Unmanned aerial vehicle detection track acquisition method based on wireless spectrum

Abstract

The invention belongs to the technical field of unmanned aerial vehicle detection tracks, and provides a wireless spectrum-based unmanned aerial vehicle detection track acquisition method, which comprises the following steps of: S1, generating defense area arrangement data; s2, collecting GPS coordinate data and environment data of the unmanned aerial vehicle in real time; s3, taking the collected GPS coordinate data and environment data as inputs, and respectively inputting the GPS coordinate data and the environment data into a BP neural network model unit and a long-short term neural network model unit for processing; s4, outputting a result according to the neural network model unit; according to the invention, the BP neural network model unit and the long and short term neural network model unit are adopted to process the collected data, and Kalman filtering processing is combined to filter noise and interference in GPS error data, so that the accuracy of track acquisition is effectively improved; meanwhile, the method can also perform quality evaluation on the filtered actual data of the GPS coordinates of the unmanned aerial vehicle, ensures that the data quality is used for drawing the flight trajectory after meeting a predetermined standard, and further ensures the accuracy of the trajectory.

Description

Technical Field

[0001] The present invention belongs to the technical field of unmanned aerial vehicle (UAV) detection trajectory, and specifically relates to a method for obtaining the UAV detection trajectory based on wireless spectrum. Background Art

[0002] In the context of the rapid development of UAV technology, the accurate acquisition of UAV flight trajectories has become increasingly important. However, there are many deficiencies in existing methods for obtaining UAV detection trajectories. For example, some methods rely solely on GPS coordinate data, but in complex environments or under interference, the accuracy of GPS data will drop significantly, resulting in inaccurate trajectory acquisition. In addition, some methods ignore the impact of environmental data on UAV flight trajectories, such as meteorological conditions like wind speed, temperature, and humidity, which all have important effects on UAV flight trajectories. Therefore, how to comprehensively consider various factors and accurately obtain the UAV flight trajectory has become an urgent technical problem to be solved.

[0003] For this reason, those skilled in the art have proposed a method for obtaining the UAV detection trajectory based on wireless spectrum to solve the problems raised in the background art. Summary of the Invention

[0004] To solve the above technical problems, the present invention provides a method for obtaining the UAV detection trajectory based on wireless spectrum to address the many deficiencies in existing methods for obtaining UAV detection trajectories. For example, some methods rely solely on GPS coordinate data, but in complex environments or under interference, the accuracy of GPS data will drop significantly, resulting in inaccurate trajectory acquisition. In addition, some methods ignore the impact of environmental data on UAV flight trajectories, such as meteorological conditions like wind speed, temperature, and humidity, which all have important effects on UAV flight trajectories, etc.

[0005] The method for obtaining the UAV detection trajectory based on wireless spectrum includes:

[0006] S1. Generate defense zone layout data, where the defense zone layout data includes the flight area of the UAV, the layout information of detection devices, and environmental parameters;

[0007] S2. Real-time collect the GPS coordinate data of the UAV and environmental data, where the environmental data includes factors affecting the UAV flight trajectory such as signal-to-noise ratio, wind speed, etc.;

[0008] S3. Take the collected GPS coordinate data and environmental data as inputs and input them into a BP neural network model unit and a long short-term neural network model unit for processing respectively;

[0009] S4. Generate error data of the UAV GPS coordinates according to the output results of the neural network model unit;

[0010] S5. Perform Kalman filtering on the GPS error data to filter out noise and interference, and obtain the actual GPS coordinate data of the UAV after filtering.

[0011] S6. Draw the flight trajectory of the UAV according to the actual GPS coordinate data of the UAV after filtering.

[0012] Preferably, in step S1, the defense area arrangement data further includes the type, detection range, and detection accuracy information of the detection equipment.

[0013] Preferably, in step S2, the environmental data further includes meteorological data such as temperature, humidity, and air pressure. At the same time, in order to improve the utilization efficiency of these data in the subsequent model, a data fusion algorithm is used to integrate data from different sources to form a more accurate environmental description.

[0014] Preferably, in step S3, before training, the BP neural network model unit and the long short-term neural network model unit are pre-trained using a large amount of historical data including the UAV flight trajectory and environmental data to improve the accuracy and generalization ability of the model.

[0015] Preferably, in step S3, the BP (backpropagation) neural network model is used to process the collected GPS coordinate data and environmental data. In order to improve the accuracy and generalization ability of the model, a weight update formula and a loss function are introduced.

[0016] Preferably, in step S5, the Kalman filter is used to filter out noise and interference in the GPS error data.

[0017] Preferably, it further includes a step of evaluating the quality of the actual GPS coordinate data of the UAV after filtering. Only when the data quality meets the predetermined standard, it is used to draw the flight trajectory of the UAV.

[0018] Preferably, for adding the data quality evaluation step, a distance metric is introduced to evaluate the accuracy of the data.

[0019] Preferably, the method further includes comparing the drawn flight trajectory of the UAV with a preset safe flight area, and when the flight trajectory of the UAV exceeds the safe flight area, a warning signal is issued.

[0020] The UAV detection trajectory acquisition system based on wireless spectrum uses the above-mentioned UAV detection trajectory acquisition method based on wireless spectrum, including:

[0021] A spectrum acquisition module for real-time collecting wireless spectrum data during the flight of the UAV.

[0022] An environmental data acquisition module, configured to acquire in real time the environmental data during the flight of the unmanned aerial vehicle, including signal-to-noise ratio, wind speed, and at least one other meteorological data;

[0023] A data processing module, connected to the spectrum acquisition module and the environmental data acquisition module, configured to preprocess the acquired spectrum data and environmental data, and input them into a pre-trained neural network model for processing to obtain the flight state information of the unmanned aerial vehicle;

[0024] A trajectory plotting module, connected to the data processing module, configured to plot the flight trajectory of the unmanned aerial vehicle according to the processed flight state information;

[0025] A GPS module, configured to acquire the real-time position information of the unmanned aerial vehicle, and input the position information into the data processing module for error filtering;

[0026] Wherein, the neural network model includes a BP neural network model unit and a long short-term neural network model unit, and the neural network model is pre-trained with a large amount of historical data.

[0027] A processor, configured to execute the method for obtaining the detection trajectory of the unmanned aerial vehicle based on wireless spectrum as described above.

[0028] A computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the method for obtaining the detection trajectory of the unmanned aerial vehicle based on wireless spectrum as described above is implemented.

[0029] Compared with the prior art, the present invention has the following beneficial effects:

[0030] 1. By comprehensively considering the GPS coordinate data of the unmanned aerial vehicle and various environmental data including signal-to-noise ratio, wind speed, temperature, humidity, and air pressure, the present invention can more comprehensively reflect the flight state of the unmanned aerial vehicle, thereby improving the accuracy of trajectory acquisition; especially in complex environments or under interference, the present invention can still maintain a high trajectory acquisition accuracy.

[0031] 2. The present invention uses a BP neural network model unit and a long short-term neural network model unit to process the acquired data, and through pre-training with a large amount of historical data, improves the accuracy and generalization ability of the model; this deep learning method can automatically learn the complex features in the data, thereby more accurately predicting the flight trajectory of the unmanned aerial vehicle.

[0032] 3. The present invention filters the GPS error data through Kalman filter processing, effectively filtering out noise and interference, and further improving the accuracy of the GPS coordinate data of the unmanned aerial vehicle; at the same time, the present invention also introduces a data quality evaluation step, and only when the data quality meets a predetermined standard, it is used to plot the flight trajectory of the unmanned aerial vehicle, further ensuring the accuracy of the trajectory.

[0033] 4. The present invention not only provides an accurate method for obtaining the flight trajectory of a drone, but also can compare the drawn drone flight trajectory with a preset safe flight area; when the drone flight trajectory exceeds the safe flight area, a warning signal can be issued, thereby improving the flight safety of the drone. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 It is a flowchart of the method for obtaining the drone detection trajectory based on wireless spectrum according to the present invention;

[0035] Figure 2 It is a framework diagram of the system for obtaining the drone detection trajectory based on wireless spectrum according to the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0036] The following further describes in detail the embodiments of the present invention in conjunction with the drawings and embodiments. The following embodiments are used to illustrate the present invention, but cannot be used to limit the scope of the present invention.

[0037] Embodiment: The present invention provides a method for obtaining the drone detection trajectory based on wireless spectrum, as Figure 1 shown, including:

[0038] S1. Generate defense area layout data, where the defense area layout data includes the flight area of the drone, the layout information of the detection equipment, and environmental parameters;

[0039] S2. Real-time collect the GPS coordinate data of the drone and environmental data, where the environmental data includes factors affecting the drone flight trajectory such as signal-to-noise ratio and wind speed;

[0040] S3. Take the collected GPS coordinate data and environmental data as inputs, and input them into the BP neural network model unit and the long short-term neural network model unit for processing respectively;

[0041] S4. Generate error data of the drone GPS coordinates according to the output results of the neural network model unit;

[0042] S5. Perform Kalman filtering on the GPS error data to filter out noise and interference, and obtain the actual data of the filtered drone GPS coordinates;

[0043] S6. Draw the flight trajectory of the drone according to the actual data of the filtered drone GPS coordinates.

[0044] As can be seen from the above, the method for obtaining the detection trajectory of an unmanned aerial vehicle (UAV) based on wireless spectrum provided by the present invention comprehensively considers the GPS coordinate data of the UAV and various environmental data including signal-to-noise ratio, wind speed, temperature, humidity, and air pressure, and uses a BP neural network model unit and a long short-term neural network model unit to process the collected data. By combining Kalman filter processing to filter out the noise and interference in the GPS error data, the accuracy of trajectory acquisition is effectively improved. At the same time, the method can also perform quality assessment on the actual GPS coordinate data of the UAV after filtering, and only uses the data for drawing the flight trajectory after ensuring that the data quality meets the predetermined standard, further ensuring the accuracy of the trajectory. In addition, the method can also compare the drawn UAV flight trajectory with the preset safe flight area, improving the flight safety of the UAV, and having significant beneficial effects.

[0045] Further, in step S1, the defense area layout data further includes the type, detection range, and detection accuracy information of the detection device.

[0046] As can be seen from the above, by making the defense area layout data include the type, detection range, and detection accuracy information of the detection device, the present invention provides more detailed and accurate basic data for subsequent UAV detection trajectory acquisition; this not only helps to more accurately plan the flight area of the UAV and the layout of the detection device, but also can more accurately evaluate the flight state and trajectory of the UAV according to the characteristics and accuracy requirements of the detection device, thereby improving the accuracy and reliability of the UAV detection trajectory acquisition method.

[0047] Further, in step S2, the environmental data further includes meteorological data such as temperature, humidity, and air pressure. At the same time, in order to improve the utilization efficiency of these data in the subsequent model, a data fusion algorithm is used to integrate data from different sources to form a more accurate environmental description. The formula of the data fusion algorithm includes:

[0048] There are multi-source data x1, x2,..., x n , and the corresponding weights are w1, w2,..., w n , then the fused data x′, its algorithm representation is:

[0049]

[0050] Among them, the weight w i should satisfy

[0051] As can be seen from the above, by including meteorological data such as temperature, humidity, and air pressure in the environmental data and using a data fusion algorithm to integrate data from different sources, the present invention significantly improves the utilization efficiency of environmental data in subsequent models; this data fusion algorithm can comprehensively consider the influence of various meteorological factors on the flight trajectory of the drone, form a more accurate environmental description, and provide more reliable data support for the flight state assessment and trajectory prediction of the drone; this not only helps to improve the accuracy of the drone detection trajectory acquisition method, but also can provide more comprehensive protection for the safe flight of the drone.

[0052] Further, in step S3, before training, the BP neural network model unit and the long short-term neural network model unit are pre-trained using a large amount of historical data including the flight trajectory of the drone and environmental data to improve the accuracy and generalization ability of the model.

[0053] As can be seen from the above, by pre-training the BP neural network model unit and the long short-term neural network model unit using a large amount of historical data including the flight trajectory of the drone and environmental data, the present invention significantly improves the accuracy and generalization ability of the model; this pre-training method enables the model to better learn the complex relationship between the flight trajectory of the drone and environmental data, so as to more accurately predict the flight trajectory of the drone when processing real-time collected data in the subsequent process; this not only helps to improve the overall performance of the drone detection trajectory acquisition method, but also can provide more solid technical support for the safe and efficient flight of the drone.

[0054] Further, in step S3, the BP (backpropagation) neural network model is used to process the collected GPS coordinate data and environmental data. In order to improve the accuracy and generalization ability of the model, a weight update formula and a loss function are introduced;

[0055] The weight update formula includes:

[0056]

[0057] where, Δw ij is the weight update amount, η is the learning rate, E is the loss function, and w ij is the weight in the neural network;

[0058] The loss function includes:

[0059]

[0060] where, N is the number of samples, y n is the true value, is the predicted value.

[0061] As can be seen from the above, the present invention optimizes the BP neural network model by introducing a weight update formula and a loss function, further improving the accuracy and generalization ability of the model; the weight update formula can automatically adjust the weights in the neural network according to the results of the loss function, enabling the model to more accurately approximate the true value when processing the collected GPS coordinate data and environmental data; while the loss function measures the difference between the predicted value and the true value of the model, providing a clear direction and goal for weight update. This optimization method can not only make the model show higher accuracy when processing similar data, but also improve the adaptability of the model to different environments and flight conditions, providing a more powerful and flexible technical means for the method of obtaining the detection trajectory of unmanned aerial vehicles.

[0062] Further, in step S5, the Kalman filter is used to filter out the noise and interference in the GPS error data; the Kalman filter includes a state prediction and an update formula;

[0063] The state prediction formula includes:

[0064]

[0065] P k|k-1 = AP k-1|k-1 A T + Q

[0066] The state update formula includes:

[0067] K k = P k|k-1 H T (HP k|k-1 H T + R) -1 ;

[0068]

[0069] P k|k = (I - K k H)P k|k-1 ;

[0070] Where, is the state estimate, P is the estimate error covariance, A and B are system matrices, H is the observation matrix, Q and R are the covariance matrices of the process noise and the observation noise respectively, K is the Kalman gain, and z is the observed value.

[0071] As can be seen from the above, the present invention uses Kalman filtering to process GPS error data, effectively filtering out noise and interference through its state prediction and update formulas, thereby significantly improving the accuracy of GPS coordinate data; Kalman filtering can optimally estimate the flight state of the drone based on historical data and current observations. Its state prediction formula and state update formula act together on the system matrix, observation matrix, and noise covariance matrix, dynamically adjusting the estimated value by calculating the Kalman gain to make it closer to the true value. This processing method not only effectively reduces the errors in GPS data, but also improves the real-time performance and reliability of the data, providing more accurate basic data for subsequent flight trajectory plotting, and further enhancing the practicability and reliability of the drone detection trajectory acquisition method.

[0072] Further, it also includes the step of evaluating the quality of the actual GPS coordinate data of the filtered drone. Only when the data quality meets the predetermined standard will it be used to plot the flight trajectory of the drone.

[0073] As can be seen from the above, in the drone detection trajectory acquisition method, adding the step of evaluating the quality of the actual GPS coordinate data of the filtered drone has crucial beneficial effects; this step ensures that only when the data quality meets the predetermined standard will it be used to plot the flight trajectory of the drone; this not only effectively avoids trajectory plotting errors caused by data quality problems, but also improves the reliability and accuracy of the entire detection trajectory acquisition method; through strict data quality evaluation, more accurate and reliable GPS coordinate data are selected, providing a solid data foundation for subsequent trajectory analysis and applications, thereby further enhancing the practicability and credibility of the drone detection trajectory acquisition method.

[0074] Further, for adding the data quality evaluation step, a distance metric is introduced to evaluate the accuracy of the data. The formula of the distance metric includes:

[0075]

[0076] where x is the data point, μ is the mean vector, and ∑ is the covariance matrix.

[0077] As can be seen from the above, in the method for obtaining the drone detection trajectory, for the added data quality evaluation step, a distance metric is introduced to evaluate the accuracy of the data. Through the distance metric formula, we conduct precise quantitative evaluation on the actual drone GPS coordinate data after filtering, so as to more objectively judge the quality of the data. This evaluation method based on statistical characteristics can not only capture the deviation degree of data points from the overall data set, but also take into account the distribution characteristics of the data, making the evaluation results more comprehensive and accurate. This not only improves the scientificity and reliability of data quality evaluation, but also further ensures that only high-quality data will be used to draw the flight trajectory of the drone, thus greatly improving the accuracy and practicality of trajectory acquisition.

[0078] Furthermore, the method further includes comparing the drawn drone flight trajectory with a preset safe flight area, and when the drone flight trajectory exceeds the safe flight area, a warning signal is issued.

[0079] As can be seen from the above, in the method of the present invention, the drawn drone flight trajectory is compared with a preset safe flight area, and a warning signal is issued when the drone flight trajectory exceeds the safe area. It can realize real-time safety monitoring of the drone and ensure that the drone always stays within the safe range during flight. By promptly issuing a warning signal, it reminds the operator to quickly respond and take necessary adjustment measures to effectively avoid potential safety risks. This not only improves the flight safety of the drone, but also enhances the reliability and success rate of the flight mission, providing a more solid safety guarantee for the wide application of the drone.

[0080] Furthermore, the method for obtaining the drone detection trajectory based on wireless spectrum in the embodiment is compared with the currently existing method for obtaining the drone detection trajectory (control example) in terms of effects, and the following table is obtained:

[0081]

[0082]

[0083] As can be seen from the above table, the method for obtaining the drone detection trajectory based on wireless spectrum in this embodiment shows significant advantages in terms of comprehensive data utilization, model accuracy, noise and interference filtering, data quality evaluation, safety monitoring, and adaptability and generalization ability. The overall effect is significantly better than the currently existing method for obtaining the drone detection trajectory.

[0084] The system for obtaining the drone detection trajectory based on wireless spectrum, as Figure 2 shown, uses the above method for obtaining the drone detection trajectory based on wireless spectrum, including:

[0085] A spectrum acquisition module for real-time acquisition of wireless spectrum data during the flight of the drone;

[0086] An environmental data acquisition module, configured to acquire environmental data during the flight of the UAV in real time, including signal-to-noise ratio, wind speed, and at least one other meteorological data;

[0087] A data processing module, connected to the spectrum acquisition module and the environmental data acquisition module, configured to preprocess the acquired spectrum data and environmental data, and input them into a pre-trained neural network model for processing to obtain the flight state information of the UAV;

[0088] A trajectory plotting module, connected to the data processing module, configured to plot the flight trajectory of the UAV according to the processed flight state information;

[0089] A GPS module, configured to acquire the real-time position information of the UAV, and input the position information into the data processing module for error filtering;

[0090] Wherein, the neural network model includes a BP neural network model unit and a long short-term neural network model unit, and the neural network model is pre-trained with a large amount of historical data.

[0091] An embodiment of the present application provides an electronic device, applicable to the above-mentioned method for obtaining the detection trajectory of a UAV based on wireless spectrum, including:

[0092] A memory, configured to store computer programs and data;

[0093] A processor, configured to run the system program.

[0094] An embodiment of the present application provides a computer storage medium, applicable to the above-mentioned method for obtaining the detection trajectory of a UAV based on wireless spectrum, and performs hierarchical confidentiality management on the above system and data according to the requirements of confidentiality management.

[0095] Those skilled in the art should understand that the embodiments of the present application can be provided as a system, or a computer program product. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memory, CD-ROM, optical memory, etc.) containing computer-usable program code.

[0096] This application is described with reference to the flowcharts and / or block diagrams of devices (systems) and computer program products according to embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram, and the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices produce a means for implementing the functions specified in one or more of the flows Figure 1 one or more of the flows and / or blocks Figure 1 or one or more of the blocks.

[0097] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory produce a manufacture including an instruction means that implements the functions specified in one or more of the flows Figure 1 one or more of the flows and / or blocks Figure 1 or one or more of the blocks.

[0098] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, so that the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more of the flows Figure 1 one or more of the flows and / or blocks Figure 1 or one or more of the blocks.

[0099] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and a memory.

[0100] The memory may include non-permanent memory in the form of computer-readable media, random access memory (RAM), and / or non-volatile memory, such as read-only memory (ROM) or flash memory (flash RAM). The memory is an example of computer-readable media.

[0101] A computer-readable medium includes both permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette tapes, magnetic disk storage or other magnetic storage devices, or any other non-transitory medium that can be used to store information accessible by a computing device. As defined herein, a computer-readable medium does not include transitory computer-readable media, such as modulated data signals and carrier waves.

[0102] It should also be noted that the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, article or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, article or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, article or device comprising the element.

[0103] The embodiments of the present invention are given for purposes of illustration and description. Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present invention.

Claims

1. A method for acquiring drone detection trajectories based on wireless spectrum, characterized in that: include: S1. Generate defense zone layout data, where the defense zone layout data includes the flight area of ​​the UAV, layout information of the detection equipment, and environmental parameters; S2, real-time collection of GPS coordinate data and environmental data of the drone, wherein the environmental data includes factors such as signal-to-noise ratio and wind speed that affect the flight trajectory of the drone; S3, taking the collected GPS coordinate data and environmental data as input, and inputting them into the BP neural network model unit and the long-term and short-term neural network model unit for processing respectively; S4, generating error data of the GPS coordinates of the drone according to the output results of the neural network model unit; S5, performing Kalman filtering on the GPS error data to obtain the actual GPS coordinate data of the UAV after filtering; S6. Draw the flight trajectory of the drone based on the filtered actual data of the drone GPS coordinates.

2. The method for acquiring the detection trajectory of a UAV based on wireless spectrum according to claim 1, characterized in that: In step S1, the defense zone layout data also includes the type, detection range and detection accuracy information of the detection equipment.

3. The method for acquiring the detection trajectory of a UAV based on wireless spectrum according to claim 1, characterized in that: In step S2, the environmental data also includes temperature, humidity and air pressure data. At the same time, in order to improve the utilization efficiency of these data in subsequent models, a data fusion algorithm is used to integrate data from different sources to form a more accurate environmental description.

4. The method for acquiring the detection trajectory of a UAV based on wireless spectrum according to claim 1, characterized in that: In step S3, the BP neural network model unit and the long-short term neural network model unit are pre-trained using a large amount of historical data including UAV flight trajectory and environmental data before training.

5. The method for acquiring the detection trajectory of a UAV based on wireless spectrum according to claim 1, characterized in that: In step S3, the BP neural network model is used to process the collected GPS coordinate data and environmental data, and in order to improve the accuracy and generalization ability of the model, the weight update formula and loss function are introduced.

6. The method for acquiring the detection trajectory of a UAV based on wireless spectrum according to claim 1, characterized in that: In step S5, the Kalman filter is used to filter out noise and interference in the GPS error data.

7. The method for acquiring the detection trajectory of a UAV based on wireless spectrum according to claim 1, characterized in that: The method also includes a step of evaluating the quality of the filtered actual data of the GPS coordinates of the UAV. Only when the data quality meets the predetermined standard will it be used to draw the flight trajectory of the UAV.

8. The method for acquiring the detection trajectory of a UAV based on wireless spectrum as claimed in claim 7, characterized in that: In order to add a data quality assessment step, a distance metric is introduced to evaluate the accuracy of the data.

9. The method for acquiring the detection trajectory of a UAV based on wireless spectrum according to claim 1, characterized in that: The method also includes comparing the drawn UAV flight trajectory with a preset safe flight area, and issuing a warning signal when the UAV flight trajectory exceeds the safe flight area.

10. A drone detection trajectory acquisition system based on wireless spectrum, characterized by: The method for obtaining the detection trajectory of a UAV based on wireless spectrum according to any one of claims 1 to 9 comprises: The spectrum acquisition module is used to collect wireless spectrum data of the drone in real time during flight; An environmental data acquisition module, used to collect environmental data of the UAV in real time during flight, including signal-to-noise ratio, wind speed, and at least one other meteorological data; A data processing module, connected to the spectrum acquisition module and the environmental data acquisition module, is used to pre-process the collected spectrum data and environmental data, and input them into the pre-trained neural network model for processing to obtain the flight status information of the UAV; A trajectory drawing module, connected to the data processing module, for drawing the flight trajectory of the UAV according to the processed flight status information; The GPS module is used to obtain the real-time location information of the drone and input the location information into the data processing module for error filtering; The neural network model includes a BP neural network model unit and a long-term and short-term neural network model unit, and the neural network model is pre-trained using a large amount of historical data.

Images