Radar False Alarm Suppression Method, Device, Storage Medium and Electronic Device

Abstract

This application relates to the field of radar detection technology, and specifically relates to a method, device, storage medium and electronic device for suppressing radar false alarms. The method includes: obtaining a plurality of consecutive target traces within an association threshold; classifying each target trace among the plurality of target traces according to a pre-established trace classification model; and suppressing false alarms for the plurality of target traces according to the classification results. In the above embodiment, through the pre-established trace classification model, the category of a plurality of consecutive target traces within the association threshold can be output based on data storage and learning marking of the environment, and then false alarms are suppressed according to the categories of the plurality of target traces. This method has advantages such as low cost, good real-time performance, and simple implementation, can effectively suppress radar false tracks, and improve the environmental adaptability and target tracking performance of the radar.

Description

Technical Field

[0001] The present application relates to the technical field of radar detection, and particularly to a method, device, storage medium and electronic device for suppressing radar false alarms. Background Art

[0002] Low-altitude small aircraft are easy to operate and convenient to take off and land. In particular, the market for unmanned aerial vehicles (UAVs), radio-controlled helicopters, and multi-rotor small UAVs has increased rapidly. However, this has brought huge potential hazards to society, military, and public safety. Radar faces many difficulties in achieving stable detection of low-altitude and ultra-low-altitude targets. When a Doppler radar is working, in order to achieve early warning detection of low-altitude and ultra-low-altitude targets, the key target types it focuses on are low-altitude slow small targets, hereinafter referred to as "low, slow, and small" targets. The motion characteristics of "low, slow, and small" targets are low flight altitude, slow flight speed, and low signal-to-noise ratio, etc.

[0003] Traditional radar target detection technology uses the false alarm rate to set a threshold and performs intensity / amplitude detection on the radar received echoes. As long as the data passing the threshold are retained as possible target information. The data passing the threshold are divided into two categories. The first category of data contains target information and is expected data, and it is hoped to obtain it as comprehensively as possible. Omitting this kind of information will cause instability in target tracking. The second category of data does not contain any target information and is non-expected data. If the proportion of this kind of data is relatively large, it will greatly increase the processing difficulty of the backend targets, resulting in an increase in false tracks. In severe cases, it may even cause the real targets to not be tracked normally. In order to ensure the stable detection of "low, slow, and small" targets, the threshold will be appropriately reduced, which will result in a large number of non-expected targets being detected, bringing difficulties to subsequent track initiation and tracking. Summary of the Invention

[0004] Aiming at the problem in the prior art that using the false alarm rate to set the threshold causes a large number of non-expected targets to be detected, bringing difficulties to subsequent track initiation and tracking, the present application provides a method, device, storage medium and electronic device for suppressing radar false alarms.

[0005] In a first aspect, the present application provides a method for suppressing radar false alarms, the method comprising:

[0006] Obtaining a plurality of consecutive target traces within an associated threshold;

[0007] Classifying each of the plurality of target traces according to a pre-established trace classification model;

[0008] Suppressing false alarms of the plurality of target traces according to the classification results.

[0009] In the above embodiments, through the pre-established point track classification model, the categories of multiple target point tracks continuous within the association threshold can be output based on data storage and learning marking of the environment, and then false alarm suppression can be performed according to the categories of the multiple target point tracks. This method has advantages such as low cost, good real-time performance, and being simple and easy to implement, can effectively suppress false radar tracks, and improve the environmental adaptability and target tracking performance of the radar.

[0010] According to an embodiment of the present application, optionally, before the step of classifying each target point track among the multiple target point tracks according to the pre-established point track classification model in the above radar false alarm suppression method, it includes:

[0011] Obtain the sample point track data of all sample point tracks corresponding to at least one detection period and the point track type identifier of the sample point track;

[0012] Generate a point track classification model based on the sample point track data of the sample point track and the point track type identifier of the sample point track.

[0013] In the above embodiments, obtaining the sample point track data and the sample point track type identifier corresponding to all sample point tracks corresponding to at least one detection period ensures the accuracy of the sample data. The point track classification model generated based on the sample point track data and the sample point track type identifier corresponding to all sample point tracks can accurately judge the point track type identifier and classify the point tracks.

[0014] According to an embodiment of the present application, optionally, in the above radar false alarm suppression method, the step of generating a point track classification model based on the sample point track data of the sample point track and the point track type identifier of the sample point track includes:

[0015] Obtain the feature data corresponding to the sample point track data of each sample point track;

[0016] Train a learning trainer based on the feature data and the point track type identifier of the sample point track to generate a point track classification model.

[0017] According to an embodiment of the present application, optionally, in the above radar false alarm suppression method, the step of obtaining the feature data corresponding to the sample point track data of each sample point track includes:

[0018] Process the sample point track data of each sample point track respectively to obtain the corresponding two-dimensional detection information;

[0019] Feed back the two-dimensional detection information based on the inverse fast Fourier transform to obtain the time-domain data and frequency-domain data corresponding to each sample point track;

[0020] Obtain the feature quantization value based on the time-domain data and the frequency-domain data;

[0021] Perform feature normalization based on the feature quantization values to obtain feature data.

[0022] According to an embodiment of the present application, optionally, in the above radar false alarm suppression method, the feature quantization values include phase coefficients, waveform entropy, and energy ratio features.

[0023] According to an embodiment of the present application, optionally, in the above radar false alarm suppression method, the method further includes:

[0024] Regularly obtain the track data and track type identifiers of multiple traces as calibration data;

[0025] Calibrate the trace classification model based on the calibration data.

[0026] According to an embodiment of the present application, optionally, in the above radar false alarm suppression method, the step of suppressing false alarms for the multiple target traces according to the classification result includes:

[0027] Obtain the number of clutter traces in the classification results of multiple target traces;

[0028] When the number of clutter traces is greater than a preset threshold, regard the tracks corresponding to the multiple target traces as false targets.

[0029] In a second aspect, the present application further provides a radar false alarm suppression device, the device includes:

[0030] A target trace acquisition module, configured to acquire multiple consecutive target traces within an association threshold;

[0031] A trace classification module, configured to classify each target trace in the multiple target traces according to a pre-established trace classification model;

[0032] A false alarm suppression module, configured to suppress false alarms for the multiple target traces according to the classification result.

[0033] According to an embodiment of the present application, optionally, in the above radar false alarm suppression device, the device includes:

[0034] A sample acquisition module, configured to acquire the sample trace data of all sample traces corresponding to at least one detection period and the trace type identifier of the sample traces;

[0035] A trace classification model generation module, configured to generate a trace classification model based on the sample trace data of the sample traces and the trace type identifier of the sample traces.

[0036] According to an embodiment of the present application, optionally, in the above radar false alarm suppression device, the track classification model generation module includes:

[0037] A feature data acquisition unit, configured to acquire feature data corresponding to the sample track data of each sample track;

[0038] A track classification model training unit, configured to train a trainer based on the feature data and the track type identifier of the sample track to generate a track classification model.

[0039] According to an embodiment of the present application, optionally, in the above radar false alarm suppression device, the feature data acquisition unit includes:

[0040] A track data processing subunit, configured to process the sample track data of each sample track respectively to obtain corresponding two-dimensional detection information;

[0041] A time-domain data and frequency-domain data acquisition subunit, configured to obtain time-domain data and frequency-domain data corresponding to each sample track by feedback of the two-dimensional detection information based on inverse fast Fourier transform;

[0042] A feature quantization value acquisition subunit, configured to acquire a feature quantization value based on the time-domain data and the frequency-domain data;

[0043] A feature normalization subunit, configured to perform feature normalization based on the feature quantization value to obtain feature data.

[0044] According to an embodiment of the present application, optionally, in the above radar false alarm suppression device, the feature quantization value includes a phase coefficient, a waveform entropy, and an energy ratio feature.

[0045] According to an embodiment of the present application, optionally, in the above radar false alarm suppression device, the method further includes:

[0046] A calibration data acquisition module, configured to periodically acquire the track data and the track type identifier of multiple tracks as calibration data;

[0047] A model calibration module, configured to calibrate the track classification model based on the calibration data.

[0048] According to an embodiment of the present application, optionally, in the above radar false alarm suppression device, the false alarm suppression module includes:

[0049] A clutter track quantity acquisition unit, configured to acquire the quantity of clutter tracks in the classification results of multiple target tracks;

[0050] A false alarm suppression unit, configured to use the tracks corresponding to the multiple target tracks as false targets when the quantity of the clutter tracks is greater than a preset threshold.

[0051] In a third aspect, the present application provides a storage medium storing a computer program executable by one or more processors and used to implement the radar false alarm suppression method as described above.

[0052] In a fourth aspect, the present application provides an electronic device including a memory and a processor, where a computer program is stored on the memory, and when the computer program is executed by the processor, the above-mentioned radar false alarm suppression method is executed.

[0053] Compared with the prior art, one or more embodiments of the above solutions may have the following advantages or beneficial effects:

[0054] A radar false alarm suppression method, device, storage medium and electronic device provided by the present application, the method includes: obtaining a plurality of consecutive target traces within an association threshold; classifying each target trace among the plurality of target traces according to a pre-established trace classification model; and suppressing false alarms for the plurality of target traces according to the classification results. In the above implementation manner, through the pre-established trace classification model, the category of a plurality of consecutive target traces within the association threshold can be output based on data storage and learning marking of the environment, and then false alarm suppression is performed according to the categories of the plurality of target traces. This method has advantages such as low cost, good real-time performance, and simple implementation, can effectively suppress radar false tracks, and improve the environmental adaptability and target tracking performance of the radar. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Hereinafter, the present application will be described in more detail based on embodiments with reference to the drawings.

[0056] Figure 1 FIG. is a schematic flowchart of a radar false alarm suppression method provided in Embodiment 1 of the present application.

[0057] Figure 2 FIG. is a linear classification illustration diagram of a radar false alarm suppression method provided in Embodiment 3 of the present application.

[0058] Figure 3 FIG. is a schematic diagram of target tracking classification association provided in Embodiment 3 of the present application.

[0059] Figure 4 FIG. is a schematic structural diagram of a radar false alarm suppression device provided in Embodiment 4 of the present application.

[0060] Figure 5 FIG. is a connection block diagram of an electronic device provided in Embodiment 6 of the present application.

[0061] In the drawings, the same components are denoted by the same reference numerals, and the drawings are not drawn to actual scale. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0062] The following will combine the accompanying drawings and embodiments to detail the implementation manners of the present application, so as to fully understand how the present application uses technical means to solve technical problems and the implementation process of achieving corresponding technical effects and implement accordingly. Each feature in the embodiments of the present application can be combined with each other on the premise of not conflicting, and the formed technical solutions are all within the protection scope of the present application.

[0063] Example 1

[0064] The present invention provides a method for suppressing radar false alarms. Please refer to Figure 1 , and the method includes the following steps:

[0065] Step S110: Obtain a plurality of consecutive target traces within an associated threshold;

[0066] Step S120: Classify each of the plurality of target traces according to a pre-established trace classification model;

[0067] Among them, before step S120 of classifying each of the plurality of target traces according to the pre-established trace classification model, the trace classification model can be established through the following steps:

[0068] Step S121: Obtain the sample trace data of all sample traces corresponding to at least one detection period and the trace type identifier of the sample traces.

[0069] The sample trace data of all sample traces corresponding to one detection period and the type of the sample traces can accurately reflect the detection situation of the radar within one detection period. Therefore, the sample trace data and the sample trace type identifier corresponding to all sample traces corresponding to at least one detection period can be obtained to ensure the accuracy of the sample data.

[0070] Step S122: Generate a trace classification model based on the sample trace data of the sample traces and the trace type identifier of the sample traces.

[0071] The trace classification model generated according to the sample trace data and the trace type identifier corresponding to all sample traces can accurately judge the trace type identifier and classify the traces.

[0072] Step S130: Suppress false alarms for the plurality of target traces according to the classification results.

[0073] When suppressing false alarms for the multiple target traces according to the classification results, the number of clutter traces in the classification results of the multiple target traces can be obtained first, and then when the number of the clutter traces is greater than a preset threshold, the traces corresponding to the multiple target traces are regarded as false targets.

[0074] For example, if more than 2 traces out of 3 consecutive traces forming a temporary track among the multiple target traces belong to clutter traces, then the track is marked as a false target and no track initiation is performed, that is, false alarm suppression is carried out.

[0075] It can be understood that false alarm suppression for the multiple target traces can also be carried out in a similar way according to the classification results. For example, after classifying each target trace among the multiple target traces according to a pre-established trace classification model, each target trace is assigned a value to represent the classification result. For example, a target trace belonging to a clutter trace is assigned a value of 0, and a target trace not belonging to a clutter trace is assigned a value of 1. Then, the sum of the assigned values of all the assigned target traces can be calculated, and it is determined whether to perform false alarm suppression according to this sum. For example, if there are three target traces in total, and the sum value calculated after assigning values to the three target traces is greater than 1, that is, false alarm suppression is carried out, that is, the target trace is filtered and not displayed. If the sum is less than or equal to 1, it is processed according to the normal track initiation process.

[0076] According to an embodiment of the present application, optionally, in the above radar false alarm suppression method, the method further includes:

[0077] Regularly obtaining the trace data and trace type identifiers of multiple traces as calibration data;

[0078] Calibrating the trace classification model based on the calibration data.

[0079] In summary, the present application provides a radar false alarm suppression method, including: obtaining multiple consecutive target traces within an association threshold; classifying each target trace among the multiple target traces according to a pre-established trace classification model; suppressing false alarms for the multiple target traces according to the classification results. In the above implementation manner, through the pre-established trace classification model, the categories of multiple consecutive target traces within the association threshold can be output based on the data storage and learning marking of the environment, and then false alarm suppression is carried out according to the categories of the multiple target traces. This method has the advantages of low cost, good real-time performance, simple and easy implementation, etc., can effectively suppress radar false tracks, and improve the environmental adaptability and target tracking performance of the radar.

[0080] Example 2

[0081] On the basis of Embodiment 1, this embodiment illustrates the method in Embodiment 1 through a specific implementation case.

[0082] According to an embodiment of the present application, optionally, in the above radar false alarm suppression method, the step of generating a point track classification model based on the sample point track data of the sample point track and the point track type identifier of the sample point track includes:

[0083] Obtain the feature data corresponding to the sample point track data of each sample point track;

[0084] Train a learning trainer based on the feature data and the point track type identifier of the sample point track to generate a point track classification model.

[0085] According to an embodiment of the present application, optionally, in the above radar false alarm suppression method, the step of obtaining the feature data corresponding to the sample point track data of each sample point track includes:

[0086] Process the sample point track data of each sample point track respectively to obtain corresponding two-dimensional detection information;

[0087] Based on the inverse fast Fourier transform, feedback the two-dimensional detection information to obtain the time domain data and frequency domain data corresponding to each sample point track;

[0088] Obtain feature quantization values based on the time domain data and the frequency domain data;

[0089] Perform feature normalization based on the feature quantization values to obtain feature data.

[0090] According to an embodiment of the present application, optionally, in the above radar false alarm suppression method, the feature quantization values include phase coefficient, waveform entropy, and energy ratio feature.

[0091] Example 3

[0092] On the basis of Embodiment 1, this embodiment illustrates the method in Embodiment 1 through specific implementation cases.

[0093] First, after performing pulse compression, MTI, MTD, and two-dimensional CFAR processing on the radar echo DDC signal after AD, two-dimensional detection information of the target is obtained. The two-dimensional detection information includes range i - Doppler channel j.

[0094] Then, based on IFFT (Inverse Fast Fourier Transform), feedback the range i in the two-dimensional detection information to extract the time domain and frequency domain information of the corresponding sampling points, and perform autoencoding to obtain quantization values of features such as phase coefficient and waveform entropy. Here, autoencoding means quantizing to a certain interval or range according to the criteria formulated by oneself.

[0095] Among them, the phase coefficient is:

[0096]

[0097] The intermediate variable q among them is as follows:

[0098]

[0099] Among them, M is the number of pulses accumulated in a single frame, is the phase difference between the (i + 1)-th and the i-th pulses, k p represents the statistical quantity of the phase changes of multiple scattering centers of the target rotating component, that is, the phase coefficient.

[0100] Among them, let the variable x = (x1, x2,..., x n ), where x here is the frequency data of the echo sequence within the time when the radar beam scans the target, and the frequency of the appearance of x i is p i , then the frequency waveform entropy is:

[0101]

[0102] Among them: The waveform entropy is used to characterize the spread degree of the frequency domain energy. The more concentrated the energy is, the smaller the entropy value is.

[0103] In order to show the echo energy characteristics of the fuselage and the rotor, the ratio of the energy before and after removing the main peak is taken as a feature.

[0104]

[0105] Among them, Z = fft(z) is the frequency spectrum after removing the Doppler main peak.

[0106] When establishing the plot classification model, first store, classify and label, auto-encode and train the sample plot data within a period, for example, 30 minutes, to establish the plot classification model. First, store all the plots within a certain time, mark the stable tracks and unused plots as target plot 1 and clutter plot 0, perform normalization processing on all plots according to the interval of features, and send all the plots into the learning trainer for training to generate a binary classification training model of the target and the background clutter.

[0107] This binary classification problem is represented by the hyperplane classification function f(x) = w T x + b. When f(x) is equal to zero, x is the point located on the hyperplane, and when f(x) is equal to -1 and 1, they respectively correspond to the critical lines of classification, as Figure 2 shown.

[0108] Relative to the critical classification line, the classification line when f(x) equals zero is the optimal classification line, which is the classification line that maximizes the classification interval between the two classes (stable targets and false alarms). In a high-dimensional space, the optimal classification line is the optimal classification surface. The support vector machine (SVM) classifier is an algorithm that searches for the optimal classification line based on the principle of structural risk minimization.

[0109] Using the binary classification training model obtained through training in the above steps, that is, the tracklet classification model, to perform model test classification on real-time radar tracklet data. Through the calculation and selection of signal layer features, information such as the amplitude corresponding to each tracklet, mined feature 1 (energy ratio), mined feature 2 (waveform entropy), and speed are extracted. Using the feature combination matching the training model for self-encoding processing according to the same rules to meet the test input of the training model (model) within a certain period of time obtained through training in the above steps. Through the real-time test of the tracklets, the category of the tracklets is marked (0: background clutter, 1: target), adding an attribute feature to the tracklets to provide favorable directional support for temporary track association and track tracking association.

[0110] During the track association process, according to the conventional association threshold, the target tracklets within the threshold are further screened using the clutter marking at the signal layer. If more than 2 out of 3 consecutive tracklets in a temporary track belong to clutter tracklets, then this track is marked as a false target and no track initiation is performed. The correct classification probability of a single point of the model is 80%, and the comprehensive judgment correct probability of two points is 1 - 0.2 2 = 0.996, which is far greater than 90%. In tracking filtering, the tracklets within the tracking gate can also use the clutter marking at the signal layer to complete the screening of the tracklets to improve the tracking accuracy. For example Figure 3 As shown, for the tracklets within the tracking circular gate, after excluding all clutter tracklets, the accurate tracking association tracklets are determined in the nearest neighbor domain manner.

[0111] Regarding the particularity of the machine learning model, the training model library for the concerned target types needs to be updated regularly to gradually improve the accuracy of the training model. According to the scheduled time prompt, the data repository is updated and retrained to output the training model.

[0112] Example 4

[0113] Please refer to Figure 4 , this application provides a radar false alarm suppression device 400, which includes:

[0114] A target tracklet acquisition module 410, configured to acquire multiple consecutive target tracklets within the association threshold;

[0115] A tracklet classification module 420, configured to classify each target tracklet among the multiple target tracklets according to a pre-established tracklet classification model;

[0116] The false alarm suppression module 430 is configured to suppress false alarms of the multiple target traces according to the classification results.

[0117] According to an embodiment of the present application, optionally, in the above radar false alarm suppression device, the device includes:

[0118] A sample acquisition module, configured to acquire sample trace data of all sample traces corresponding to at least one detection period and the trace type identifier of the sample traces;

[0119] A trace classification model generation module, configured to generate a trace classification model based on the sample trace data of the sample traces and the trace type identifier of the sample traces.

[0120] According to an embodiment of the present application, optionally, in the above radar false alarm suppression device, the trace classification model generation module includes:

[0121] A feature data acquisition unit, configured to acquire feature data corresponding to the sample trace data of each sample trace;

[0122] A trace classification model training unit, configured to train a learning trainer based on the feature data and the trace type identifier of the sample traces to generate a trace classification model.

[0123] According to an embodiment of the present application, optionally, in the above radar false alarm suppression device, the feature data acquisition unit includes:

[0124] A trace data processing subunit, configured to process the sample trace data of each sample trace respectively to obtain corresponding two-dimensional detection information;

[0125] A time domain data and frequency domain data acquisition subunit, configured to obtain time domain data and frequency domain data corresponding to each sample trace by feedback of the two-dimensional detection information based on the inverse fast Fourier transform;

[0126] A feature quantization value acquisition subunit, configured to acquire feature quantization values based on the time domain data and the frequency domain data;

[0127] A feature normalization subunit, configured to perform feature normalization based on the feature quantization values to obtain feature data.

[0128] According to an embodiment of the present application, optionally, in the above radar false alarm suppression device, the feature quantization values include phase coefficients, waveform entropy, and energy ratio features.

[0129] According to an embodiment of the present application, optionally, in the above radar false alarm suppression device, the method further includes:

[0130] A calibration data acquisition module, configured to regularly acquire the track data and track type identifiers of multiple traces as calibration data;

[0131] A model calibration module, configured to calibrate the trace classification model based on the calibration data.

[0132] According to an embodiment of the present application, optionally, in the above radar false alarm suppression device, the false alarm suppression module includes:

[0133] A clutter trace quantity acquisition unit, configured to acquire the quantity of clutter traces in the classification results of multiple target traces;

[0134] A false alarm suppression unit, configured to, when the quantity of the clutter traces is greater than a preset threshold, regard the tracks corresponding to the multiple target traces as false targets.

[0135] In summary, the present application provides a radar false alarm suppression device, including: a target trace acquisition module 410, configured to acquire multiple continuous target traces within an association threshold; a trace classification module 420, configured to classify each target trace in the multiple target traces according to a pre-established trace classification model; a false alarm suppression module 430, configured to perform false alarm suppression on the multiple target traces according to the classification results. In the above embodiment, through the pre-established trace classification model, the categories of multiple continuous target traces within the association threshold can be output based on the data storage and learning marking of the environment, and then false alarm suppression is performed according to the categories of the multiple target traces. This method has the advantages of low cost, good real-time performance, simple implementation, etc., and can effectively suppress radar false tracks, improving the environmental adaptability and target tracking performance of the radar.

[0136] Example 5

[0137] The present embodiment further provides a computer-readable storage medium, such as a flash memory, a hard disk, a multimedia card, a card-type memory (for example, an SD or DX memory, etc.), a random access memory (RAM), a static random access memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, an optical disc, a server, an App application store, etc., on which a computer program is stored. When the computer program is executed by a processor, the above method steps can be implemented. For the specific implementation process of the embodiment, reference can be made to Embodiment 1, and this embodiment will not be repeated here.

[0138] Example 6

[0139] An embodiment of the present application provides an electronic device, which can be a mobile phone, a computer, a tablet computer, etc. The electronic device includes a memory and a processor. A calculator program is stored on the memory. When the computer program is executed by the processor, the radar false alarm suppression method described in the first embodiment is implemented. It can be understood that as Figure 5 shown, the electronic device 500 may further include: a processor 501, a memory 502, a multimedia component 503, an input / output (I / O) interface 504, and a communication component 505.

[0140] Among them, the processor 501 is used to execute all or part of the steps in the radar false alarm suppression method in the first embodiment. The memory 502 is used to store various types of data, which may include, for example, instructions of any application program or method in the electronic device, and data related to the application program.

[0141] The processor 501 can be implemented by an application specific integrated circuit (ASIC), a digital signal processor (DSP), a digital signal processing device (DSPD), a programmable logic device (PLD), a field programmable gate array (FPGA), a controller, a microcontroller, a microprocessor or other electronic components, and is used to execute the radar false alarm suppression method in the first embodiment above.

[0142] The memory 502 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as a static random access memory (SRAM), an electrically erasable programmable read-only memory (EEPROM), an erasable programmable read-only memory (EPROM), a programmable read-only memory (PROM), a read-only memory (ROM), a magnetic memory, a flash memory, a magnetic disk or an optical disc.

[0143] The multimedia component 503 may include a screen and an audio component. The screen may be a touch screen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signals may be further stored in the memory or sent through the communication component. The audio component also includes at least one speaker for outputting audio signals.

[0144] The I / O interface 504 provides an interface between the processor 501 and other interface modules, and the other interface modules may be a keyboard, a mouse, buttons, etc. These buttons may be virtual buttons or physical buttons.

[0145] The communication component 505 is used for wired or wireless communication between the electronic device 500 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, or 4G, or a combination of one or more of them. Accordingly, the communication component 505 may include: a Wi-Fi module, a Bluetooth module, and an NFC module.

[0146] In summary, a method, device, storage medium, and electronic device for suppressing radar false alarms provided in this application. The method includes: obtaining a plurality of consecutive target traces within an association threshold; classifying each target trace among the plurality of target traces according to a pre-established trace classification model; and suppressing false alarms for the plurality of target traces according to the classification results. In the above embodiments, through the pre-established trace classification model, the category of a plurality of consecutive target traces within the association threshold can be output based on data storage and learning marking of the environment, and then false alarms are suppressed according to the categories of the plurality of target traces. This method has the advantages of low cost, good real-time performance, and simple implementation, can effectively suppress radar false tracks, and improve the environmental adaptability and target tracking performance of the radar.

[0147] In several embodiments provided in the embodiments of this application, it should be understood that the disclosed systems and methods can also be implemented in other ways. The system and method embodiments described above are merely illustrative.

[0148] It should be noted that in this article, the term "including", "comprising", or any other variant thereof is intended to cover a non-exclusive inclusion, such that a process, method, article, or device including a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or device. Without further limitation, an element defined by the statement "including a..." does not exclude the existence of additional identical elements in the process, method, article, or device including the element.

[0149] Although the embodiments disclosed in this application are as above, the content described is only an embodiment adopted for the convenience of understanding this application and is not intended to limit this application. Any person skilled in the art within the technical field to which this application pertains may make any modifications and changes in the form of implementation and details without departing from the spirit and scope disclosed in this application. However, the scope of patent protection of this application shall still be subject to the scope defined by the appended claims.

Claims

1. A method for suppressing radar false alarms, characterized in that, The method includes: Obtaining a plurality of target traces that are continuous within an association threshold; Classifying each of the plurality of target traces according to a pre-established trace classification model; Performing false alarm suppression on the plurality of target traces according to the classification result; Before the step of classifying each of the plurality of target traces according to a pre-established trace classification model, it includes: Obtaining the sample trace data of all sample traces corresponding to at least one detection period and the trace type identifier of the sample traces; Generating a trace classification model based on the sample trace data of the sample traces and the trace type identifier of the sample traces; The step of generating a trace classification model based on the sample trace data of the sample traces and the trace type identifier of the sample traces includes: Obtaining the feature data corresponding to the sample trace data of each sample trace; Training a learning trainer based on the feature data and the trace type identifier of the sample traces to generate a trace classification model; The step of obtaining the feature data corresponding to the sample trace data of each sample trace includes: Processing the sample trace data of each sample trace respectively to obtain corresponding two-dimensional detection information; Feeding back the two-dimensional detection information based on the inverse fast Fourier transform to obtain the time domain data and frequency domain data corresponding to each sample trace; Obtaining a feature quantization value based on the time domain data and the frequency domain data; Performing feature normalization based on the feature quantization value to obtain feature data; The feature quantization value includes a phase coefficient, waveform entropy, and energy ratio feature.

2. The method according to claim 1, wherein The method further includes: Timely obtaining the trace data and trace type identifier of a plurality of traces as calibration data; Calibrating the trace classification model based on the calibration data.

3. The method according to claim 1, characterized in that The step of performing false alarm suppression on the plurality of target traces according to the classification result includes: Obtaining the number of clutter traces in the classification results of the plurality of target traces; When the number of the clutter traces is greater than a preset threshold, regarding the tracks corresponding to the plurality of target traces as false targets.

4. A radar false alarm suppression device, characterized in that, The device includes: A target trace acquisition module for obtaining a plurality of target traces that are continuous within an association threshold; A trace classification module for classifying each of the plurality of target traces according to a pre-established trace classification model; A false alarm suppression module for performing false alarm suppression on the plurality of target traces according to the classification result; A sample acquisition module for obtaining the sample trace data of all sample traces corresponding to at least one detection period and the trace type identifier of the sample traces; A trace classification model generation module for generating a trace classification model based on the sample trace data of the sample traces and the trace type identifier of the sample traces; The trace classification model generation module includes: A feature data acquisition unit for obtaining the feature data corresponding to the sample trace data of each sample trace; A trace classification model training unit for training a learning trainer based on the feature data and the trace type identifier of the sample traces to generate a trace classification model; The feature data acquisition unit includes: The dot trace data processing subunit is used to process the sample dot trace data of each sample dot trace respectively to obtain corresponding two-dimensional detection information; The time-domain data and frequency-domain data acquisition subunit is used to obtain the time-domain data and frequency-domain data corresponding to each sample dot trace by feeding back the two-dimensional detection information based on the inverse fast Fourier transform; The feature quantization value acquisition subunit is used to acquire feature quantization values based on the time-domain data and the frequency-domain data; The feature normalization subunit is used to perform feature normalization based on the feature quantization values to obtain feature data; The feature quantization values include phase coefficients, waveform entropy, and energy ratio features.

5. A storage medium, characterized in that, The computer program stored in the storage medium, when executed by one or more processors, is used to implement the method according to any one of claims 1-3.

6. An electronic device, characterized in that, It includes a memory and a processor. A computer program is stored on the memory. When the computer program is executed by the processor, the method according to any one of claims 1-3 is executed.

Images