A UAV target recognition method based on radar data

Abstract

The present application relates to a method for identifying drone targets based on radar data, and belongs to the field of drone identification technology. The method includes: based on a historical database, obtaining and preprocessing radar data of multiple historical target objects within a preset time period to obtain first radar data information; based on the first radar data information, marking different radar data respectively and storing them in an information database; obtaining second radar data information corresponding to radar data of multiple real-time target objects, and prioritizing the second radar data information based on the radar data in the information database to obtain a priority sorting result; based on the priority sorting result, inputting the radar data of the real-time target object into a drone target identification model in order to obtain an output result; based on the output result, determining the drone target identification result. The present application can improve the efficiency and accuracy of drone identification.

Description

Technical Field

[0001] The present application relates to the technical field of drone identification, and in particular to a drone target identification method based on radar data. Background Art

[0002] Generally speaking, a drone detection system consists of radar and an optoelectronic system. Under the premise that the number of targets is small, the radar is responsible for detecting targets, and the optoelectronic system is responsible for identifying and confirming targets. The working process is that after the radar detects the target, the optoelectronic system identifies, confirms and alarms the targets detected by the radar one by one. However, if there are many radar echoes similar to drones in a certain area (for example, non-drone targets such as birds or vehicles), the optoelectronic system does not immediately identify and confirm every target. All targets need to be confirmed one by one. Only when it is confirmed that it is a drone target will it alarm, and only after the alarm will it take countermeasures against the drone. This method takes a long time to detect and confirm drones, and there are safety risks.

[0003] Therefore, it is urgent to propose a UAV target recognition method based on radar data that can improve the efficiency of UAV recognition. Summary of the invention

[0004] Based on this, it is necessary to provide a drone target recognition method based on radar data that can improve the efficiency of drone recognition in response to the above technical problems.

[0005] In a first aspect, a method for identifying a drone target based on radar data is provided, the method comprising:

[0006] Based on the historical database, radar data of multiple historical target objects within a preset time period are acquired, and preprocessed to obtain first radar data information;

[0007] Based on the first radar data information, marking different radar data respectively and storing them in an information database;

[0008] Acquire second radar data information corresponding to radar data of multiple real-time target objects, and prioritize the second radar data information based on the radar data in the information database to obtain a priority ranking result;

[0009] Based on the priority sorting result, inputting the radar data of the real-time target object into the drone target recognition model in order to obtain an output result;

[0010] Based on the output result, the drone target recognition result is determined.

[0011] Optionally, the method for acquiring radar data includes:

[0012] Use radar to emit high-frequency electromagnetic waves, and receive the reflected signal of the target object through radar;

[0013] The object reflection signal of the target object is filtered to obtain the radar data.

[0014] Optionally, the radar data preprocessing method includes:

[0015] Acquire radar data of a target object at two target times within a target time period, wherein the radar data includes at least height, speed, length and width of the target object, and micro-Doppler frequency shift;

[0016] Based on the radar data of the target object at two target moments and the target function, an offset of the target object is determined, and the offsets of the plurality of target objects are defined as first radar data information.

[0017] Optionally, determining the offset of the target object based on radar data of the target object at two target times and a target function includes:

[0018] The radar data is normalized, and an offset of the target object is determined based on the normalization result and the objective function, wherein the objective function includes:

[0019]

[0020] Where P represents the offset, δ1, δ2, δ3, and δ4 represent weight coefficients, and their sum is 1, a1 and a2 represent the height of the first target moment and the height of the second target moment, respectively, b1 and b2 represent the speed of the first target moment and the speed of the second target moment, respectively, c1 and c2 represent the aspect ratio of the first target moment and the aspect ratio of the second target moment, respectively, d1 and d2 represent the micro-Doppler shift at the first target moment and the micro-Doppler shift at the second target moment, respectively, R t Represents the parameter function of the i-th target object at time t.

[0021] Optionally, based on the first radar data information, marking different radar data respectively and storing them in the information database includes:

[0022] Based on the offset of the target object and the attribute characteristics of the target object, the radar data corresponding to the first radar data information is marked with a unique identifier, wherein the unique identifier is generated based on the offset and the attribute characteristics of the target object;

[0023] The marked radar data is stored in the information database.

[0024] Optionally, a method for acquiring second radar data information corresponding to radar data of a real-time target object includes:

[0025] Acquire radar data of a real-time target object at two target time nodes, wherein the radar data includes at least height, speed, length and width of the target object, and micro-Doppler frequency shift;

[0026] Based on the radar data and the target function of the real-time target object at two target time nodes, the offset of the real-time target object is determined, and the offsets of the multiple real-time target objects are defined as the second radar data information.

[0027] Optionally, based on the radar data in the information database, the second radar data information is prioritized, and the priority ranking result obtained includes:

[0028] Comparing the second radar data information with the first radar data information corresponding to the radar data in the information database;

[0029] In response to detecting that the comparison is successful, marking the second radar data information based on the unique identifier of the target radar data;

[0030] According to the marking result, a priority sorting result of the radar data in the second radar data information is determined.

[0031] Optionally, based on the priority sorting result, the radar data of the real-time target object is input into the drone target recognition model in order, and the output results obtained include:

[0032] Construct an initial UAV target recognition model, and train and verify the initial UAV target recognition model based on radar data in the historical database;

[0033] In response to detecting that the verification result meets the preset standard, a target drone target recognition model is output, and the target drone target recognition model includes:

[0034]

[0035] Among them, n represents the value corresponding to the unique identifier, K m represents the correction coefficient when the unique identifier is m, β represents the number of target objects, x represents the target recognition threshold, which is an adjustable parameter, S represents the output result, and w represents the sum of radar data assignments;

[0036] The radar data of the real-time target object is input into the target drone target recognition model in sequence to obtain the output result.

[0037] Optionally, based on the output result, determining the drone target recognition result includes:

[0038] In response to detecting that the output result is greater than a preset threshold, the target object is determined to be a drone, and a warning message is sent to the terminal.

[0039] In a second aspect, a computer device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the following steps are implemented:

[0040] Based on the historical database, radar data of multiple historical target objects within a preset time period are acquired, and preprocessed to obtain first radar data information;

[0041] Based on the first radar data information, marking different radar data respectively and storing them in an information database;

[0042] Acquire second radar data information corresponding to radar data of multiple real-time target objects, and prioritize the second radar data information based on the radar data in the information database to obtain a priority ranking result;

[0043] Based on the priority sorting result, inputting the radar data of the real-time target object into the drone target recognition model in order to obtain an output result;

[0044] Based on the output result, the drone target recognition result is determined.

[0045] In a third aspect, 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:

[0046] Based on the historical database, radar data of multiple historical target objects within a preset time period are acquired, and preprocessed to obtain first radar data information;

[0047] Based on the first radar data information, marking different radar data respectively and storing them in an information database;

[0048] Acquire second radar data information corresponding to radar data of multiple real-time target objects, and prioritize the second radar data information based on the radar data in the information database to obtain a priority ranking result;

[0049] Based on the priority sorting result, inputting the radar data of the real-time target object into the drone target recognition model in order to obtain an output result;

[0050] Based on the output result, the drone target recognition result is determined.

[0051] In a fourth aspect, a computer program product is provided, the computer program product comprising a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0052] Based on the historical database, radar data of multiple historical target objects within a preset time period are acquired, and preprocessed to obtain first radar data information;

[0053] Based on the first radar data information, marking different radar data respectively and storing them in an information database;

[0054] Acquire second radar data information corresponding to radar data of multiple real-time target objects, and prioritize the second radar data information based on the radar data in the information database to obtain a priority ranking result;

[0055] Based on the priority sorting result, inputting the radar data of the real-time target object into the drone target recognition model in order to obtain an output result;

[0056] Based on the output result, the drone target recognition result is determined.

[0057] The above-mentioned UAV target recognition method based on radar data includes: based on a historical database, obtaining radar data of multiple historical target objects within a preset time period, and preprocessing to obtain first radar data information; based on the first radar data information, marking different radar data respectively, and storing them in an information database; obtaining second radar data information corresponding to the radar data of multiple real-time target objects, and based on the radar data in the information database, prioritizing the second radar data information to obtain a priority sorting result; based on the priority sorting result, inputting the radar data of the real-time target object into the UAV target recognition model in sequence to obtain an output result; based on the output result, determining the UAV target recognition result. The present application can reduce the time for discovering and confirming UAVs, improve the efficiency of UAV recognition, and perform secondary recognition through the UAV target recognition model to improve the accuracy of UAV recognition. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 A diagram showing an application environment of a method for identifying unmanned aerial vehicle targets based on radar data in one embodiment;

[0059] Figure 2 A schematic diagram of a flow chart of a method for identifying a drone target based on radar data in one embodiment;

[0060] Figure 3 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0061] In order to make the purpose, technical solutions and advantages of this application clearer, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0062] It should be understood that in the description of the present application, unless the context clearly requires otherwise, words such as "include", "comprises", and the like throughout the specification should be interpreted as including rather than being exclusive or exhaustive; that is, as including but not limited to.

[0063] It should also be understood that the terms "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance. In addition, in the description of this application, unless otherwise specified, "plurality" means two or more.

[0064] It should be noted that the terms "S1", "S2", etc. are only used for the purpose of describing the steps, and do not specifically refer to the order or sequence, nor are they used to limit the present application. They are only for the convenience of describing the method of the present application, and cannot be understood as indicating the order of the steps. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in this field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection required by the present application.

[0065] The drone target recognition method based on radar data provided in this application can be applied to Figure 1 In the application environment shown, the terminal 102 communicates with the data processing platform set on the server 104 through the network, wherein the terminal 102 can be but not limited to various personal computers, laptops, smart phones, tablet computers and portable wearable devices, and the server 104 can be implemented by an independent server or a server cluster composed of multiple servers.

[0066] In one embodiment, Figure 2 As shown in the figure, a method for UAV target recognition based on radar data is provided. Figure 1 The terminal in is used as an example to illustrate, including the following steps:

[0067] S1: Based on a historical database, radar data of multiple historical target objects within a preset time period are acquired, and preprocessed to obtain first radar data information.

[0068] It should be noted that the historical database refers to a database that stores historical target object radar data. The target objects may include drones, helicopters, and flying birds. The radar data may include the height, speed, length and width of the target object, and micro-Doppler frequency shift. The micro-Doppler frequency shift is used to describe the frequency change information of the drone wings, which can be calculated according to common methods and will not be repeated here. The preset time period can be set according to actual needs, such as within one year.

[0069] In some specific implementations, the method for acquiring radar data includes:

[0070] Use radar to emit high-frequency electromagnetic waves, and receive the reflected signal of the target object through radar;

[0071] The object reflection signal of the target object is filtered to obtain the radar data, wherein the filtering process mainly includes steps such as removing noise, clutter and interference to improve data quality and the accuracy of subsequent analysis. The specific processing method is a common method and will not be repeated here.

[0072] In some specific implementations, the radar data preprocessing method includes:

[0073] Acquire radar data of the target object at two target moments within the target time period, wherein the radar data includes at least the height, speed, length and width of the target object, and micro-Doppler shift, wherein the two target moments can be selected according to actual needs, and generally more representative moments are selected, such as two moments with large changes in height or speed;

[0074] Based on the radar data of the target object at two target moments and the target function, an offset of the target object is determined, and the offsets of the plurality of target objects are defined as first radar data information.

[0075] In some specific implementations, determining the offset of the target object based on the radar data of the target object at two target times and the target function includes:

[0076] The radar data is normalized, and based on the normalized processing result and the objective function, the offset of the target object is determined, wherein the data normalization processing method is a common method and will not be described in detail here. The objective function includes:

[0077]

[0078] Where P represents the offset, δ1, δ2, δ3, and δ4 represent weight coefficients, and their sum is 1. a1 and a2 represent the height of the first target moment and the height of the second target moment, respectively. b1 and b2 represent the speed of the first target moment and the speed of the second target moment, respectively. c1 and c2 represent the aspect ratio of the first target moment and the aspect ratio of the second target moment, that is, the ratio of length to width, respectively. d1 and d2 represent the micro-Doppler shift of the first target moment and the micro-Doppler shift of the second target moment, respectively. R t represents the parameter adjustment function of the i-th target object at time t, where the velocity and micro-Doppler shift are instantaneous data.

[0079] S2: Based on the first radar data information, mark different radar data respectively and store them in the information database.

[0080] It should be noted that the identifier used to mark radar data is a unique identifier, which is generated by the offset and attribute characteristics of the target object. The attribute characteristics refer to whether the target object is a drone. Based on this, if the offset is 0.95 and the target object is a drone, the unique identifier can be X-1-0.95, where 1 means that the target object is a drone, and if it is 2, it means that the target object is not a drone. X is used for subsequent priority sorting marking.

[0081] In some specific implementations, based on the first radar data information, marking different radar data respectively and storing them in the information database includes:

[0082] Based on the offset of the target object and the attribute characteristics of the target object, the radar data corresponding to the first radar data information is marked with a unique identifier, wherein the unique identifier is generated based on the offset and the attribute characteristics of the target object;

[0083] The marked radar data is stored in the information database.

[0084] S3: Obtain second radar data information corresponding to radar data of multiple real-time target objects, and prioritize the second radar data information based on the radar data in the information database to obtain a priority ranking result.

[0085] It should be noted that the real-time target object can be one or multiple, such as multiple drones, or one drone and multiple flying birds.

[0086] In some specific implementations, a method for acquiring second radar data information corresponding to radar data of a real-time target object includes:

[0087] Acquire radar data of the real-time target object at two target time nodes, wherein the radar data includes at least the height, speed, length and width of the target object, and micro-Doppler shift, wherein the two target time nodes can be set according to actual needs, generally two relatively close time nodes, so as to quickly determine whether it is a drone;

[0088] Based on the radar data and target function of the real-time target object at two target time nodes, the offset of the real-time target object is determined, and the offsets of multiple real-time target objects are defined as the second radar data information, wherein the calculation method of the offset is the same as above and will not be repeated here.

[0089] In some specific implementations, based on the radar data in the information database, the second radar data information is prioritized, and obtaining the priority ranking result includes:

[0090] Comparing the second radar data information with the first radar data information corresponding to the radar data in the information database, wherein the comparison here is an offset;

[0091] In response to detecting that the comparison is successful, the second radar data information is marked based on the unique identifier of the target radar data, wherein the judgment criterion for whether the comparison is successful is whether the absolute value of the difference between the second radar data information and the first radar data information is within a preset range. If so, the comparison is judged to be successful; if not, the comparison is judged to be unsuccessful. The preset range can be set according to actual needs, and the marking is marked according to the unique identifier. For example, when the unique identifier contains the drone attribute feature and other target objects do not contain the drone attribute feature, such as X-1-0.95, the priority sorting feature X is set to 1, which has a higher priority. If other target objects also contain drone attribute features, they are set according to the offset size. The smaller the offset, the higher the priority, and so on.

[0092] According to the marking result, the priority sorting result of the radar data in the second radar data information is determined, that is, the radar data is sorted according to the priority sorting feature X, and the data with higher priority is sorted first.

[0093] S4: Based on the priority sorting result, the radar data of the real-time target object is input into the UAV target recognition model in order to obtain an output result.

[0094] It should be noted that the drone target recognition model is used to perform secondary confirmation of the offset comparison results to improve the recognition accuracy.

[0095] In some specific implementations, based on the priority sorting result, the radar data of the real-time target object is input into the drone target recognition model in order, and the output results obtained include:

[0096] Construct an initial UAV target recognition model, and train and verify the initial UAV target recognition model based on the radar data in the historical database, wherein the radar data in the historical database can be divided into a training set and a verification set in a ratio of 7:3 for training and verifying the initial UAV target recognition model;

[0097] In response to detecting that the verification result meets the preset standard, the target drone target recognition model is output, wherein the preset standard may refer to the recognition accuracy reaching a certain threshold, such as 95%, etc. The target drone target recognition model includes:

[0098]

[0099] Among them, n represents the value corresponding to the unique identifier, that is, the priority ranking value, K m represents the correction coefficient when the unique identifier is m, β represents the number of target objects, x represents the target recognition threshold, which is an adjustable parameter, S represents the output result, and w represents the sum of radar data assignments;

[0100] The radar data of the real-time target object is input into the target drone target recognition model in sequence to obtain the output result.

[0101] S5: Based on the output result, determine the drone target recognition result.

[0102] In some specific implementations, determining the drone target recognition result based on the output result includes:

[0103] In response to detecting that the output result is greater than a preset threshold, the target object is determined to be a drone, and a warning message is sent to the terminal. If it is less than or equal to the preset threshold, no processing is performed. The preset threshold can be set according to actual needs, and is generally set to 0, that is, when the output result is greater than 0, the target object is determined to be a drone, and a warning message is sent to the terminal.

[0104] In the above-mentioned UAV target recognition method based on radar data, the method includes: based on a historical database, obtaining radar data of multiple historical target objects within a preset time period, and preprocessing to obtain first radar data information; based on the first radar data information, marking different radar data respectively, and storing them in the information database; obtaining second radar data information corresponding to the radar data of multiple real-time target objects, and based on the radar data in the information database, prioritizing the second radar data information to obtain a priority sorting result; based on the priority sorting result, inputting the radar data of the real-time target object into the UAV target recognition model in sequence to obtain an output result; based on the output result, determining the UAV target recognition result. The present application can reduce the time for discovering and confirming UAVs, improve the efficiency of UAV recognition, and perform secondary recognition through the UAV target recognition model to improve the accuracy of UAV recognition.

[0105] It should be understood that although Figure 2 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 2 At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0106] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 3 As shown. The computer device includes a processor, a memory, a network interface, a display screen and an input device connected through a system bus. Among them, 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 network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for identifying drone targets based on radar data is implemented. The display screen of the computer device 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 covered on the display screen, or a key, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse, etc.

[0107] Those skilled in the art will understand that Figure 3 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.

[0108] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer program:

[0109] S1: Based on the historical database, radar data of multiple historical target objects within a preset time period are obtained, and preprocessed to obtain first radar data information;

[0110] S2: Based on the first radar data information, mark different radar data respectively and store them in an information database;

[0111] S3: Acquire second radar data information corresponding to radar data of multiple real-time target objects, and prioritize the second radar data information based on the radar data in the information database to obtain a priority ranking result;

[0112] S4: Based on the priority sorting result, input the radar data of the real-time target object into the UAV target recognition model in order to obtain an output result;

[0113] S5: Based on the output result, determine the drone target recognition result.

[0114] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0115] Use radar to emit high-frequency electromagnetic waves, and receive the reflected signal of the target object through radar;

[0116] The object reflection signal of the target object is filtered to obtain the radar data.

[0117] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0118] Acquire radar data of a target object at two target times within a target time period, wherein the radar data includes at least height, speed, length and width of the target object, and micro-Doppler frequency shift;

[0119] Based on the radar data of the target object at two target moments and the target function, an offset of the target object is determined, and the offsets of the plurality of target objects are defined as first radar data information.

[0120] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0121] The radar data is normalized, and an offset of the target object is determined based on the normalization result and the objective function, wherein the objective function includes:

[0122]

[0123] Where P represents the offset, δ1, δ2, δ3, and δ4 represent weight coefficients, and their sum is 1, a1 and a2 represent the height of the first target moment and the height of the second target moment, respectively, b1 and b2 represent the speed of the first target moment and the speed of the second target moment, respectively, c1 and c2 represent the aspect ratio of the first target moment and the aspect ratio of the second target moment, respectively, d1 and d2 represent the micro-Doppler shift at the first target moment and the micro-Doppler shift at the second target moment, respectively, R t Represents the parameter function of the i-th target object at time t.

[0124] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0125] Based on the offset of the target object and the attribute characteristics of the target object, the radar data corresponding to the first radar data information is marked with a unique identifier, wherein the unique identifier is generated based on the offset and the attribute characteristics of the target object;

[0126] The marked radar data is stored in the information database.

[0127] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0128] Acquire radar data of a real-time target object at two target time nodes, wherein the radar data includes at least height, speed, length and width of the target object, and micro-Doppler frequency shift;

[0129] Based on the radar data and the target function of the real-time target object at two target time nodes, the offset of the real-time target object is determined, and the offsets of the multiple real-time target objects are defined as the second radar data information.

[0130] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0131] Comparing the second radar data information with the first radar data information corresponding to the radar data in the information database;

[0132] In response to detecting that the comparison is successful, marking the second radar data information based on the unique identifier of the target radar data;

[0133] According to the marking result, a priority sorting result of the radar data in the second radar data information is determined.

[0134] In one embodiment, when the processor executes the computer program, the following steps are also implemented:

[0135] Construct an initial UAV target recognition model, and train and verify the initial UAV target recognition model based on radar data in the historical database;

[0136] In response to detecting that the verification result meets the preset standard, a target drone target recognition model is output, and the target drone target recognition model includes:

[0137]

[0138] Among them, n represents the value corresponding to the unique identifier, K m represents the correction coefficient when the unique identifier is m, β represents the number of target objects, x represents the target recognition threshold, which is an adjustable parameter, S represents the output result, and w represents the sum of radar data assignments;

[0139] The radar data of the real-time target object is input into the target drone target recognition model in sequence to obtain the output result.

[0140] In one embodiment, when the processor executes the computer program, the following steps are also implemented:

[0141] In response to detecting that the output result is greater than a preset threshold, the target object is determined to be a drone, and a warning message is sent to the terminal.

[0142] 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:

[0143] S1: Based on the historical database, radar data of multiple historical target objects within a preset time period are obtained, and preprocessed to obtain first radar data information;

[0144] S2: Based on the first radar data information, mark different radar data respectively and store them in an information database;

[0145] S3: Acquire second radar data information corresponding to radar data of multiple real-time target objects, and prioritize the second radar data information based on the radar data in the information database to obtain a priority ranking result;

[0146] S4: Based on the priority sorting result, input the radar data of the real-time target object into the UAV target recognition model in order to obtain an output result;

[0147] S5: Based on the output result, determine the drone target recognition result.

[0148] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0149] Use radar to emit high-frequency electromagnetic waves, and receive the reflected signal of the target object through radar;

[0150] The object reflection signal of the target object is filtered to obtain the radar data.

[0151] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0152] Acquire radar data of a target object at two target times within a target time period, wherein the radar data includes at least height, speed, length and width of the target object, and micro-Doppler frequency shift;

[0153] Based on the radar data of the target object at two target moments and the target function, an offset of the target object is determined, and the offsets of the plurality of target objects are defined as first radar data information.

[0154] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0155] The radar data is normalized, and an offset of the target object is determined based on the normalization result and the objective function, wherein the objective function includes:

[0156]

[0157] Where P represents the offset, δ1, δ2, δ3, and δ4 represent weight coefficients, and their sum is 1, a1 and a2 represent the height of the first target moment and the height of the second target moment, respectively, b1 and b2 represent the speed of the first target moment and the speed of the second target moment, respectively, c1 and c2 represent the aspect ratio of the first target moment and the aspect ratio of the second target moment, respectively, d1 and d2 represent the micro-Doppler shift at the first target moment and the micro-Doppler shift at the second target moment, respectively, R t Represents the parameter function of the i-th target object at time t.

[0158] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0159] Based on the offset of the target object and the attribute characteristics of the target object, the radar data corresponding to the first radar data information is marked with a unique identifier, wherein the unique identifier is generated based on the offset and the attribute characteristics of the target object;

[0160] The marked radar data is stored in the information database.

[0161] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0162] Acquire radar data of a real-time target object at two target time nodes, wherein the radar data includes at least height, speed, length and width of the target object, and micro-Doppler frequency shift;

[0163] Based on the radar data and the target function of the real-time target object at two target time nodes, the offset of the real-time target object is determined, and the offsets of the multiple real-time target objects are defined as the second radar data information.

[0164] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0165] Comparing the second radar data information with the first radar data information corresponding to the radar data in the information database;

[0166] In response to detecting that the comparison is successful, marking the second radar data information based on the unique identifier of the target radar data;

[0167] According to the marking result, a priority sorting result of the radar data in the second radar data information is determined.

[0168] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0169] Construct an initial UAV target recognition model, and train and verify the initial UAV target recognition model based on radar data in the historical database;

[0170] In response to detecting that the verification result meets the preset standard, a target drone target recognition model is output, and the target drone target recognition model includes:

[0171]

[0172] Among them, n represents the value corresponding to the unique identifier, K m represents the correction coefficient when the unique identifier is m, β represents the number of target objects, x represents the target recognition threshold, which is an adjustable parameter, S represents the output result, and w represents the sum of radar data assignments;

[0173] The radar data of the real-time target object is input into the target drone target recognition model in sequence to obtain the output result.

[0174] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0175] In response to detecting that the output result is greater than a preset threshold, the target object is determined to be a drone, and a warning message is sent to the terminal.

[0176] In one embodiment, a computer program product is provided, the computer program product comprising a computer program, the computer program when executed by a processor implements the following steps:

[0177] S1: Based on the historical database, radar data of multiple historical target objects within a preset time period are obtained, and preprocessed to obtain first radar data information;

[0178] S2: Based on the first radar data information, mark different radar data respectively and store them in an information database;

[0179] S3: Acquire second radar data information corresponding to radar data of multiple real-time target objects, and prioritize the second radar data information based on the radar data in the information database to obtain a priority ranking result;

[0180] S4: Based on the priority sorting result, input the radar data of the real-time target object into the UAV target recognition model in order to obtain an output result;

[0181] S5: Based on the output result, determine the drone target recognition result.

[0182] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0183] Use radar to emit high-frequency electromagnetic waves, and receive the reflected signal of the target object through radar;

[0184] The object reflection signal of the target object is filtered to obtain the radar data.

[0185] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0186] Acquire radar data of a target object at two target times within a target time period, wherein the radar data includes at least height, speed, length and width of the target object, and micro-Doppler frequency shift;

[0187] Based on the radar data of the target object at two target moments and the target function, an offset of the target object is determined, and the offsets of the plurality of target objects are defined as first radar data information.

[0188] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0189] The radar data is normalized, and an offset of the target object is determined based on the normalization result and the objective function, wherein the objective function includes:

[0190]

[0191] Where P represents the offset, δ1, δ2, δ3, and δ4 represent weight coefficients, and their sum is 1, a1 and a2 represent the height of the first target moment and the height of the second target moment, respectively, b1 and b2 represent the speed of the first target moment and the speed of the second target moment, respectively, c1 and c2 represent the aspect ratio of the first target moment and the aspect ratio of the second target moment, respectively, d1 and d2 represent the micro-Doppler shift at the first target moment and the micro-Doppler shift at the second target moment, respectively, R t Represents the parameter function of the i-th target object at time t.

[0192] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0193] Based on the offset of the target object and the attribute characteristics of the target object, the radar data corresponding to the first radar data information is marked with a unique identifier, wherein the unique identifier is generated based on the offset and the attribute characteristics of the target object;

[0194] The marked radar data is stored in the information database.

[0195] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0196] Acquire radar data of a real-time target object at two target time nodes, wherein the radar data includes at least height, speed, length and width of the target object, and micro-Doppler frequency shift;

[0197] Based on the radar data and the target function of the real-time target object at two target time nodes, the offset of the real-time target object is determined, and the offsets of the multiple real-time target objects are defined as the second radar data information.

[0198] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0199] Comparing the second radar data information with the first radar data information corresponding to the radar data in the information database;

[0200] In response to detecting that the comparison is successful, marking the second radar data information based on the unique identifier of the target radar data;

[0201] According to the marking result, a priority sorting result of the radar data in the second radar data information is determined.

[0202] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0203] Construct an initial UAV target recognition model, and train and verify the initial UAV target recognition model based on radar data in the historical database;

[0204] In response to detecting that the verification result meets the preset standard, a target drone target recognition model is output, and the target drone target recognition model includes:

[0205]

[0206] Among them, n represents the value corresponding to the unique identifier, K m represents the correction coefficient when the unique identifier is m, β represents the number of target objects, x represents the target recognition threshold, which is an adjustable parameter, S represents the output result, and w represents the sum of radar data assignments;

[0207] The radar data of the real-time target object is input into the target drone target recognition model in sequence to obtain the output result.

[0208] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0209] In response to detecting that the output result is greater than a preset threshold, the target object is determined to be a drone, and a warning message is sent to the terminal.

[0210] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods 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 memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0211] 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 specification.

[0212] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for ordinary technicians in this field, several variations 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.

Claims

1. A method for identifying unmanned aerial vehicle targets based on radar data, characterized in that: The method comprises: Based on the historical database, radar data of multiple historical target objects within a preset time period are obtained, and preprocessed to obtain first radar data information, and the offset of multiple target objects is defined as the first radar data information: is the offset, , , , are weight coefficients, and , and , and as well as and are the height, speed, aspect ratio and micro-Doppler shift of the two targets at the same time. For Moment The parameter tuning function of the target object; Based on the first radar data information, different radar data are marked respectively and stored in the information database; Acquire second radar data information corresponding to radar data of multiple real-time target objects, and prioritize the second radar data information based on the radar data in the information database to obtain a priority ranking result; Based on the priority sorting results, the radar data of the real-time target objects are input into the UAV target recognition model in order to obtain the output results; Based on the output results, the drone target recognition results are determined.

2. The method for identifying unmanned aerial vehicle targets based on radar data according to claim 1, characterized in that: The radar data acquisition method comprises: Use radar to emit high-frequency electromagnetic waves, and receive the reflected signal of the target object through radar; The object reflection signal of the target object is filtered to obtain the radar data.

3. The method for identifying unmanned aerial vehicle targets based on radar data according to claim 2, characterized in that: The radar data preprocessing method comprises: Acquire radar data of a target object at two target times within a target time period, wherein the radar data includes at least height, speed, length and width of the target object, and micro-Doppler frequency shift; Based on the radar data of the target object at two target moments and the target function, an offset of the target object is determined, and the offsets of the plurality of target objects are defined as first radar data information.

4. The method for identifying unmanned aerial vehicle targets based on radar data according to claim 3, characterized in that: Determining the offset of the target object based on radar data of the target object at two target times and the target function includes: The radar data is normalized, and an offset of the target object is determined based on the normalization result and the objective function, wherein the objective function includes: in, Indicates the offset, , , , Both represent weight coefficients, and their sum is 1. and They represent the altitude at the first target moment and the altitude at the second target moment respectively. and They represent the speed at the first target moment and the speed at the second target moment respectively. and Respectively represent the aspect ratio of the first target moment and the aspect ratio of the second target moment, and represent the micro-Doppler frequency shift at the first target moment and the micro-Doppler frequency shift at the second target moment, respectively. Indicated in Moment The parameter tuning function of a target object.

5. The method for identifying unmanned aerial vehicle targets based on radar data according to claim 4, characterized in that: Based on the first radar data information, marking different radar data respectively and storing them in the information database includes: Based on the offset of the target object and the attribute characteristics of the target object, the radar data corresponding to the first radar data information is marked with a unique identifier, wherein the unique identifier is generated based on the offset and the attribute characteristics of the target object; The marked radar data is stored in the information database.

6. The method for identifying unmanned aerial vehicle targets based on radar data according to claim 5, characterized in that: The method for acquiring the second radar data information corresponding to the radar data of the real-time target object includes: Acquire radar data of a real-time target object at two target time nodes, wherein the radar data includes at least height, speed, length and width of the target object, and micro-Doppler frequency shift; Based on the radar data and the target function of the real-time target object at two target time nodes, the offset of the real-time target object is determined, and the offsets of the multiple real-time target objects are defined as the second radar data information.

7. The method for identifying unmanned aerial vehicle targets based on radar data according to claim 6, characterized in that: Based on the radar data in the information database, the second radar data information is prioritized, and the priority ranking result obtained includes: Comparing the second radar data information with the first radar data information corresponding to the radar data in the information database; In response to detecting that the comparison is successful, marking the second radar data information based on the unique identifier of the target radar data; According to the marking result, a priority sorting result of the radar data in the second radar data information is determined.

8. The method for identifying unmanned aerial vehicle targets based on radar data according to claim 7, characterized in that: Based on the priority sorting results, the radar data of the real-time target objects are input into the drone target recognition model in order, and the output results obtained include: Construct an initial UAV target recognition model, and train and verify the initial UAV target recognition model based on radar data in the historical database; In response to detecting that the verification result meets the preset standard, a target drone target recognition model is output, and the target drone target recognition model includes: in, Indicates the value corresponding to the unique identifier. Indicates that the unique identifier is The correction factor when Indicates the number of target objects. Represents the target recognition threshold, which is an adjustable parameter. Indicates the output result, Represents the sum of radar data assignments; The radar data of the real-time target object is input into the target drone target recognition model in sequence to obtain the output result.

9. The method for identifying unmanned aerial vehicle targets based on radar data according to claim 8, characterized in that: Based on the output result, determining the drone target recognition result includes: In response to detecting that the output result is greater than a preset threshold, the target object is determined to be a drone, and a warning message is sent to the terminal.

Images