Anti-interference method and device, computer equipment, storage medium and program product

Abstract

The invention relates to an anti-interference method and device, computer equipment, a storage medium and a program product. The method comprises the following steps: extracting a distance feature and a speed feature of a radar image according to a preset algorithm to obtain feature information of the radar image; classifying the to-be-identified object in the radar image according to the feature information of the radar image to obtain a classification result; the classification result comprises an interference object and a target object; the interference objects comprise chaff clouds and corner reflectors; and removing the interference object from the radar image according to the classification result. When the radar image comprises chaff cloud interference and corner reflector interference, feature extraction is performed on the chaff cloud and the corner reflector in the radar image at the same time, so that interference objects corresponding to the chaff cloud and the corner reflector are removed from the radar image, and the anti-interference effect on the radar image is improved.

Description

Technical Field

[0001] The present application relates to the field of radar technology, and in particular to an anti-interference method, device, computer equipment, storage medium and program product. Background Art

[0002] In complex confrontation scenarios, in order to better protect its own targets from being searched and tracked by radar, the targets will launch chaff and angular reflectors to interfere with the radar while making evasive movements, forming a combined deception interference to the radar, which poses a serious challenge to the radar's accurate detection. Therefore, an anti-interference method suitable for radar is needed to improve the radar's detection accuracy.

[0003] In traditional technology, passive interference and real targets are classified and identified by inputting the characteristic differences of different interference signals in the time domain, frequency domain, and polarization domain into a classifier with appropriate parameters.

[0004] However, the traditional anti-interference method has the problem of poor anti-interference effect. Summary of the invention

[0005] Based on this, it is necessary to provide an anti-interference method, device, computer equipment, storage medium and program product that can improve the anti-interference effect in response to the above technical problems.

[0006] In a first aspect, the present application provides an anti-interference method, comprising:

[0007] Extracting distance features and speed features of the radar image according to a preset algorithm to obtain feature information of the radar image;

[0008] Classifying the objects to be identified in the radar image according to the characteristic information of the radar image to obtain a classification result; the classification result includes interference objects and target objects; the interference objects include chaff clouds and corner reflectors;

[0009] The interfering object is removed from the radar image according to the classification result.

[0010] In one embodiment, classifying the objects to be identified in the radar image according to the feature information of the radar image to obtain the classification result includes:

[0011] Determine the number of one-dimensional range image scattering points, echo waveform entropy, inter-pulse gray correlation and spatial position in the radar image according to the characteristic information of the radar image;

[0012] Determining a first classification result according to the number of scattering points in the one-dimensional range image and the echo amplitude in the radar image;

[0013] Determining a second classification result according to the echo waveform entropy of the radar image;

[0014] determining a third classification result according to the inter-pulse gray relational degree and the decay speed of the inter-pulse gray relational degree;

[0015] A fourth classification result is determined according to the spatial position.

[0016] In one embodiment, the first classification result includes a first foil cloud, a first target object, and a first corner reflector, and determining the first classification result according to the number of scattering points in the one-dimensional range image and the echo amplitude in the radar image includes:

[0017] Determine the object whose number of scattering points in the one-dimensional range image is greater than a first preset threshold and whose echo amplitude is at a first level as the first foil strip cloud;

[0018] Determine an object whose number of scattering points in the one-dimensional range image is not greater than the first preset threshold, whose number of scattering points in the one-dimensional range image is not less than the second preset threshold, and whose echo amplitude is at the second level as the first target object;

[0019] An object whose number of scattering points in the one-dimensional range image is less than the second preset threshold and whose echo amplitude is at the third level is determined as the first corner reflector.

[0020] In one embodiment, the second classification result includes a second foil cloud, a second target object, and a second corner reflector, and determining the second classification result according to the echo waveform entropy of the radar image includes:

[0021] Determine the object whose echo waveform entropy is greater than the first preset entropy as the second foil strip cloud;

[0022] Determine the object whose echo waveform entropy is not greater than the first preset entropy and the object whose echo waveform entropy is not less than the second preset entropy as the second target object;

[0023] The object whose echo waveform entropy is less than the second preset entropy is determined as the second corner reflector.

[0024] In one embodiment, the third classification result includes a third foil cloud, a third target object, and a third corner reflector, and determining the third classification result according to the inter-pulse gray correlation degree and the attenuation speed of the inter-pulse gray correlation degree includes:

[0025] Determine the object whose inter-pulse gray correlation degree is less than the first preset correlation degree and whose decay speed is the first level as the third foil strip cloud;

[0026] Determine the object whose gray correlation degree is not less than the first preset correlation degree, whose gray correlation degree is not less than the second preset correlation degree, and whose decay speed is the second level as the third target object; and whose decay speed of the second level is less than the decay speed of the first level;

[0027] An object whose gray correlation degree is greater than a second preset correlation degree and whose decay speed is a third level is determined as the third corner reflector; and the decay speed of the third level is less than the decay speed of the second level.

[0028] In one embodiment, the fourth classification result includes a fourth foil cloud, a fourth target object, and a fourth corner reflector, and determining the fourth classification result according to the spatial position includes:

[0029] Determine the object whose spatial position is higher than a preset height as the fourth foil cloud;

[0030] The object whose spatial position is not higher than the preset height is determined as the fourth corner reflector and the fourth target object.

[0031] In one embodiment, removing the interfering object from the radar image according to the classification result includes:

[0032] Determining a final classification result according to a preset weight value of each of the classification results and each of the classification results;

[0033] The interfering object is removed from the radar image according to the final classification result.

[0034] In a second aspect, the present application also provides an anti-interference device, comprising:

[0035] A processing module, used to process the distance dimension and speed dimension of the radar image according to a preset algorithm to obtain a radar image;

[0036] A determination module, used to determine a classification result of the radar image according to feature information of the radar image; the classification result includes a chaff cloud, a corner reflector and a target object;

[0037] An extraction module is used to extract the target object of the radar image according to the classification result.

[0038] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0039] Extracting distance features and speed features of the radar image according to a preset algorithm to obtain feature information of the radar image;

[0040] Classifying the objects to be identified in the radar image according to the characteristic information of the radar image to obtain a classification result; the classification result includes interference objects and target objects; the interference objects include chaff clouds and corner reflectors;

[0041] The interfering object is removed from the radar image according to the classification result.

[0042] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0043] Extracting distance features and speed features of the radar image according to a preset algorithm to obtain feature information of the radar image;

[0044] Classifying the objects to be identified in the radar image according to the characteristic information of the radar image to obtain a classification result; the classification result includes interference objects and target objects; the interference objects include chaff clouds and corner reflectors;

[0045] The interfering object is removed from the radar image according to the classification result.

[0046] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0047] Extracting distance features and speed features of the radar image according to a preset algorithm to obtain feature information of the radar image;

[0048] Classifying the objects to be identified in the radar image according to the characteristic information of the radar image to obtain a classification result; the classification result includes interference objects and target objects; the interference objects include chaff clouds and corner reflectors;

[0049] The interfering object is removed from the radar image according to the classification result.

[0050] The anti-interference method, device, computer equipment, storage medium and program product extract the distance feature and speed feature of the radar image according to a preset algorithm to obtain the feature information of the radar image; classify the objects to be identified in the radar image according to the feature information of the radar image to obtain the classification result; the classification result includes interference objects and target objects; the interference objects include chaff cloud and corner reflector; according to the classification result, the interference objects are removed from the radar image. When the radar image includes chaff cloud interference and corner reflector interference, the features of the chaff cloud and corner reflector in the radar image are extracted at the same time, so as to remove the interference objects corresponding to the chaff cloud and corner reflector from the radar image, thereby improving the anti-interference effect of the radar image. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0052] Figure 1 An application environment diagram of an anti-interference method in an embodiment;

[0053] Figure 2 A schematic diagram of a flow chart of an anti-interference method in an embodiment;

[0054] Figure 3 is a flow chart of an anti-interference method in another embodiment;

[0055] Figure 3A is a schematic diagram of extracting features from a radar image in one embodiment;

[0056] Figure 3B A schematic diagram of determining a spatial position in one embodiment;

[0057] Figure 4 is a flow chart of an anti-interference method in another embodiment;

[0058] Figure 4A is a schematic diagram of the number of scattering points in one embodiment;

[0059] Figure 5 is a flow chart of an anti-interference method in another embodiment;

[0060] Figure 5A is a schematic diagram of waveform entropy in one embodiment;

[0061] Figure 6 is a flow chart of an anti-interference method in another embodiment;

[0062] Fig. 6A is a schematic diagram of grey relational degree in one embodiment;

[0063] Figure 7 is a flow chart of an anti-interference method in another embodiment;

[0064] Figure 8 is a flow chart of an anti-interference method in another embodiment;

[0065] Fig. 9 FIG. 4 is a structural block diagram of an anti-interference device in an embodiment. DETAILED DESCRIPTION

[0066] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0067] In complex confrontation scenarios, in order to better protect its own targets from being searched and tracked by radar, the targets will launch chaff and angular reflector jammers while performing evasive maneuvers, thus forming a combined deception jammer to the radar. Therefore, it poses a serious challenge to the radar's accurate detection.

[0068] In the sea detection scenario, passive interference against radar detection mainly includes two technologies. The first is the corner reflector, which is a radar wave reflector of different specifications made of metal plates. When the radar electromagnetic wave scans the corner reflector, the electromagnetic wave will produce a strong echo on the metal corner reflector, resulting in a strong false target echo on the radar screen, interfering with radar detection and identification. The second is the chaff cloud, which uses a cloud-like interference body made of metal foil, which can produce a large amount of reflection and scattering, thereby interfering with the detection of enemy radars.

[0069] Radar anti-passive interference is mainly achieved through interference identification. Traditional methods mainly rely on the characteristic differences of different interference signals in the time domain, frequency domain, and polarization domain, and input them into a classifier with appropriate parameters to achieve classification and identification of passive interference and real targets. However, when faced with combined interference, it is often impossible to extract significant features of the two and the target itself. It is difficult for a single identification method to achieve good identification results in combined interference.

[0070] The anti-interference method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown in FIG. 1 , the computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 1As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, near field communication (NearField Communication, NFC) or other technologies. When the computer program is executed by the processor, an anti-interference method is implemented. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0071] Those skilled in the art will understand that Figure 1 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0072] In one embodiment, Figure 2 As shown, an anti-interference method is provided, which is applied to Figure 1 The following is an example of a terminal in the example, including:

[0073] S201, extracting distance features and speed features of the radar image according to a preset algorithm to obtain feature information of the radar image.

[0074] In the embodiment of the present application, two-dimensional unit average-constant false alarm rate (CA-CFAR) detection is used to process the distance dimension and velocity dimension of the one-dimensional range profile (High Resolution Range Profile, HRRP) respectively to obtain echo pulse amplitude detection and range unit segmentation results.

[0075] Optionally, using two-dimensional unit average-constant false alarm rate detection to process the distance dimension and speed dimension of HRRP respectively may include: first preprocessing the echo data of the radar image, for example, range-Doppler correction, clutter suppression, etc., and then dividing the area to be detected into multiple units, each unit represents a potential target position, so that a number of adjacent units are selected on both sides of the detection unit as a reference window and a statistical window, wherein the reference window is used to protect the detection unit from the influence of adjacent strong targets, and the statistical window is used to estimate the background noise level; further, calculating the average power of all units in the statistical window, denoted as P_avg, and setting a constant K related to the expected false alarm rate, and the detection threshold T is determined by the following formula: T=K⋅P_avg, so as to compare the power P_d of the detection unit with the threshold T, if P_d> T, it is determined that there is a target; otherwise, it is determined that there is no target.

[0076] S202, classifying the objects to be identified in the radar image according to the feature information of the radar image to obtain a classification result; the classification result includes interference objects and target objects; the interference objects include chaff clouds and corner reflectors.

[0077] Among them, the chaff cloud is an interference area formed by a large number of randomly distributed metal scatterers in the air, which is used to passively interfere with detection systems such as radar;

[0078] In the embodiment of the present application, the objects to be identified in the radar image are classified according to the preset classification logic to obtain the chaff cloud, the corner reflector and the target object. Optionally, the objects to be identified in the radar image can be classified according to the preset first classification logic to obtain the interference object and the target object, and then the interference image can be classified according to the second classification logic to obtain the chaff cloud and the corner reflector.

[0079] As an optional implementation, a correspondence between feature information and the identification object may be established in advance, so as to determine the classification result according to the feature information and the correspondence of the radar image.

[0080] As another optional implementation, the feature information of the radar image may be input into a pre-trained recognition model, and the recognition model analyzes and processes the feature information and outputs a classification result of the radar image.

[0081] S203: removing interference objects from the radar image according to the classification result.

[0082] In the embodiment of the present application, the foil cloud and the corner reflector are removed from the radar image to obtain the radar image after anti-interference processing. Optionally, the image information corresponding to the target object in the radar image can be extracted from the radar image to obtain the radar image after anti-interference processing.

[0083] In the above anti-interference method, the distance feature and speed feature of the radar image are extracted according to a preset algorithm to obtain feature information of the radar image; the objects to be identified in the radar image are classified according to the feature information of the radar image to obtain a classification result; the classification result includes interference objects and target objects; the interference objects include chaff cloud and corner reflector; according to the classification result, the interference objects are removed from the radar image. When the radar image includes chaff cloud interference and corner reflector interference, feature extraction is performed on the chaff cloud and corner reflector in the radar image at the same time, so as to remove the interference objects corresponding to the chaff cloud and corner reflector from the radar image, thereby improving the anti-interference effect of the radar image.

[0084] In one embodiment, an implementation of the above S202 is provided, such as Figure 3 As shown, the above “classifying the objects to be identified in the radar image according to the feature information of the radar image to obtain the classification result” includes:

[0085] S301, determining the number of scattering points of a one-dimensional range image, echo waveform entropy, inter-pulse gray correlation and spatial position in the radar image according to characteristic information of the radar image.

[0086] In the embodiments of the present application, Figure 3A As shown, the characteristic information of the radar image can include segmenting four characteristic objects on the one-dimensional range image, which are respectively recorded as target1, target2, target3 and target4. Further, the gray correlation degree and waveform entropy of the four characteristic objects and the number of scattering points in the one-dimensional range image are determined, so as to obtain the classification result according to the gray correlation degree and waveform entropy of the four characteristic objects and the number of scattering points in the one-dimensional range image.

[0087] Optionally, waveform entropy is used to describe the concentration of signal energy along the time axis. The more concentrated the energy distribution, the greater the waveform entropy; the more dispersed the energy distribution, the smaller the waveform entropy. Perform the processing as in equation 1 and equation 2:

[0088] (Formula 1)

[0089] (Formula 2)

[0090] Where N is the total amount of signal energy. Further, The waveform entropy is: .

[0091] Optionally, Gray Correlation Degree (GCD) is a physical quantity that measures the degree of correlation between factors based on the similarity or difference in the time series development trends between the factors. GCD is a study of the dynamic development process of factors. is the reference time series, For The time series for comparison are and The GCD is defined as: ,in, , , , .

[0092] Optionally, the spatial position matching method utilizes the characteristic that the spatial position of the target is basically unchanged, and determines whether the target is above sea level by analyzing whether the angle and distance of the threshold point are consistent. Under the condition that the height of the airborne radar above the sea surface and the angle of the threshold point are known, the expected distance between the radar and the sea surface target can be solved, where the height of the airborne radar above the sea surface is obtained based on the inertial navigation information, and the angle of the threshold point is obtained based on the sum and difference angle measurement. If the interference signal is a cloud of foil strips diffusing in the air, the measured distance will be less than the expected distance, so the spatial position matching method can be used to counteract the foil strip anti-interference processing. For example, if Figure 3B As shown, is the height of the airborne radar from the sea level; is the height of the chaff cloud from the sea level; is the reentry angle; Point is the intersection of the antenna beam pointing and the sea level; is the ship position; is the projection point of the ship on the radar line of sight; is the chaff cloud position; is the projection point of the chaff cloud on the radar line of sight; It is the intersection of the line connecting the chaff cloud and the airborne radar with the sea level; for The projection point of the point on the radar line of sight; is the radar angle deviation. Assume that the radar is The angle measurement deviation is , that is, the angle of the chaff cloud is mismeasured as , the delay corresponding to the difference between the measured distance and the expected distance is shown in Equation 3:

[0093] (Formula 3)

[0094] Optionally, you can The corresponding maximum value The value is used as the decision threshold, and the tracking stage The maximum value is , search phase The maximum value of .

[0095] S302: Determine a first classification result according to the number of scattering points in the one-dimensional range image and the echo amplitude in the radar image.

[0096] In an embodiment of the present application, the number of scattering points in the one-dimensional range image and the echo amplitude in the radar image can be input into a trained first classification model to obtain a first classification result; or, the number of scattering points in the one-dimensional range image and the echo amplitude in the radar image can be substituted into the first relationship to obtain the first classification result.

[0097] Optionally, the above “determining a first classification result according to the number of scattering points in the one-dimensional range image and the echo amplitude in the radar image” includes:

[0098] S303: Determine a second classification result according to the echo waveform entropy of the radar image.

[0099] In an embodiment of the present application, the echo waveform entropy of the radar image can be input into a trained second classification model to obtain a second classification result; or, the echo waveform entropy of the radar image can be substituted into the second relationship to obtain the second classification result.

[0100] S304, determining a third classification result according to the inter-pulse grey relational degree and the decay speed of the inter-pulse grey relational degree.

[0101] In an embodiment of the present application, the echo waveform entropy of the radar image can be input into a trained second classification model to obtain a second classification result; or, the echo waveform entropy of the radar image can be substituted into the second relationship to obtain the second classification result.

[0102] S305: Determine a fourth classification result according to the spatial position.

[0103] In an embodiment of the present application, the echo waveform entropy of the radar image can be input into a trained second classification model to obtain a second classification result; or, the echo waveform entropy of the radar image can be substituted into the second relationship to obtain the second classification result.

[0104] In the above application embodiment, the characteristic information of the radar image is analyzed from four angles to obtain the first classification results, the second classification results, the third classification results and the fourth classification results corresponding to the four analysis methods, thereby improving the comprehensiveness and accuracy of the classification results.

[0105] In one embodiment, an implementation of the above S302 is provided, wherein the first classification result includes a first foil cloud, a first target object, and a first corner reflector, such as Figure 4 As shown, the above “determining the first classification result according to the number of scattering points in the one-dimensional range image and the echo amplitude in the radar image” includes:

[0106] S401, determining an object whose one-dimensional range image scattering point number is greater than a first preset threshold and whose echo amplitude is a first level as a first chaff cloud.

[0107] S402: Determine an object whose one-dimensional range image scattering point number is not greater than a first preset threshold, whose one-dimensional range image scattering point number is not less than a second preset threshold, and whose echo amplitude is a second level as a first target object.

[0108] S403: Determine an object whose one-dimensional range image scattering point number is less than a second preset threshold and whose echo amplitude is at the third level as a first corner reflector.

[0109] Among them, the first level can be the level at which the echo amplitude changes most obviously over time, the second level can be the level at which the echo amplitude changes over time is in the middle, and the third level can be the level at which the echo amplitude changes most stably over time; the first preset threshold is greater than the second threshold.

[0110] In the embodiments of the present application, Figure 4A As shown in the figure, for the scattering points and amplitude characteristics within the pulse, the foil cloud diffuses freely in the air with factors such as wind speed and its own gravity, resulting in randomness in the high-resolution one-dimensional range image of the foil cloud echo pulse, and small correlation between echoes between pulses. Since there are many target objects and they are relatively stable, their one-dimensional range image has low randomness and large correlation between echoes between pulses. However, the corner reflector has few scattering points and stable amplitude.

[0111] In the embodiment of the present application, the object with the most one-dimensional range image scattering points and the most obvious echo amplitude change over time is determined as the first foil strip cloud; the object with more one-dimensional range image scattering points and the echo amplitude change level in the middle over time is determined as the first target object; the object with fewer one-dimensional range image scattering points and the most stable echo amplitude change over time is determined as the first corner reflector. Therefore, the characteristics of the three mixed echoes are: 1) The foil strip cloud has a high density of foil strips, and the free diffusion movement characteristics are easily affected by the external environment. The Rich Communication Services (RCS) has strong random fluctuations, and its one-dimensional range image has particularly many scattering points. Therefore, the echo amplitude changes most obviously over time; 2) The target object echo is a discrete multiple strong scattering points, and the RCS will fluctuate randomly, but the target's RCS is less affected by external environmental factors, and the RCS fluctuation is smaller than that of the foil strip cloud; 3) The corner reflector has fewer scattering points and stable amplitude.

[0112] In the above application embodiment, the first classification result is determined according to the number of scattering points in the one-dimensional range image and the level of change of the echo amplitude over time, thereby ensuring the accuracy of the first classification result.

[0113] In one embodiment, an implementation of the above S303 is provided, wherein the second classification result includes a second foil cloud, a second target object, and a second corner reflector, such as Figure 5 As shown, the above “determining the second classification result according to the echo waveform entropy of the radar image” includes:

[0114] S501, determining an object whose echo waveform entropy is greater than a first preset entropy as a second foil cloud.

[0115] S502: Determine an object whose echo waveform entropy is not greater than a first preset entropy and an object whose echo waveform entropy is not less than a second preset entropy as a second target object.

[0116] S503: Determine the object whose echo waveform entropy is less than the second preset entropy as a second corner reflector.

[0117] The first preset entropy is greater than the second preset entropy.

[0118] In the embodiments of the present application, Figure 5A As shown in the figure, waveform entropy is used to describe the concentration of signal energy along the time axis. The more concentrated the energy distribution, the greater the waveform entropy, and the more dispersed the energy distribution, the smaller the waveform entropy. The waveform entropy of the foil cloud is the largest, the waveform entropy of the target object is the second, and the waveform entropy of the corner reflector is the smallest. The object with the largest waveform entropy is determined as the second foil cloud; the object with the middle waveform entropy is determined as the second target object; and the object with the smallest waveform entropy is determined as the second corner reflector.

[0119] In the above application embodiment, the second classification result is determined based on the echo waveform entropy of the radar image, the first preset entropy and the second preset entropy, thereby ensuring the accuracy of the second classification result.

[0120] In one embodiment, an implementation of the above S304 is provided, wherein the third classification result includes a third foil cloud, a third target object, and a third corner reflector, such as Figure 6 As shown, the above “determining the third classification result according to the inter-pulse gray correlation degree and the attenuation speed of the inter-pulse gray correlation degree” includes:

[0121] S601, determining an object whose inter-pulse gray correlation degree is less than a first preset correlation degree and whose decay speed is a first level as a third foil strip cloud.

[0122] S602, determining an object whose gray correlation degree is not less than the first preset correlation degree, whose gray correlation degree is not less than the second preset correlation degree, and whose decay speed is the second level as the third target object; the decay speed of the second level is less than the decay speed of the first level.

[0123] S603, determining an object whose gray correlation degree is greater than the second preset correlation degree and whose attenuation speed is the third level as a third corner reflector; the attenuation speed of the third level is less than the attenuation speed of the second level.

[0124] Among them, Gray Correlation Degree (GCD) is a physical quantity that measures the degree of correlation between factors according to the similarity or difference of the time series development trends between the elements. The first level is the level at which the gray correlation between pulses decays most obviously, the second level is the level at which the gray correlation between pulses decays moderately, and the third level is the level at which the gray correlation between pulses decays least obviously; the second preset correlation is greater than the first preset correlation.

[0125] In the embodiments of the present application, Fig. 6A As shown in the figure, the decay speed of the grey correlation degree is determined according to the data size of the grey correlation degree of the radar image at multiple time points. The GCD of the foil cloud in the diffusion stage is significantly lower than that of the target, and decays significantly over time; the GCD of the target object is relatively high and changes less over time; the GCD of the corner reflector is the highest and relatively stable. Therefore, the object with the lowest CGD and the most obvious decay over time is determined to be the third foil cloud; the object with a higher CGD and a smaller decay over time is determined to be the third target object; and the object with the highest CGD and almost no decay over time is determined to be the third corner reflector.

[0126] In the above application embodiment, the third classification result is determined according to the magnitude of the grey correlation degree and the attenuation speed of the radar image, thereby ensuring the accuracy of the third classification result.

[0127] In one embodiment, an implementation of the above S305 is provided, wherein the fourth classification result includes a fourth foil cloud, a fourth target object, and a fourth corner reflector, such as Figure 7 As shown, the above “determining the fourth classification result according to the spatial position” includes:

[0128] S701, determining an object whose spatial position is higher than a preset height as a fourth foil cloud.

[0129] S702: Determine an object whose spatial position is not higher than a preset height as a fourth corner reflector and a fourth target object.

[0130] In the embodiment of the present application, if the interference signal is a foil cloud diffused in the air, the measured distance will be less than the expected distance, so the spatial position matching method can be used to counteract the foil interference. The preset height can be the sea level, that is, the object with a spatial position higher than the sea surface is identified as the fourth foil cloud, and the object on the sea surface is identified as the fourth corner reflector and the fourth target object.

[0131] In the above application embodiment, the fourth classification result is determined according to the spatial position of each object in the radar image, thereby ensuring the accuracy of the fourth classification result.

[0132] In one embodiment, an implementation of the above 203 is provided, and the classification results include a first classification result, a second classification result, a third classification result and a fourth classification result, such as Figure 8 As shown, the above-mentioned “removing interference objects from radar images according to classification results” includes:

[0133] S801, determining a final classification result according to preset weight values ​​of each classification result and the classification result.

[0134] In the embodiment of the present application, through decision fusion and confidence evaluation, the first classification result, the second classification result, the third classification result, and the fourth classification result are comprehensively considered, and the maximum echo category confidence evaluation score is used as the final category. Optionally, the decision fusion and confidence evaluation method may include: recording the output result of the decision fusion model as Z, ,in, (i=1,2,3,4) are the first classification results, the second classification results, the third classification results, and the fourth classification results, respectively. , , Represent the weights of the first classification result, the second classification result, and the third classification result respectively. To interfere with the final classification results.

[0135] S802: Remove interference objects from the radar image according to the final classification result.

[0136] In the embodiment of the present application, the foil cloud and the corner reflector are removed from the radar image to obtain the radar image after anti-interference processing. Optionally, the image information corresponding to the target object in the radar image can be extracted from the radar image to obtain the radar image after anti-interference processing.

[0137] In the above application embodiment, multi-dimensional features are used for joint decision making, thereby avoiding the problem of failure of the traditional single determination method due to complex interference patterns.

[0138] In one embodiment, a complete anti-interference method is provided, the method comprising:

[0139] S1, extracting the distance features and speed features of the radar image according to a preset algorithm to obtain feature information of the radar image.

[0140] S2, according to the characteristic information of the radar image, determine the number of scattering points, echo waveform entropy, pulse-to-pulse gray correlation and spatial position in the radar image.

[0141] S3, determining an object whose one-dimensional range image scattering point number is greater than a first preset threshold and whose echo amplitude is a first level as a first chaff cloud.

[0142] S4, determining an object whose one-dimensional range image scattering point number is not greater than a first preset threshold, whose one-dimensional range image scattering point number is not less than a second preset threshold, and whose echo amplitude is a second level as a first target object.

[0143] S5, determining the object whose one-dimensional range image scattering point number is less than the second preset threshold and whose echo amplitude is the third level as the first corner reflector.

[0144] S6, determining the object whose echo waveform entropy is greater than the first preset entropy as the second foil cloud.

[0145] S7, determining the object whose echo waveform entropy is not greater than the first preset entropy and the object whose echo waveform entropy is not less than the second preset entropy as the second target object.

[0146] S8, determining the object whose echo waveform entropy is less than the second preset entropy as a second corner reflector.

[0147] S9, determining the object whose inter-pulse gray correlation degree is less than the first preset correlation degree and whose decay speed is the first level as the third foil strip cloud.

[0148] S10, determining an object whose gray correlation degree is not less than the first preset correlation degree, whose gray correlation degree is not less than the second preset correlation degree, and whose decay speed is the second level as the third target object; the decay speed of the second level is less than the decay speed of the first level.

[0149] S11, determining an object whose gray correlation degree is greater than a second preset correlation degree and whose attenuation speed is a third level as a third corner reflector; the attenuation speed of the third level is less than the attenuation speed of the second level.

[0150] S12, determining an object whose spatial position is higher than a preset height as a fourth foil cloud.

[0151] S13, determining an object whose spatial position is not higher than a preset height as a fourth corner reflector and a fourth target object.

[0152] S14, determining a final classification result according to the preset weight values ​​of each classification result and the classification result.

[0153] S15, removing interference objects from the radar image according to the final classification result.

[0154] In the above anti-interference method, the distance feature and speed feature of the radar image are extracted according to a preset algorithm to obtain feature information of the radar image; the objects to be identified in the radar image are classified according to the feature information of the radar image to obtain a classification result; the classification result includes interference objects and target objects; the interference objects include chaff cloud and corner reflector; according to the classification result, the interference objects are removed from the radar image. When the radar image includes chaff cloud interference and corner reflector interference, feature extraction is performed on the chaff cloud and corner reflector in the radar image at the same time, so as to remove the interference objects corresponding to the chaff cloud and corner reflector from the radar image, thereby improving the anti-interference effect of the radar image.

[0155] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0156] Based on the same inventive concept, the embodiment of the present application also provides an anti-interference device for implementing the anti-interference method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more anti-interference device embodiments provided below can refer to the limitations of the anti-interference method above, and will not be repeated here.

[0157] In one embodiment, Fig. 9 As shown, an anti-interference device is provided, comprising: a processing module 10, a determination module 11 and a removal module 12, wherein:

[0158] The processing module 10 is used to extract the distance feature and the speed feature of the radar image according to a preset algorithm to obtain feature information of the radar image.

[0159] The determination module 11 is used to classify the objects to be identified in the radar image according to the characteristic information of the radar image to obtain the classification results; the classification results include interference objects and target objects; the interference objects include foil clouds and corner reflectors.

[0160] The removal module 12 is used to remove interference objects from the radar image according to the classification result.

[0161] In one embodiment, the determination module 11 includes: a first determination unit, a second determination unit, a third determination unit, a fourth determination unit and a fifth determination unit, wherein:

[0162] The first determination unit is used to determine the number of one-dimensional range image scattering points, echo waveform entropy, pulse-to-pulse gray correlation and spatial position in the radar image according to the characteristic information of the radar image.

[0163] The second determining unit is used to determine the first classification result according to the number of scattering points in the one-dimensional range image and the echo amplitude in the radar image.

[0164] A third determining unit, configured to determine a second classification result according to the echo waveform entropy of the radar image;

[0165] The fourth determining unit is used to determine the third classification result according to the inter-pulse gray relational degree and the decay speed of the inter-pulse gray relational degree.

[0166] The fifth determining unit is used to determine a fourth classification result according to the spatial position.

[0167] In one embodiment, the first classification result includes a first foil strip cloud, a first target object and a first corner reflector. The above-mentioned second determination unit is specifically used to determine an object whose one-dimensional range image scattering point number is greater than a first preset threshold and whose echo amplitude is a first level as the first foil strip cloud; to determine an object whose one-dimensional range image scattering point number is not greater than the first preset threshold, whose one-dimensional range image scattering point number is not less than a second preset threshold, and whose echo amplitude is a second level as the first target object; and to determine an object whose one-dimensional range image scattering point number is less than the second preset threshold and whose echo amplitude is a third level as the first corner reflector.

[0168] In one embodiment, the second classification result includes a second foil strip cloud, a second target object, and a second corner reflector. The above-mentioned third determination unit is specifically used to determine an object whose echo waveform entropy is greater than a first preset entropy as a second foil strip cloud; determine an object whose echo waveform entropy is not greater than the first preset entropy and an object whose echo waveform entropy is not less than a second preset entropy as a second target object; and determine an object whose echo waveform entropy is less than the second preset entropy as a second corner reflector.

[0169] In one embodiment, the third classification result includes a third foil strip cloud, a third target object and a third corner reflector. The above-mentioned fourth determination unit is specifically used to determine an object whose inter-pulse gray correlation degree is less than a first preset correlation degree and whose attenuation speed is a first level as a third foil strip cloud; to determine an object whose gray correlation degree is not less than the first preset correlation degree, and whose gray correlation degree is not less than the second preset correlation degree, and whose attenuation speed is a second level as a third target object; whose attenuation speed of the second level is less than that of the first level; to determine an object whose gray correlation degree is greater than the second preset correlation degree and whose attenuation speed is a third level as a third corner reflector; whose attenuation speed of the third level is less than that of the second level.

[0170] In one embodiment, the fourth classification result includes a fourth foil strip cloud, a fourth target object and a fourth corner reflector. The above-mentioned fifth determination unit is specifically used to determine an object whose spatial position is higher than a preset height as a fourth foil strip cloud; and to determine an object whose spatial position is not higher than a preset height as a fourth corner reflector and a fourth target object.

[0171] In one embodiment, the classification results include a first classification result, a second classification result, a third classification result, and a fourth classification result. According to the classification results, the interference object is removed from the radar image. The removal module 12 includes: a sixth determination unit and a removal unit, wherein:

[0172] The sixth determining unit is used to determine the final classification result according to the preset weight values ​​of each classification result and the classification result.

[0173] The removal unit is used to remove interference objects from the radar image according to the final classification result.

[0174] Each module in the above anti-interference device can be implemented in whole or in part by software, hardware and a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module above.

[0175] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0176] Extracting distance features and speed features of the radar image according to a preset algorithm to obtain feature information of the radar image;

[0177] Classifying the objects to be identified in the radar image according to the characteristic information of the radar image to obtain a classification result; the classification result includes interference objects and target objects; the interference objects include chaff clouds and corner reflectors;

[0178] According to the classification results, interference objects are removed from the radar image.

[0179] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0180] According to the characteristic information of radar image, the number of scattering points of one-dimensional range image, echo waveform entropy, pulse-to-pulse gray correlation and spatial position in radar image are determined;

[0181] Determining a first classification result according to the number of scattering points in the one-dimensional range image and the echo amplitude in the radar image;

[0182] Determining a second classification result according to the echo waveform entropy of the radar image;

[0183] Determining the third classification result according to the inter-pulse grey relational degree and the decay speed of the inter-pulse grey relational degree;

[0184] According to the spatial position, the fourth classification result is determined.

[0185] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0186] Determine an object whose number of scattering points in the one-dimensional range image is greater than a first preset threshold and whose echo amplitude is at a first level as a first chaff cloud;

[0187] Determine an object whose number of scattering points in the one-dimensional range image is not greater than a first preset threshold, whose number of scattering points in the one-dimensional range image is not less than a second preset threshold, and whose echo amplitude is at the second level as a first target object;

[0188] An object whose one-dimensional range image scattering point number is less than a second preset threshold and whose echo amplitude is at the third level is determined as a first corner reflector.

[0189] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0190] Determine the object whose echo waveform entropy is greater than the first preset entropy as the second foil cloud;

[0191] Determine an object whose echo waveform entropy is not greater than a first preset entropy and an object whose echo waveform entropy is not less than a second preset entropy as a second target object;

[0192] An object whose echo waveform entropy is less than a second preset entropy is determined as a second corner reflector.

[0193] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0194] Determine the objects whose inter-pulse gray correlation degree is less than the first preset correlation degree and whose decay speed is the first level as the third foil strip cloud;

[0195] Determine as the third target object an object whose gray correlation degree is not less than the first preset correlation degree, whose gray correlation degree is not less than the second preset correlation degree, and whose decay speed is the second level; and whose decay speed of the second level is less than that of the first level;

[0196] An object whose gray correlation degree is greater than the second preset correlation degree and whose decay speed is the third level is determined as a third corner reflector; and the decay speed of the third level is less than the decay speed of the second level.

[0197] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0198] Determine an object whose spatial position is higher than a preset height as a fourth foil cloud;

[0199] An object whose spatial position is not higher than a preset height is determined as a fourth corner reflector and a fourth target object.

[0200] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0201] Determine the final classification result according to the preset weight values ​​of each classification result and the classification result;

[0202] According to the final classification results, the interference objects are removed from the radar image.

[0203] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0204] Extracting distance features and speed features of the radar image according to a preset algorithm to obtain feature information of the radar image;

[0205] Classifying the objects to be identified in the radar image according to the characteristic information of the radar image to obtain a classification result; the classification result includes interference objects and target objects; the interference objects include chaff clouds and corner reflectors;

[0206] According to the classification results, interference objects are removed from the radar image.

[0207] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0208] According to the characteristic information of radar image, the number of scattering points of one-dimensional range image, echo waveform entropy, pulse-to-pulse gray correlation and spatial position in radar image are determined;

[0209] Determining a first classification result according to the number of scattering points in the one-dimensional range image and the echo amplitude in the radar image;

[0210] Determining a second classification result according to the echo waveform entropy of the radar image;

[0211] Determining the third classification result according to the inter-pulse grey relational degree and the decay speed of the inter-pulse grey relational degree;

[0212] According to the spatial position, the fourth classification result is determined.

[0213] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0214] Determine an object whose number of scattering points in the one-dimensional range image is greater than a first preset threshold and whose echo amplitude is at a first level as a first chaff cloud;

[0215] Determine an object whose number of scattering points in the one-dimensional range image is not greater than a first preset threshold, whose number of scattering points in the one-dimensional range image is not less than a second preset threshold, and whose echo amplitude is at the second level as a first target object;

[0216] An object whose one-dimensional range image scattering point number is less than a second preset threshold and whose echo amplitude is at the third level is determined as a first corner reflector.

[0217] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0218] Determine the object whose echo waveform entropy is greater than the first preset entropy as the second foil cloud;

[0219] Determine an object whose echo waveform entropy is not greater than a first preset entropy and an object whose echo waveform entropy is not less than a second preset entropy as a second target object;

[0220] An object whose echo waveform entropy is less than a second preset entropy is determined as a second corner reflector.

[0221] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0222] Determine the objects whose inter-pulse gray correlation degree is less than the first preset correlation degree and whose decay speed is the first level as the third foil strip cloud;

[0223] Determine as the third target object an object whose gray correlation degree is not less than the first preset correlation degree, whose gray correlation degree is not less than the second preset correlation degree, and whose decay speed is the second level; and whose decay speed of the second level is less than that of the first level;

[0224] An object whose gray correlation degree is greater than the second preset correlation degree and whose decay speed is the third level is determined as a third corner reflector; and the decay speed of the third level is less than the decay speed of the second level.

[0225] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0226] Determine an object whose spatial position is higher than a preset height as a fourth foil cloud;

[0227] An object whose spatial position is not higher than a preset height is determined as a fourth corner reflector and a fourth target object.

[0228] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0229] Determine the final classification result according to the preset weight values ​​of each classification result and the classification result;

[0230] According to the final classification results, the interference objects are removed from the radar image.

[0231] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0232] Extracting distance features and speed features of the radar image according to a preset algorithm to obtain feature information of the radar image;

[0233] Classifying the objects to be identified in the radar image according to the characteristic information of the radar image to obtain a classification result; the classification result includes interference objects and target objects; the interference objects include chaff clouds and corner reflectors;

[0234] According to the classification results, interference objects are removed from the radar image.

[0235] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0236] According to the characteristic information of radar image, the number of scattering points of one-dimensional range image, echo waveform entropy, pulse-to-pulse gray correlation and spatial position in radar image are determined;

[0237] Determining a first classification result according to the number of scattering points in the one-dimensional range image and the echo amplitude in the radar image;

[0238] Determining a second classification result according to the echo waveform entropy of the radar image;

[0239] Determining the third classification result according to the inter-pulse grey relational degree and the decay speed of the inter-pulse grey relational degree;

[0240] According to the spatial position, the fourth classification result is determined.

[0241] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0242] Determine an object whose number of scattering points in the one-dimensional range image is greater than a first preset threshold and whose echo amplitude is at a first level as a first chaff cloud;

[0243] Determine an object whose number of scattering points in the one-dimensional range image is not greater than a first preset threshold, whose number of scattering points in the one-dimensional range image is not less than a second preset threshold, and whose echo amplitude is at the second level as a first target object;

[0244] An object whose one-dimensional range image scattering point number is less than a second preset threshold and whose echo amplitude is at the third level is determined as a first corner reflector.

[0245] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0246] Determine the object whose echo waveform entropy is greater than the first preset entropy as the second foil cloud;

[0247] Determine an object whose echo waveform entropy is not greater than a first preset entropy and an object whose echo waveform entropy is not less than a second preset entropy as a second target object;

[0248] An object whose echo waveform entropy is less than a second preset entropy is determined as a second corner reflector.

[0249] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0250] Determine the objects whose inter-pulse gray correlation degree is less than the first preset correlation degree and whose decay speed is the first level as the third foil strip cloud;

[0251] Determine as the third target object an object whose gray correlation degree is not less than the first preset correlation degree, whose gray correlation degree is not less than the second preset correlation degree, and whose decay speed is the second level; and whose decay speed of the second level is less than that of the first level;

[0252] An object whose gray correlation degree is greater than the second preset correlation degree and whose decay speed is the third level is determined as a third corner reflector; and the decay speed of the third level is less than the decay speed of the second level.

[0253] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0254] Determine an object whose spatial position is higher than a preset height as a fourth foil cloud;

[0255] An object whose spatial position is not higher than a preset height is determined as a fourth corner reflector and a fourth target object.

[0256] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0257] Determine the final classification result according to the preset weight values ​​of each classification result and the classification result;

[0258] According to the final classification results, the interference objects are removed from the radar image.

[0259] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0260] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0261] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be construed as limiting the scope of the present application. It should be noted that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. An anti-interference method, characterized in that: The method comprises: Extracting distance features and speed features of the radar image according to a preset algorithm to obtain feature information of the radar image; Classifying the objects to be identified in the radar image according to the characteristic information of the radar image to obtain a classification result; the classification result includes interference objects and target objects; the interference objects include chaff clouds and corner reflectors; The interfering object is removed from the radar image according to the classification result.

2. The method according to claim 1, characterized in that The classifying the objects to be identified in the radar image according to the feature information of the radar image to obtain a classification result includes: Determine the number of one-dimensional range image scattering points, echo waveform entropy, inter-pulse gray correlation and spatial position in the radar image according to the characteristic information of the radar image; Determining a first classification result according to the number of scattering points in the one-dimensional range image and the echo amplitude in the radar image; Determining a second classification result according to the echo waveform entropy of the radar image; determining a third classification result according to the inter-pulse gray relational degree and the decay speed of the inter-pulse gray relational degree; A fourth classification result is determined according to the spatial position.

3. The method according to claim 2, characterized in that The first classification result includes a first foil cloud, a first target object, and a first corner reflector, and determining the first classification result according to the number of scattering points in the one-dimensional range image and the echo amplitude in the radar image includes: Determine the object whose number of scattering points in the one-dimensional range image is greater than a first preset threshold and whose echo amplitude is at a first level as the first foil strip cloud; Determine an object whose number of scattering points in the one-dimensional range image is not greater than the first preset threshold, whose number of scattering points in the one-dimensional range image is not less than the second preset threshold, and whose echo amplitude is at the second level as the first target object; An object whose number of scattering points in the one-dimensional range image is less than the second preset threshold and whose echo amplitude is at the third level is determined as the first corner reflector.

4. The method according to claim 2, characterized in that: The second classification result includes a second foil cloud, a second target object, and a second corner reflector, and determining the second classification result according to the echo waveform entropy of the radar image includes: Determine the object whose echo waveform entropy is greater than the first preset entropy as the second foil strip cloud; Determine the object whose echo waveform entropy is not greater than the first preset entropy and the object whose echo waveform entropy is not less than the second preset entropy as the second target object; The object whose echo waveform entropy is less than the second preset entropy is determined as the second corner reflector.

5. The method according to claim 2, characterized in that: The third classification result includes a third foil cloud, a third target object, and a third corner reflector, and the third classification result is determined according to the inter-pulse gray correlation degree and the attenuation speed of the inter-pulse gray correlation degree, including: Determine the object whose inter-pulse gray correlation degree is less than the first preset correlation degree and whose decay speed is the first level as the third foil strip cloud; Determine the object whose gray correlation degree is not less than the first preset correlation degree, whose gray correlation degree is not less than the second preset correlation degree, and whose decay speed is the second level as the third target object; and whose decay speed of the second level is less than the decay speed of the first level; An object whose gray correlation degree is greater than a second preset correlation degree and whose decay speed is a third level is determined as the third corner reflector; and the decay speed of the third level is less than the decay speed of the second level.

6. The method according to claim 2, characterized in that The fourth classification result includes a fourth foil cloud, a fourth target object, and a fourth corner reflector, and determining the fourth classification result according to the spatial position includes: Determine the object whose spatial position is higher than a preset height as the fourth foil cloud; The object whose spatial position is not higher than the preset height is determined as the fourth corner reflector and the fourth target object.

7. The method according to any one of claims 1 to 6, characterized in that: The classification results include a first classification result, a second classification result, a third classification result, and a fourth classification result. Removing the interference object from the radar image according to the classification results includes: Determining a final classification result according to the preset weight values ​​of each of the classification results and the classification result; The interfering object is removed from the radar image according to the final classification result.

8. An anti-interference device, characterized in that: The device comprises: A processing module, used to extract the distance feature and the speed feature of the radar image according to a preset algorithm to obtain feature information of the radar image; A determination module, used for classifying the objects to be identified in the radar image according to the characteristic information of the radar image to obtain a classification result; the classification result includes an interference object and a target object; the interference object includes a foil cloud and a corner reflector; A removal module is used to remove the interference object from the radar image according to the classification result.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images