Tracking methods, devices, computer equipment, and storage media for low-altitude unmanned aerial vehicles (UAVs)

Abstract

This application relates to a method, apparatus, computer equipment, and storage medium for tracking low-altitude unmanned aerial vehicles (UAVs). The method includes: acquiring signals from a target UAV in a target area to obtain raw UAV signals; detecting and removing errors from the raw UAV signals to obtain clean target UAV signals; identifying the clean target UAV signals to determine the model category of the target UAV; determining whether the clean target UAV signals are decipherable based on the model category to obtain a determination result; if the determination result is decipherable, locating the target UAV based on the clean target UAV signals to obtain position information; and predicting and tracking the trajectory of the target UAV based on the position information. This application has the advantage of improving the positioning accuracy and tracking effect of low-altitude UAVs in complex electromagnetic environments.

Description

Technical Field

[0001] This application relates to the field of unmanned aerial vehicle (UAV) monitoring technology, and in particular to a method, apparatus, computer equipment, and storage medium for tracking low-altitude UAVs. Background Technology

[0002] With the continuous development of artificial intelligence technology, the application of drones in the low-altitude field is becoming increasingly mature, and the requirements for detecting and tracking the trajectory of low-altitude drones are becoming more stringent. When drones operate at low altitudes in urban areas, the electromagnetic environment in these areas is complex due to the dense urban population, concentrated civil aviation routes, and comprehensive electromagnetic equipment. The signals of low-altitude drones are relatively weak and difficult to detect, making real-time positioning and tracking of target drones quite challenging.

[0003] Existing drone tracking technologies suffer from the following main problems: First, they struggle to effectively collect and identify weak drone signals in complex electromagnetic environments; second, they lack effective means of decoding drone signals, resulting in insufficient positioning accuracy; and third, current technologies cannot achieve real-time prediction and dynamic tracking of drone trajectories. These issues severely impact the safety supervision of low-altitude drones, particularly in applications such as urban airspace management and protection of critical facilities, necessitating a technological solution capable of achieving precise positioning and intelligent tracking of low-altitude drones.

[0004] How to use the collaborative operation of multiple sensor devices to collect low-altitude UAV signals for the positioning and tracking of target UAVs, and achieve real-time perception of low-altitude UAV signals and real-time tracking of their positions, thereby ensuring the normal flight of UAVs, eliminating potential safety hazards in urban low-altitude airspace, and safeguarding urban low-altitude airspace safety, is a technical problem faced by those skilled in the art. Summary of the Invention

[0005] The purpose of this application is to provide a tracking method, device, computer equipment, and storage medium for low-altitude unmanned aerial vehicles (UAVs) to improve the positioning accuracy and tracking effect of low-altitude UAVs in complex electromagnetic environments.

[0006] To address the aforementioned technical problems, embodiments of this application provide a tracking method for low-altitude unmanned aerial vehicles (UAVs), comprising: The signal of the target drone in the target area is collected to obtain the original drone signal. The original drone signal is then detected and error removed to obtain a clean target drone signal. The clean target drone signal is identified to determine the model category of the target drone; Based on the model category, determine whether the signal of the clean target drone can be decoded, and obtain the determination result; If the judgment result is decipherable, the target drone is located based on the clean target drone signal to obtain location information; The trajectory of the target drone is predicted and tracked based on the location information.

[0007] To address the aforementioned technical problems, embodiments of this application provide a tracking device for a low-altitude unmanned aerial vehicle (UAV), comprising: The signal acquisition module is used to acquire the signal of the target drone in the target area, obtain the original drone signal, and perform detection and error removal on the original drone signal to obtain a clean target drone signal. A model category identification module is used to identify the signal of the clean target drone in order to determine the model category of the target drone; The decoding and judgment module is used to determine whether the signal of the clean target drone can be decoded based on the model category, and to obtain a judgment result; The drone positioning module is used to locate the target drone based on the clean target drone signal if the judgment result is decipherable, and obtain the location information. The trajectory tracking module is used to predict and track the trajectory of the target UAV based on the location information.

[0008] To solve the above-mentioned technical problems, one technical solution adopted by the present invention is to provide a computer device, including one or more processors; and a memory for storing one or more programs, so that the one or more processors implement the low-altitude UAV tracking method described in any one of the above-mentioned methods.

[0009] To solve the above-mentioned technical problems, one technical solution adopted by the present invention is: a computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the tracking method of any one of the above-mentioned low-altitude UAVs.

[0010] This invention provides a method, apparatus, computer device, and storage medium for tracking low-altitude unmanned aerial vehicles (UAVs). The method includes: acquiring signals from a target UAV in a target area to obtain raw UAV signals; detecting and removing errors from the raw UAV signals to obtain clean target UAV signals; identifying the clean target UAV signals to determine the model category of the target UAV; determining whether the clean target UAV signals are decipherable based on the model category to obtain a determination result; if the determination result is decipherable, locating the target UAV based on the clean target UAV signals to obtain location information; and predicting and tracking the trajectory of the target UAV based on the location information. This invention, through a complete process of signal acquisition, model identification, deciphering judgment, positioning, and trajectory tracking, effectively extracts and enhances weak UAV signals in complex electromagnetic environments. Combined with decipherable signal analysis, it achieves high-precision real-time tracking of low-altitude UAVs, offering the advantage of improving the positioning accuracy and tracking effect of low-altitude UAVs in complex electromagnetic environments. Attached Figure Description

[0011] To more clearly illustrate the solutions in this application, the accompanying drawings used in the description of the embodiments of this application will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1 This is a flowchart of an implementation of the tracking method for low-altitude unmanned aerial vehicles provided in this application embodiment; Figure 2 yes Figure 1 The flowchart of the implementation of the first sub-process in the provided low-altitude UAV tracking method; Figure 3 yes Figure 1 The flowchart of the implementation of the second sub-process in the provided low-altitude UAV tracking method; Figure 4 yes Figure 1 The flowchart of the implementation of the third sub-process in the provided low-altitude UAV tracking method; Figure 5 yes Figure 1 Another implementation flowchart of the third sub-process in the provided low-altitude UAV tracking method; Figure 6 yes Figure 1 The implementation flowchart of the fourth sub-process in the provided low-altitude UAV tracking method; Figure 7 This is a schematic diagram of a tracking device for a low-altitude unmanned aerial vehicle provided in an embodiment of this application; Figure 8This is a schematic diagram of the computer device provided in the embodiments of this application. Detailed Implementation

[0013] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains; the terminology used herein in the specification of the application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application; the terms "comprising" and "having," and any variations thereof, in the specification, claims, and foregoing drawings of this application, are intended to cover non-exclusive inclusion. The terms "first," "second," etc., in the specification, claims, or foregoing drawings of this application are used to distinguish different objects, not to describe a particular order.

[0014] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0015] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings.

[0016] The present invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0017] It should be noted that the low-altitude UAV tracking method provided in this application embodiment is generally executed by a server, and correspondingly, the low-altitude UAV tracking device is generally configured in the server.

[0018] In existing technologies, low-altitude drones face complex electromagnetic interference when operating in urban areas, making it difficult for traditional signal acquisition methods to effectively extract weak target signals. Current drone tracking technologies mainly suffer from the following problems: First, they struggle to effectively acquire and identify weak drone signals in complex electromagnetic environments; second, they lack effective means of interpreting drone signals, resulting in insufficient positioning accuracy; and third, existing technologies cannot achieve real-time prediction and dynamic tracking of drone trajectories.

[0019] To address the aforementioned issues, the inventors discovered that urban low-altitude electromagnetic interference exhibits time-frequency domain distribution characteristics, necessitating the establishment of a frequency-band signal processing mechanism. Analysis of the communication characteristics of different UAV models revealed a strong correlation between signal oscillation patterns and model type, which can serve as a classification criterion. For the challenge of locating undecipherable signals, it was observed that time-difference measurement using multi-device collaborative operation can overcome the limitations of single-point positioning. This led to a phased processing strategy: first, eliminating environmental interference to extract effective signals; then, selecting the optimal positioning method through model identification; and finally, achieving dynamic tracking and resource allocation.

[0020] Therefore, this application proposes to collect signals from a target UAV in a target area to obtain raw UAV signals, perform detection and error removal on the raw UAV signals to obtain clean target UAV signals; identify the clean target UAV signals to determine the model category of the target UAV; determine whether the clean target UAV signals are decipherable based on the model category to obtain a determination result; if the determination result is decipherable, locate the target UAV based on the clean target UAV signals to obtain location information; and predict and track the trajectory of the target UAV based on the location information.

[0021] Specifically, a collaborative sensing network is formed by deploying multiple types of sensors to cover the entire frequency band of the target area. Bandpass filtering is applied to the raw collected signals to eliminate base station interference, and wavelet transform is used to detect burst signal characteristics. During the identification phase, signal carrier frequency offset features are extracted and matched against pre-stored feature libraries from manufacturers such as DJI and Autel. When a drone signal with the ADS-B protocol is detected, its broadcast location message is directly parsed. For undecipherable signals using proprietary protocols, three-station time difference positioning is used to calculate spatial coordinates. Finally, the flight trajectory is fitted using kinematic equations, and the radar beam direction is dynamically adjusted to maintain continuous tracking.

[0022] This application effectively improves the signal acquisition probability of UAVs in complex electromagnetic environments and achieves compatible processing of equipment from different manufacturers. Intelligent decision-making through model identification and interpretation optimizes the efficiency of positioning resource allocation. Employing a trajectory prediction method based on multi-source data fusion significantly improves the continuity and accuracy of low-altitude aircraft tracking, providing reliable technical support for urban airspace safety supervision.

[0023] Please see Figure 1 , Figure 1 This paper illustrates one specific implementation of a tracking method for low-altitude unmanned aerial vehicles (UAVs).

[0024] It should be noted that if substantially the same result is obtained, the method of this invention is not based on... Figure 1 Limited to the order of the processes shown, this method includes the following steps: S1: Collect the signal of the target drone in the target area to obtain the original drone signal, and perform detection and error removal on the original drone signal to obtain the clean target drone signal.

[0025] Specifically, the system collects signals from the target drone in the target area via an antenna. These signals include the drone's speed, latitude and longitude, etc., and confirms the corresponding pilot's location information. The system then detects these signals, removes error signals, and transmits the filtered signals to the control center.

[0026] This application enables the sensing and identification of low-altitude electromagnetic signals in complex electromagnetic environments. However, its sensing of UAV wireless links is affected by surrounding electromagnetic interference, terrain obstruction, and multipath propagation. In complex urban electromagnetic environments, using general detection methods may fail to extract the required target signals, making it difficult to effectively distinguish between unauthorized UAVs and those flying normally. This application designs a multi-resolution detection technology for complex electromagnetic environments, enabling deep signal identification and improving target recognition accuracy. This meets the detection needs under conditions of weak signals and low signal-to-noise ratios in urban environments, expanding the detection range. Furthermore, the application features an adaptive design for the signal identification method, meeting the signal sensing requirements of various UAV data transmission systems.

[0027] Among them, detection and error removal refer to eliminating environmental noise interference through signal preprocessing. Specifically, multi-resolution detection technology can be used to achieve joint analysis in the time and frequency domains to separate effective signals from noise components.

[0028] Please see Figure 2 , Figure 2 A specific implementation of step S1 is shown below: S11: Acquire the signal of the target UAV using a sensor antenna array deployed in the target area to obtain the original UAV signal. S12: Detect and filter the original UAV signal to generate a filtered UAV signal. S13: Perform time-frequency domain analysis on the filtered UAV signal using multi-resolution detection technology to remove errors and obtain an initially clean target UAV signal. S14: Enhance the initially clean target UAV signal to obtain the clean target UAV signal.

[0029] Specifically, the sensor antenna array deployed in the target area captures UAV signals through spatial diversity reception, effectively suppressing multipath interference when receiving signals from a single antenna. The detection and filtering process uses a sliding window energy detection algorithm to identify valid signal segments. For example, a threshold value of three times the average energy of the background noise is set, and signal segments below this threshold are deemed invalid and discarded. After filtering, the signals undergo time-domain joint analysis using multi-resolution detection techniques, such as wavelet transform to decompose signal components into different frequency bands, combined with time-domain correlation analysis to remove impulse interference and narrowband noise. The initial clean signal undergoes adaptive filtering, such as adjusting the filter coefficients based on the minimum mean square error criterion to suppress residual broadband noise and improve signal feature discriminability. This application solves the problems of interference superposition and feature distortion in low-altitude UAV signal acquisition under complex electromagnetic environments. Through a multi-stage signal processing flow, it significantly improves signal quality, providing highly reliable data input for subsequent model identification and positioning, ensuring the accuracy and real-time performance of target tracking.

[0030] Among them, a sensor antenna array refers to a signal receiving device formed by arranging multiple antenna elements in a specific geometric structure. This can be achieved through a hybrid deployment of directional and omnidirectional antennas to collect signals covering different spatial directions within a target area. Detection and filtering refer to the initial filtering of the original signal by setting a signal strength threshold or using feature matching algorithms. This can be implemented using sliding window energy detection or matched filter banks to remove significant noise interference or non-UAV signal components. Multi-resolution detection technology refers to the method of jointly analyzing signals at different time and frequency resolutions. This can be implemented using wavelet transform or short-time Fourier transform algorithms to separate time-varying interference and frequency domain aliasing errors superimposed on the signal. Signal enhancement refers to improving the signal-to-noise ratio of the denoised signal. This can be achieved using adaptive filtering or spectral subtraction techniques to recover effective signal features masked by environmental noise.

[0031] S2: Identify the clean target drone signal to determine the model category of the target drone.

[0032] Specifically, based on the differences in the radio frequency signals of the target UAV, such as signal oscillation before and after signal transmission and cyclic preamble, a UAV model identification feature library is established. The identified signals are compared with the signals in the feature library to determine the UAV model category.

[0033] Please see Figure 3 , Figure 3 A specific implementation of step S2 is shown below: S21: Analyze the clean target drone signal to extract the target features of the clean target drone, wherein the target features include signal oscillation features and cyclic code features. S22: Compare the target features with a drone model identification feature database to obtain a comparison result. S23: Determine the model category of the target drone based on the comparison result.

[0034] Specifically, in complex electromagnetic environments, after the clean target UAV signal is analyzed, the signal oscillation characteristics are captured by analyzing the physical layer modulation parameters to obtain the unique waveform characteristics of the UAV signal, such as frequency hopping interval or modulation depth. Cyclic preamble features, also known as "preambles" or "training sequences," are a specific data sequence in communication protocols, primarily used for synchronization and channel estimation. These two features extract complementary information from the physical and protocol layers, respectively. By jointly comparing them with pre-stored model feature vectors in the feature library, mismatches caused by environmental interference due to a single feature can be eliminated. For example, when the signal oscillation characteristics deviate due to multipath effects, the cyclic preamble features can still provide accurate matching criteria through protocol identifiers, thereby improving the reliability of model classification under a dual verification mechanism. This application can accurately identify the specific model category of a target UAV in complex low-altitude electromagnetic environments in cities through joint comparison of dual feature extraction and a standardized feature library, providing a reliable classification basis for subsequent judgment of signal decipherability, thus ensuring the effective execution of the positioning and tracking process.

[0035] Among them, the UAV model identification feature library refers to a database that pre-stores the signal features of known UAV models. Specifically, it can be implemented by using multi-dimensional feature vectors to store the mapping relationship between the signal oscillation parameters of different models and the cyclic preamble sequence, in order to provide a standardized comparison benchmark.

[0036] S3: Determine whether the signal of the clean target drone can be decoded based on the model category, and obtain the determination result.

[0037] Further, step S3 includes: determining whether the model category exists in the list of interpretable models, so as to determine whether the clean target drone signal is interpretable, and obtaining the determination result; if the model category exists in the list of interpretable models, the determination result is interpretable; if the model category does not exist in the list of interpretable models, the determination result is uninterpretable.

[0038] Specifically, in urban low-altitude areas with complex electromagnetic environments, after the sensor array acquires the signal of a target UAV, its model category is first determined through feature extraction and comparison. At this point, a list of decipherable models, serving as a pre-built database of protocol parsing capabilities, is used to quickly verify whether the current model belongs to a known recipientable type. If a match is found, the signal demodulation and decoding process is triggered, directly extracting location information from the communication content; if no decipherable model is found, the system immediately switches to backup solutions such as time-of-flight positioning to avoid tracking interruptions due to unknown protocols. This classification processing mechanism, by predicting the feasibility of signal parsing, achieves dynamic selection of positioning strategies, balancing the parsing efficiency of known models with the tracking assurance of unknown signals. This application effectively solves the problem of not being able to uniformly process multiple types of UAV signals in complex electromagnetic environments. By predicting the feasibility of signal parsing, it achieves intelligent diversion of positioning strategies, avoiding resource waste in the parsing process of known models while ensuring continuous tracking capability for unknown models, significantly improving the environmental adaptability and real-time response of the low-altitude UAV tracking system.

[0039] The decipherable model list refers to a pre-established database of UAV models containing known communication protocol characteristics. This database can be implemented offline or dynamically updated in the cloud, storing model identifiers that have completed signal analysis capability verification. The model category refers to the UAV model classification determined through signal feature comparison, specifically using signal oscillation feature matching or cyclic prefix feature recognition, used to characterize the standardization level of the UAV communication protocol. Signal decipherability judgment refers to the mapping relationship between model category and the decipherable model list, specifically using hash table lookups or database index matching, used to determine whether the conditions for directly parsing the signal content are met.

[0040] Please see Figure 4 , Figure 4 A specific implementation method following step S3 is shown below: S3A: If the judgment result is undecipherable, the target signal is obtained by simultaneously receiving signals emitted by the same target UAV through multiple time-difference positioning devices. S3B: The time difference between the arrival times of the signal at different time-difference positioning devices is calculated based on the target signal. S3C: The positions of the time-difference positioning devices are obtained, and the spatial position of the target UAV is calculated based on the positions of the time-difference positioning devices and the time differences. S3D: The spatial position is filtered and optimized using a particle filter tracking algorithm to generate the position information.

[0041] Specifically, when the UAV signal cannot be decoded, three or more time-difference positioning devices distributed within the target area simultaneously capture the target signal, and each device achieves microsecond-level time synchronization through a satellite timing system. The signal arrival time difference data is transmitted to the central processing unit, which constructs a hyperboloid equation system based on the known geographical coordinates of each device and uses the least squares method to solve for the UAV's three-dimensional coordinates. Subsequently, the particle filter uses the previous position as its initial state, generates a predicted particle swarm based on the kinematic model, calculates the particle weights using the current observation data, and filters out high-probability particle clusters through a resampling process, finally outputting the optimized position estimate. This application can still achieve continuous and stable position tracking through multi-station collaborative measurement and dynamic filtering even when the UAV communication protocol is unknown or the signal is interfered with, solving the problem of positioning failure caused by traditional demodulation relying on communication protocols, and improving the robustness of low-altitude UAV monitoring systems in complex electromagnetic environments.

[0042] Among them, the time difference positioning device refers to the signal receiving device deployed within the target area. Specifically, it can be implemented using a radio monitoring station with high-precision clock synchronization function, used to synchronously capture the radio frequency signals transmitted by the UAV and record the signal arrival time. Time difference calculation refers to comparing the timestamp difference of the same signal arriving at different devices. Specifically, it can be implemented using a generalized cross-correlation algorithm or a phase difference detection method, used to construct the mathematical constraints of a hyperbolic equation system. The particle filter tracking algorithm is a dynamic state prediction method based on the Bayesian estimation principle. Specifically, it can be implemented using a sequential importance sampling and resampling mechanism, eliminating positioning errors caused by environmental noise by iteratively updating the particle weight distribution.

[0043] S4: If the judgment result is decipherable, then the target drone is located based on the clean target drone signal to obtain location information.

[0044] Please see Figure 5 , Figure 5 A specific implementation of step S4 is shown below: S41: If the judgment result is decipherable, demodulate the clean target drone signal to generate a digital code stream. S42: Perform channel coding identification and decoding on the digital code stream to generate preliminary payload data. S43: Perform source coding identification and decoding on the preliminary payload data to generate the original information content for communication between the target drone and the pilot. S44: Extract location information from the original information content to obtain the location information.

[0045] Specifically, in complex electromagnetic environments, once the UAV signal is confirmed to be decipherable, the radio frequency signal is first converted into a baseband digital code stream using an orthogonal demodulator, providing standardized data input for subsequent processing. Then, a channel coding identification module performs error correction code detection and decoding on the code stream, stripping redundant verification information from the transport layer and restoring the original data packet structure to ensure the integrity of the communication content. Next, a source coding identification module performs compressed encoding and reverse parsing on the payload data to reconstruct the communication protocol content between the UAV and the control terminal, including structured information such as flight status and control commands. Finally, based on the known communication protocol format, the latitude and longitude coordinate fields are located from the parsed original information, and real-time position data is extracted for trajectory tracking. This application can accurately parse the UAV communication protocol in complex electromagnetic environments and directly extract high-precision position information from the original communication content, solving the problem of insufficient reliability of traditional positioning methods in signal interference scenarios and achieving real-time and accurate tracking of decipherable UAV signals.

[0046] Demodulation refers to the process of converting analog signals into digital signal sequences. This can be achieved using a QPSK demodulator in conjunction with a carrier synchronization module, converting clean signals into a resolvable binary data stream. Channel coding identification and decoding refers to the reverse analysis of transport layer error correction codes. This can be achieved using a Viterbi decoding algorithm combined with cyclic redundancy check (CRC) to eliminate transmission interference and restore the original data format. Source coding identification and decoding refers to the reverse analysis of application layer compression codes. This can be achieved using a Huffman decoder combined with entropy coding analysis to reconstruct the structured data content in the communication protocol. Location information extraction refers to the process of locating coordinate fields from the communication protocol. This can be achieved using regular expression matching or protocol field offset parsing to directly obtain the geographic location data reported by the UAV.

[0047] S5: Predict and track the trajectory of the target UAV based on the location information.

[0048] Specifically, after obtaining the real-time location of the target drone, its trajectory can be predicted. Ground equipment can then coordinate to detect and deploy defenses in adjacent areas based on the prediction results, thereby further achieving efficient tracking of the target drone's trajectory.

[0049] Please see Figure 6 , Figure 6 A specific implementation of step S5 is shown below: S51: Fit the current flight trajectory of the target UAV based on multiple location information using a preset motion model, and predict the flight path and arrival area of ​​the target UAV within a preset time. S52: Dynamically dispatch ground detection equipment to the arrival area based on the flight trajectory, flight path, and arrival area to track the target UAV.

[0050] Specifically, in a complex electromagnetic environment, multiple time-difference positioning devices continuously collect the position information of the target UAV, forming a discrete coordinate sequence. A preset motion model filters the coordinate sequence to eliminate positioning jitter caused by signal interference, generating a smooth flight trajectory curve. Based on this curve, kinematic analysis is performed, and combined with physical constraints such as the UAV's maximum speed and turning rate, the set of all possible flight paths within a preset time window is calculated. The probability density function is used to evaluate the likelihood of each path, and spatial areas with arrival probabilities exceeding a threshold are identified as predicted arrival areas. The ground control center generates equipment scheduling instructions based on the prediction results, adjusting the orientation of mobile detection stations deployed around the target area to align the antenna beam main lobe with the predicted area, while reducing monitoring resource investment in non-critical areas. When the UAV enters a new predicted area, nearby detection devices automatically switch operating modes, forming a relay tracking mechanism. This application solves the problem of UAV tracking interruption in weak signal environments by continuously maintaining effective signal acquisition during target movement through trajectory prediction and dynamic equipment scheduling. The prediction model compensates for trajectory deviations caused by positioning errors, and dynamic resource allocation improves the utilization efficiency of monitoring equipment, achieving continuous tracking of low-altitude UAVs in complex electromagnetic environments.

[0051] The key components of this system include: a preset motion model (which can be implemented using a Kalman filter or particle motion model, eliminating single-point positioning errors by fusing historical location data), multiple location information (which refers to target UAV coordinate data collected at different times using time-difference positioning equipment, calculated using time difference of arrival (TDOA) technology to construct a continuous trajectory), flight trajectory fitting (which involves reconstructing a continuous motion path based on discrete location points, using polynomial interpolation or Bézier curve algorithms to address trajectory fragmentation issues in traditional methods), preset time (which refers to the length of the time window for predicting future flight paths, adjustable from 5 to 30 seconds to balance prediction accuracy and computational load), flight path and arrival area prediction (which involves extrapolating future motion trends based on the current trajectory, calculated using kinematic equations combined with environmental constraints), and dynamic scheduling of ground detection equipment (which involves adjusting monitoring resource deployment based on prediction results, using resource scheduling algorithms to optimize equipment azimuth and pitch angles to ensure coverage of the target area).

[0052] In this embodiment, signals from a target UAV in a target area are collected to obtain raw UAV signals. These raw signals are then inspected and error-removed to obtain clean target UAV signals. The clean target UAV signals are then identified to determine the model type of the target UAV. Based on the model type, it is determined whether the clean target UAV signals are decipherable, resulting in a determination result. If the determination result indicates that the signals are decipherable, the target UAV is located based on the clean target UAV signals to obtain location information. The trajectory of the target UAV is then predicted and tracked based on the location information. This embodiment of the invention, through a complete process of signal acquisition, model identification, deciphering judgment, positioning, and trajectory tracking, effectively extracts and enhances weak UAV signals in complex electromagnetic environments. Combined with decipherable signal analysis, it achieves high-precision real-time tracking of low-altitude UAVs, offering the advantage of improving the positioning accuracy and tracking effect of low-altitude UAVs in complex electromagnetic environments.

[0053] Please refer to Figure 7 As a response to the above Figure 1 The implementation of the method shown in this application provides an embodiment of a tracking device for a low-altitude unmanned aerial vehicle (UAV), which is similar to... Figure 1 Corresponding to the method embodiments shown, this device can be specifically applied to various electronic devices.

[0054] like Figure 7 As shown, the tracking device for the low-altitude UAV in this embodiment includes: a signal acquisition module 61, a model type identification module 62, an interpretation and judgment module 63, a UAV positioning module 64, and a trajectory tracking module 65, wherein: Signal acquisition module 61 is used to acquire the signal of the target drone in the target area, obtain the original drone signal, and perform detection and error removal on the original drone signal to obtain a clean target drone signal; Model category identification module 62 is used to identify the clean target drone signal in order to determine the model category of the target drone; The decoding and judgment module 63 is used to determine whether the clean target drone signal can be decoded according to the model category, and obtain the judgment result; The drone positioning module 64 is used to locate the target drone based on the clean target drone signal if the judgment result is decipherable, and obtain the location information. The trajectory tracking module 65 is used to predict and track the trajectory of the target UAV based on the location information.

[0055] Furthermore, the signal acquisition module 61 includes: The acquisition unit is used to acquire signals from the target UAV through a sensor antenna array deployed in the target area to obtain the original UAV signal. The signal filtering unit is used to detect and filter the original UAV signal to generate a filtered UAV signal. The error removal unit is used to perform time-frequency domain analysis on the filtered UAV signal using multi-resolution detection technology to remove errors from the filtered UAV signal and obtain an initially clean target UAV signal. A signal enhancement unit is used to enhance the initially cleaned target drone signal to obtain the cleaned target drone signal.

[0056] Furthermore, the model category identification module 62 includes: The feature extraction unit is used to analyze the clean target drone signal to extract the target features of the clean target drone, wherein the target features include signal oscillation features and cyclic code features; The feature comparison unit is used to compare the target features with the UAV model identification feature library to obtain the comparison result; A category determination unit is used to determine the model category of the target UAV based on the comparison results.

[0057] Furthermore, the interpretation and judgment module 63 includes: The judgment unit is used to determine whether the model category exists in the list of decipherable models, so as to determine whether the clean target drone signal is decipherable, and to obtain the judgment result; The first result unit is used to determine that the judgment result is translatable if the model category exists in the list of translatable models. The second result unit is used to determine that the judgment result is undecipherable if the model category does not exist in the list of decipherable models.

[0058] Furthermore, the drone positioning module 64 includes: The demodulation unit is used to demodulate the clean target drone signal and generate a digital code stream if the judgment result is decipherable. The first decoding unit is used to perform channel coding identification and decoding on the digital code stream to generate preliminary payload data; The second decoding unit is used to perform source coding identification and decoding on the preliminary payload data to generate the original information content of the communication between the target UAV and the pilot. The location information extraction unit is used to extract location information from the original information content to obtain the location information.

[0059] Furthermore, the decoding and judgment module 63 also includes: The signal receiving unit is used to receive the signal emitted by the same target UAV synchronously through multiple time difference positioning devices if the judgment result is undecipherable, so as to obtain the target signal. A time difference calculation unit is used to calculate the time difference between the arrival of the signal at different time difference positioning devices based on the target signal; A spatial position calculation unit is used to obtain the position of the time difference positioning device and calculate the spatial position of the target UAV based on the position of the time difference positioning device and the time difference. The filtering optimization unit is used to filter and optimize the spatial position using a particle filter tracking algorithm to generate the position information.

[0060] Furthermore, the trajectory tracking module 65 includes: The flight trajectory fitting unit is used to fit the current flight trajectory of the target UAV based on multiple location information using a preset motion model, and to predict the flight path and arrival area of ​​the target UAV within a preset time. The drone tracking unit is used to dynamically dispatch ground detection equipment to the arrival area based on the flight trajectory, the flight path, and the arrival area in order to track the target drone.

[0061] To address the aforementioned technical problems, embodiments of this application also provide a computer device. Please refer to [link / reference] for details. Figure 8 , Figure 8 This is a basic structural block diagram of the computer device in this embodiment.

[0062] Computer device 7 includes a memory 71, a processor 72, and a network interface 73 that are interconnected via a system bus. It should be noted that... Figure 8 Only a computer device 7 with three components—memory 71, processor 72, and network interface 73—is shown. It should be understood that implementing all shown components is not required; more or fewer components may be implemented alternatively. Those skilled in the art will understand that this computer device is a device capable of automatically performing numerical calculations and / or information processing according to pre-set or stored instructions. Its hardware includes, but is not limited to, microprocessors, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), and embedded devices.

[0063] Computer devices can include desktop computers, laptops, handheld computers, and cloud servers. These devices allow for human-computer interaction with users through keyboards, mice, remote controls, touchpads, or voice-activated devices.

[0064] The memory 71 includes at least one type of readable storage medium, including flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 71 may be an internal storage unit of the computer device 7, such as the hard disk or memory of the computer device 7. In other embodiments, the memory 71 may also be an external storage device of the computer device 7, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the computer device 7. Of course, the memory 71 may include both internal storage units and external storage devices of the computer device 7. In this embodiment, the memory 71 is typically used to store the operating system and various application software installed on the computer device 7, such as the program code of a tracking method for a low-altitude unmanned aerial vehicle. In addition, the memory 71 may also be used to temporarily store various types of data that have been output or will be output.

[0065] In some embodiments, processor 72 may be a central processing unit (CPU), controller, microcontroller, microprocessor, or other data processing chip. This processor 72 is typically used to control the overall operation of computer device 7. In this embodiment, processor 72 is used to run program code stored in memory 71 or process data, for example, to run the program code of the aforementioned low-altitude UAV tracking method to implement various embodiments of the low-altitude UAV tracking method.

[0066] The network interface 73 may include a wireless network interface or a wired network interface, which is typically used to establish a communication connection between the computer device 7 and other electronic devices.

[0067] This application also provides another embodiment, namely, providing a computer-readable storage medium storing a computer program that can be executed by at least one processor to cause the at least one processor to perform the steps of the tracking method for a low-altitude unmanned aerial vehicle as described above.

[0068] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods of the various embodiments of this application.

[0069] Obviously, the embodiments described above are merely some embodiments of this application, not all embodiments. The accompanying drawings show preferred embodiments of this application, but do not limit the scope of this application. This application can be implemented in many different forms; rather, these embodiments are provided to provide a more thorough and comprehensive understanding of the disclosure of this application. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing specific embodiments, or make equivalent substitutions for some of the technical features. Any equivalent structures made using the content of this application's specification and drawings, directly or indirectly applied to other related technical fields, are similarly within the scope of protection of this application.

Claims

1. A tracking method for a low-altitude unmanned aerial vehicle (UAV), characterized in that, include: The signal of the target drone in the target area is collected to obtain the original drone signal. The original drone signal is then detected and error removed to obtain a clean target drone signal. The clean target drone signal is identified to determine the model category of the target drone; Based on the model category, determine whether the signal of the clean target drone can be decoded, and obtain the determination result; If the judgment result is decipherable, the target drone is located based on the clean target drone signal to obtain location information; The trajectory of the target drone is predicted and tracked based on the location information; The process of identifying the clean target drone signal to determine the model category of the target drone includes: The clean target drone signal is analyzed to extract the target features of the clean target drone, wherein the target features include signal oscillation features and cyclic code features; The target features are compared with the UAV model identification feature database to obtain the comparison results; The model category of the target UAV is determined based on the comparison results.

2. The tracking method for low-altitude unmanned aerial vehicles according to claim 1, characterized in that, The process of collecting signals from the target drone in the target area to obtain the original drone signal, and then performing detection and error removal on the original drone signal to obtain a clean target drone signal includes: The original UAV signal is obtained by acquiring the signal of the target UAV through a sensor antenna array deployed in the target area; The original UAV signals are detected and filtered to generate filtered UAV signals; Multi-resolution detection technology is used to perform time-frequency domain analysis on the filtered UAV signals in order to remove errors from the filtered UAV signals and obtain the initial clean target UAV signals. The initially cleaned target drone signal is enhanced to obtain the cleaned target drone signal.

3. The tracking method for low-altitude unmanned aerial vehicles according to claim 1, characterized in that, The step of determining whether the clean target drone signal is decipherable based on the model category, and obtaining the determination result, includes: Determine whether the model category exists in the list of decipherable models to determine whether the clean target drone signal is decipherable, and obtain the determination result; If the model category exists in the list of translatable models, then the determination result is translatable; If the model category does not exist in the list of decipherable models, the determination result is that it is undecipherable.

4. The tracking method for low-altitude unmanned aerial vehicles according to claim 1, characterized in that, If the determination result is interpretable, then the target drone is located based on the clean target drone signal to obtain location information, including: If the judgment result is decipherable, the clean target drone signal is demodulated to generate a digital code stream; The digital code stream is subjected to channel coding identification and decoding to generate preliminary payload data; The preliminary payload data is subjected to source coding identification and decoding to generate the original information content of communication between the target UAV and the pilot; The location information is obtained by extracting location information from the original information content.

5. The tracking method for low-altitude unmanned aerial vehicles according to any one of claims 1 to 4, characterized in that, After determining whether the signal of the clean target drone is decipherable based on the model category and obtaining the determination result, the method further includes: If the judgment result is undecipherable, the target signal is obtained by synchronously receiving the signal emitted by the same target UAV through multiple time difference positioning devices. The time difference between the arrival of the signal at different time difference positioning devices is calculated based on the target signal. The location of the time difference positioning device is obtained, and the spatial location of the target UAV is calculated based on the location of the time difference positioning device and the time difference. The spatial position is filtered and optimized using a particle filter tracking algorithm to generate the position information.

6. The tracking method for low-altitude unmanned aerial vehicles according to any one of claims 1 to 4, characterized in that, The step of predicting and tracking the trajectory of the target drone based on the location information includes: The current flight trajectory of the target UAV is fitted based on multiple location information using a preset motion model, and the flight path and arrival area of ​​the target UAV within a preset time period are predicted. Based on the flight trajectory, flight path, and arrival area, ground detection equipment is dynamically dispatched to the arrival area to track the target UAV.

7. A tracking device for a low-altitude unmanned aerial vehicle, characterized in that, include: The signal acquisition module is used to acquire the signal of the target drone in the target area, obtain the original drone signal, and perform detection and error removal on the original drone signal to obtain a clean target drone signal. A model category identification module is used to identify the signal of the clean target drone in order to determine the model category of the target drone; The decoding and judgment module is used to determine whether the signal of the clean target drone can be decoded based on the model category, and to obtain a judgment result; The drone positioning module is used to locate the target drone based on the clean target drone signal if the judgment result is decipherable, and obtain the location information. A trajectory tracking module is used to predict and track the trajectory of the target UAV based on the location information; The model category identification module includes: The feature extraction unit is used to analyze the clean target drone signal to extract the target features of the clean target drone, wherein the target features include signal oscillation features and cyclic code features; The feature comparison unit is used to compare the target features with the UAV model identification feature library to obtain the comparison result; A category determination unit is used to determine the model category of the target UAV based on the comparison results.

8. A computer device, characterized in that, It includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the tracking method for a low-altitude unmanned aerial vehicle as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the tracking method for a low-altitude unmanned aerial vehicle as described in any one of claims 1 to 6.

Images