Urban hidden unmanned aerial vehicle identification method and system

Abstract

The invention provides a city hidden unmanned aerial vehicle identification method and system. The method comprises the following steps: acquiring geometric morphology and material dielectric constant data of an urban building group, and generating a building material reflection parameter set; secondly, based on reflection parameters, millimeter wave frequency band combinations adaptive to building attenuation characteristics are screened, millimeter wave signals are directionally transmitted, reflection components of metal parts and unmanned aerial vehicle composite materials are separated, and a three-dimensional millimeter wave imaging map fused with multipath interference suppression parameters is generated; collecting a radio frequency signal, compensating path loss by using scattering phase offset, extracting a harmonic component of a propeller motor and a frequency hopping residual component of a communication module, and generating a time-space synchronous radio frequency fingerprint coding sequence; through constructing a millimeter wave and radio frequency coupling model, cross validation is carried out on a reflection component and a harmonic component, and accurate identification of the hidden unmanned aerial vehicle in the urban building group shielding area is realized. According to the invention, the urban hidden unmanned aerial vehicle identification precision is improved.

Description

Technical Field

[0001] This application relates to the technical field of unmanned aerial vehicle (UAV) identification, and particularly to a method and system for identifying concealed UAVs in cities. Background Art

[0002] In areas with dense urban building complexes, the detection of concealed UAV activities faces multiple challenges. The complex geometric forms and diverse materials of building structures can significantly change the propagation characteristics of electromagnetic waves, resulting in problems such as signal attenuation, multipath interference, and scattering phase shift. In addition, metal components and UAV composite materials in the sheltered areas of building complexes may produce similar reflection characteristics, further increasing the difficulty of target identification. Therefore, there is an urgent need for a technical solution that can separate multi-band signals in real time, suppress multipath effects, and accurately extract the radio frequency harmonic characteristics of UAVs in a dynamic environment to achieve reliable detection of concealed UAVs.

[0003] The current mainstream solutions are based on the detection framework of the fusion of millimeter-wave radar and radio frequency signals. By deploying multiple groups of millimeter-wave radar arrays to transmit high-frequency signals, combined with inertial measurement units and backscatter tags for auxiliary positioning, polarization modulation technology is used to separate environmental reflection components. For example, by combining dual-polarization radar (horizontal and vertical polarization) with frequency modulation, the tag echo and environmental clutter are distinguished, and the UAV attitude change is compensated by inertial data to generate six-degree-of-freedom spatial positioning information.

[0004] The existing solutions have limited adaptability in complex building complex environments. Single-band millimeter-wave signals are difficult to match the dynamic reflection attenuation characteristics of building materials, resulting in ineffective separation of the reflection components of metal components and UAV composite materials; relying on tag-assisted positioning requires pre-deployment of hardware, and the backscatter signals of tags are easily affected by the dielectric constant differences of multiple materials, with insufficient path loss compensation accuracy; the extraction of radio frequency harmonic components relies on fixed-band filtering and cannot dynamically adapt to the time-varying characteristics of the hopping residue components of communication modules, resulting in a high missed detection rate of the radio frequency fingerprints of concealed UAVs and low accuracy in identifying concealed UAVs in cities. Summary of the Invention

[0005] This application provides a method and system for identifying concealed UAVs in cities to solve the problem of low accuracy in identifying concealed UAVs in the prior art.

[0006] In a first aspect, this application provides a method for identifying concealed UAVs in cities, including: In the urban building complex covered by the UAV activity area, obtain the geometric form of the building structure and the distribution data of the material dielectric constant, and generate a set of building material reflection parameters including multi-band attenuation gradients and scattering phase offsets through a dynamic reflection attenuation model; Based on the set of reflection parameters of the building material, screen the millimeter-wave frequency band combination that matches the dynamic reflection attenuation characteristics, transmit millimeter-wave signals to the sheltered area of the building complex, separate the reflection components of metal parts and unmanned aerial vehicle (UAV) composite materials according to the echo signals, and generate a three-dimensional millimeter-wave imaging map containing multipath interference suppression parameters; Synchronously collect the radio frequency signals in the sheltered area of the building complex, compensate for the path loss through the scattering phase offset, extract the harmonic components of the UAV propeller motor and the frequency hopping residual components of the communication module, and combine the radio frequency signals with the multipath interference suppression parameters in the three-dimensional millimeter-wave imaging map to generate a spatio-temporally synchronized radio frequency fingerprint coding sequence; Based on the set of reflection parameters of the building material, construct a coupling model of millimeter-wave and radio frequency. Through the cross-validation of the reflection components, the harmonic components, and the radio frequency fingerprint coding sequence, identify the concealed UAVs in the sheltered area of the urban building complex.

[0007] Optionally, the separating the reflection components of metal parts and UAV composite materials according to the echo signals and generating a three-dimensional millimeter-wave imaging map containing multipath interference suppression parameters includes: Perform joint time-frequency domain analysis on the echo signals, separate the steady-state reflection components of metal parts and the transient scattering components of UAV composite materials, and construct multipath interference suppression parameters in combination with the attenuation gradient distribution in the set of reflection parameters of the building material; Use the multipath interference suppression parameters to perform parametric filtering on the transient scattering components, eliminate the aliased reflections caused by multipath propagation in the sheltered area of the building complex, visualize the multipath interference suppression parameters and the spatial distribution characteristics of the UAV composite materials, and generate a three-dimensional millimeter-wave imaging map.

[0008] Optionally, the synchronously collecting the radio frequency signals in the sheltered area of the building complex, compensating for the path loss through the scattering phase offset, and extracting the harmonic components of the UAV propeller motor and the frequency hopping residual components of the communication module includes: Compensate for the path loss through the scattering phase offset, construct a dynamic attenuation compensation function for the radio frequency signal propagation path, reconstruct the multipath propagation sequence of the radio frequency signals collected in the sheltered area of the building complex, and eliminate the scattering phase distortion of the radio frequency signals caused by the building material; Perform joint time-frequency domain decomposition on the adjusted radio frequency signals, separate the harmonic components generated during the operation of the UAV propeller motor and the frequency hopping residual components remaining during the frequency hopping switching process of the communication module, and extract a set of transient harmonic features associated with the motion state of the UAV.

[0009] Optionally, the combining the radio frequency signals with the multipath interference suppression parameters in the three-dimensional millimeter-wave imaging map to generate a spatio-temporally synchronized radio frequency fingerprint coding sequence includes: Based on the multipath interference suppression parameters in the three-dimensional millimeter-wave imaging map, establish the mapping relationship between the radio frequency signal propagation path and the millimeter-wave imaging spatial position, and perform spatio-temporal synchronous alignment on the harmonic component and the frequency hopping residual component according to the mapping relationship; Based on the spatio-temporal synchronous alignment result, combine the radio frequency signal and the reflector distribution characteristics in the three-dimensional millimeter-wave imaging map to generate a spatio-temporally synchronous radio frequency fingerprint coding sequence.

[0010] Optionally, the step of establishing the mapping relationship between the radio frequency signal propagation path and the millimeter-wave imaging spatial position based on the multipath interference suppression parameters in the three-dimensional millimeter-wave imaging map, and performing spatio-temporal synchronous alignment on the harmonic component and the frequency hopping residual component according to the mapping relationship includes: Based on the multipath interference suppression parameters in the three-dimensional millimeter-wave imaging map, analyze the reflector distribution characteristics and millimeter-wave signal attenuation coefficient in the three-dimensional millimeter-wave imaging map, and establish the geometric topology mapping relationship between the radio frequency signal propagation path and the millimeter-wave imaging spatial grid; According to the geometric topology mapping relationship, combine the time delay and Doppler characteristic information of the radio frequency signal propagation path to construct a multipath propagation path topology model in the building complex shielding area, and the multipath propagation path topology model associates the reflector position in the millimeter-wave imaging spatial grid with the geometric constraint conditions of the radio frequency signal propagation path; Extract the timestamp sequence in the transient harmonic feature set and the frequency domain hopping interval of the frequency hopping residual component, and perform spatio-temporal reference alignment on the timestamp sequence and the frequency domain hopping interval based on the reflector position and geometric constraint conditions associated with the multipath propagation path topology model; Use the update rate of the millimeter-wave imaging spatial grid to perform dynamic interpolation compensation on the spatio-temporal reference alignment result, generate spatio-temporal constraint parameters synchronized with the UAV motion state and communication frequency hopping mode, and complete the spatio-temporal synchronous alignment of the harmonic component and the frequency hopping residual component.

[0011] Optionally, the step of constructing the multipath propagation path topology model in the building complex shielding area according to the geometric topology mapping relationship, and the multipath propagation path topology model associates the reflector position in the millimeter-wave imaging spatial grid with the geometric constraint conditions of the radio frequency signal propagation path includes: Analyze the correlation between the reflector spatial position and the millimeter-wave signal attenuation coefficient in the geometric topology mapping relationship, and combine the shielding weights of each reflector in the building complex shielding area on the radio frequency signal propagation path to generate initial path propagation parameters; Combining the delay and Doppler characteristic information of the radio frequency signal propagation path, and correcting the delay estimation error in the initial path propagation parameters according to the dynamic influence of the UAV motion state on the Doppler frequency shift, to generate updated path propagation parameters including path loss gradient and time-frequency joint constraints; Based on the updated path propagation parameters, perform ray tracing modeling on the multi-path signal propagation paths in the building complex shielding area to generate a set of path clusters that match the reflector positions in the millimeter-wave imaging space grid; According to the overlapping area distribution of the path cluster set and the reflector positions in the millimeter-wave imaging space grid, quantify the attenuation ratio of the direct path and multi-path reflection paths of the radio frequency signal propagation path, and then construct a multi-path propagation path topology model, and associate the multi-path propagation path topology model with the geometric constraint conditions of the reflector positions in the millimeter-wave imaging space grid and the radio frequency signal propagation path.

[0012] Optionally, the combining the delay and Doppler characteristic information of the radio frequency signal propagation path, and correcting the delay estimation error in the initial path propagation parameters according to the dynamic influence of the UAV motion state on the Doppler frequency shift, to generate updated path propagation parameters including path loss gradient and time-frequency joint constraints, includes: Extract the Doppler frequency shift dynamic characteristics associated with the UAV motion state in the delay and Doppler characteristic information of the radio frequency signal propagation path, and combine the mapping relationship between the propeller rotation frequency and the UAV speed to generate the association parameters between the Doppler frequency shift and the motion state; According to the association parameters, establish a dynamic influence model of the UAV motion acceleration on the multi-path propagation delay, and quantify the non-linear relationship between the delay estimation error in the initial path propagation parameters and the UAV motion acceleration through the dynamic influence model; Based on the dynamic influence model, perform dynamic weight allocation on the delay estimation value in the initial path propagation parameters, and combine the allocation result with the loss gradient distribution of radio frequency signals by different materials in the building complex shielding area to generate path propagation parameters after delay compensation; Perform matrix fusion on the path propagation parameters and the time-frequency joint constraint conditions of the radio frequency signal. The fusion process eliminates the time-frequency aliasing error caused by the UAV's maneuvering flight, and generates updated path propagation parameters including path loss gradient and time-frequency joint constraints.

[0013] Optionally, the constructing a millimeter-wave and radio frequency coupling model based on the building material reflection parameter set, and identifying the concealed UAV in the urban building complex shielding area through the cross-validation of the reflection component, the harmonic component, and the radio frequency fingerprint coding sequence, includes: Based on the multi-band attenuation gradient and the spatio-temporal synchronization constraint conditions in the radio frequency fingerprint coding sequence, establish a dynamic correlation matrix between the intensity of the millimeter-wave reflection component and the amplitude of the radio frequency harmonic component, and generate an initial feature mapping relationship of the coupling model between the millimeter wave and the radio frequency according to the dynamic correlation matrix; According to the spatial distribution density and material attenuation difference of the reflectors in the three-dimensional millimeter-wave imaging map, and combining the initial feature mapping relationship, perform multi-modal feature fusion on the dynamic correlation matrix to construct a harmonic component amplitude compensation function under the constraint of millimeter-wave spatial resolution; Use the harmonic component amplitude compensation function to correct the harmonic attenuation distortion caused by building shielding in the radio frequency fingerprint coding sequence, and extract the spatio-temporal consistency constraint parameters of the reflection characteristics of the unmanned aerial vehicle composite material and the amplitude of the radio frequency harmonic component based on the corrected harmonic attenuation distortion; Based on the spatio-temporal consistency constraint parameters, perform multi-dimensional joint verification on the reflection component distribution in the three-dimensional millimeter-wave imaging map, the hopping residue pattern of the radio frequency harmonic component amplitude, and the radio frequency fingerprint coding sequence. The verification process eliminates the feature confusion between the metal frame inside the building and the unmanned aerial vehicle composite material, and completes the spatial positioning and identification of the urban concealed unmanned aerial vehicle.

[0014] Optionally, the multi-dimensional joint verification of the reflection component distribution in the three-dimensional millimeter-wave imaging map, the hopping residue pattern of the radio frequency harmonic component amplitude, and the radio frequency fingerprint coding sequence based on the spatio-temporal consistency constraint parameters, and the verification process eliminates the feature confusion between the metal frame inside the building and the unmanned aerial vehicle composite material, and completes the spatial positioning and identification of the urban concealed unmanned aerial vehicle, includes: Based on the spatial distribution correlation between the millimeter-wave reflection component and the radio frequency harmonic component in the spatio-temporal consistency constraint parameters, extract the steady-state reflection characteristics of the metal frame inside the building and the transient scattering characteristics of the unmanned aerial vehicle composite material, and generate a joint distribution map of the reflection component and the harmonic component; According to the spatial overlapping area between the metal frame inside the building and the unmanned aerial vehicle composite material in the joint distribution map, and combining the amplitude hopping residue pattern of the radio frequency harmonic component, construct a metal reflection suppression function and a composite material enhancement function, and generate a set of feature confusion elimination parameters; Use the set of feature confusion elimination parameters to perform dynamic weight assignment on the reflection component distribution in the three-dimensional millimeter-wave imaging map, and combine the distributed reflection component distribution, the time evolution law of the amplitude hopping residue pattern of the radio frequency harmonic component, and the radio frequency fingerprint coding sequence to generate joint verification parameters that fuse spatial positioning constraints and harmonic feature identification; Perform multi-dimensional iterative optimization on the joint distribution map based on the joint verification parameters. The optimization process eliminates the feature confusion between the metal frames inside the building and the composite materials of the drone, and completes the spatial positioning and identification of the urban stealth drone.

[0015] In a second aspect, the present application provides an urban stealth drone identification system, including: An acquisition module, configured to obtain the geometric morphology and material dielectric constant distribution data of the building structure in the urban building complex covered by the drone activity area, and generate a set of building material reflection parameters including multi-band attenuation gradients and scattering phase offsets through a dynamic reflection attenuation model; A screening module, configured to screen millimeter-wave frequency band combinations that match the dynamic reflection attenuation characteristics based on the set of building material reflection parameters, transmit millimeter-wave signals to the building complex shielding area, separate the reflection components of the metal parts and the drone composite materials according to the echo signals, and generate a three-dimensional millimeter-wave imaging map including multi-path interference suppression parameters; An extraction module, configured to synchronously collect the radio frequency signals in the building complex shielding area, compensate for the path loss through the scattering phase offset, extract the harmonic components of the drone propeller motor and the frequency hopping residual components of the communication module, and combine the radio frequency signals with the multi-path interference suppression parameters in the three-dimensional millimeter-wave imaging map to generate a spatio-temporally synchronized radio frequency fingerprint coding sequence; An identification module, configured to construct a coupling model of millimeter-wave and radio frequency based on the set of building material reflection parameters, and identify the stealth drone in the urban building complex shielding area through the cross-verification of the reflection components, the harmonic components, and the radio frequency fingerprint coding sequence.

[0016] In an embodiment of the present application, in the urban building complex covered by the drone activity area, the geometric morphology and material dielectric constant distribution data of the building structure are obtained, and a set of building material reflection parameters including multi-band attenuation gradients and scattering phase offsets are generated through a dynamic reflection attenuation model; based on the set of building material reflection parameters, millimeter-wave frequency band combinations that match the dynamic reflection attenuation characteristics are screened, millimeter-wave signals are transmitted to the building complex shielding area, the reflection components of the metal parts and the drone composite materials are separated according to the echo signals, and a three-dimensional millimeter-wave imaging map including multi-path interference suppression parameters is generated; the radio frequency signals in the building complex shielding area are synchronously collected, the path loss is compensated through the scattering phase offset, the harmonic components of the drone propeller motor and the frequency hopping residual components of the communication module are extracted, and a spatio-temporally synchronized radio frequency fingerprint coding sequence is generated in combination with the multi-path interference suppression parameters in the three-dimensional millimeter-wave imaging map; a coupling model of millimeter-wave and radio frequency is constructed based on the set of building material reflection parameters, and the stealth drone in the urban building complex shielding area is identified through the cross-verification of the reflection components and the harmonic components.

[0017] The technical solution of this application has the following beneficial effects: By accurately obtaining the geometric morphology and material dielectric constant distribution data of the building complex, the dynamic reflection attenuation model can quantify the millimeter-wave reflection characteristics of different materials (such as attenuation gradient, scattering phase offset), providing a physical basis for subsequent signal processing and ensuring the adaptability of multi-band signals in complex environments; the millimeter-wave frequency band combination screened in combination with the dynamic reflection attenuation characteristics can penetrate the building complex shielding area and suppress multipath interference. By separating the reflection components of metal parts and UAV composite materials, a high-resolution three-dimensional millimeter-wave imaging map is generated, significantly improving the detection accuracy of hidden targets; using the scattering phase offset to compensate for path loss, extracting the harmonic components of the propeller motor and the residual signals of communication frequency hopping, enhancing the ability to capture the electromagnetic characteristics of UAVs, especially performing excellently in low signal-to-noise ratio environments; through the cross-validation of the reflection components and harmonic components, the coupling model can effectively distinguish UAVs from background interference (such as building metal structures), realizing high-confidence hidden target recognition. This method combines the advantages of multi-source data and improves the anti-interference performance in complex urban environments.

[0018] Furthermore, based on the set of building material reflection parameters, a millimeter-wave frequency band combination matching the dynamic reflection attenuation characteristics is screened, and millimeter-wave signals are transmitted to the building complex shielding area. By separating the reflection components of metal parts and UAV composite materials from the echo signals, a three-dimensional millimeter-wave imaging map containing multipath interference suppression parameters is generated. This method utilizes the strong penetration of millimeter waves and combines multipath interference suppression algorithms to achieve high-resolution three-dimensional imaging of the building complex shielding area. Through the reflection component separation technology, it can effectively distinguish UAV composite materials from background metal structures, significantly improving the detection accuracy of hidden targets and reducing the impact of environmental clutter on the imaging quality at the same time.

[0019] These aspects or other aspects of this application will be more clearly understood in the following description of the embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of this application. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0021] Figure 1 Shows a flowchart of a method for identifying hidden UAVs in cities provided by this application; Figure 2 Shows a schematic structural diagram of a system for identifying hidden UAVs in cities provided by this application.

[0022] Figure 3The scene diagram of an urban stealth drone recognition method provided by this application is shown. Detailed implementation manners

[0023] In order to enable those skilled in the art to better understand the solutions of this application, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of this application.

[0024] In some processes described in the specification, claims and the above-mentioned accompanying drawings of this application, there are multiple operations that appear in a specific order. However, it should be clearly understood that these operations may not be executed in the order in which they appear in this article or may be executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish each different operation, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions such as "first" and "second" in this article are used to distinguish different messages, devices, modules, etc., do not represent a sequence, and do not limit that "first" and "second" are of different types.

[0025] The current urban stealth drone detection technology faces three major core bottlenecks: First, in the complex building group environment, the difference in the dielectric constants of building materials leads to serious multi-path interference and scattering phase shift of electromagnetic waves. A single-band millimeter-wave radar is difficult to adapt to the dynamic reflection attenuation characteristics, and the reflection components of metal parts and drone composite materials cannot be effectively separated due to frequency band mismatch; Second, the existing solutions rely on pre-deployed backscatter tags for assisted positioning, but the tag signals are easily affected by the dielectric property differences of multiple materials, the path loss compensation accuracy is insufficient, and the hardware deployment cost is high and the flexibility is poor; Third, the extraction of radio frequency harmonic features relies on fixed-band filtering and cannot dynamically adapt to the time-varying characteristics of the frequency-hopping residual components of the drone communication module, resulting in a high missed detection rate of the radio frequency fingerprints of stealth targets and limited recognition accuracy.

[0026] In view of the above deficiencies, the present invention proposes a UAV identification method based on the collaborative use of the reflection characteristics of building materials, millimeter-wave penetration imaging, and RF fingerprint coding. The core lies in constructing a cross-modal dynamic adaptation framework. First, a set of multi-band attenuation gradients and scattering phase offsets is generated through a dynamic reflection attenuation model, and a millimeter-wave frequency band combination that matches the attenuation characteristics of building materials is selected. A multi-band signal is transmitted directionally, and the reflection components of metals and composite materials are separated to generate a three-dimensional millimeter-wave imaging map that incorporates multi-path interference suppression parameters. At the same time, RF signals are collected, and the path loss is compensated by combining the scattering phase offsets. The harmonic components and hopping residue components of the UAV propellers are extracted to generate a spatio-temporally synchronized RF fingerprint coding sequence. Finally, cross-verification is performed on the reflection components, harmonic components, and RF fingerprint coding sequence through a millimeter-wave-RF coupling model. This solution breaks through the limitations of traditional technologies: multi-band dynamic adaptation effectively suppresses metal interference reflections and eliminates label dependence; scattering phase offset compensation and dynamic extraction of hopping residues improve the accuracy of RF fingerprint capture; cross-modal cross-verification enables high-confidence identification of concealed UAVs in non-line-of-sight scenarios, providing reliable technical support for urban low-altitude security.

[0027] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative efforts shall fall within the protection scope of the present application.

[0028] Figure 1 The flowchart of a method for identifying concealed UAVs in cities provided for the embodiments of the present application is as Figure 1 shown, and the method includes: 101. In the urban building complex covered by the UAV activity area, obtain the geometric shape and material dielectric constant distribution data of the building structure, and generate a set of building material reflection parameters including multi-band attenuation gradients and scattering phase offsets through a dynamic reflection attenuation model; In the above solution, the geometric form refers to the three-dimensional spatial shape and dimensional data of the building structure, including physical topology features such as wall inclination, surface curvature, building spacing, etc. The dielectric constant distribution data of the material is to describe the dielectric response characteristics of the building material to electromagnetic waves at different spatial positions, including the real part and the imaginary part. The dynamic reflection attenuation model is a mathematical model based on the physics of electromagnetic wave propagation, used to calculate the reflection intensity attenuation rate and phase shift amount of millimeter waves in building materials at different frequency bands, and its input is the dielectric constant distribution and geometric form data. The multi-band attenuation gradient refers to the slope distribution of the reflection intensity attenuation rate of the building material to the millimeter wave band with respect to frequency change, characterizing the differential attenuation characteristics of the material to multi-band signals. The scattering phase shift amount is to describe the phase change amount caused by the difference in dielectric properties of the material during the scattering process of electromagnetic waves on the building surface, used to quantify the phase distortion degree of the multipath propagation path. The building material reflection parameter set is a parameter matrix composed of the multi-band attenuation gradient and the scattering phase shift amount, serving as a physical prior knowledge base for millimeter wave band optimization and radio frequency path compensation.

[0029] In the embodiments of the present application, first, through lidar and oblique photogrammetry techniques, three-dimensional point cloud scanning and dense reconstruction are performed on the target building complex to generate building geometric form data with sub-meter accuracy. For example, a multi-rotor unmanned aerial vehicle is used to carry a LiDAR sensor to obtain the building facade point cloud at a resolution of 0.1 meter, and a three-dimensional mesh model of the building structure is generated through the Poisson surface reconstruction algorithm.

[0030] Secondly, based on a near-field microwave flaw detector and a dielectric resonance probe, non-contact dielectric property measurement is performed on the building surface material. For example, microwave probes with adjustable frequencies from 1 - 100 GHz are deployed on the surface of the concrete wall, and the real part and the imaginary part of the dielectric constant are inverted through the resonance frequency shift amount, and the Kalman filtering algorithm is combined to eliminate environmental noise interference to generate a dielectric constant spatial distribution heat map.

[0031] Finally, the geometric form data and the dielectric constant distribution are input into the dynamic reflection attenuation model, and the propagation path of millimeter waves in the building complex is simulated through the finite-difference time-domain algorithm to calculate the multi-band signal reflection intensity attenuation gradient and the scattering phase shift amount: the reflection intensity attenuation gradient is calculated through the frequency-domain attenuation spectrum analysis method. The short-time Fourier transform is performed on the reflection signal of each frequency band, and the exponential attenuation curve of the signal energy with respect to the propagation distance is extracted, and its logarithmic attenuation slope is calculated as the attenuation gradient; the scattering phase shift amount is obtained through the phase unwrapping technique. The discrete Fourier transform is performed on the complex frequency spectrum of the echo signal, the phase response of the main scattering path is extracted, and combined with the surface curvature in the geometric form data, the least squares phase gradient integration method is used to solve the absolute phase shift amount, and finally the building material reflection parameter set is output. For example, a 10 ns time window is intercepted for the 24 GHz band echo signal, and a time-frequency spectrum matrix is generated through the short-time Fourier transform, and the energy attenuation curve is fitted along the propagation distance axis. , extract the value as the attenuation gradient of this frequency band; perform discrete Fourier transform on the complex echo signal of the 60 GHz frequency band, and extract the main scattering path phase value , combined with the wall surface curvature radius , through the phase gradient integral formula , solve the absolute phase offset , where is the wave number.

[0032] It should be noted that the above dynamic reflection attenuation model is a training model, and its specific training process mainly includes the following steps: First, obtain the building geometric shape data (such as wall inclination, curvature, spacing) through lidar and oblique photography, construct a three-dimensional grid model with sub-meter accuracy, and at the same time use a near-field microwave flaw detector to measure the dielectric constant (real part and imaginary part) of the building surface. After eliminating noise through Kalman filtering, generate a dielectric constant spatial distribution heat map, and finally pair the geometric shape and dielectric distribution data to form a training sample set.

[0033] Secondly, use the finite-difference time-domain (FDTD) algorithm to simulate the propagation process of millimeter waves in the building structure, and perform physical calculations on the simulation results to generate label data: for the multi-frequency attenuation gradient, intercept the time-domain segments of the reflected signals of each frequency band (such as a 10 ns time window), extract the energy attenuation curve through short-time Fourier transform (STFT), and fit the exponential equation , with the attenuation coefficient as the attenuation gradient label.

[0034] For the scattering phase offset, perform discrete Fourier transform (DFT) on the complex echo signal, and extract the main path phase , combined with the curvature radius in the geometric data , through the phase gradient integral formula ( is the wave number) to calculate the absolute phase offset as the label.

[0035] Finally, using the geometric shape and material dielectric constant distribution data as the input, the attenuation coefficient and the phase offset as the output target, construct a deep learning model (such as a physics-constrained neural network). Through a large number of samples, train the model to learn the physical laws of electromagnetic reflection, and use the FDTD simulation results to verify the model accuracy until its output error with the physical simulation is less than the set threshold, and define the trained model as the dynamic reflection attenuation model.

[0036] By means of a dynamic reflection attenuation model, the interaction law between internalized electromagnetic waves and building materials is trained, and the reflection physical quantity at any frequency band can be directly predicted according to new geometric-dielectric input data: the model automatically calculates the attenuation coefficient of signal energy with distance through an internal frequency-domain attenuation spectrum analysis module , outputs a multi-band attenuation gradient matrix, and at the same time combines geometric curvature and dielectric characteristics, solves the least-squares phase integral through an embedded phase unwrapping algorithm, and outputs the scattering phase offset , and finally integrates the attenuation gradient and phase offset in multiple frequency bands (such as 24 / 60 GHz) into a two-dimensional parameter matrix to form a set of building material reflection parameters, which serves as a prior knowledge base for millimeter-wave communication frequency band optimization and multipath phase compensation

[0037] 102. Based on the set of building material reflection parameters, screen the millimeter-wave frequency band combinations that match the dynamic reflection attenuation characteristics, transmit millimeter-wave signals to the building complex shielding area, separate the reflection components of metal components and UAV composite materials according to the echo signals, and generate a three-dimensional millimeter-wave imaging map containing multipath interference suppression parameters Optionally, step 102 may specifically include the following steps 1021. Perform joint time-frequency domain analysis on the echo signals, separate the steady-state reflection components of metal components and the transient scattering components of UAV composite materials, and construct multipath interference suppression parameters in combination with the attenuation gradient distribution in the set of building material reflection parameters 1022. Use the multipath interference suppression parameters to perform parametric filtering on the transient scattering components, eliminate the aliased reflections caused by multipath propagation in the building complex shielding area, visualize the multipath interference suppression parameters and the spatial distribution characteristics of the UAV composite materials, and generate a three-dimensional millimeter-wave imaging map

[0038] In the above solution, the dynamic reflection attenuation characteristic refers to the characteristic that the reflection intensity attenuation rate of building materials for millimeter-wave signals in different frequency bands changes with time or space. The millimeter-wave frequency band combination is a set of multiple millimeter-wave frequency bands selected according to the building material attenuation gradient, which is used to optimize the signal penetration and reflection separation effects. The joint time-frequency domain analysis is to simultaneously analyze the time-domain waveform and frequency-domain spectrum characteristics of the echo signals to distinguish the signal components of different reflectors. The steady-state reflection component is a stable high-reflection intensity signal generated by metal components inside the building. The transient scattering component is a time-varying scattering signal generated by UAV composite materials due to movement or material characteristics. The multipath interference suppression parameter is a set of parameters that quantify the interference degree of multipath propagation paths on the target signal. The three-dimensional millimeter-wave imaging map is a three-dimensional visualization image generated based on the spatial distribution of reflection components and multipath interference suppression parameters, which characterizes the position and material characteristics of the target object

[0039] In the embodiments of the present application, first, through step 1021, based on the attenuation gradient distribution in the building material reflection parameter set, a millimeter-wave frequency band combination (such as 60 GHz and 94 GHz frequency bands) whose penetration ability matches the material dynamic attenuation characteristics is selected by using a frequency band optimization algorithm. A multi-band frequency-modulated continuous wave signal is directionally transmitted to the building complex shielding area, and the reflected components are separated through joint time-frequency domain analysis: the echo signal is subjected to short-time Fourier transform to generate a time-frequency spectrum matrix, and wavelet transform is used to extract the steady-state reflection components of metal components and the transient scattering components of UAV composite materials. For example, for the 60 GHz frequency band echo signal, the fixed frequency shift component of the metal frame is locked through time-frequency ridge tracking technology, and the multipath interference suppression parameters are calculated in combination with the attenuation gradient distribution: the path attenuation coefficient λ = 2.5 dB / m, and the phase offset Δφ = 30°, generating a suppression parameter matrix.

[0040] Subsequently, through step 1022, parametric Wiener filtering is performed on the transient scattering components by using the multipath interference suppression parameter matrix: a frequency domain filter H(f) = 1 / (1 + λ(f) / SNR(f)) is constructed, where SNR(f) is the signal-to-noise ratio spectrum, suppressing the aliased reflection caused by multipath propagation. For example, the intensity of the secondary reflection signal of the glass curtain wall is attenuated by 6 dB. The filtered transient scattering components and the multipath interference suppression parameters are fused through the Kriging spatial interpolation algorithm, and a three-dimensional millimeter-wave imaging map is generated in combination with the spatial distribution characteristics of the UAV composite material. For example, for the UAV hovering area, density clustering and pseudo-color rendering are performed on the scattering point cloud with coordinates X = 35.2, Y = 78.6, Z = 12.3, and a three-dimensional millimeter-wave imaging map with a metal frame highlighted in red and the UAV marked in blue is output.

[0041] In practical applications, in the urban historical building protection area mainly composed of masonry structures and with dense metal decorative parts, step 1021 selects the 94 GHz frequency band as the main transmission frequency band, where the masonry attenuation gradient α = 1.5 dB / m. The steady-state reflection components of the metal decorative parts are separated through time-frequency ridge tracking, with a reflection intensity of 22 dBm and a Doppler frequency shift of ±30 Hz; and the transient scattering components of the UAV fiberglass fuselage are tracked, with a reflection intensity of 7 dBm and a Doppler frequency shift of ±180 Hz, generating a suppression parameter matrix of λ = 1.8 dB / m and Δφ = 25°; step 1022 uses Wiener filtering to eliminate the multipath interference of the masonry wall, and a three-dimensional imaging map is generated through inverse distance weighted interpolation, clearly marking that the UAV is located at the top of the bell tower: coordinates X = 102.3, Y = 55.7, Z = 45.2.

[0042] The overall solution of step 102 above realizes the precise separation of the reflection components of metals and composite materials through dynamic frequency band optimization and time-frequency joint analysis, breaking through the material confusion bottleneck of traditional single-frequency radars; the Wiener filter driven by multipath interference suppression parameters effectively eliminates environmental clutter and improves the signal-to-noise ratio of transient scattering components; the three-dimensional millimeter-wave imaging map fuses the spatial distribution and material attenuation characteristics, providing high-resolution spatial positioning and anti-interference imaging capabilities for stealth drones, and significantly enhancing the target detection reliability in complex urban shielding environments.

[0043] 103. Synchronously collect the radio frequency signals in the building complex shielding area, compensate the path loss through the scattering phase offset, extract the harmonic components of the drone propeller motor and the hopping residue components of the communication module, and generate a spatio-temporally synchronized radio frequency fingerprint coding sequence by combining the radio frequency signals with the multipath interference suppression parameters in the three-dimensional millimeter-wave imaging map; Optionally, step 103 may specifically include the following steps: 1031. Compensate the path loss through the scattering phase offset, construct a dynamic attenuation compensation function for the radio frequency signal propagation path, reconstruct the multipath propagation sequence of the radio frequency signals collected in the building complex shielding area, and eliminate the scattering phase distortion of the radio frequency signals caused by building materials; 1032. Perform time-frequency domain joint decomposition on the adjusted radio frequency signals, separate the harmonic components generated during the operation of the drone propeller motor and the hopping residue components remaining during the hopping frequency switching of the communication module, and extract the transient harmonic feature set associated with the drone motion state.

[0044] 1033. According to the multipath interference suppression parameters in the three-dimensional millimeter-wave imaging map, establish a mapping relationship between the radio frequency signal propagation path and the millimeter-wave imaging spatial position, and perform spatio-temporal synchronization alignment on the harmonic components and the hopping residue components according to the mapping relationship; Among them, step 1033 may specifically include the following process: Based on the multipath interference suppression parameters in the three-dimensional millimeter-wave imaging map, analyze the reflector distribution characteristics and millimeter-wave signal attenuation coefficient in the three-dimensional millimeter-wave imaging map, and establish the geometric topological mapping relationship between the radio frequency signal propagation path and the millimeter-wave imaging space grid; According to the geometric topological mapping relationship, combined with the characteristic information of the time delay and Doppler of the radio frequency signal propagation path, construct a multipath propagation path topological model within the building complex shielding area, and the multipath propagation path topological model associates the reflector position in the millimeter-wave imaging space grid with the geometric constraint conditions of the radio frequency signal propagation path; Extract the timestamp sequence in the transient harmonic feature set and the frequency-domain hopping interval of the frequency-hopping residual component, and perform spatio-temporal reference alignment on the timestamp sequence and the frequency-domain hopping interval based on the reflector position and geometric constraint conditions associated with the multipath propagation path topological model; Use the update rate of the millimeter-wave imaging space grid to perform dynamic interpolation compensation on the spatio-temporal reference alignment result, generate spatio-temporal constraint parameters synchronized with the UAV motion state and communication frequency-hopping mode, and complete the spatio-temporal synchronization alignment of the harmonic component and the frequency-hopping residual component.

[0045] Among them, the process of constructing the multipath propagation path topological model within the building complex shielding area according to the geometric topological mapping relationship, combined with the characteristic information of the time delay and Doppler of the radio frequency signal propagation path, and associating the multipath propagation path topological model with the geometric constraint conditions of the reflector position in the millimeter-wave imaging space grid and the radio frequency signal propagation path includes:

[0046] Analyze the correlation between the reflector spatial position and the millimeter-wave signal attenuation coefficient in the geometric topological mapping relationship, and combine the shielding weights of each reflector in the building complex shielding area on the radio frequency signal propagation path to generate initial path propagation parameters; Combine the characteristic information of the time delay and Doppler of the radio frequency signal propagation path, and correct the time delay estimation error in the initial path propagation parameters according to the dynamic influence of the UAV motion state on the Doppler frequency shift to generate updated path propagation parameters including path loss gradient and time-frequency joint constraints; Based on the updated path propagation parameters, perform ray tracing modeling on the multipath signal propagation paths within the building complex shielding area to generate a set of path clusters that match the reflector positions in the millimeter-wave imaging space grid; According to the overlapping area distribution of the path cluster set and the reflector positions in the millimeter-wave imaging space grid, quantify the attenuation ratio of the direct path and the multipath reflection path of the radio frequency signal propagation path, and then construct a multipath propagation path topological model, and associate the multipath propagation path topological model with the geometric constraint conditions of the reflector position in the millimeter-wave imaging space grid and the radio frequency signal propagation path.

[0047] Among them, the process of combining the characteristic information of the time delay and Doppler of the radio frequency signal propagation path, and correcting the time delay estimation error in the initial path propagation parameters according to the dynamic influence of the UAV motion state on the Doppler frequency shift to generate updated path propagation parameters including path loss gradient and time-frequency joint constraint includes:

[0048] Extract the dynamic Doppler frequency shift characteristics associated with the UAV motion state in the characteristic information of the time delay and Doppler of the radio frequency signal propagation path, combine the mapping relationship between the propeller rotation frequency and the UAV speed to generate the correlation parameter between the Doppler frequency shift and the motion state; according to the correlation parameter, establish a dynamic influence model of the UAV motion acceleration on the multipath propagation time delay, and quantify the non-linear relationship between the time delay estimation error in the initial path propagation parameters and the UAV motion acceleration through the dynamic influence model; based on the dynamic influence model, perform dynamic weight allocation on the time delay estimation value in the initial path propagation parameters, and combine the allocation result with the loss gradient distribution of the radio frequency signal by different materials in the building complex shielding area to generate the path propagation parameters after time delay compensation; perform matrix fusion on the path propagation parameters and the time-frequency joint constraint conditions of the radio frequency signal, and eliminate the time-frequency aliasing error caused by the UAV's maneuvering flight during the fusion process to generate updated path propagation parameters including path loss gradient and time-frequency joint constraint.

[0049] Among them, the training process of the dynamic influence model is: By collecting UAV maneuvering flight data (including acceleration , propeller rotation speed ), combining with the Doppler frequency shift formula to invert the motion speed , and using the gradient descent method to construct a quadratic function model of the time delay estimation error and acceleration (for example, when fitting ), and then optimizing the parameters using the least squares method to minimize the prediction error (objective function ), and finally verifying the model accuracy using the measured data of the maneuvering flight (such as when the error ). ).

[0050] This dynamic influence model quantifies the non-linear influence of acceleration on the multipath time delay through the quadratic term (for example increasing from 2 to when increasing from 0.45 ns to 1.65 ns), and corrects the initial time delay based on the dynamic weight allocation rule when ​ Initial and integrate the building material loss gradient such as glass to generate compensation parameters ), and finally, jointly use time-frequency constraints to eliminate the mixing error through orthogonal decomposition (such as frequency shift automatically correct when the over-tolerance is 150 Hz).

[0051] 1034. Based on the spatio-temporal synchronization alignment result, combine the radio frequency signal with the reflector distribution characteristics in the three-dimensional millimeter-wave imaging map to generate a spatio-temporally synchronized radio frequency fingerprint coding sequence.

[0052] In the above solution, the scattering phase offset is the phase distortion amount caused by the building material during the scattering process of the radio frequency signal, which is used to compensate for the phase distortion of the multi-path propagation path. The dynamic attenuation compensation function is a mathematical function constructed based on the scattering phase offset, which is used to correct the path loss caused by the attenuation of the radio frequency signal due to the building material. The time-frequency domain joint decomposition is a technique for simultaneously analyzing the time-domain waveform and frequency-domain spectrum characteristics of the radio frequency signal to separate different signal components. The harmonic component is a periodic electromagnetic radiation signal generated during the operation of the drone propeller motor, and its frequency is an integer multiple of the motor fundamental frequency. The frequency hopping residual component is a discontinuous frequency band signal remaining during the frequency hopping switching process of the drone communication module, which characterizes the frequency hopping mode characteristics. The spatio-temporal synchronization alignment is a process of spatio-temporal correlation matching between the timing characteristics of the radio frequency signal and the spatial position of the millimeter-wave imaging. The radio frequency fingerprint coding sequence is a spatio-temporal correlation feature sequence that integrates harmonic components, frequency hopping residual components, and millimeter-wave spatial constraints.

[0053] In the embodiment of the present application, first, through step 1031, deploy a broadband radio frequency sensor array in the building complex shielding area to collect the original waveform of the multi-path propagated radio frequency signal in real time. Based on the scattering phase offset generated in step 101, construct a dynamic attenuation compensation function H(f) = e^{jΔφ(f)}·A(f)^{-1}, where Δφ is the phase offset and A(f) is the frequency-dependent attenuation coefficient, perform phase rotation and amplitude compensation on the original signal to eliminate the signal distortion caused by the building material. For example, for the 5.8 GHz band signal, reconstruct the propagation time delay difference between the direct path and the multi-path reflection path through the reverse ray tracing algorithm, and combine the phase gradient alignment technology to output the compensated radio frequency signal sequence.

[0054] Subsequently, the compensated RF signal sequence is subjected to joint time-frequency domain decomposition through step 1032: Adaptive wavelet packet transform is used to separate the periodic harmonic components generated by the propeller motor and the discontinuous pulse components remaining from the frequency hopping of the communication module in the time-frequency plane. Specifically, the instantaneous frequency curve of the harmonic components is extracted through time-frequency ridge tracking technology, and the frequency band switching interval of the frequency hopping remaining components is identified in combination with the Viterbi state transition algorithm. For example, the hopping interval from 5.8 GHz to 2.4 GHz is 50 ms, generating a transient harmonic feature set containing harmonic amplitudes and frequency hopping time series.

[0055] Meanwhile, through step 1033, based on the multipath interference suppression parameters in the 3D millimeter-wave imaging map, such as the path attenuation coefficient < 3 dB / m, a geometric mapping relationship between the RF signal propagation path and the millimeter-wave space grid is established: The incident angle of the RF signal is analyzed based on the direction-of-arrival estimation algorithm, and in combination with the millimeter-wave imaging grid coordinates, the delay information of the harmonic components is mapped to the 3D space, and the time series features of the frequency hopping remaining components are aligned with the millimeter-wave imaging refresh period (such as 10 Hz) through the dynamic time warping algorithm, generating spatio-temporal synchronization alignment parameters.

[0056] Finally, through step 1034, feature fusion of the harmonic components and the frequency hopping remaining components is performed based on the spatio-temporal synchronization alignment parameters: The spatial density clustering algorithm is used to perform spatial filtering on the reflector distribution area in the millimeter-wave imaging (such as the dense area of the metal frame), and in combination with the hidden Markov model to perform state modeling on the frequency hopping pattern, generating a spatio-temporal synchronized RF fingerprint coding sequence that combines X, Y, Z space coordinates, harmonic amplitudes, and frequency hopping intervals. For example, the 5.8 GHz frequency hopping remaining pulse is associated with the reflection component in the hovering area in the millimeter-wave imaging, generating a unique RF fingerprint coding sequence: "F_5.8G_50ms_35.2_78.6_12.3".

[0057] In practical applications, distributed RF sensors and millimeter-wave radar arrays are deployed in the sheltered area of an urban commercial complex (where the glass curtain wall accounts for 60% and the steel structure corridors are dense). In step 1031, dynamic attenuation compensation is performed on the 5.8 GHz RF signal to eliminate the 120° phase shift and 15 dB path loss caused by the steel structure corridors, and the direct path signal is reconstructed; in step 1032, the 1.2 kHz harmonic component (amplitude -30 dBm) of the propeller motor and the 5.8 GHz / 2.4 GHz dual-band pulses (interval 50 ms) remaining after frequency hopping are extracted; in step 1033, it is determined by millimeter-wave imaging that the UAV hovers in the area 3 meters behind the glass curtain wall (coordinates X = 35.2, Y = 78.6, Z = 12.3), and the harmonic time delay (8 ns) is mapped to this coordinate; in step 1034, an RF fingerprint code "F_5.8G_50ms_35.2_78.6_12.3" that combines spatial coordinates, frequency hopping interval, and harmonic amplitude is generated as the unique RF fingerprint code sequence of the target.

[0058] The overall solution of step 103 above improves the quality of RF signals through dynamic attenuation compensation and multipath reconstruction, breaking through the harmonic distortion caused by building material interference; time-frequency joint decomposition accurately separates the power and communication characteristics of the UAV, solving the problem of dynamic capture of the remaining components after frequency hopping; the space-time synchronization alignment mechanism maps the RF timing characteristics to the millimeter-wave spatial coordinates, enhancing the target correlation; the finally generated RF fingerprint code sequence combines multi-dimensional characteristics of space, time, and frequency domain, significantly improving the feature recognition and anti-confusion capabilities of hidden UAVs in complex sheltered environments, providing high-robustness recognition support for urban low-altitude security.

[0059] 104. Based on the set of building material reflection parameters, construct a coupling model of millimeter-wave and RF, and identify hidden UAVs in the sheltered area of urban building complexes through cross-validation of the reflection component, the harmonic component, and the RF fingerprint code sequence.

[0060] Optionally, step 104 may specifically include the following steps: 1041. Based on the multi-band attenuation gradient and the space-time synchronization constraint conditions in the RF fingerprint code sequence, establish a dynamic correlation matrix between the intensity of the millimeter-wave reflection component and the amplitude of the RF harmonic component, and generate an initial feature mapping relationship of the coupling model of millimeter-wave and RF according to the dynamic correlation matrix; 1042. According to the spatial distribution density of reflectors and the material attenuation difference in the three-dimensional millimeter-wave imaging map, and in combination with the initial feature mapping relationship, perform multi-modal feature fusion on the dynamic correlation matrix to construct a harmonic component amplitude compensation function under the constraint of millimeter-wave spatial resolution; 1043. Use the harmonic component amplitude compensation function to correct the harmonic attenuation distortion caused by building shielding in the RF fingerprint coding sequence, and extract the spatio-temporal consistency constraint parameters of the reflection characteristics of the UAV composite material and the RF harmonic component amplitude based on the corrected harmonic attenuation distortion. 1044. Perform multi-dimensional joint verification on the reflection component distribution in the three-dimensional millimeter-wave imaging map, the hopping residue pattern of the RF harmonic component amplitude, and the RF fingerprint coding sequence. The verification process eliminates the feature confusion between the metal frame inside the building and the UAV composite material, and completes the spatial positioning and identification of the urban concealed UAV.

[0061] Among them, step 1044 may specifically include the following process: Based on the spatial distribution correlation between the millimeter-wave reflection component and the RF harmonic component in the spatio-temporal consistency constraint parameters, extract the steady-state reflection characteristics of the metal frame inside the building and the transient scattering characteristics of the UAV composite material, and generate a joint distribution map of the reflection component and the harmonic component; According to the spatial overlap region between the metal frame inside the building and the UAV composite material in the joint distribution map, combined with the hopping residue pattern of the RF harmonic component amplitude, construct a metal reflection suppression function and a composite material enhancement function, and generate a set of feature confusion elimination parameters; Use the set of feature confusion elimination parameters to dynamically assign weights to the reflection component distribution in the three-dimensional millimeter-wave imaging map, and combine the weighted reflection component distribution, the time evolution law of the hopping residue pattern of the RF harmonic component amplitude, and the RF fingerprint coding sequence to generate joint verification parameters that fuse spatial positioning constraints and harmonic feature identification; Based on the joint verification parameters, perform multi-dimensional iterative optimization on the joint distribution map. The optimization process eliminates the feature confusion between the metal frame inside the building and the UAV composite material, and completes the spatial positioning and identification of the urban concealed UAV.

[0062] In the above solution, the dynamic correlation matrix is a matrix that represents the non-linear mapping relationship between the millimeter-wave reflection component intensity and the RF harmonic component amplitude, and is used to quantify the coupling characteristics of the two in the spatio-temporal dimension. The harmonic component amplitude compensation function is a function constructed based on the millimeter-wave spatial resolution constraint, and is used to correct the RF harmonic amplitude attenuation distortion caused by building shielding. The spatio-temporal consistency constraint parameter is a parameter that describes the correlation between the reflection characteristics of the UAV composite material and the RF harmonic component in the spatio-temporal dimension, and is used to eliminate feature confusion. The multi-dimensional joint verification is a multi-modal feature cross-verification mechanism based on the reflection component distribution, the hopping residue pattern, and the RF fingerprint coding sequence.

[0063] In the embodiments of the present application, first, based on the multi-band attenuation gradients in the building material reflection parameter set, such as the 24 GHz band attenuation gradient α = 2.3 dB / m, and the spatio-temporal synchronization constraint conditions in the RF fingerprint coding sequence, such as coordinates X = 35.2, Y = 78.6, Z = 12.3 and timestamp T = 100 ms, a non-linear initial feature mapping relationship between the millimeter-wave reflection component intensity and the RF harmonic component amplitude is established using the kernel regression algorithm. Specifically, with the millimeter-wave reflection intensity as the input and the harmonic amplitude as the output, the dynamic correlation matrix is calculated through the Gaussian kernel function K(S_i, H_j) = exp(-||S_i - H_j||² / 2σ²), where σ is the bandwidth parameter, S_i is the reflection intensity sample, and H_j is the harmonic amplitude sample. For example, for the hovering area of the drone (reflection intensity 12 dBm), the dynamic correlation matrix outputs a matching harmonic amplitude of -28 dBm, generating an initial feature mapping relationship table.

[0064] Subsequently, through step 1042, according to the spatial distribution density of the reflectors and the material attenuation differences in the millimeter-wave imaging map, such as the metal attenuation gradient α = 15 dB / m and the concrete α = 3 dB / m, the tensor decomposition technique is used to decompose the dynamic correlation matrix into spatial distribution factors, material attenuation factors, and time sequence factors, and combined with the millimeter-wave spatial resolution constraint, a harmonic component amplitude compensation function H'(f) is constructed. For example, for the concrete shielding area with a spatial resolution of 0.5 meters, the compensation function H'(f) = H(f)·e^{βΔα} is calculated, where β = 0.8 is the material attenuation difference coefficient and Δα = 1.2 is the spatial resolution attenuation correction amount, and the harmonic amplitude after compensation is increased by 3 dB.

[0065] Meanwhile, through step 1043, the compensation function is used to correct the harmonic attenuation distortion caused by building shielding in the RF fingerprint coding sequence, the noise of the corrected harmonic amplitude is suppressed by adaptive Kalman filtering, and the spatio-temporal correlation with the reflection characteristics of the drone composite material (such as the transient scattering intensity of 8 dB) is extracted. For example, within the time window T = 100 ms, the sliding window correlation coefficient ρ between the harmonic amplitude and the reflection intensity is calculated to be ρ > 0.8, generating a spatio-temporal consistency constraint parameter table.

[0066] Finally, through step 1044, based on the spatio-temporal consistency constraint parameter table, multi-dimensional joint verification is performed on the reflection component distribution, frequency hopping residue pattern, and RF fingerprint coding sequence in the millimeter-wave imaging map: the evidence theory is used to fuse the reflection component confidence of 0.9, the harmonic amplitude confidence of 0.85, and the frequency hopping pattern confidence of 0.8, and the fuzzy clustering algorithm is used to separate the characteristic confusion areas of the metal frame with a clustering center reflection intensity > 18 dBm and the drone composite material with a clustering center harmonic amplitude > -30 dBm, and finally the drone spatial coordinates and identification labels are output.

[0067] It should be noted that the coupling model is a training model, and its training process includes the following steps: First, based on the multi-band attenuation gradient in the building material reflection parameter set (such as the 24 GHz band attenuation gradient α = 2.3 dB / m) and the spatio-temporal synchronization constraint conditions of the RF fingerprint coding sequence (such as coordinates X = 35.2, Y = 78.6, Z = 12.3 and timestamp T = 100 ms), a non-linear dynamic correlation matrix between the millimeter-wave reflection component intensity and the RF harmonic component amplitude is established using the kernel regression algorithm. Specifically, with the millimeter-wave reflection intensity as the input and the harmonic amplitude as the output, through the Gaussian kernel function ) calculate the mapping relationship (where is the bandwidth parameter, is the reflection intensity sample, is the harmonic amplitude sample), and generate an initial feature mapping relationship table (for example, the reflection intensity of 12 dBm in the hovering area matches the harmonic amplitude of -28 dBm).

[0068] Subsequently, according to the spatial distribution density of the reflectors and the material attenuation difference in the three-dimensional millimeter-wave imaging atlas (such as the metal attenuation gradient , concrete ), the dynamic correlation matrix is decomposed into a spatial distribution factor, a material attenuation factor, and a time series factor using tensor decomposition technology, and combined with the millimeter-wave spatial resolution constraint (such as 0.5 m resolution) to construct a harmonic component amplitude compensation function (where is the material attenuation difference coefficient, is the spatial resolution attenuation correction amount, and the harmonic amplitude is increased by 3 dB after compensation).

[0069] Finally, using the corrected harmonic amplitude, reflection component distribution, and RF fingerprint coding sequence as training data, the coupling law between millimeter-wave and RF signals is learned through a deep learning model (such as a multi-modal fusion network). After iterative optimization, the model output converges with the measured error, and the trained model is defined as the coupling model.

[0070] The coupling model is based on the set of reflection parameters of building materials. It maps the non - linear relationship between the millimeter - wave reflection intensity and the RF harmonic amplitude through a dynamic correlation matrix (for example, a reflection intensity of 12 dBm corresponds to a harmonic amplitude of - 28 dBm), and uses the harmonic component amplitude compensation function to correct the harmonic attenuation distortion caused by building shielding (such as compensating 3 dB in the concrete shielding area); based on the corrected harmonic amplitude, it extracts the spatio - temporal consistency constraint parameters between the transient scattering characteristics (such as intensity 8 dB) of the UAV composite material and the harmonic amplitude (such as the sliding - window correlation coefficient ρ>0.8), combines the metal reflection suppression function (suppressing the steady - state metal frame with a reflection intensity>18 dBm) and the composite material enhancement function (enhancing the transient frequency - hopping residual mode with a harmonic amplitude>-30 dBm) to eliminate feature confusion; finally, it fuses the confidence of the reflection component distribution (0.9), the confidence of the harmonic amplitude (0.85), and the confidence of the frequency - hopping mode of the RF fingerprint coding sequence (0.8), and separates the metal and UAV feature regions through the fuzzy clustering algorithm, outputting the spatial coordinates of the UAV (such as X = 35.2, Y = 78.6, Z = 12.3) and the identification label, achieving the identification of concealed targets with a positioning error <0.5 meters.

[0071] In practical applications, in the shielding area of urban transportation hubs, such as steel - structure ceilings and dense concrete columns, step 1041 generates a dynamic correlation matrix based on the 60 - GHz frequency - band attenuation gradient α = 1.8 dB / m and the spatio - temporal constraints X = 22.5, Y = 45.8, Z = 8.2, T = 150 ms in the RF fingerprint coding sequence, mapping a reflection intensity of 10 dBm to a harmonic amplitude of - 26 dBm; step 1042 optimizes the matrix through tensor decomposition, constructs a compensation function to correct the - 6 - dB harmonic attenuation caused by concrete columns, and outputs a corrected amplitude of - 20 dBm; step 1043 extracts the spatio - temporal consistency parameter ρ = 0.85 between the harmonic amplitude and the reflection intensity; step 1044 fuses multi - modal confidences, eliminates the reflection interference of the steel - structure ceiling, locates the UAV at the coordinates X = 22.5, Y = 45.8, Z = 8.2 and labels it as a "high - risk target".

[0072] The overall solution of step 104 above realizes the deep coupling of millimeter - wave and RF data through the construction of a dynamic correlation matrix and multi - modal tensor decomposition, breaking through the perception limitations of a single modality; the harmonic component amplitude compensation function accurately corrects the signal attenuation distortion caused by building shielding, enhancing feature consistency; the spatio - temporal consistency constraint parameters fuse the spatio - temporal correlation between reflection and harmonics, solving the problem of target confusion under the interference of complex materials; the multi - dimensional joint verification mechanism fuses spatial, temporal, and frequency - domain features through evidence theory and fuzzy clustering, and finally realizes the high - confidence positioning and identification of concealed UAVs, providing anti - interference and highly robust technical support for urban low - altitude security.

[0073] The following is a complete embodiment for steps 101 to 104, as Figure 3 shown below: Suppose there are covert drone activities using building shielding for illegal photography in the core business district complex where the proportion of glass curtain walls is 60% and steel structure link corridors are dense in a certain city. The reflection characteristics of the metal frames and the composite materials of the drones in the area are highly similar, and the multipath interference is serious.

[0074] In step 101, a 0.1-meter resolution lidar on the drone scans the building complex to generate building geometric shape data, including building spacing and surface curvature; a near-field microwave flaw detector with adjustable frequency from 1 to 100 GHz measures the dielectric constant distributions of the glass curtain wall (ε = 5.2 - j0.7) and the steel structure (ε = 1e6 - j1e7); a multi-band attenuation gradient is generated based on the finite-difference time-domain simulation. For example, the glass attenuation gradient α = 1.8 dB / m and the scattering phase offset Δφ = 25° at the 94 GHz band, and a set of building material reflection parameters is output.

[0075] In step 102, the 94 GHz band with an attenuation gradient α = 1.8 dB / m is selected as the main transmission band, supplemented by the 60 GHz band with a metal attenuation gradient α = 15 dB / m; a frequency-modulated continuous wave signal is transmitted, and the reflection intensities of the steady-state reflection component of the steel structure and the transient scattering component of the carbon fiber fuselage of the drone are separated by time-frequency ridge tracking, which are 20 dBm and 8 dBm respectively; a multipath interference suppression parameter is constructed, with a path attenuation coefficient λ = 1.5 dB / m, and a three-dimensional millimeter-wave imaging map is generated, marking that the drone hovers behind the glass curtain wall, with coordinates X = 102.3, Y = 55.7, Z = 45.2.

[0076] In step 103, a 5.8 GHz radio frequency signal is synchronously collected, and the path loss is compensated using the scattering phase offset Δφ = 25°. For example, the glass curtain wall causes a -10 dB attenuation; the harmonic components of the propeller motor are extracted through adaptive wavelet packet transform, with a fundamental frequency of 1.2 kHz and an amplitude of -28 dBm, and the frequency hopping residual component is extracted as 5.8 GHz → 2.4 GHz, with an interval of 50 ms; combined with the multipath interference suppression parameters in the millimeter-wave imaging, a spatio-temporal synchronous radio frequency fingerprint code "F_5.8G_50ms_102.3_55.7_45.2" is generated.

[0077] In step 104, a millimeter-wave and radio frequency coupling model is constructed to dynamically correlate the reflection intensity and the harmonic amplitude; the confidence levels of the reflection component, the harmonic component, and the radio frequency fingerprint code are fused through the D-S theory, which are 0.9 / 0.85 / 0.8; the steel structure interference is eliminated by fuzzy clustering. For example, in the area where the reflection intensity > 18 dBm, and finally the drone is identified and located at coordinates X = 102.3, Y = 55.7, Z = 45.2.

[0078] This application optimizes the millimeter-wave band based on the material attenuation gradient, breaks through the limitation of insufficient signal penetration ability in a single band, and significantly improves the target separation accuracy in complex building environments; through time-frequency joint analysis and radio frequency fingerprint coding, it effectively suppresses metal structure reflections and multipath propagation interference, and enhances the ability to capture transient characteristics of hidden targets; by integrating the coupling model of millimeter-wave spatial resolution and radio frequency timing characteristics, it solves the problem of feature confusion in non-line-of-sight scenarios and realizes high-precision positioning and robust identification of unmanned aerial vehicles.

[0079] Figure 2 FIG. is a schematic structural diagram of an urban hidden unmanned aerial vehicle identification system provided by an embodiment of this application, as Figure 2 shown. The system includes: An acquisition module 21, configured to obtain data on the geometric form and material dielectric constant distribution of building structures in the urban building complex covered by the activity area of the unmanned aerial vehicle, and generate a set of building material reflection parameters including multi-band attenuation gradients and scattering phase offsets through a dynamic reflection attenuation model; A screening module 22, configured to screen a combination of millimeter-wave bands that match the dynamic reflection attenuation characteristics based on the set of building material reflection parameters, transmit millimeter-wave signals to the building complex shielding area, separate the reflection components of metal components and unmanned aerial vehicle composite materials according to the echo signals, and generate a three-dimensional millimeter-wave imaging map including multipath interference suppression parameters; An extraction module 23, configured to synchronously collect radio frequency signals in the building complex shielding area, compensate for path loss through the scattering phase offset, extract harmonic components of the unmanned aerial vehicle propeller motor and hopping residue components of the communication module, and combine the radio frequency signals with the multipath interference suppression parameters in the three-dimensional millimeter-wave imaging map to generate a spatio-temporally synchronized radio frequency fingerprint coding sequence; An identification module 24, configured to construct a coupling model of millimeter-wave and radio frequency based on the set of building material reflection parameters, and identify hidden unmanned aerial vehicles in the urban building complex shielding area through cross-verification of the reflection components, the harmonic components, and the radio frequency fingerprint coding sequence.

[0080] Figure 2 The described urban hidden unmanned aerial vehicle identification system can execute Figure 1 the urban hidden unmanned aerial vehicle identification method described in the embodiment shown. Its implementation principle and technical effects will not be elaborated again. For the urban hidden unmanned aerial vehicle identification system in the above embodiment, the specific manners in which each module and unit perform operations have been described in detail in the embodiment related to this method, and will not be elaborated here.

[0081] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than limiting them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. An urban stealth drone identification method, characterized in that, Including: In the urban building complex covered by the UAV activity area, obtain the geometric form of the building structure and the data of the dielectric constant distribution of the materials, and generate a set of building material reflection parameters including multi-band attenuation gradients and scattering phase offsets through a dynamic reflection attenuation model; Based on the set of building material reflection parameters, screen the millimeter-wave frequency band combinations that match the dynamic reflection attenuation characteristics, transmit millimeter-wave signals to the building complex shielding area, separate the reflection components of metal parts and UAV composite materials according to the echo signals, and generate a three-dimensional millimeter-wave imaging map including multi-path interference suppression parameters; Synchronously collect the radio frequency signals in the building complex shielding area, compensate for the path loss through the scattering phase offset, extract the harmonic components of the UAV propeller motor and the hopping residue components of the communication module, and combine the radio frequency signals with the multi-path interference suppression parameters in the three-dimensional millimeter-wave imaging map to generate a spatio-temporally synchronized radio frequency fingerprint coding sequence; Based on the set of building material reflection parameters, construct a coupling model of millimeter-wave and radio frequency, and identify the concealed UAVs in the building complex shielding area through the cross-validation of the reflection components, the harmonic components and the radio frequency fingerprint coding sequence.

2. The method according to claim 1, characterized in that The separating the reflection components of metal parts and UAV composite materials according to the echo signals and generating a three-dimensional millimeter-wave imaging map including multi-path interference suppression parameters includes: Conduct a joint time-frequency domain analysis on the echo signals, separate the steady-state reflection components of metal parts and the transient scattering components of UAV composite materials, and construct multi-path interference suppression parameters in combination with the attenuation gradient distribution in the set of building material reflection parameters; Use the multi-path interference suppression parameters to parametrically filter the transient scattering components, eliminate the aliased reflections caused by multi-path propagation in the building complex shielding area, and visualize the multi-path interference suppression parameters and the spatial distribution characteristics of the UAV composite materials to generate a three-dimensional millimeter-wave imaging map.

3. The method according to claim 1, characterized in that, The synchronously collecting the radio frequency signals in the building complex shielding area, compensating for the path loss through the scattering phase offset, and extracting the harmonic components of the UAV propeller motor and the hopping residue components of the communication module includes: Compensate for the path loss through the scattering phase offset, construct a dynamic attenuation compensation function for the radio frequency signal propagation path, reconstruct the multi-path propagation sequence of the radio frequency signals collected in the building complex shielding area, and eliminate the scattering phase distortion of the radio frequency signals by the building materials; Conduct a joint time-frequency domain decomposition on the adjusted radio frequency signals, separate the harmonic components generated during the operation of the UAV propeller motor and the hopping residue components remaining during the hopping switching process of the communication module, and extract a set of transient harmonic characteristics associated with the UAV motion state.

4. The method according to claim 3, characterized in that, Combining the radio frequency signals with the multi-path interference suppression parameters in the three-dimensional millimeter-wave imaging map to generate a spatio-temporally synchronized radio frequency fingerprint coding sequence includes: According to the multi-path interference suppression parameters in the three-dimensional millimeter-wave imaging map, establish a mapping relationship between the radio frequency signal propagation path and the millimeter-wave imaging spatial position, and perform spatio-temporal synchronization alignment on the harmonic components and the hopping residue components according to the mapping relationship. Based on the spatio-temporal synchronization alignment result, combining the radio frequency signal and the reflector distribution characteristics in the three-dimensional millimeter-wave imaging map, a spatio-temporally synchronized radio frequency fingerprint coding sequence is generated.

5. The method according to claim 3, characterized in that The method for establishing the mapping relationship between the radio frequency signal propagation path and the millimeter-wave imaging spatial position according to the multipath interference suppression parameter in the three-dimensional millimeter-wave imaging map, and performing spatio-temporal synchronization alignment on the harmonic component and the frequency hopping residual component according to the mapping relationship includes: Based on the multipath interference suppression parameter in the three-dimensional millimeter-wave imaging map, analyzing the reflector distribution characteristics and the millimeter-wave signal attenuation coefficient in the three-dimensional millimeter-wave imaging map, and establishing the geometric topology mapping relationship between the radio frequency signal propagation path and the millimeter-wave imaging spatial grid; According to the geometric topology mapping relationship, combining the characteristic information of the time delay and Doppler of the radio frequency signal propagation path, constructing a multipath propagation path topology model in the building complex shielding area, and the multipath propagation path topology model associates the reflector position in the millimeter-wave imaging spatial grid with the geometric constraint conditions of the radio frequency signal propagation path; Extracting the timestamp sequence in the transient harmonic feature set and the frequency domain hopping interval of the frequency hopping residual component, and performing spatio-temporal reference alignment on the timestamp sequence and the frequency domain hopping interval based on the reflector position and geometric constraint conditions associated with the multipath propagation path topology model; Using the update rate of the millimeter-wave imaging spatial grid to perform dynamic interpolation compensation on the spatio-temporal reference alignment result, generating spatio-temporal constraint parameters synchronized with the UAV motion state and the communication frequency hopping mode, and completing the spatio-temporal synchronization alignment of the harmonic component and the frequency hopping residual component.

6. The method according to claim 5, characterized in that The method for constructing the multipath propagation path topology model in the building complex shielding area according to the geometric topology mapping relationship, combining the characteristic information of the time delay and Doppler of the radio frequency signal propagation path, and the multipath propagation path topology model associates the reflector position in the millimeter-wave imaging spatial grid with the geometric constraint conditions of the radio frequency signal propagation path includes: Analyzing the correlation between the reflector spatial position and the millimeter-wave signal attenuation coefficient in the geometric topology mapping relationship, and combining the shielding weights of each reflector in the building complex shielding area on the radio frequency signal propagation path to generate initial path propagation parameters; Combining the characteristic information of the time delay and Doppler of the radio frequency signal propagation path, and correcting the time delay estimation error in the initial path propagation parameters according to the dynamic influence of the UAV motion state on the Doppler frequency shift, generating updated path propagation parameters including path loss gradient and time-frequency joint constraints; Based on the updated path propagation parameters, performing ray tracing modeling on the multipath signal propagation path in the building complex shielding area, and generating a set of path clusters matching the reflector position in the millimeter-wave imaging spatial grid; Quantify the attenuation ratio of the direct path and the multipath reflection path of the radio frequency signal propagation path according to the overlapping area distribution between the path cluster set and the reflector positions in the millimeter-wave imaging space grid, and then construct a multipath propagation path topology model. Associate the multipath propagation path topology model with the geometric constraint conditions of the reflector positions in the millimeter-wave imaging space grid and the radio frequency signal propagation path.

7. The method according to claim 6, characterized in that, Combining the characteristic information of the time delay and Doppler of the radio frequency signal propagation path, and correcting the time delay estimation error in the initial path propagation parameters according to the dynamic influence of the UAV motion state on the Doppler frequency shift, to generate updated path propagation parameters including path loss gradient and time-frequency joint constraints, including: Extract the Doppler frequency shift dynamic characteristics associated with the UAV motion state in the characteristic information of the time delay and Doppler of the radio frequency signal propagation path, and combine the mapping relationship between the propeller rotation frequency and the UAV speed to generate the correlation parameters between the Doppler frequency shift and the motion state; According to the correlation parameters, establish a dynamic influence model of the UAV motion acceleration on the multipath propagation time delay, and quantify the non-linear relationship between the time delay estimation error in the initial path propagation parameters and the UAV motion acceleration through the dynamic influence model; Based on the dynamic influence model, perform dynamic weight allocation on the time delay estimation value in the initial path propagation parameters, and combine the allocation result with the loss gradient distribution of the radio frequency signal by different materials in the building complex shielding area to generate path propagation parameters after time delay compensation; Perform matrix fusion on the path propagation parameters and the time-frequency joint constraint conditions of the radio frequency signal. The fusion process eliminates the time-frequency aliasing error caused by the UAV's maneuvering flight, and generates updated path propagation parameters including path loss gradient and time-frequency joint constraints.

8. The method according to claim 1, wherein Based on the set of building material reflection parameters, construct a coupling model of millimeter-wave and radio frequency. Identify the concealed UAV in the urban building complex shielding area through the cross-validation of the reflection component, the harmonic component, and the radio frequency fingerprint coding sequence, including: Based on the multi-band attenuation gradient and the spatio-temporal synchronization constraint conditions in the radio frequency fingerprint coding sequence, establish a dynamic correlation matrix between the intensity of the millimeter-wave reflection component and the amplitude of the radio frequency harmonic component, and generate the initial characteristic mapping relationship of the coupling model of millimeter-wave and radio frequency according to the dynamic correlation matrix; According to the spatial distribution density and material attenuation difference of the reflectors in the three-dimensional millimeter-wave imaging atlas, and combining the initial characteristic mapping relationship, perform multi-modal feature fusion on the dynamic correlation matrix, and construct a harmonic component amplitude compensation function under the constraint of the millimeter-wave spatial resolution; Use the harmonic component amplitude compensation function to correct the harmonic attenuation distortion caused by building shielding in the radio frequency fingerprint coding sequence, and extract the spatio-temporal consistency constraint parameters between the reflection characteristics of the UAV composite material and the amplitude of the radio frequency harmonic component based on the corrected harmonic attenuation distortion. Based on the spatio-temporal consistency constraint parameters, perform multi-dimensional joint verification on the reflection component distribution in the three-dimensional millimeter-wave imaging map, the hopping residue pattern of the RF harmonic component amplitude, and the RF fingerprint coding sequence. The verification process eliminates the feature confusion between the internal metal frame of the building and the composite material of the UAV, and completes the spatial positioning and identification of the urban stealth UAV.

9. The method according to claim 8, wherein The multi-dimensional joint verification of the reflection component distribution in the three-dimensional millimeter-wave imaging map, the hopping residue pattern of the RF harmonic component amplitude, and the RF fingerprint coding sequence based on the spatio-temporal consistency constraint parameters, and the verification process eliminates the feature confusion between the internal metal frame of the building and the composite material of the UAV, and completes the spatial positioning and identification of the urban stealth UAV, including: Based on the spatial distribution correlation between the millimeter-wave reflection component and the RF harmonic component in the spatio-temporal consistency constraint parameters, extract the steady-state reflection characteristics of the internal metal frame of the building and the transient scattering characteristics of the composite material of the UAV, and generate a joint distribution map of the reflection component and the harmonic component; According to the spatial overlapping area between the internal metal frame of the building and the composite material of the UAV in the joint distribution map, combined with the hopping residue pattern of the amplitude of the RF harmonic component, construct a metal reflection suppression function and a composite material enhancement function, and generate a set of feature confusion elimination parameters; Use the set of feature confusion elimination parameters to perform dynamic weight allocation on the reflection component distribution in the three-dimensional millimeter-wave imaging map, and combine the allocated reflection component distribution, the time evolution law of the hopping residue pattern of the RF harmonic component amplitude, and the RF fingerprint coding sequence to generate joint verification parameters that fuse spatial positioning constraints and harmonic feature identification; Based on the joint verification parameters, perform multi-dimensional iterative optimization on the joint distribution map. The optimization process eliminates the feature confusion between the internal metal frame of the building and the composite material of the UAV, and completes the spatial positioning and identification of the urban stealth UAV.

10. An urban stealth drone identification system, characterized in that, Including: An acquisition module, used to obtain the geometric shape and material dielectric constant distribution data of the building structure in the urban building complex covered by the UAV activity area, and generate a set of building material reflection parameters including multi-band attenuation gradients and scattering phase offsets through a dynamic reflection attenuation model; A screening module, used to screen the millimeter-wave frequency band combinations that match the dynamic reflection attenuation characteristics based on the set of building material reflection parameters, transmit millimeter-wave signals to the building complex shielding area, and separate the reflection components of the metal components and the UAV composite material according to the echo signals, and generate a three-dimensional millimeter-wave imaging map including multi-path interference suppression parameters; An extraction module, used to synchronously collect the RF signals in the building complex shielding area, compensate the path loss through the scattering phase offset, extract the harmonic components of the UAV propeller motor and the hopping residue components of the communication module, and combine the RF signals with the multi-path interference suppression parameters in the three-dimensional millimeter-wave imaging map to generate a spatio-temporally synchronized RF fingerprint coding sequence; An identification module, configured to construct a coupling model of millimeter wave and radio frequency based on the set of building material reflection parameters, and identify the concealed drones in the shielding area of urban building complexes through the cross-validation of the reflection component, the harmonic component and the radio frequency fingerprint coding sequence.

Images