sizes of targets, and the accuracy of target identification is improved.

Description

Technical Field

[0001] This invention relates to the field of intelligent vehicle technology, and in particular to a radar target identification method, device, equipment, and storage medium. Background Technology

[0002] With the continuous development of autonomous driving technology, millimeter-wave radar is being used more and more widely in the field of automotive driver assistance. Millimeter-wave radar can determine the status of a target by acquiring radar data reflected back from the target. However, a target usually has multiple reflection points, and it is necessary to distinguish and classify the multiple reflection points identified during target identification.

[0003] Existing technologies typically use clustering algorithms to process reflected radar data. These algorithms require pre-setting the neighborhood radius for clustering the point data and the minimum number of recognizable points within that radius, i.e., the density threshold. However, different targets have different reflective areas and reflective points. If the neighborhood radius and density threshold are set too large, multiple adjacent targets may be merged into one; conversely, if they are set too small, the same target may split into multiple targets. Summary of the Invention

[0004] This invention provides a method, apparatus, device, and storage medium for radar target identification, so as to achieve accurate identification of radar targets.

[0005] According to one aspect of the present invention, a method for identifying radar targets is provided, comprising:

[0006] Acquire radar data for at least one identification point;

[0007] The algorithm parameters corresponding to each identification point are determined based on the radar data of the at least one identification point.

[0008] Based on the algorithm parameters and the set algorithm, the identified radar target is determined according to the algorithm output.

[0009] Furthermore, the radar data includes amplitude and detection range.

[0010] Further, the algorithm parameters corresponding to each identification point are determined based on the radar data of the at least one identification point, including:

[0011] The first and second coefficients corresponding to each identification point are determined based on the amplitude and detection distance of the at least one identification point.

[0012] Obtain the initial values ​​of the parameters corresponding to the algorithm parameters;

[0013] The sum of the products of the first coefficient, the second coefficient, and the initial value of the parameter is determined as the algorithm parameter corresponding to each identification point.

[0014] Further, the first coefficient and the second coefficient corresponding to each of the at least one identification point are determined according to the amplitude and the detection distance of the identification point, including:

[0015] For each of the at least one identification point, the amplitude and the detection distance corresponding to the identification point are determined;

[0016] The maximum amplitude and the minimum amplitude in the amplitudes of the at least one identification point are determined, and the first coefficient is determined according to the amplitude corresponding to the identification point and the maximum amplitude and the minimum amplitude;

[0017] The product of the detection distance and a set scaling factor is determined as the second coefficient.

[0018] Further, the set algorithm includes a clustering algorithm, and the radar target identified according to the algorithm output result is determined according to the algorithm parameter and the set algorithm, including:

[0019] The clustering analysis is performed according to the algorithm parameter corresponding to each of the identification points, and a clustering cluster output by the set algorithm is determined;

[0020] The clustering cluster is determined as the radar target, and the clustering cluster corresponds to the radar target one by one.

[0021] Further, the algorithm parameter includes a neighborhood radius and a density threshold, the clustering analysis is performed according to the algorithm parameter corresponding to each of the identification points, and the clustering cluster output by the set algorithm is determined, including:

[0022] Any identification point in the at least one identification point is determined as a first target point;

[0023] The first neighborhood radius and the first density threshold corresponding to the first target point are obtained, and if the number of identification points in the first neighborhood radius range near the first target point is greater than or equal to the first density threshold, a clustering cluster is established, and the clustering cluster includes the first target point and the identification points in the first neighborhood radius range near the first target point;

[0024] The final size of the clustering cluster is determined according to the neighborhood radius and the density threshold corresponding to each of the identification points in the first neighborhood radius range near the first target point;

[0025] The clustering cluster is output, any identification point other than the clustering cluster is determined as a first target point, and the steps of obtaining the first neighborhood radius and the first density threshold corresponding to the first target point and establishing a clustering cluster if the number of identification points in the first neighborhood radius range near the first target point is greater than or equal to the first density threshold are returned to be executed until all identification points are traversed.

[0026] Further, the final size of the cluster is determined according to the neighborhood radius and the density threshold corresponding to each identified point within the first neighborhood radius range near the first target point, comprising:

[0027] The identified points within the first neighborhood radius range near the first target point are determined as second target points;

[0028] For each second target point, a second neighborhood radius and a second density threshold corresponding to the second target point are obtained, and if the number of identified points within the second neighborhood radius range near the second target point is greater than or equal to the second density threshold, the identified points within the second neighborhood radius range near the second target point are added to the cluster until all the second target points are traversed.

[0029] According to another aspect of the present application, a radar target identification device is provided, comprising:

[0030] A radar data acquisition module is configured to acquire radar data of at least one identified point;

[0031] An algorithm parameter determination module is configured to determine algorithm parameters corresponding to each identified point according to the radar data of the at least one identified point;

[0032] A radar target determination module is configured to determine the identified radar target according to the algorithm output result by combining a set algorithm according to the algorithm parameters.

[0033] Optionally, the radar data comprises amplitude and detection distance.

[0034] Optionally, the algorithm parameter determination module is further configured to:

[0035] determine a first coefficient and a second coefficient corresponding to each identified point according to the amplitude and the detection distance of the at least one identified point;

[0036] acquire a parameter initial value corresponding to the algorithm parameters;

[0037] determine the sum of the product of the first coefficient, the second coefficient and the parameter initial value as the algorithm parameters corresponding to each identified point.

[0038] Optionally, the algorithm parameter determination module is further configured to:

[0039] determine the amplitude and the detection distance corresponding to each identified point in the at least one identified point;

[0040] determine a maximum amplitude and a minimum amplitude in the amplitude of the at least one identified point, and determine the first coefficient according to the amplitude corresponding to the identified point and the maximum amplitude and the minimum amplitude;

[0041] determining a product of the detection distance and a set scaling factor as the second coefficient.

[0042] Optionally, the set algorithm comprises a clustering algorithm, and the radar target determination module is further configured to:

[0043] performing clustering analysis according to the algorithm parameters corresponding to the respective identified points, to determine a clustering cluster output by the set algorithm;

[0044] determining the clustering cluster as the radar target, the clustering cluster corresponding to the radar target in a one-to-one manner.

[0045] Optionally, the algorithm parameters comprise a neighborhood radius and a density threshold, and the radar target determination module is further configured to:

[0046] determining any identified point in the at least one identified point as a first target point;

[0047] obtaining a first neighborhood radius and a first density threshold corresponding to the first target point, and if the number of identified points within a first neighborhood radius range near the first target point is greater than or equal to the first density threshold, establishing a clustering cluster, the clustering cluster comprising the first target point and the identified points within the first neighborhood radius range near the first target point;

[0048] determining a final size of the clustering cluster according to the neighborhood radius and the density threshold corresponding to each identified point within the first neighborhood radius range near the first target point;

[0049] outputting the clustering cluster, determining any identified point other than the clustering cluster as a first target point, and returning to perform the steps of obtaining the first neighborhood radius and the first density threshold corresponding to the first target point, and if the number of identified points within a first neighborhood radius range near the first target point is greater than or equal to the first density threshold, establishing a clustering cluster, until all identified points are traversed.

[0050] Optionally, the radar target determination module is further configured to:

[0051] determining the identified points within a first neighborhood radius range near the first target point as second target points;

[0052] for each of the second target points, obtaining a second neighborhood radius and a second density threshold corresponding to the second target point, and if the number of identified points within a second neighborhood radius range near the second target point is greater than or equal to the second density threshold, adding the identified points within the second neighborhood radius range near the second target point to the clustering cluster, until all of the second target points are traversed.

[0053] According to another aspect of the present application, there is provided an electronic device, comprising:

[0054] at least one processor; and

[0055] a memory communicatively connected with the at least one processor; wherein

[0056] the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to perform the radar target identification method according to any one of the embodiments of the present application.

[0057] According to another aspect of the present application, a computer readable storage medium is provided, which stores computer instructions for enabling a processor to implement the radar target identification method according to any one of the embodiments of the present application when executed by the processor.

[0058] The radar target identification method disclosed by the present application firstly acquires radar data of at least one identification point, then determines algorithm parameters corresponding to each identification point according to the radar data of the at least one identification point, and finally determines the identified radar target according to the algorithm output result by combining the set algorithm according to the algorithm parameters. The radar target identification method provided by the present application solves the problem of target merging or splitting caused by fixed algorithm parameters in the prior art by adaptively adjusting the size of the algorithm parameters according to the radar data of each identification point, and can be applied to identification of different types and different sizes of targets, thereby improving the accuracy of target identification.

[0059] It should be understood that the content described in this part is not intended to identify key or important features of the embodiments of the present application, nor is it used to limit the scope of the present application. Other features of the present application will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0060] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0061] Figure 1 is a flow chart of a radar target identification method according to an embodiment of the present application;

[0062] Figure 2 is a flow chart of a radar target identification method according to an embodiment of the present application;

[0063] Figure 3 is a structural schematic diagram of a radar target identification device according to an embodiment of the present application;

[0064] Figure 4 is a structural schematic diagram of an electronic device for implementing the radar target recognition method of embodiment four of the present application. DETAILED DESCRIPTION

[0065] In order for those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should fall within the scope of protection of the present application.

[0066] It should be noted that the terms "first", "second", and the like in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily indicate a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but can include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0067] Embodiment one

[0068] Figure 1 A flowchart of a radar target recognition method provided for embodiment one of the present application, the present embodiment can be applicable to the case of target recognition using a radar device, and the method can be performed by a radar target recognition device, which can be realized in the form of hardware and / or software, and can be configured in an electronic device. As shown in the figure, the method comprises: Figure 1

[0069] S110, obtaining radar data of at least one recognition point.

[0070] In the use of radar for target recognition, the radar emits electromagnetic waves outwardly and receives the reflected electromagnetic wave signals, and then judges the state of the target. However, there can be multiple reflection points of reflected electromagnetic waves for one target, so for the same target, the radar can identify multiple point electromagnetic wave signals, each point being a recognition point. The radar data is the track data obtained by analyzing and processing the electromagnetic wave signals emitted and received by the radar, such as the amplitude, distance and other data corresponding to each recognition point.​

[0071] Preferably, the target recognition is usually performed by using a millimeter wave radar in the field of automobile auxiliary driving, wherein the millimeter wave radar is a radar working in a millimeter wave band (millimeter wave) for detection, and the frequency domain of the millimeter wave is usually 30-300 GHz (wavelength is 1-10 mm). The wavelength of the millimeter wave is between that of a microwave and that of a centimeter wave, so the millimeter wave radar has some advantages of both a microwave radar and an optoelectronic radar.

[0072] In this embodiment, the millimeter wave radar device on the vehicle is used to transmit and receive electromagnetic waves, and then the radar data of at least one recognition point is obtained by analyzing and processing the electromagnetic wave signals.

[0073] S120, determining algorithm parameters corresponding to each recognition point according to the radar data of the at least one recognition point.

[0074] In this embodiment, in order to accurately distinguish the target objects corresponding to each recognition point, the radar data obtained is processed by an algorithm to determine the target objects to which each recognition point belongs. Since the radar cross sections (RCS) of different types and different sizes of target objects are different, the radar data of each recognition point is also different. Therefore, when the radar data of each recognition point is processed by an algorithm, the corresponding algorithm parameters can be adaptively adjusted according to the radar data of each recognition point, so as to achieve the purpose of dynamic detection and more accurate analysis.

[0075] Optionally, taking a clustering algorithm as an example, when the clustering algorithm is used to process the radar data, the corresponding algorithm parameters are neighborhood radius and density threshold. Based on these parameters, the algorithm can output one or more clustering clusters, and each clustering cluster can be considered as a target object. When the corresponding neighborhood radius and density threshold are adaptively determined according to the radar data of each recognition point, the clustering clusters output by the algorithm can be more accurate, thereby avoiding the problems of merging or splitting of targets caused by fixed algorithm parameters.

[0076] S130, determining the recognized radar target according to the algorithm output result based on the algorithm parameters and the set algorithm.

[0077] In this embodiment, after the algorithm parameters corresponding to each recognition point are determined, the radar data is used as an input variable to calculate the output result of the algorithm by using the corresponding algorithm, and then the recognized radar target can be determined according to the algorithm output result.

[0078] The radar target recognition method disclosed by the embodiment of the present application firstly acquires radar data of at least one recognition point, then determines algorithm parameters corresponding to each recognition point according to the radar data of the at least one recognition point, and finally determines the recognized radar target according to an algorithm output result in combination with a set algorithm according to the algorithm parameters. The radar target recognition method provided by the embodiment of the present application solves the problem of target merging or splitting caused by fixed algorithm parameters in the prior art by adaptively adjusting the size of the algorithm parameters according to the radar data of each recognition point, can be applied to target recognition of different types and different sizes, and improves the accuracy of target recognition.

[0079] Embodiment two

[0080] Figure 2 A flowchart of a radar target recognition method provided by the embodiment two of the present application, and the embodiment is a refinement of the above-mentioned embodiment. As shown in the figure, the method comprises the following steps. Figure 2

[0081] S210, radar data of at least one recognition point is acquired.

[0082] In the embodiment, when target recognition is performed by using a radar, the radar emits electromagnetic waves outwardly, receives reflected electromagnetic wave signals, and then judges the state of the target. However, one target may have multiple reflection points of reflected electromagnetic waves, and therefore, the radar may recognize multiple point electromagnetic wave signals of the same target, each point being a recognition point. The radar data is track data obtained by analyzing and processing the electromagnetic wave signals emitted and received by the radar, such as amplitude, distance and other data corresponding to each recognition point.

[0083] Optionally, the radar data comprises amplitude and detection distance, and the radar data of at least one recognition point can be acquired by using a radar device to send and receive electromagnetic waves, and then analyzing and processing the electromagnetic wave signals to obtain the amplitude and detection distance corresponding to each recognition point of the nearby target.

[0084] S220, a first coefficient and a second coefficient corresponding to each recognition point are determined according to the amplitude and detection distance of the at least one recognition point.

[0085] The first coefficient and the second coefficient are related coefficients of algorithm parameters used for radar data processing, and by determining the first coefficient and the second coefficient, the algorithm parameters corresponding to each recognition point can be determined.

[0086] ​Optionally, the manner of determining the first coefficient and the second coefficient corresponding to each identification point according to the amplitude and the detection distance of the at least one identification point can be: determining the amplitude and the detection distance corresponding to each of the at least one identification point; determining the maximum amplitude and the minimum amplitude in the amplitudes of the at least one identification point, and determining the first coefficient according to the amplitude corresponding to the identification point and the maximum amplitude and the minimum amplitude; and determining the second coefficient as the product of the detection distance and a set scaling factor.

[0087] Specifically, it is assumed that N identification points are collected by the radar device, and the amplitudes and the detection distances of each point are recorded as {A1, A2,..., A N} and {D1, D2,..., D N}, respectively. By comparing the amplitudes of the points, the maximum amplitude A max and the minimum amplitude A min can be found. For any identification point i (i = 1, 2,..., N), the corresponding first coefficient can be represented as:

[0088]

[0089] The second coefficient can be represented as:

[0090] b i = cor2 x D i

[0091] wherein cor1 and cor2 are scaling factors.

[0092] In S230, a parameter initial value corresponding to an algorithm parameter is obtained, and a sum of the product of the first coefficient, the second coefficient, and the parameter initial value is determined as the algorithm parameter corresponding to each identification point.

[0093] In the embodiment, the parameter initial value can be obtained by initializing the algorithm, and the algorithm parameter corresponding to each identification point can be determined by combining the first coefficient and the second coefficient corresponding to each identification point determined in the previous step.

[0094] Optionally, taking a clustering algorithm as an example, the algorithm parameters related to the clustering algorithm are a neighborhood radius and a density threshold, which are represented as Eps and minPts, respectively. By initializing the operation, an initial neighborhood radius and an initial density threshold can be obtained, which are represented as R -eps and T -pts , respectively. For any identification point i (i = 1, 2,..., N), the corresponding neighborhood radius can be represented as:

[0095] Eps i = a i x R -eps + b i x R -eps

[0096] The density threshold can be expressed as:

[0097] minPts i = a i × T -pts + b i × T -pts

[0098] S240, clustering analysis is performed according to the algorithm parameters corresponding to each identification point to determine the clustering cluster output by the set algorithm.

[0099] The set algorithm includes a clustering algorithm. The clustering algorithm is a statistical analysis method for research (sample or index) classification problems, and is also an important algorithm for data mining. Cluster analysis is composed of a plurality of patterns. Usually, a pattern is a vector of measurements or a point in a multi-dimensional space. Cluster analysis is based on similarity, and the patterns in a cluster have more similarity than the patterns not in the same cluster.

[0100] Preferably, the DBSCAN clustering algorithm in the clustering algorithm can be used for data processing. DBSCAN (Density-Based Spatial Clustering of Applications with Noise) is a representative density-based clustering algorithm. Unlike partitioning and hierarchical clustering methods, it defines a cluster as the maximum set of density-connected points, and can divide regions with sufficiently high density into clusters and find clusters of arbitrary shape in a noisy spatial database.

[0101] In the embodiment, the radar data of each identification point is processed by the clustering algorithm, and the output of the algorithm is one or more clustering clusters. In the clustering analysis, the algorithm parameters corresponding to each identification point are adaptively determined according to the radar data of each point.

[0102] Optionally, the algorithm parameters include a neighborhood radius and a density threshold value, and the clustering analysis is performed according to the algorithm parameters corresponding to each recognition point. The manner of determining the clustering cluster output by the set algorithm can be: determining any recognition point in the at least one recognition point as a first target point; obtaining a first neighborhood radius and a first density threshold value corresponding to the first target point; if the number of recognition points within the first neighborhood radius range near the first target point is greater than or equal to the first density threshold value, a clustering cluster is established, and the clustering cluster includes the first target point and the recognition points within the first neighborhood radius range near the first target point; determining the final size of the clustering cluster according to the neighborhood radius and the density threshold value corresponding to each recognition point within the first neighborhood radius range near the first target point; outputting the clustering cluster, determining any recognition point other than the clustering cluster as the first target point, and returning to execute the step of obtaining the first neighborhood radius and the first density threshold value corresponding to the first target point, if the number of recognition points within the first neighborhood radius range near the first target point is greater than or equal to the first density threshold value, a clustering cluster is established, until all recognition points are traversed.

[0103] Further, the manner of determining the final size of the clustering cluster according to the neighborhood radius and the density threshold value corresponding to each recognition point within the first neighborhood radius range near the first target point can be: determining the recognition points within the first neighborhood radius range near the first target point as second target points; for each second target point, obtaining a second neighborhood radius and a second density threshold value corresponding to the second target point, if the number of recognition points within the second neighborhood radius range near the second target point is greater than or equal to the second density threshold value, adding the recognition points within the second neighborhood radius range near the second target point to the clustering cluster, until all second target points are traversed.

[0104] Specifically, for the N recognition points obtained, each point can be marked as an unvisited object, that is, the flag information of each point can be set as flag = "unvisited". One of the recognition points i (i = 1, 2,..., N) is selected as a first target point, and the first target point is marked as an visited object, that is, flag i = "visited", and the neighborhood radius and the density threshold value thereof are obtained as Eps i and minPts i , respectively, where Eps i = a i × R -eps + b i × R -eps , and minPts i = a i × T -pts + b i × T -pts . If the number of recognition points within a circle with the first target point i as the center and Eps i as the radius is greater than or equal to minPts iThen, a new cluster M is created, and the first target point i and its neighborhood radius Eps are set together. i All identification points within the range are added to cluster M; if the neighborhood radius of the first target point i is Eps i The number of internal target points is less than minPts i If so, then the first target point i is marked as a noise point.

[0105] Assuming there are K identification points in cluster M, then for one identification point j, determine its flag information. j Is it equal to "unvisited"? If so, then identify point j as the second target point and set flag... j ="visited", determines its neighborhood radius and density threshold as Eps respectively. j and minPts j If not, then search again for points in cluster M with the flag "unvisited". Where Eps j =a j ×R -eps +b j ×R -eps minPts j =a j ×T -pts +b j ×T -pts Determine the neighborhood radius Eps of the second target point j. j Is the number of identification points within greater than minPts? j If so, add the points in the neighborhood to cluster M. Iterate through all K identification points until all points in cluster M are marked as "visited", output cluster M, re-determine any identification point outside cluster M as the first target point, return to perform the cluster building operation, until all N identification points are marked as "visited".

[0106] S250. The clusters are identified as radar targets, and there is a one-to-one correspondence between the clusters and the radar targets.

[0107] In this embodiment, the clustering algorithm outputs one or more clusters, each cluster corresponding to a radar target. Through the above steps, identification points belonging to different target objects can be distinguished, and identification points belonging to the same target object can be unified, thereby determining the target finally identified by the radar.

[0108] The radar target identification method disclosed in this invention first acquires radar data for at least one identification point. Then, based on the amplitude and detection range of the at least one identification point, it determines a first coefficient and a second coefficient corresponding to each identification point. Next, it acquires the initial values ​​of the algorithm parameters. The sum of the products of the first coefficient, the second coefficient, and the initial values ​​of the parameters is determined as the algorithm parameters corresponding to each identification point. Then, it performs cluster analysis based on the algorithm parameters corresponding to each identification point to determine the clusters output by the set algorithm. Finally, it identifies the clusters as radar targets, with a one-to-one correspondence between the clusters and radar targets. The radar target identification method provided in this invention uses a clustering algorithm to analyze radar data and adaptively adjusts the neighborhood radius and density threshold based on the radar data of each identification point. This solves the problem of target merging or splitting caused by fixed algorithm parameters in the prior art, and is applicable to the identification of targets of different types and sizes, improving the accuracy of target identification.

[0109] Example 3

[0110] Figure 3 This is a schematic diagram of the structure of a radar target identification device provided in Embodiment 3 of the present invention. Figure 3 As shown, the device includes: a radar data acquisition module 310, an algorithm parameter determination module 320, and a radar target determination module 330.

[0111] The radar data acquisition module 310 is used to acquire radar data of at least one identification point.

[0112] The algorithm parameter determination module 320 is used to determine the algorithm parameters corresponding to each identification point based on radar data of at least one identification point.

[0113] The radar target determination module 330 is used to determine the identified radar target based on the algorithm parameters, the set algorithm, and the algorithm output results.

[0114] Optionally, radar data includes amplitude and detection range.

[0115] Optionally, the algorithm parameter determination module 320 is also used for:

[0116] The first and second coefficients corresponding to each identification point are determined based on the amplitude and detection distance of at least one identification point; the initial values ​​of the algorithm parameters are obtained; and the sum of the products of the first and second coefficients and the initial values ​​of the parameters is determined as the algorithm parameters corresponding to each identification point.

[0117] Optionally, the algorithm parameter determination module 320 is also used for:

[0118] For each of the at least one identified point, a corresponding amplitude and a detection distance of the identified point are determined; a maximum amplitude and a minimum amplitude in the amplitudes of the at least one identified point are determined; a first coefficient is determined according to the corresponding amplitude of the identified point and the maximum amplitude and the minimum amplitude; and a product of the detection distance and a set scaling factor is determined as a second coefficient.

[0119] Optionally, the set algorithm comprises a clustering algorithm, and the radar target determination module 330 is further configured to:

[0120] According to the algorithm parameters corresponding to the identified points, clustering analysis is performed to determine a clustering cluster output by the set algorithm; and the clustering cluster is determined as the radar target, and the clustering cluster and the radar target correspond one by one.

[0121] Optionally, the algorithm parameters comprise a neighborhood radius and a density threshold, and the radar target determination module 330 is further configured to:

[0122] Any identified point in the at least one identified point is determined as a first target point; a first neighborhood radius and a first density threshold corresponding to the first target point are obtained; if the number of identified points within the first neighborhood radius range near the first target point is greater than or equal to the first density threshold, a clustering cluster is established, and the clustering cluster comprises the first target point and the identified points within the first neighborhood radius range near the first target point; the final size of the clustering cluster is determined according to the neighborhood radius and the density threshold corresponding to each identified point within the first neighborhood radius range near the first target point; the clustering cluster is output, any identified point other than the clustering cluster is determined as the first target point, and the step of obtaining the first neighborhood radius and the first density threshold corresponding to the first target point is returned to be executed, if the number of identified points within the first neighborhood radius range near the first target point is greater than or equal to the first density threshold, the clustering cluster is established, until all identified points are traversed.

[0123] Optionally, the radar target determination module 330 is further configured to:

[0124] The identified points within the first neighborhood radius range near the first target point are determined as second target points; for each second target point, a second neighborhood radius and a second density threshold corresponding to the second target point are obtained; if the number of identified points within the second neighborhood radius range near the second target point is greater than or equal to the second density threshold, the identified points within the second neighborhood radius range near the second target point are added to the clustering cluster, until all second target points are traversed.

[0125] The radar target identification device provided in the embodiments of the present application can execute the radar target identification method provided in any of the embodiments of the present application, and has the corresponding function modules and beneficial effects of the execution method.

[0126] Embodiment Four

[0127] Figure 4A schematic diagram of an electronic device 10 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0128] like Figure 4 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0129] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0130] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as radar target identification methods.

[0131] In some embodiments, the method of radar target recognition can be implemented as a computer program tangibly embodied in a computer readable storage medium, e.g., storage unit 18. In some embodiments, parts or all of the computer program can be loaded and / or installed onto electronic device 10 via, e.g., ROM 12 and / or communication unit 19. When the computer program is loaded onto RAM 13 and executed by processor 11, one or more of the steps of the method of radar target recognition described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to perform the method of radar target recognition by other means, e.g., with the aid of firmware.

[0132] Various implementations of the systems and techniques described above can be realized in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a programmable logic device (PLD), a computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0133] Computer programs used to implement the methods of the present application can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the computer program, when executed by the processor of the machine, implements the functions / acts specified in the flowcharts and / or block diagrams. The computer program can be executed entirely on a machine, partially on a machine, partially on a machine as a stand-alone software package, partially on a machine and partially on a remote machine or entirely on a remote machine or server.

[0134] In the context of the present application, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. A computer-readable storage medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. More specific examples of a machine-readable storage medium will include one or more lines of a program of instructions in a transitory signal, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0135] To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the electronic device. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0136] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0137] The computing system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system, to solve the defects of large management difficulty and weak business scalability in traditional physical host and VPS service.

[0138] It should be understood that the various forms of flow shown above can be reordered, added to, or have steps deleted. For example, the steps described in the present application can be performed in parallel, in series, or in a different order, as long as the desired results of the technical solutions of the present application can be achieved, and this is not limited herein.

[0139] The above detailed description does not constitute a limitation on the protection scope of the present application. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent replacements, and improvements made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method for identifying radar targets, characterized in that, include: Acquire radar data for at least one identification point; The algorithm parameters corresponding to each identification point are determined based on the radar data of the at least one identification point. Based on the algorithm parameters and the set algorithm, the identified radar target is determined according to the algorithm output results; The method for obtaining radar data for at least one identification point is to use vehicle-mounted millimeter-wave radar equipment to transmit and receive electromagnetic waves, analyze and process the electromagnetic wave signals, and obtain radar data for at least one identification point corresponding to a nearby target. The set algorithm includes a clustering algorithm. When the clustering algorithm is applied, the identified radar target is determined based on the algorithm parameters, the set algorithm, and the algorithm output results, including: Cluster analysis is performed based on the algorithm parameters corresponding to each identification point to determine the clusters output by the set algorithm; The clusters are identified as radar targets, and each cluster corresponds one-to-one with a radar target; The algorithm parameters include neighborhood radius and density threshold. Cluster analysis is performed based on the algorithm parameters corresponding to each identification point to determine the clusters output by the set algorithm, including: Any one of the at least one identification points is designated as the first target point; Obtain the first neighborhood radius and the first density threshold corresponding to the first target point. If the number of identification points within the first neighborhood radius of the first target point is greater than or equal to the first density threshold, then establish a cluster. The cluster includes the first target point and the identification points within the first neighborhood radius of the first target point. The final size of the cluster is determined based on the neighborhood radius and density threshold of each identification point within the first neighborhood radius of the first target point; Output the cluster, determine any identification point outside the cluster as the first target point, return to execute the step of obtaining the first neighborhood radius and the first density threshold corresponding to the first target point, and if the number of identification points within the first neighborhood radius near the first target point is greater than or equal to the first density threshold, then establish the cluster, until all identification points are traversed; The determination of the final size of the cluster based on the neighborhood radius and density threshold of each identification point within a first neighborhood radius near the first target point includes: Identification points within a first neighborhood radius of the first target point are identified as the second target point; For each second target point, obtain the second neighborhood radius and the second density threshold corresponding to the second target point. If the number of identification points within the second neighborhood radius of the second target point is greater than or equal to the second density threshold, then add the identification points within the second neighborhood radius of the second target point to the cluster, until all second target points are traversed.

2. The method according to claim 1, characterized in that, The radar data includes amplitude and detection range.

3. The method according to claim 2, characterized in that, Determine the algorithm parameters corresponding to each identification point based on the radar data of the at least one identification point, including: The first and second coefficients corresponding to each identification point are determined based on the amplitude and detection distance of the at least one identification point. Obtain the initial values ​​of the parameters corresponding to the algorithm parameters; The sum of the products of the first coefficient, the second coefficient, and the initial value of the parameter is determined as the algorithm parameter corresponding to each identification point.

4. The method according to claim 3, characterized in that, Determining the first and second coefficients corresponding to each identification point based on the amplitude and detection distance of the at least one identification point includes: For each of the at least one identification point, determine the amplitude and detection distance corresponding to that identification point; Determine the maximum and minimum amplitude values ​​among the amplitude values ​​of the at least one identification point, and determine the first coefficient based on the amplitude value corresponding to the identification point and the maximum and minimum amplitude values; The product of the detection distance and the set scaling factor is determined as the second coefficient.

5. A radar target identification device, characterized in that, include: The radar data acquisition module is used to acquire radar data for at least one identification point; The algorithm parameter determination module is used to determine the algorithm parameters corresponding to each identification point based on the radar data of the at least one identification point. The radar target determination module is used to determine the identified radar target based on the algorithm parameters, combined with a set algorithm, and the algorithm output result. The acquisition of radar data for at least one identification point includes using vehicle-mounted millimeter-wave radar equipment to transmit and receive electromagnetic waves, and then analyzing and processing the electromagnetic wave signals to obtain radar data for at least one identification point corresponding to a nearby target. The algorithm parameter determination module is also used for: Determine the first and second coefficients corresponding to each identification point based on the amplitude and detection distance of at least one identification point; obtain the initial values ​​of the algorithm parameters; and determine the algorithm parameters corresponding to each identification point by summing the products of the first and second coefficients and the initial values ​​of the parameters. For each of the at least one identification point, determine the amplitude and detection distance corresponding to the identification point; determine the maximum and minimum amplitude values ​​among the amplitude values ​​of the at least one identification point; determine a first coefficient based on the amplitude value corresponding to the identification point and the maximum and minimum amplitude values; and determine a second coefficient by multiplying the detection distance by a set scaling factor. The radar target determination module is also used for: Cluster analysis is performed based on the algorithm parameters corresponding to each identification point to determine the clusters output by the set algorithm; the clusters are identified as radar targets, and there is a one-to-one correspondence between the clusters and radar targets; the set algorithm includes a clustering algorithm; The algorithm identifies any one of at least one identification point as the first target point; obtains the first neighborhood radius and first density threshold corresponding to the first target point; if the number of identification points within the first neighborhood radius of the first target point is greater than or equal to the first density threshold, a cluster is established, which includes the first target point and the identification points within the first neighborhood radius of the first target point; the final size of the cluster is determined based on the neighborhood radius and density threshold corresponding to each identification point within the first neighborhood radius of the first target point; the cluster is output, and any identification point outside the cluster is identified as the first target point. The algorithm then returns to the previous steps of obtaining the first neighborhood radius and first density threshold corresponding to the first target point and establishing a cluster if the number of identification points within the first neighborhood radius of the first target point is greater than or equal to the first density threshold, until all identification points are traversed; the algorithm parameters include the neighborhood radius and density threshold. Identification points within a first neighborhood radius of the first target point are identified as the second target point; For each second target point, obtain the second neighborhood radius and the second density threshold corresponding to the second target point. If the number of identification points within the second neighborhood radius of the second target point is greater than or equal to the second density threshold, then add the identification points within the second neighborhood radius of the second target point to the cluster, until all second target points are traversed.

6. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the radar target identification method according to any one of claims 1-4.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the radar target identification method according to any one of claims 1-4.

Images