Unmanned aerial vehicle countering method and device based on multi-target detection and program product

Abstract

The invention belongs to the technical field of unmanned aerial vehicle management and control, and particularly discloses an unmanned aerial vehicle countering method and device based on multi-target detection and a program product, and the method comprises the steps: carrying out the linkage detection of a multi-target unmanned aerial vehicle, obtaining the radar detection data, radio frequency monitoring data, spectrum detection data and acoustic detection data of each target unmanned aerial vehicle, then performing model preliminary screening based on radar detection data, performing model pre-selection based on radio frequency monitoring data and acoustic detection data, performing final matching based on spectrum detection data, determining the model of a target unmanned aerial vehicle, and performing signal interference by pertinently adapting to a corresponding unmanned aerial vehicle countering strategy; and efficient and accurate multi-target unmanned aerial vehicle detection and signal interference countering can be realized. According to the invention, by fusing the multi-dimensional linkage detection data and carrying out multi-level information matching, different types of unmanned aerial vehicles can be accurately distinguished, and an optimized countering strategy is specifically implemented, so that the countering efficiency of the unmanned aerial vehicles is improved, and the low-altitude safety is effectively guaranteed.

Description

Technical Field

[0001] This invention belongs to the field of unmanned aerial vehicle (UAV) management technology, specifically relating to UAV countermeasures methods, devices, and software products based on multi-target detection. Background Technology

[0002] Unmanned aerial vehicles (UAVs) are unmanned aerial vehicles controlled by radio remote control equipment and onboard program control devices. They have no cockpit but are equipped with autopilots and other equipment, and can be tracked, located, and digitally transmitted by personnel at ground or mother-aircraft remote control stations. UAVs have advantages such as small size, low cost, and ease of use, and are widely used in fields such as aerial photography, agricultural plant protection, and power line inspection.

[0003] However, with the rapid increase in the number of drones in use, incidents of unauthorized drone flights and intrusions are frequent, bringing numerous security risks. Developing effective countermeasures against drones is urgently needed to address the current situation of unauthorized drone flights and intrusions. Currently, the most common countermeasures involve detecting unauthorized drone flights through human observation or radar detection, and then countering them through physical interception or signal jamming.

[0004] Due to differences in their design purpose, communication and navigation technologies, and anti-jamming capabilities, different types of drones result in varying effectiveness of countermeasures when employing different strategies. Consumer-grade drones, with their small size and small radar cross-section, coupled with ground clutter interference, suffer from low radar detection accuracy. Therefore, it is difficult to implement targeted countermeasures, forcing the use of uniform and crude countermeasures, which necessitates improvements in overall efficiency. Summary of the Invention

[0005] The purpose of this invention is to provide a method, apparatus, and program product for countering unmanned aerial vehicles (UAVs) based on multi-target detection, in order to solve the aforementioned problems existing in the prior art.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: Firstly, it provides a method for countering drones based on multi-target detection, including: The radar detection results of multiple targets unmanned aerial vehicles (UAVs) are obtained, including the azimuth parameters, range parameters, velocity parameters and radar cross-section parameters of each target UAV. The corresponding linkage detection range is determined based on the azimuth and distance parameters of the target UAV, and radio frequency monitoring, spectral detection and acoustic detection are performed on the corresponding linkage detection range to obtain the radio frequency monitoring data, spectral detection data and acoustic detection data of the target UAV. Radio frequency fingerprint features are extracted from the radio frequency monitoring data of the target UAV; shape contour features, texture features and infrared features are extracted from the spectral detection data of the target UAV; and acoustic fingerprint features are extracted from the acoustic detection data of the target UAV. Based on the speed parameters and radar cross-section parameters of the target UAV, a preliminary set of target UAV models is selected from the model library. The preliminary set of target UAV models includes several preliminary models. Based on the radio frequency fingerprint and voiceprint characteristics of the target drone, a pre-selection set of target drones is selected from the initial screening set. The pre-selection set includes several pre-selected models. Based on the shape contour features, texture features and infrared features of the target UAV, the optical feature similarity between the target UAV and each of the pre-selected models in the pre-selection model set is determined, and the pre-selected models whose optical feature similarity with the target UAV meets the set conditions are taken as the target UAV's target models. Match the appropriate countermeasure strategy to the target drone model and execute the countermeasure strategy to interfere with the target drone's signal.

[0007] In one possible design, determining the corresponding coordinated detection range based on the azimuth and distance parameters of the target UAV includes: Determine the reference point of the target UAV in the set spatial coordinate system based on the azimuth and distance parameters of the target UAV; The line connecting the reference point and the origin of the set spatial coordinate system is used as the reference line, and a cone-shaped spatial region of a set size is defined around the reference line as the linkage detection range.

[0008] In one possible design, the model library contains several UAV models, and each UAV model is associated with a corresponding set of attribute features. The set of attribute features includes a speed parameter range, a radar cross section parameter range, template radio frequency fingerprint features, template acoustic features, template shape contour features, template texture features, and template infrared features.

[0009] In one possible design, the initial screening of the target UAV model set from the model library based on the target UAV's speed parameters and radar cross-section parameters includes: The speed parameters and radar cross section parameters of the target UAV are compared with the speed parameter ranges and radar cross section parameter ranges associated with each UAV model in the model database; If the speed parameters of the target drone are within the speed parameter range of the corresponding drone model, and the radar cross section parameters of the target drone are within the radar cross section parameter range of the corresponding drone model, then the corresponding drone model will be used as the initial screening model of the target drone. The initial screening models of the target drones selected from the model library are summarized to obtain the initial screening model set of the target drones.

[0010] In one possible design, the step of selecting a pre-selection set of target drones from the initial screening set based on the target drone's radio frequency fingerprint and voiceprint characteristics includes: The radio frequency fingerprint and acoustic signature features of the target UAV, along with the template radio frequency fingerprint and template acoustic signature features of the corresponding primary screening model in the primary screening model set, are substituted into a preset correlation formula to calculate the correlation coefficient between the target UAV and the corresponding primary screening model. The correlation formula is as follows:

[0011] Where R represents the correlation coefficient, i represents the component index of the RF fingerprint feature or template RF fingerprint feature, m is the total number of components of the RF fingerprint feature or template RF fingerprint feature, and X i The i-th component, Y, characterizes the features of an RF fingerprint. i The i-th component characterizing the template RF fingerprint feature, j being the component index characterizing the acoustic signature feature or template acoustic signature feature, n being the total number of acoustic signature feature or template acoustic signature feature components, and x being the component index characterizing the template RF fingerprint feature. j The j-th component representing the voiceprint feature, y j The j-th component characterizing the template voiceprint features, where α is the first weighting coefficient and β is the second weighting coefficient; The preliminary screening models whose correlation coefficient with the target drone exceeds a set threshold are selected as the pre-selected models of the target drone. The pre-selected models of the target drone are then aggregated to obtain the pre-selected model set of the target drone.

[0012] In one possible design, the determination of the optical feature similarity between the target UAV and each pre-selected model in the pre-selection model set based on the target UAV's shape contour features, texture features, and infrared features, and the selection of pre-selected models whose optical feature similarity with the target UAV meets the set conditions as the target UAV's target model, includes: The shape contour features, texture features and infrared features of the target UAV are fused to obtain the optical feature vector of the target UAV. The shape contour features, texture features and infrared features of the templates of each pre-selected UAV in the pre-selected UAV set are fused to obtain the template optical feature vector of each pre-selected UAV. The optical feature vector of the target UAV and the template optical feature vector of the corresponding pre-selected UAV in the pre-selected model set are substituted into a preset optical feature similarity formula for calculation to obtain the optical feature similarity between the target UAV and the corresponding pre-selected model. The optical feature similarity formula is as follows:

[0013] Where S represents the optical feature similarity, k represents the component index of the optical feature vector or template optical feature vector, W represents the total number of components of the optical feature vector or template optical feature vector, and z k p represents the k-th component of the optical eigenvector. k The k-th component of the template optical eigenvector is represented by ω, which is a set constant to prevent it from being reduced to zero. The pre-selected model with the highest optical feature similarity to the target drone exceeding the set similarity threshold will be used as the target drone model.

[0014] In one possible design, the countermeasure strategy includes signal jamming methods, signal jamming frequency bands, and signal jamming intensity. The signal jamming methods include communication jamming, navigation jamming, or electromagnetic shielding. Matching the appropriate countermeasure strategy based on the target UAV's model includes: Determine the model number corresponding to the target drone model; The model number is substituted into a preset countermeasure strategy table for matching to determine the signal interference method, signal interference frequency band and signal interference intensity corresponding to the model number. The countermeasure strategy table contains several model numbers and the signal interference method, signal interference frequency band and signal interference intensity associated with each model number. The corresponding countermeasures are formed by matching the signal interference method, signal interference frequency band, and signal interference intensity with the model number.

[0015] Secondly, it provides a UAV countermeasure device based on multi-target detection, including a radar detection unit, a linkage detection unit, a feature extraction unit, an aircraft type initial screening unit, an aircraft type pre-selection unit, an aircraft type determination unit, and a target countermeasure unit, wherein: The radar detection unit is used to acquire radar detection results of multiple targets UAVs, which include the azimuth parameters, range parameters, velocity parameters and radar cross section parameters of each target UAV. The linkage detection unit is used to determine the corresponding linkage detection range based on the azimuth and distance parameters of the target UAV, and to perform radio frequency monitoring, spectral detection and acoustic detection on the corresponding linkage detection range to obtain the radio frequency monitoring data, spectral detection data and acoustic detection data of the target UAV. The feature extraction unit is used to extract radio frequency fingerprint features from the radio frequency monitoring data of the target UAV, extract shape contour features, texture features and infrared features from the spectral detection data of the target UAV, and extract acoustic fingerprint features from the acoustic detection data of the target UAV. The model screening unit is used to select a preliminary set of target UAV models from the model library based on the speed parameters and radar cross-section parameters of the target UAV. The preliminary set of models includes several preliminary models. The model pre-selection unit is used to select a pre-selection set of target drones from the initial model set based on the radio frequency fingerprint and voiceprint features of the target drones. The pre-selection set of drones includes several pre-selection models. The model determination unit is used to determine the similarity of the optical features of the target UAV with each of the pre-selected models in the pre-selection model set based on the shape contour features, texture features and infrared features of the target UAV, and to take the pre-selected models whose optical feature similarity with the target UAV meets the set conditions as the target UAV's target model; The target countermeasure unit is used to match the corresponding countermeasure strategy according to the target UAV model and execute the countermeasure strategy to interfere with the signal of the target UAV.

[0016] Thirdly, it provides anti-drone devices based on multi-target detection, including: Memory, used to store instructions; The processor is configured to read instructions stored in the memory and execute any one of the UAV countermeasures methods based on multi-target detection described in the first aspect above, according to the instructions.

[0017] Fourthly, a computer-readable storage medium is provided, on which instructions are stored, which, when executed on a computer, cause the computer to perform any one of the multi-target detection-based UAV countermeasure methods described in the first aspect. Simultaneously, a computer program product is also provided, which, when executed on a computer, performs any one of the multi-target detection-based UAV countermeasure methods described in the first aspect.

[0018] Beneficial Effects: This invention achieves efficient and accurate multi-target UAV detection and signal jamming countermeasures by coordinating the detection of multiple UAVs, obtaining radar detection data, radio frequency monitoring data, spectral detection data, and acoustic detection data for each target UAV. Based on the radar detection data, initial screening of UAV types is performed; based on the radio frequency monitoring and acoustic detection data, pre-selection of UAV types is conducted; and based on the spectral detection data, final matching is performed to determine the target UAV type. Then, appropriate UAV countermeasure strategies are tailored for signal jamming. This invention integrates multi-dimensional coordinated detection data and performs multi-level information matching to accurately distinguish different types of UAVs and implement targeted optimized countermeasure strategies, thereby improving the efficiency of UAV countermeasures, preventing unauthorized UAV flights and intrusions, and effectively ensuring low-altitude safety. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a flowchart illustrating the method in Embodiment 1 of the present invention; Figure 2 This is a schematic diagram of the device in Embodiment 2 of the present invention; Figure 3 This is a schematic diagram of the device in Embodiment 3 of the present invention. Detailed Implementation

[0021] It should be noted that the descriptions of these embodiments are intended to aid in understanding the invention and do not constitute a limitation thereof. The specific structural and functional details disclosed herein are merely for describing exemplary embodiments of the invention. However, the invention may be embodied in many alternative forms and should not be construed as being limited to the embodiments described herein.

[0022] It should be understood that, unless otherwise explicitly specified and limited, the corresponding terms should be interpreted broadly. For example, "connection" can be a fixed connection, a detachable connection, or an integral connection; it can be a direct connection or an indirect connection through an intermediate medium; it can be a connection within two components. Those skilled in the art can understand the specific meaning of the above terms in the embodiments according to the specific circumstances.

[0023] Specific details are provided in the following description to provide a complete understanding of the exemplary embodiments. However, those skilled in the art will understand that the exemplary embodiments can be implemented without these specific details. For example, apparatus may be shown in block diagrams to avoid obscuring the examples with unnecessary details. In other embodiments, well-known processes, structures, and techniques may be omitted with non-essential details to avoid obscuring the embodiments.

[0024] Example 1: This embodiment provides a UAV countermeasure method based on multi-target detection, which can be applied to a corresponding UAV countermeasure system. This UAV countermeasure system includes a radar detection subsystem, a radio frequency monitoring subsystem, a spectral detection subsystem, an acoustic detection subsystem, a signal jamming subsystem, and a controller. For example... Figure 1 As shown, the method includes the following steps: S1. Obtain the radar detection results of multiple targets UAVs, which include the azimuth parameters, range parameters, velocity parameters and radar cross section parameters of each target UAV.

[0025] In practice, the radar detection subsystem can perform real-time radar scanning of the no-fly zone to detect whether any UAVs are flying within the zone. When a UAV is detected, the radar detection results of each target UAV can be aggregated into a multi-target UAV radar detection result, which is then sent to the controller for further processing. The multi-target UAV radar detection result includes the azimuth, range, velocity, and radar cross section (RCS) parameters of each target UAV. RCS is a core indicator in radar stealth technology, quantifying the target's ability to scatter radar waves through a power ratio. Its value is defined as 4π times the ratio of the reflected power per unit solid angle in the incident direction to the target intercept power density, expressed in square meters or decibels per square meter.

[0026] S2. Determine the corresponding linkage detection range based on the azimuth and distance parameters of the target UAV, and perform radio frequency monitoring, spectral detection and acoustic detection on the corresponding linkage detection range to obtain the radio frequency monitoring data, spectral detection data and acoustic detection data of the target UAV.

[0027] In practice, after receiving the radar detection results of each target UAV, the controller determines the reference point of the target UAV in a set spatial coordinate system based on its azimuth and range parameters. The line connecting the reference point to the origin of the set spatial coordinate system is used as the reference line, and a cone-shaped spatial region of a set size around the reference line is defined as the linkage detection range. Then, the radio frequency monitoring subsystem, the spectral detection subsystem, and the acoustic detection subsystem are controlled respectively to perform radio frequency monitoring, spectral detection, and acoustic detection on the linkage detection range of each target UAV, obtaining the radio frequency monitoring data, spectral detection data, and acoustic detection data of the corresponding target UAV within each linkage detection range. The radio frequency monitoring data includes radio frequency fingerprint features (i.e., electromagnetic spectrum fingerprints, such as the carrier frequency, bandwidth, modulation method, and typical power of the target UAV's transmission / control signals, which can be obtained by radio frequency scanning and signal modulation analysis by the radio frequency monitoring subsystem). The spectral detection data may include shape contour features, texture features, and infrared features (which can be obtained by the spectral detection subsystem performing visible light and long-wave infrared imaging on the target UAV and extracting corresponding image features from the visible light and infrared images). The acoustic detection data may include acoustic signature features (which can be obtained by the acoustic detection subsystem performing sound array acquisition on the target UAV and processing the acquired sound signals for spectral features).

[0028] S3. Extract radio frequency fingerprint features from the radio frequency monitoring data of the target UAV, extract shape contour features, texture features and infrared features from the spectral detection data of the target UAV, and extract acoustic fingerprint features from the acoustic detection data of the target UAV.

[0029] In practice, the controller can extract radio frequency fingerprint features from the radio frequency monitoring data of the target UAV, extract shape contour features, texture features and infrared features from the spectral detection data of the target UAV, and extract voiceprint features from the acoustic detection data of the target UAV, so as to perform subsequent UAV type identification and matching based on radio frequency fingerprint features, voiceprint features, shape contour features, texture features and infrared features.

[0030] S4. Select a preliminary set of target UAV models from the model library based on the target UAV's speed parameters and radar cross-section parameters. The preliminary set of models includes several preliminary models.

[0031] In practice, during the first-level UAV type matching process, the controller can filter out a preliminary set of target UAVs from the model library based on the target UAV's speed parameters and radar cross-section parameters. The model library contains several UAV models, and each UAV model is associated with a corresponding set of attribute features. These attribute feature sets include speed parameter ranges, radar cross-section parameter ranges, template RF fingerprint features, template acoustic signature features, template outline features, template texture features, and template infrared features.

[0032] When selecting the initial screening set of target UAVs from the model library, the controller first compares the speed parameters and radar cross section parameters of the target UAV with the speed parameter ranges and radar cross section parameter ranges associated with each UAV model in the model library. If the speed parameters of the target UAV are within the speed parameter range of the corresponding UAV model, and the radar cross section parameters of the target UAV are within the radar cross section parameter range of the corresponding UAV model, then the corresponding UAV model is selected as the initial screening set of target UAVs. After summarizing the initial screening sets of target UAVs selected from the model library, the initial screening set of target UAVs is obtained.

[0033] S5. Based on the radio frequency fingerprint and voiceprint characteristics of the target UAV, a pre-selection set of target UAVs is selected from the initial screening set of UAVs. The pre-selection set of UAVs includes several pre-selection models.

[0034] In specific implementation, during the second-level UAV type matching process, the controller substitutes the target UAV's radio frequency fingerprint and voiceprint features, as well as the template radio frequency fingerprint and template voiceprint features of the corresponding initial screening models in the initial screening model set, into a preset correlation formula to calculate the correlation coefficient between the target UAV and the corresponding initial screening model. The correlation formula is as follows:

[0035] Where R represents the correlation coefficient, i represents the component index of the RF fingerprint feature or template RF fingerprint feature, m is the total number of components of the RF fingerprint feature or template RF fingerprint feature, and X i The i-th component, Y, characterizes the features of an RF fingerprint. i The i-th component characterizing the template RF fingerprint feature, j being the component index characterizing the acoustic signature feature or template acoustic signature feature, n being the total number of acoustic signature feature or template acoustic signature feature components, and x being the component index characterizing the template RF fingerprint feature. j The j-th component representing the voiceprint feature, y j The j-th component characterizing the template voiceprint features, where α is the first weighting coefficient and β is the second weighting coefficient.

[0036] Then, the models in the initial screening set whose correlation coefficient with the target drone exceeds a set threshold are taken as the pre-selected models of the target drone, and the pre-selected models of the target drone are summarized to obtain the pre-selected model set of the target drone.

[0037] S6. Based on the shape contour features, texture features and infrared features of the target UAV, determine the optical feature similarity between the target UAV and each of the pre-selected models in the pre-selected model set, and take the pre-selected models whose optical feature similarity with the target UAV meets the set conditions as the target UAV's target model.

[0038] In practice, during the third-level UAV type matching process, the controller first fuses the shape contour features, texture features, and infrared features of the target UAV to obtain the optical feature vector of the target UAV. Then, it fuses the template shape contour features, template texture features, and template infrared features of each pre-selected UAV in the pre-selected UAV set to obtain the template optical feature vector of each pre-selected UAV.

[0039] Then, the optical feature vector of the target UAV and the template optical feature vector of the corresponding pre-selected model in the pre-selected model set are substituted into a preset optical feature similarity formula for calculation to obtain the optical feature similarity between the target UAV and the corresponding pre-selected model. The optical feature similarity formula is as follows:

[0040] Where S represents the optical feature similarity, k represents the component index of the optical feature vector or template optical feature vector, W represents the total number of components of the optical feature vector or template optical feature vector, and z k p represents the k-th component of the optical eigenvector. k The k-th component of the template optical eigenvector is represented by ω, which is a set constant to prevent zeroing.

[0041] Then, the pre-selected model with the highest optical feature similarity to the target drone that exceeds the set similarity threshold is selected as the target drone model.

[0042] S7. Match the corresponding countermeasure strategy according to the target UAV model, and execute the countermeasure strategy to interfere with the target UAV's signal.

[0043] In practice, after determining the target drone model, the controller can match the corresponding countermeasure strategy according to the target drone model. The countermeasure strategy includes signal jamming method, signal jamming frequency band, and signal jamming intensity. The signal jamming method includes communication jamming (communication jamming aims to block the communication link between the drone and the remote controller or ground control station, so that the drone cannot receive control commands), navigation jamming (navigation jamming mainly targets the satellite navigation system that the drone relies on, such as GPS, Beidou, etc., by emitting jamming signals, so that the drone cannot obtain accurate position information, thereby losing control and deviating from the predetermined route or executing incorrect flight commands) or electromagnetic shielding (electromagnetic shielding forms an electromagnetic shielding space in a specific area by emitting strong electromagnetic signals, so that the drone's communication signals, navigation signals, etc. cannot be transmitted normally, thereby achieving the purpose of countermeasure). When matching a corresponding countermeasure strategy based on the target UAV's model, the controller first determines the model number corresponding to the target UAV's model; then, it substitutes the model number into a preset countermeasure strategy table for matching, determining the signal interference method, signal interference frequency band, and signal interference intensity corresponding to the model number. The countermeasure strategy table contains several model numbers and the signal interference method, signal interference frequency band, and signal interference intensity associated with each model number; then, it uses the signal interference method, signal interference frequency band, and signal interference intensity matched by the model number to form the corresponding countermeasure strategy.

[0044] After adapting to the corresponding countermeasure strategy for the target drone, the controller can control the signal jamming subsystem to perform tracking signal jamming on the target drone, thereby blocking the target drone's communication or navigation links, causing it to lose control signals or be unable to accurately obtain location information, thus achieving the countermeasure purpose.

[0045] This method, by integrating multi-dimensional joint detection data and performing multi-level information matching, can accurately identify different types of drones and implement targeted and optimized countermeasures to improve the efficiency of drone countermeasures, eliminate drone black flight and intrusion incidents, and effectively ensure low-altitude safety.

[0046] Example 2: This embodiment provides a drone countermeasure device based on multi-target detection, such as... Figure 2As shown, it includes a radar detection unit, a linkage detection unit, a feature extraction unit, an aircraft type initial screening unit, an aircraft type pre-selection unit, an aircraft type determination unit, and a target countermeasure unit, wherein: The radar detection unit is used to acquire radar detection results of multiple targets UAVs, which include the azimuth parameters, range parameters, velocity parameters and radar cross section parameters of each target UAV. The linkage detection unit is used to determine the corresponding linkage detection range based on the azimuth and distance parameters of the target UAV, and to perform radio frequency monitoring, spectral detection and acoustic detection on the corresponding linkage detection range to obtain the radio frequency monitoring data, spectral detection data and acoustic detection data of the target UAV. The feature extraction unit is used to extract radio frequency fingerprint features from the radio frequency monitoring data of the target UAV, extract shape contour features, texture features and infrared features from the spectral detection data of the target UAV, and extract acoustic fingerprint features from the acoustic detection data of the target UAV. The model screening unit is used to select a preliminary set of target UAV models from the model library based on the speed parameters and radar cross-section parameters of the target UAV. The preliminary set of models includes several preliminary models. The model pre-selection unit is used to select a pre-selection set of target drones from the initial model set based on the radio frequency fingerprint and voiceprint features of the target drones. The pre-selection set of drones includes several pre-selection models. The model determination unit is used to determine the similarity of the optical features of the target UAV with each of the pre-selected models in the pre-selection model set based on the shape contour features, texture features and infrared features of the target UAV, and to take the pre-selected models whose optical feature similarity with the target UAV meets the set conditions as the target UAV's target model; The target countermeasure unit is used to match the corresponding countermeasure strategy according to the target UAV model and execute the countermeasure strategy to interfere with the signal of the target UAV.

[0047] Example 3: This embodiment provides a drone countermeasure device based on multi-target detection, such as... Figure 3 As shown, at the hardware level, it includes: The data interface is used to establish data communication between the processor and external data terminals; Memory, used to store instructions; The processor is used to read the instructions stored in the memory and execute the UAV countermeasure method based on multi-target detection in Embodiment 1 according to the instructions.

[0048] Optionally, the device also includes an internal bus, through which the processor, memory, and data interface can be interconnected. This internal bus can be a PCIe (Peripheral Component Interconnect Eexpress) bus, which can be divided into an address bus, data bus, control bus, etc. The memory can include, but is not limited to, Random Access Memory (RAM), Read Only Memory (ROM), Flash Memory, First Input First Output (FIFO), and / or First In Last Out (FILO). The processor can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0049] Example 4: This embodiment provides a computer-readable storage medium storing instructions. When these instructions are executed on a computer, the computer performs the UAV countermeasure method based on multi-target detection as described in Embodiment 1. The computer-readable storage medium refers to a data storage medium, which may include, but is not limited to, floppy disks, optical disks, hard disks, flash memory, USB flash drives, and / or Memory Sticks. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.

[0050] This embodiment also provides a computer program product that, when run on a computer, executes the UAV countermeasure method based on multi-target detection in Embodiment 1. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device.

[0051] Finally, it should be noted that the above description is merely a preferred embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for countering unmanned aerial vehicles (UAVs) based on multi-target detection, characterized in that, include: The radar detection results of multiple targets unmanned aerial vehicles (UAVs) are obtained, including the azimuth parameters, range parameters, velocity parameters and radar cross-section parameters of each target UAV. The corresponding linkage detection range is determined based on the azimuth and distance parameters of the target UAV, and radio frequency monitoring, spectral detection and acoustic detection are performed on the corresponding linkage detection range to obtain the radio frequency monitoring data, spectral detection data and acoustic detection data of the target UAV. Radio frequency fingerprint features are extracted from the radio frequency monitoring data of the target UAV; shape contour features, texture features and infrared features are extracted from the spectral detection data of the target UAV; and acoustic fingerprint features are extracted from the acoustic detection data of the target UAV. Based on the speed parameters and radar cross-section parameters of the target UAV, a preliminary set of target UAV models is selected from the model library. The preliminary set of target UAV models includes several preliminary models. Based on the radio frequency fingerprint and voiceprint characteristics of the target drone, a pre-selection set of target drones is selected from the initial screening set. The pre-selection set includes several pre-selected models. Based on the shape contour features, texture features and infrared features of the target UAV, the optical feature similarity between the target UAV and each of the pre-selected models in the pre-selection model set is determined, and the pre-selected models whose optical feature similarity with the target UAV meets the set conditions are taken as the target UAV's target models. Match the appropriate countermeasure strategy to the target drone model and execute the countermeasure strategy to interfere with the target drone's signal.

2. The UAV countermeasure method based on multi-target detection according to claim 1, characterized in that, The step of determining the corresponding coordinated detection range based on the azimuth and distance parameters of the target UAV includes: Determine the reference point of the target UAV in the set spatial coordinate system based on the azimuth and distance parameters of the target UAV; The line connecting the reference point and the origin of the set spatial coordinate system is used as the reference line, and a cone-shaped spatial region of a set size is defined around the reference line as the linkage detection range.

3. The UAV countermeasure method based on multi-target detection according to claim 1, characterized in that, The model library contains several UAV models, and each UAV model is associated with a corresponding set of attribute features. The set of attribute features includes speed parameter range, radar cross section parameter range, template radio frequency fingerprint features, template acoustic features, template shape contour features, template texture features, and template infrared features.

4. The UAV countermeasure method based on multi-target detection according to claim 3, characterized in that, The initial screening set of target UAVs, selected from the model database based on the target UAV's speed parameters and radar cross-section parameters, includes: The speed parameters and radar cross section parameters of the target UAV are compared with the speed parameter ranges and radar cross section parameter ranges associated with each UAV model in the model database; If the speed parameters of the target drone are within the speed parameter range of the corresponding drone model, and the radar cross section parameters of the target drone are within the radar cross section parameter range of the corresponding drone model, then the corresponding drone model will be used as the initial screening model of the target drone. The initial screening models of the target drones selected from the model library are summarized to obtain the initial screening model set of the target drones.

5. The UAV countermeasure method based on multi-target detection according to claim 3, characterized in that, The process of selecting a pre-selection set of target drones from the initial screening set based on the radio frequency fingerprint and voiceprint characteristics of the target drones includes: The radio frequency fingerprint and acoustic signature features of the target UAV, along with the template radio frequency fingerprint and template acoustic signature features of the corresponding primary screening model in the primary screening model set, are substituted into a preset correlation formula to calculate the correlation coefficient between the target UAV and the corresponding primary screening model. The correlation formula is as follows: Where R represents the correlation coefficient, i represents the component index of the RF fingerprint feature or template RF fingerprint feature, m is the total number of components of the RF fingerprint feature or template RF fingerprint feature, and X i The i-th component, Y, characterizes the features of an RF fingerprint. i The i-th component characterizing the template RF fingerprint feature, j being the component index characterizing the acoustic signature feature or template acoustic signature feature, n being the total number of acoustic signature feature or template acoustic signature feature components, and x being the component index characterizing the template RF fingerprint feature. j The j-th component representing the voiceprint feature, y j The j-th component characterizing the template voiceprint features, where α is the first weighting coefficient and β is the second weighting coefficient; The preliminary screening models whose correlation coefficient with the target drone exceeds a set threshold are selected as the pre-selected models of the target drone. The pre-selected models of the target drone are then aggregated to obtain the pre-selected model set of the target drone.

6. The UAV countermeasure method based on multi-target detection according to claim 3, characterized in that, The process of determining the optical feature similarity between the target UAV and each pre-selected UAV in the pre-selection model set based on the target UAV's shape contour features, texture features, and infrared features, and then selecting the pre-selected UAVs whose optical feature similarity with the target UAV meets the set conditions as the target UAV's target model, includes: The shape contour features, texture features and infrared features of the target UAV are fused to obtain the optical feature vector of the target UAV. The shape contour features, texture features and infrared features of the templates of each pre-selected UAV in the pre-selected UAV set are fused to obtain the template optical feature vector of each pre-selected UAV. The optical feature vector of the target UAV and the template optical feature vector of the corresponding pre-selected UAV in the pre-selected model set are substituted into a preset optical feature similarity formula for calculation to obtain the optical feature similarity between the target UAV and the corresponding pre-selected model. The optical feature similarity formula is as follows: Where S represents the optical feature similarity, k represents the component index of the optical feature vector or template optical feature vector, W represents the total number of components of the optical feature vector or template optical feature vector, and z k p represents the k-th component of the optical eigenvector. k The k-th component of the template optical eigenvector is represented by ω, which is a set constant to prevent it from being reduced to zero. The pre-selected model with the highest optical feature similarity to the target drone exceeding the set similarity threshold will be used as the target drone model.

7. The UAV countermeasure method based on multi-target detection according to claim 1, characterized in that, The countermeasure strategy includes signal jamming methods, signal jamming frequency bands, and signal jamming intensity. The signal jamming methods include communication jamming, navigation jamming, or electromagnetic shielding. Matching the appropriate countermeasure strategy according to the target UAV model includes: Determine the model number corresponding to the target drone model; The model number is substituted into a preset countermeasure strategy table for matching to determine the signal interference method, signal interference frequency band and signal interference intensity corresponding to the model number. The countermeasure strategy table contains several model numbers and the signal interference method, signal interference frequency band and signal interference intensity associated with each model number. The corresponding countermeasures are formed by matching the signal interference method, signal interference frequency band, and signal interference intensity with the model number.

8. A UAV countermeasure device based on multi-target detection, characterized in that, It includes a radar detection unit, a coordinated detection unit, a feature extraction unit, an aircraft type initial screening unit, an aircraft type pre-selection unit, an aircraft type determination unit, and a target countermeasure unit, among which: The radar detection unit is used to acquire radar detection results of multiple targets UAVs, which include the azimuth parameters, range parameters, velocity parameters and radar cross section parameters of each target UAV. The linkage detection unit is used to determine the corresponding linkage detection range based on the azimuth and distance parameters of the target UAV, and to perform radio frequency monitoring, spectral detection and acoustic detection on the corresponding linkage detection range to obtain the radio frequency monitoring data, spectral detection data and acoustic detection data of the target UAV. The feature extraction unit is used to extract radio frequency fingerprint features from the radio frequency monitoring data of the target UAV, extract shape contour features, texture features and infrared features from the spectral detection data of the target UAV, and extract acoustic fingerprint features from the acoustic detection data of the target UAV. The model screening unit is used to select a preliminary set of target UAV models from the model library based on the speed parameters and radar cross-section parameters of the target UAV. The preliminary set of models includes several preliminary models. The model pre-selection unit is used to select a pre-selection set of target drones from the initial model set based on the radio frequency fingerprint and voiceprint features of the target drones. The pre-selection set of drones includes several pre-selection models. The model determination unit is used to determine the similarity of the optical features of the target UAV with each of the pre-selected models in the pre-selection model set based on the shape contour features, texture features and infrared features of the target UAV, and to take the pre-selected models whose optical feature similarity with the target UAV meets the set conditions as the target UAV's target model; The target countermeasure unit is used to match the corresponding countermeasure strategy according to the target UAV model and execute the countermeasure strategy to interfere with the signal of the target UAV.

9. A UAV countermeasure device based on multi-target detection, characterized in that, include: Memory, used to store instructions; A processor is configured to read instructions stored in the memory and execute the UAV countermeasure method based on multi-target detection as described in any one of claims 1-7 according to the instructions.

10. A computer program product, characterized in that, When the computer program product is run on a computer, it executes the UAV countermeasure method based on multi-target detection as described in any one of claims 1-7.

Images