Unmanned aerial vehicle countering method and system based on multi-source heterogeneous data fusion

Abstract

The invention provides an unmanned aerial vehicle countering method and system based on multi-source heterogeneous data fusion, and the method comprises the steps: obtaining monitoring data and photoelectric video data transmitted by a multi-source heterogeneous unmanned aerial vehicle detection sensor, and carrying out the preliminary fusion of the monitoring data, so as to obtain first fusion data; determining an initial weight of the unmanned aerial vehicle detection sensor, and performing attenuation processing on the initial weight to obtain an attenuation weight; performing final fusion on the first fusion data and the photoelectric video data based on the attenuation weight to obtain second fusion data; constructing a state space, and mapping the second fusion data into the state space to obtain multi-dimensional data; based on multi-dimensional data, a distributed countering device control protocol is linked with a plurality of unmanned aerial vehicle countering devices to carry out unmanned aerial vehicle countering, and the problems that a traditional countering system is slow in response and poor in environmental adaptability are solved.

Description

Technical Field

[0001] This invention belongs to the technical field of drone countermeasures, specifically relating to a drone countermeasures method and system based on multi-source heterogeneous data fusion. Background Technology

[0002] Existing drone detection and countermeasure technologies mainly focus on the following aspects: Detection technologies typically include radar detection, radio spectrum detection, photoelectric identification detection, and acoustic detection. Radar detection obtains information such as the distance, altitude, and speed of a drone by emitting electromagnetic waves and receiving reflected signals. Its advantage lies in its suitability for long-range detection, but it is susceptible to ground clutter interference with "low-altitude, slow-speed, and small" targets (low-altitude, slow-speed, and small drones), requiring specialized algorithm optimization. It is commonly used in scenarios such as airports and border areas and needs to be paired with photoelectric equipment to confirm the target. Radio spectrum detection involves intercepting communication signals between the drone and its remote controller (such as the 2.4GHz and 5.8GHz bands), and then identifying the drone model through spectrum analysis and protocol decryption. It can be used for passive detection, but it is ineffective against drones with encrypted signals or flying silently. It needs to be combined with AI algorithms (such as artificial neural networks) to improve the identification efficiency and build a blacklist and whitelist database. Photoelectric identification detection is further divided into visible light and infrared. Visible light captures drone images during the day using high-definition cameras, and combines image segmentation algorithms (such as neural networks) to identify targets. This method is low-cost but affected by weather. Infrared light utilizes the thermal radiation from the drone's motors and batteries to achieve nighttime monitoring, but it is easily interfered with by sunlight or heat sources. It is often used as an auxiliary means of radar detection, providing visual tracking and evidence collection. Acoustic detection collects drone propeller noise and identifies targets by matching it with a voiceprint database. It is highly covert and low-cost, but it is easily affected by environmental noise and requires continuous updates to the voiceprint database.

[0003] Countermeasures against drones mainly include interference blocking, hard-kill, physical capture, and signal hijacking / takeover. Interference blocking is the most common and widely used. Electromagnetic interference relies on emitting interference signals in the same frequency band to cut off communication between the drone and its control unit, forcing it to land or return to base; navigation signal deception uses simulated false GPS signals to induce the drone to deviate from its flight path. Hard-kill drones use high-energy lasers to burn critical parts of the drone at high temperatures, damaging its components. Physical capture methods involve launching a capture net to entangle the drone's rotor blades. These methods are suitable for close-range interception, but their effectiveness against high-speed or highly maneuverable targets is limited. Signal hijacking and takeover involves cracking the drone's communication protocol and sending stronger control signals to seize control.

[0004] However, existing drone detection and countermeasure technologies still have the following shortcomings: 1. Limitations of single-source detection: Traditional radar / optoelectronic equipment has detection blind spots, and radio monitoring is susceptible to electromagnetic interference; 2. Low data fusion efficiency: Spatiotemporal registration of heterogeneous data is difficult, and feature-level fusion algorithms are hard to meet real-time requirements; 3. Limited countermeasures: Electromagnetic suppression and navigation deception lack coordination and are easily countered by anti-jamming technologies; 4. Decision lag: The response time of existing systems generally exceeds 500ms, making it difficult to cope with high-speed flying drones. Summary of the Invention

[0005] To address the aforementioned technical problems, this invention provides a method and system for countering unmanned aerial vehicles (UAVs) based on multi-source heterogeneous data fusion, which solves the technical problems in the prior art.

[0006] On the one hand, the present invention provides the following technical solution: a method for countering unmanned aerial vehicles (UAVs) based on multi-source heterogeneous data fusion, comprising: Acquire monitoring data and photoelectric video data transmitted from multi-source heterogeneous UAV detection sensors, and perform preliminary fusion of the monitoring data to obtain first fused data; Determine the initial weights of the UAV detection sensors, and then perform attenuation processing on the initial weights to obtain attenuated weights; Based on the attenuation weight, the first fused data and the photoelectric video data are finally fused to obtain the second fused data; Construct a state space and map the second fused data into the state space to obtain multidimensional data; Based on the aforementioned multidimensional data and distributed countermeasure device control protocol, several UAV countermeasure devices are linked to carry out UAV countermeasures.

[0007] Compared to existing technologies, the advantages of this invention are as follows: Firstly, this invention fuses multi-source heterogeneous monitoring data, then integrates it with optoelectronic and video data. Based on this, it introduces attenuation weights and adjusts the weights of multi-source data in conjunction with real-time electromagnetic noise, solving the problem of misjudgment in complex environments. This invention fuses data into a unified standard target information format. For the target and its surrounding environment, it uses a reinforcement learning-driven dynamic decision engine to construct a 12-dimensional state space. A three-dimensional PEM matrix quantifies the weight relationships of threat level, countermeasure costs, and environmental constraints. Finally, a distributed countermeasure device control protocol supports the coordinated countermeasure of multiple countermeasure devices to ultimately dispose of the drone. Through a closed-loop design of "integrated platform - dynamic decision-making - environment adaptation," it solves the problems of slow response and poor environmental adaptability in traditional countermeasure systems.

[0008] Preferably, the step of initially fusing the monitoring data to obtain the first fused data includes: The monitoring data is subjected to feature standardization processing to obtain monitoring data; The monitoring data is combined into feature vectors to obtain a feature matrix. : ; In the formula, For the first Feature vectors of a drone detection sensor; Calculate the covariance matrix of the characteristic matrix. : ; In the formula, Indicates the sample degrees of freedom; The covariance matrix is ​​decomposed into eigenvalues ​​to obtain the eigenvector matrix. With eigenvalue matrix : ; Selecting the first from the eigenvalue matrix The largest feature is identified, and the corresponding eigenvector in the eigenvector matrix is ​​selected as the principal component to obtain the feature space. : ; In the formula, For the first The feature vectors corresponding to the principal components; Based on the feature space Determine the first fused data : .

[0009] Preferably, in the step of attenuating the initial weights to obtain attenuated weights, the attenuated weights are: : ; In the formula, For the first The initial weights of the drone detection sensors The attenuation coefficient is... This represents the current noise interference index.

[0010] Preferably, the step of finally fusing the first fused data and the photoelectric video data based on the attenuation weight to obtain the second fused data includes: Feature extraction is performed on the photoelectric video data to obtain video features; The video features are aligned with the first fused data in time and space to obtain aligned video features and aligned fused data; The aligned video features are combined into a video feature matrix, and the aligned fusion data is combined into a fusion feature matrix; The video feature matrix and the fused feature matrix are standardized respectively to obtain the video standard matrix and the fused standard matrix; Calculate the sample covariance matrix between the video standard matrix and the fusion standard matrix, and perform canonical eigenvalue decomposition on the sample covariance matrix to obtain several canonical correlation coefficients and corresponding canonical variables; Before selection The canonical variable corresponding to the largest canonical correlation coefficient is taken as the variable to be fused. Based on the decay weight, several variables to be fused are fused to obtain the second fused data.

[0011] Preferably, in the step of constructing the state space and mapping the second fused data into the state space to obtain multidimensional data, the state space is a 12-dimensional state space, and the multidimensional data includes radar cross-section, flight altitude, flight speed, signal modulation type, payload type, no-fly zone distance, population density index, electromagnetic interference intensity, meteorological conditions, remaining energy of jammer, physical interceptor inventory, and availability of cooperative equipment.

[0012] Preferably, the step of using the multi-dimensional data and distributed countermeasure device control protocol to coordinate several UAV countermeasure devices for UAV countermeasure includes: Construct a PEM matrix, and calculate the PEM score of the multidimensional data in three dimensions: threat level, countermeasure cost, and environmental constraints. Select the countermeasure with the highest PEM score from the preset solution library as the final countermeasure; The resource scheduling based on game theory selects the optimal equipment combination corresponding to the final countermeasure scheme, and uses a precise time protocol and the optimal equipment combination to counter the UAV target.

[0013] Secondly, the present invention provides the following technical solution: a UAV countermeasure system based on multi-source heterogeneous data fusion, the system comprising: The first fusion module is used to acquire monitoring data and photoelectric video data transmitted from multi-source heterogeneous UAV detection sensors, and to perform preliminary fusion of the monitoring data to obtain the first fused data. The attenuation module is used to determine the initial weights of the UAV detection sensors and perform attenuation processing on the initial weights to obtain attenuation weights. The second fusion module is used to perform a final fusion of the first fused data and the photoelectric video data based on the attenuation weight to obtain the second fused data; A mapping module is used to construct a state space and map the second fused data onto the state space to obtain multidimensional data; The countermeasure module is used to coordinate several UAV countermeasure devices to counter UAVs based on the multidimensional data and the distributed countermeasure device control protocol.

[0014] Preferably, the state space is a 12-dimensional state space, and the multi-dimensional data includes radar cross-section, flight altitude, flight speed, signal modulation type, payload type, no-fly zone distance, population density index, electromagnetic interference intensity, meteorological conditions, remaining energy of jammer, physical interceptor inventory, and availability of cooperative equipment.

[0015] Thirdly, the present invention provides the following technical solution: a computer, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above-described method for countering unmanned aerial vehicles based on multi-source heterogeneous data fusion.

[0016] Fourthly, the present invention provides the following technical solution: a storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the above-described method for countering unmanned aerial vehicles based on multi-source heterogeneous data fusion. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention, 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.

[0018] Figure 1 A flowchart of a UAV countermeasure method based on multi-source heterogeneous data fusion provided in Embodiment 1 of the present invention; Figure 2 This is a structural block diagram of the UAV countermeasure system based on multi-source heterogeneous data fusion provided in Embodiment 2 of the present invention; Figure 3 This is a schematic diagram of the hardware structure of a computer provided for another embodiment of the present invention.

[0019] The embodiments of the present invention will be further described below with reference to the accompanying drawings. Detailed Implementation

[0020] Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain embodiments of the present invention, and should not be construed as limiting the present invention.

[0021] Example 1 In Embodiment 1 of the present invention, as Figure 1 As shown, a method for countering unmanned aerial vehicles (UAVs) based on multi-source heterogeneous data fusion includes: S1. Acquire monitoring data and photoelectric video data transmitted from multi-source heterogeneous UAV detection sensors, and perform preliminary fusion of the monitoring data to obtain first fused data; The drone detection sensors here include four types: radar, spectrum, photoelectric, and cloud whistle. The data returned by the photoelectric devices is video data, while the data returned by the other three types of devices is text data. The data has multimodal characteristics.

[0022] Step S1 includes: S11. Perform feature standardization processing on the monitoring data to obtain monitoring data; Specifically, the feature standardization process here uses the Z-score standardization method.

[0023] S12. Combine the monitoring data into feature vectors to obtain a feature matrix. : ; In the formula, For the first The feature vector of a drone's detection sensor.

[0024] S13. Calculate the covariance matrix of the characteristic matrix. : ; In the formula, Indicates the sample degrees of freedom.

[0025] S14. Perform eigenvalue decomposition on the covariance matrix to obtain the eigenvector matrix. With eigenvalue matrix : .

[0026] S15. Select the first from the eigenvalue matrix. The largest feature is identified, and the corresponding eigenvector in the eigenvector matrix is ​​selected as the principal component to obtain the feature space. : ; In the formula, For the first The eigenvectors corresponding to each principal component.

[0027] S16, Based on the feature space Determine the first fused data : .

[0028] Specifically, through preliminary fusion, information such as the longitude, latitude, and model of the drone contained in the detection information can be processed accordingly to reduce redundant information.

[0029] S2. Determine the initial weights of the UAV detection sensors, and perform attenuation processing on the initial weights to obtain attenuated weights; Specifically, the attenuation weight is : ; In the formula, For the first The initial weights of the drone detection sensors The attenuation coefficient is... This represents the current noise interference index. The attenuation weights obtained here can be applied to the fusion process, both in the initial fusion and the final fusion process. The attenuation weights obtained above are dynamic weights, which can replace the traditional fixed weights. In the actual fusion process, if the confidence difference exceeds the threshold (e.g., the deviation between the radar and the target position in the spectrum > 50m), the corresponding data will be reweighted or a sensor self-test process will be performed. By detecting drones obstructed by tall buildings in the city, it was found that noise interference can reflect between buildings, leading to an increase in radar false alarm rate. Meanwhile, Wi-Fi signals (2.4GHz) used in daily life and work can interfere with spectrum monitoring. In this case, introducing attenuation weights can reduce false alarms. For example, when the current interference index is detected to be 0.8, it is considered high interference. Therefore, the weight of spectrum data can be automatically reduced and the radar weight can be increased. During the actual fusion process, the weight of radar micro-motion feature evidence is increased, suppressing spectrum false alarms. This attenuation weight can achieve dynamic self-adaptation, and the weight is adjusted in real time according to the environmental noise, avoiding the overfitting problem of traditional fixed weight schemes.

[0030] S3. Based on the attenuation weight, the first fused data and the photoelectric video data are finally fused to obtain the second fused data; Step S3 includes: S31. Extract features from the photoelectric video data to obtain video features; Specifically, before fusing optoelectronic video data, feature extraction is required to obtain drone target features. These drone target features can be used for target tracking, detection, etc. By obtaining information such as speed, altitude, and orientation from the feature information and converting it into text data, video features can be obtained. The feature extraction algorithm can also use edge detection algorithms (such as Canny) or gradient filtering methods to extract texture information from video frames.

[0031] S32. Align the video features with the first fused data in time and space to obtain aligned video features and aligned fused data; Specifically, time and space alignment can be achieved through timestamps or spatial registration methods.

[0032] S33. Combine the aligned video features into a video feature matrix, and combine the aligned fusion data into a fusion feature matrix.

[0033] S34. Standardize the video feature matrix and the fusion feature matrix respectively to obtain the video standard matrix and the fusion standard matrix; Specifically, the standardization process here can be performed using the same methods as the steps described above.

[0034] S35. Calculate the sample covariance matrix between the video standard matrix and the fusion standard matrix, and perform canonical eigenvalue decomposition on the sample covariance matrix to obtain several canonical correlation coefficients and corresponding canonical variables.

[0035] S36, Before Selection The canonical variable corresponding to the largest canonical correlation coefficient is taken as the variable to be fused. Based on the decay weight, several variables to be fused are fused to obtain the second fused data.

[0036] S4. Construct a state space and map the second fused data into the state space to obtain multidimensional data; The state space is a 12-dimensional state space, and the multi-dimensional data includes radar cross-section, flight altitude, flight speed, signal modulation type, payload type, no-fly zone distance, population density index, electromagnetic interference intensity, meteorological conditions, remaining energy of jammer, physical interceptor inventory, and availability of cooperative equipment.

[0037] Specifically, for actual multidimensional data, it can be represented as shown in the table below:

[0038] After obtaining the multidimensional data, spatial normalization is required to normalize the non-standardized parameters.

[0039] S5. Based on the multi-dimensional data and the distributed countermeasure device control protocol, several UAV countermeasure devices are linked to perform UAV countermeasures. Step S5 includes: S51. Construct a PEM matrix, and calculate the PEM score of the multidimensional data in three dimensions: threat level, countermeasure cost, and environmental constraints. Specifically, when specifying actual countermeasures, the PEM matrix can calculate the optimal countermeasure strategy weights through three dimensions: Threat, Cost, and Constraint, as shown in the table below:

[0040] The actual decision-making process is as follows: Multiple data points are updated in real time. Based on the current threat level, countermeasure cost, and environmental constraints, the scores of each option are calculated. The option with the highest score is then selected as the final countermeasure. It should be noted that if the score is suppressed, the option with low collateral damage is prioritized. Assuming that in the actual countermeasure process, the threat level T=8 (infrared identification is of a metal object), the countermeasure cost C=0.4 (requiring the use of 2 interceptors), and the environmental constraint E=0.7 (no-fly zone boundary 50m), the actual PEM score is: Interference score = 0.6 × 8 + 0.3 × (1 / 0.2) + 0.1 × (1 / 0.7) = 6.94; Interception score = 0.6 × 8 + 0.3 × (1 / 0.4) + 0.1 × (1 / 0.7) = 6.12; Decision output: Prioritize the activation of electromagnetic interference (6.94>6.12).

[0041] S52. Select the countermeasure corresponding to the highest PEM score from the preset solution library as the final countermeasure.

[0042] S53. Based on game theory, resource scheduling selects the optimal equipment combination corresponding to the final countermeasure scheme, and uses a precise time protocol and the optimal equipment combination to counter the UAV target; Specifically, in the countermeasure phase, the system determines whether a drone is flying illegally based on the drone target information in a unified data format and its flight registration information. If it is found to be flying illegally, countermeasures are activated to take action. During the action phase, countermeasures such as electromagnetic suppression and navigation deception are implemented based on the DECP protocol. The process is as follows: Dynamic task allocation: Resource scheduling based on game theory, defining device utility functions. The optimal combination of equipment is selected using the Nash equilibrium algorithm. For example, for a drone 500m away, a jamming drone is selected to lure the drone into navigation.

[0043] Real-time coordinated control: PTP (Precise Time Protocol) is used to ensure that the transmission phases of the jamming signal and the decoy signal are aligned.

[0044] Conflict resolution mechanism: Real-time monitoring of the device's transmission frequency band. If the jammer (2.4GHz) overlaps with the police communication frequency band, the dynamic spectrum protection window (DSPW) is automatically triggered, and the device switches to the 5.8GHz frequency band within 1ms. Experimental Example: The decision-making level calculates the optimal strategy (disruption + deception) using the PEM matrix. The control layer sends a command to the 1.5kW directional jammer (frequency 5.8GHz, power 800W). After the interference takes effect, the decoy transmits fake GPS coordinates (offset by 500m). If the drone deviates from its course and fails to escape, laser ablation is initiated (power adjustable). Synergistic effect: The entire process from target identification to removal takes 1.8 seconds, with a total energy consumption of ≤200Wh (only 35% of the single-device solution) and an electromagnetic leakage intensity of ≤-65dBm (without affecting civilian frequency bands).

[0045] The UAV countermeasure method based on multi-source heterogeneous data fusion provided in Embodiment 1 of this invention first fuses multi-source heterogeneous monitoring data, then fuses it with optoelectronic and video data. Based on this, attenuation weights are introduced, and the weights of the multi-source data are adjusted in conjunction with real-time electromagnetic noise to solve the problem of misjudgment in complex environments. This invention fuses data into a unified standard target information format. For the target and its surrounding environment, a reinforcement learning-driven dynamic decision engine is used to construct a 12-dimensional state space. The weighted relationship between threat level, countermeasure cost, and environmental constraints is quantified through a three-dimensional PEM matrix. Finally, a distributed countermeasure device control protocol is used to support the coordinated countermeasure of multiple countermeasure devices to ultimately dispose of the UAV. Through a closed-loop design of "integrated platform - dynamic decision - environment adaptation," the problems of slow response and poor environmental adaptability in traditional countermeasure systems are solved.

[0046] Example 2 like Figure 2 As shown, in Embodiment 2 of the present invention, a UAV countermeasure system based on multi-source heterogeneous data fusion is provided, the system comprising: The first fusion module 1 is used to acquire monitoring data and photoelectric video data transmitted by multi-source heterogeneous UAV detection sensors, and to perform preliminary fusion of the monitoring data to obtain the first fused data; Attenuation module 2 is used to determine the initial weights of the UAV detection sensors and perform attenuation processing on the initial weights to obtain attenuation weights; The second fusion module 3 is used to perform a final fusion of the first fusion data and the photoelectric video data based on the attenuation weight to obtain the second fusion data; Mapping module 4 is used to construct a state space and map the second fused data into the state space to obtain multidimensional data; Countermeasure module 5 is used to coordinate several UAV countermeasure devices to counter UAVs based on the multidimensional data and the distributed countermeasure device control protocol. The first fusion module 1 includes: The first standardization submodule is used to perform feature standardization processing on the monitoring data to obtain monitoring data; The first combination submodule is used to combine the monitoring data into feature vectors to obtain a feature matrix. : ; In the formula, For the first Feature vectors of a drone detection sensor; The first covariance submodule is used to calculate the covariance matrix of the feature matrix. : ; In the formula, Indicates the sample degrees of freedom; The first decomposition submodule is used to perform eigenvalue decomposition on the covariance matrix to obtain the eigenvector matrix. With eigenvalue matrix : ; Spatial submodule, used to select the first eigenvalue from the eigenvalue matrix. The largest feature is identified, and the corresponding eigenvector in the eigenvector matrix is ​​selected as the principal component to obtain the feature space. : ; In the formula, For the first The feature vectors corresponding to the principal components; The first fusion submodule is used to base on the feature space. Determine the first fused data : .

[0047] Wherein, the attenuation weight is : ; In the formula, For the first The initial weights of the drone detection sensors The attenuation coefficient is... This represents the current noise interference index.

[0048] The second fusion module 3 includes: An extraction submodule is used to extract features from the photoelectric video data to obtain video features; The alignment submodule is used to align the video features with the first fused data in time and space to obtain aligned video features and aligned fused data. The second combination submodule is used to combine the aligned video features into a video feature matrix and the aligned fusion data into a fusion feature matrix; The second standardization submodule is used to standardize the video feature matrix and the fusion feature matrix respectively to obtain the video standard matrix and the fusion standard matrix; The second covariance submodule is used to calculate the sample covariance matrix between the video standard matrix and the fusion standard matrix, and to perform canonical eigenvalue decomposition on the sample covariance matrix to obtain several canonical correlation coefficients and corresponding canonical variables. The second fusion submodule is used to select the previous... The canonical variable corresponding to the largest canonical correlation coefficient is taken as the variable to be fused. Based on the decay weight, several variables to be fused are fused to obtain the second fused data.

[0049] The state space is a 12-dimensional state space, and the multi-dimensional data includes radar cross-section, flight altitude, flight speed, signal modulation type, payload type, no-fly zone distance, population density index, electromagnetic interference intensity, meteorological conditions, remaining energy of jammer, physical interceptor inventory, and availability of cooperative equipment.

[0050] The countermeasure module 5 includes: A molecular module is obtained to construct a PEM matrix, and the PEM score of the multidimensional data is calculated through the PEM matrix in three dimensions: threat level, countermeasure cost, and environmental constraints. The solution submodule is used to select the countermeasure corresponding to the highest PEM score from the preset solution library as the final countermeasure; The countermeasure submodule is used to select the optimal combination of equipment corresponding to the final countermeasure scheme based on game theory resource scheduling, and to counter the UAV target using a precise time protocol and the optimal combination of equipment.

[0051] In other embodiments of the present invention, the present invention provides the following technical solution: a computer, including a memory 102, a processor 101, and a computer program stored in the memory 102 and executable on the processor 101, wherein the processor 101 executes the computer program to implement the UAV countermeasure method based on multi-source heterogeneous data fusion as described above.

[0052] Specifically, the processor 101 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of the present invention.

[0053] The memory 102 may include a large-capacity memory for data or instructions. For example, and not limitingly, the memory 102 may include a hard disk drive (HDD), a floppy disk drive, a solid-state drive (SSD), flash memory, an optical disk drive, a magneto-optical disk drive, magnetic tape, or a Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, the memory 102 may include removable or non-removable (or fixed) media. Where appropriate, the memory 102 may be internal or external to a data processing device. In a particular embodiment, the memory 102 is non-volatile memory. In a particular embodiment, the memory 102 includes read-only memory (ROM) and random access memory (RAM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable read-only memory (PROM), an erasable read-only memory (EPROM), an electrically erasable read-only memory (EEPROM), an electrically alterable read-only memory (EAROM), or flash memory, or a combination of two or more of these. Where appropriate, the RAM can be Static Random-Access Memory (SRAM) or Dynamic Random-Access Memory (DRAM). DRAM can be Fast Page Mode Dynamic Random Access Memory (FPMDRAM), Extended Data Out Dynamic Random Access Memory (EDODRAM), Synchronous Dynamic Random-Access Memory (SDRAM), etc.

[0054] The memory 102 can be used to store or cache various data files that need to be processed and / or used for communication, as well as possible computer program instructions executed by the processor 101.

[0055] The processor 101 reads and executes the computer program instructions stored in the memory 102 to implement the above-mentioned UAV countermeasure method based on multi-source heterogeneous data fusion.

[0056] In some embodiments, the computer may further include a communication interface 103 and a bus 100. For example, Figure 3 As shown, the processor 101, memory 102, and communication interface 103 are connected through bus 100 and complete communication with each other.

[0057] The communication interface 103 is used to enable communication between the various modules, devices, units, and / or equipment in the embodiments of the present invention. The communication interface 103 can also enable data communication with other components such as external devices, image / data acquisition devices, databases, external storage, and image / data processing workstations.

[0058] Bus 100 includes hardware, software, or both, that couples components of a computer device together. Bus 100 includes, but is not limited to, at least one of the following: data bus, address bus, control bus, expansion bus, and local bus. For example, and not as a limitation, bus 100 may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VLB) bus, or other suitable buses, or a combination of two or more of these. Where appropriate, bus 100 may include one or more buses. Although specific buses are described and illustrated in the embodiments of the present invention, the present invention is contemplated by any suitable bus or interconnect.

[0059] The computer can execute the drone countermeasure method based on multi-source heterogeneous data fusion of the present invention based on the drone countermeasure system acquired based on multi-source heterogeneous data fusion, thereby realizing drone countermeasure based on multi-source heterogeneous data fusion.

[0060] In some further embodiments of the present invention, in conjunction with the above-described method for countering unmanned aerial vehicles (UAVs) based on multi-source heterogeneous data fusion, the present invention provides the following technical solution: a storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the above-described method for countering UAVs based on multi-source heterogeneous data fusion.

[0061] Those skilled in the art will understand that the logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can mean any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0062] More specific examples of readable media (a non-exhaustive list) include: electrical connections (electronic devices) with one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0063] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0064] The technical features of the above embodiments can be combined in any way. For the sake of brevity, 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.

[0065] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these all fall within the protection scope of the present invention. Therefore, the protection scope of this invention patent should be determined by the appended claims.

Claims

1. A method for anti-UAV based on multi-source heterogeneous data fusion, characterized in that, The system comprises: obtaining monitoring data transmitted by multiple-source heterogeneous unmanned aerial vehicle detection sensors and photoelectric video data, and preliminarily fusing the monitoring data to obtain first fused data; determining an initial weight of the unmanned aerial vehicle detection sensor, and performing attenuation processing on the initial weight to obtain an attenuation weight; based on the attenuation weight, finally fusing the first fused data and the photoelectric video data to obtain second fused data; constructing a state space, and mapping the second fused data into the state space to obtain multi-dimensional data; based on the multi-dimensional data, a distributed countermeasure equipment control protocol is used to link several unmanned aerial vehicle countermeasure equipments to perform unmanned aerial vehicle countermeasures.

2. The method of claim 1, wherein the method is based on multi-source heterogeneous data fusion. The step of preliminarily fusing the monitoring data to obtain first fused data comprises: performing feature standardization processing on the monitoring data to obtain monitoring data; combining the monitoring data into eigenvector groups to obtain an eigenvector matrix : ； In the formula, is the feature vector of the nth unmanned aerial vehicle detection sensor; computing a covariance matrix of the feature matrix : ； In the formula, denotes the sample degrees of freedom; performing an eigenvalue decomposition on the covariance matrix to obtain an eigenvector matrix and an eigenvalue matrix : ； Selecting the first from the eigenvalue matrix The largest feature is identified, and the corresponding eigenvector in the eigenvector matrix is ​​selected as the principal component to obtain the feature space. : ； In the formula, is the eigenvector corresponding to the first principal component. based on the feature space determining first fused data : 。 3.The method of claim 1, wherein, In the step of performing the attenuation processing on the initial weight to obtain an attenuated weight, the attenuated weight is : ； In the formula, is the initial weight of the first unmanned aerial vehicle detection sensor, is the decay coefficient, is the current noise interference index.

4. The method of claim 1, wherein the method further comprises: The step of finally fusing the first fused data and the photoelectric video data based on the attenuation weight to obtain second fused data comprises: performing feature extraction on the photoelectric video data to obtain video features; aligning the video features and the first fused data in time and space to obtain aligned video features and aligned fused data; combining the aligned video features into a video feature matrix and combining the aligned fused data into a fused feature matrix; respectively performing standardization processing on the video feature matrix and the fused feature matrix to obtain a video standard matrix and a fused standard matrix; calculating a sample covariance matrix between the video standard matrix and the fused standard matrix, and performing canonical eigenvalue decomposition on the sample covariance matrix to obtain several canonical correlation coefficients and corresponding canonical variables; Before selection The canonical variable corresponding to the largest canonical correlation coefficient is taken as the variable to be fused. Based on the decay weight, several variables to be fused are fused to obtain the second fused data.

5. The method of claim 1, wherein the method further comprises: In the step of constructing a state space and mapping the second fused data into the state space to obtain multi-dimensional data, the state space is a 12-dimensional state space, and the multi-dimensional data comprises radar cross section, flight height, flight speed, signal modulation type, load type, no-fly zone distance, population density index, electromagnetic interference intensity, weather condition, jammer residual energy, physical interceptor inventory, and cooperative equipment availability.

6. The method of claim 1, wherein the method further comprises: The step of performing unmanned aerial vehicle countermeasures based on the multi-dimensional data and a distributed countermeasure equipment control protocol to link several unmanned aerial vehicle countermeasure equipments comprises: constructing a PEM matrix, and calculating a PEM score of the multi-dimensional data in three dimensions of threat level, countermeasure cost and environmental constraint through the PEM matrix; selecting a countermeasure scheme corresponding to the highest PEM score in a preset scheme library as a final countermeasure scheme; based on game theory, selecting an optimal equipment combination corresponding to the final countermeasure scheme, adopting a precise time protocol, and adopting the optimal equipment combination to perform countermeasures on the unmanned aerial vehicle target.

7. An unmanned aerial vehicle countermeasure system based on multi-source heterogeneous data fusion, characterized in that, The system comprises: a first fusion module for obtaining monitoring data transmitted by multiple-source heterogeneous unmanned aerial vehicle detection sensors and photoelectric video data, and preliminarily fusing the monitoring data to obtain first fused data; an attenuation module for determining an initial weight of the unmanned aerial vehicle detection sensor, and performing attenuation processing on the initial weight to obtain an attenuation weight; a second fusion module configured to perform final fusion of the first fusion data and the photoelectric video data based on the attenuation weight to obtain second fusion data; a mapping module configured to construct a state space and map the second fusion data into the state space to obtain multi-dimensional data; a countermeasure module configured to control a plurality of UAV countermeasure devices based on the multi-dimensional data and a distributed countermeasure device control protocol to perform UAV countermeasures.

8. The multi-source heterogeneous data fusion based UAV countermeasure system of claim 7, wherein, The state space is a 12-dimensional state space, and the multi-dimensional data includes radar cross section, flight height, flight speed, signal modulation type, load type, no-fly zone distance, population density index, electromagnetic interference intensity, weather condition, jammer residual energy, physical interceptor inventory, and cooperative device availability.

9. A computer comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor executes the computer program to implement the multi-source heterogeneous data fusion-based UAV countermeasure method of any one of claims 1 to 6.

10. A storage medium, characterized by The storage medium stores the computer program, and the computer program is executed by the processor to implement the multi-source heterogeneous data fusion-based UAV countermeasure method of any one of claims 1 to 6.

Images