No-fly zone-oriented unmanned aerial vehicle route early warning method, system, equipment and medium

Abstract

The embodiment of the invention provides an unmanned aerial vehicle route early warning method, system and device for a no-fly zone and a medium, and belongs to the field of unmanned aerial vehicles. The method comprises the following steps: establishing a no-fly zone spatial database, and storing electronic fence boundaries and security level attributes of each zone; the method comprises the following steps: acquiring detection data, tracking an unmanned aerial vehicle entering a no-fly zone, generating a real-time flight path, performing compliance verification on the real-time flight path by taking a reported planned route of the unmanned aerial vehicle as a reference, marking the unmanned aerial vehicle deviating from the planned route as a suspicious target, associating identity information of the unmanned aerial vehicle with pilot information, and triggering primary early warning at the same time; and for a suspicious target, carrying out spatial superposition calculation on the flight path of the suspicious target and the electronic fence of the no-fly zone, determining an intrusion risk level according to a security level attribute, and generating an intrusion event and advanced early warning information. Accurate monitoring and track traceability management and control of the unmanned aerial vehicles in key areas are realized, and the accuracy of safety prevention and control of the unmanned aerial vehicles in the areas is improved.

Description

Technical Field

[0001] This invention relates to the field of unmanned aerial vehicle (UAV) technology, and more specifically to a method, system, device, and medium for UAV flight path early warning in no-fly zones. Background Technology

[0002] With the widespread adoption of drone technology, unauthorized "reckless flying" in no-fly zones, such as around airports and nuclear power plants, poses a serious threat to low-altitude safety and public safety. Therefore, effective drone detection and post-flight trajectory tracing in key areas have become crucial technologies for airspace safety management.

[0003] First, existing solutions primarily focus on single-function intrusion detection, triggering alarms only when a drone physically crosses the electronic fence boundary of a no-fly zone. This reactive approach results in a delayed response, failing to anticipate and intervene in potential or impending intrusions, leaving security personnel with an extremely short window for emergency response. Second, there is a lack of assessment of the compliance of flight intentions. This leads to monitoring systems either missing suspicious targets that deviate from their flight paths but have not yet entered the core area, or issuing alarms indiscriminately for all targets, generating numerous false alarms. This results in a lack of specificity in warning information, significantly hindering the judgment efficiency of security personnel. Moreover, existing warning information is often one-dimensional, only including location and trajectory, lacking real-time correlation and integration of target identity. Furthermore, the warning mechanism is crude, failing to provide differentiated and tiered risk warnings based on the different security levels within the no-fly zone, thus failing to support tiered response decisions. Summary of the Invention

[0004] The purpose of this invention is to provide a method, system, device, and medium for drone flight path early warning in no-fly zones, which enables compliance assessment and graded risk early warning and control of drones in key areas, thereby improving the accuracy of regional drone safety control.

[0005] To achieve the above objectives, embodiments of the present invention provide a method for early warning of unmanned aerial vehicle (UAV) flight paths in no-fly zones, comprising: Establish a spatial database of no-fly zones to store the electronic fence boundaries and security level attributes of each no-fly zone; based on the spatial database, deploy detection equipment within the corresponding geographical area to form an air-ground collaborative monitoring network; The monitoring network collects detection data in real time, identifies, locates, and tracks drones entering the no-fly zone, and generates real-time flight trajectories. Based on the reported drone flight plans, the real-time flight trajectory is verified for compliance. Drones that deviate from the planned flight path are marked as suspicious targets. The drone identity information and pilot information are associated with the real-time broadcast ADS-B message, and a primary warning is triggered. For the suspicious target, its flight trajectory is spatially superimposed with the electronic fence of the no-fly zone, and the intrusion risk level of the suspicious target is determined according to the security level attribute of the electronic fence, generating intrusion events and advanced early warning information; The primary warning information, advanced warning information, drone identity information, pilot information, flight trajectory, and intrusion event records are synchronized to a spatiotemporal database, which supports composite indexes based on time, space, and target ID. Based on the aforementioned spatiotemporal database, the historical flight trajectories of the drones that triggered the early warning are traced back to obtain the complete flight trajectories of the drones before, during, and after the intrusion. Multidimensional data analysis is then performed to generate an early warning analysis report.

[0006] Optionally, the monitoring network collects detection data in real time to identify, locate, and track drones entering the no-fly zone, generating real-time flight trajectories, including: The spatiotemporal reference will be unified based on the detection data obtained from the monitoring network, the reported UAV flight plans, and the real-time broadcast ADS-B messages. Dynamic weights are assigned to the detected data, conditional weights are assigned to the planned flight routes, and trust weights are assigned to the ADS-B messages. An adaptive Kalman filter algorithm is used for dynamic weighted fusion calculation. The current time data of the detection data, the planned route, and the ADS-B message are used as the filter input. Based on the dynamic weight assigned to the detection data, the conditional weight assigned to the planned route, and the trust weight assigned to the ADS-B message, the filter gain of each data source is dynamically adjusted to obtain the initial flight trajectory. The initial trajectory was smoothed using cubic B-spline curves, and a confidence value was labeled for each trajectory point of each initial trajectory. The trajectory points with high confidence are selected and connected sequentially to generate a real-time flight trajectory.

[0007] Optionally, based on the reported drone flight plan, the real-time flight trajectory is verified for compliance. Drones deviating from the planned flight path are marked as suspicious targets. The drone's identity information and pilot information are linked to the real-time broadcast ADS-B message, and a primary warning is triggered, including: By interfacing with radio frequency spectrum data, radar point cloud data, and optical image data, a timestamp alignment algorithm is used to synchronize the same UAV data collected by different devices to a unified time reference, and a spatial coordinate registration algorithm is used to convert the data to the same geographic coordinate system. The extended Kalman filter algorithm is used to fuse radio frequency spectrum data, radar point cloud data, and optical image data to output the estimated position of the UAV and form a trajectory point stream. The system extracts the radio frequency fingerprint features of the UAV from radio frequency spectrum data, the fuselage appearance features of the UAV from optical image data, and the flight attitude features and flight trajectory of the UAV from radar point cloud data. These features are then matched against the UAV's reported planned flight route information and the identity identifier in the real-time broadcast ADS-B message. If the match is successful, the UAV's legal identity information is marked; if the match fails, it is marked as an unreported target. Based on the real-time distance, flight speed, heading angle, and identity attributes of the drone and the no-fly zone, the primary warning level is dynamically adjusted, and the marked drones are continuously tracked to generate real-time flight trajectories. If the drone has been registered, the planned flight path is used as the basis, and the corresponding primary warning level is triggered according to the deviation between the real-time distance and the planned flight path threshold, and the comparison between the speed and the planned threshold. If the drone has not been registered, it is determined whether it has entered the outer monitoring area, the buffer warning area, or the core control area to trigger the corresponding primary warning level.

[0008] Optionally, based on the aforementioned spatiotemporal database, the historical flight trajectory of the drone that triggered the warning is traced back to obtain the complete flight trajectory of the drone before, during, and after the intrusion, including: Predefine an intrusion behavior pattern and its spatial judgment rules; The real-time flight trajectory is matched with electronic fences and behavior pattern rules. When any pattern rule is met, an intrusion event record is created. The intrusion event record includes at least the event type, occurrence time, location, associated drone ID, and trajectory segment ID. Based on the trajectory segment ID and the event in the intrusion event record, the complete trajectory data within a preset time window before and after the intrusion behavior is retrieved from the spatiotemporal database, as well as the environmental data and device status data within that time period, to form a retrospective analysis context.

[0009] Optionally, multi-dimensional data analysis can be performed on the recalled flight trajectory, and an early warning analysis report can be generated, including: Track point density analysis is performed on the traced flight trajectories to identify clusters and common routes of suspicious targets around the no-fly zone; Draw speed and altitude profiles, analyze the maneuvering behavior of suspicious targets during the set phase, and perform behavior pattern matching on the backtracked flight trajectory to determine whether the flight behavior of suspicious targets conforms to predefined typical reconnaissance, mapping, or logistics patterns. By comprehensively considering the degree of abnormality of flight behavior, the security level attributes of the intrusion area, and the credibility of the identity information of suspicious targets, the intrusion behavior is assessed at a certain level, and the take-off and landing areas of suspicious targets are inferred by combining the starting point of the flight trajectory. Based on the clustering areas and common routes of suspicious targets around the no-fly zone, the maneuvering behavior of suspicious targets during the set phase, whether the flight behavior of suspicious targets conforms to predefined typical reconnaissance, mapping or logistics patterns, the degree of anomaly of suspicious targets, the security level attributes of the intrusion area, the credibility of the identity of suspicious targets, the level assessment, and the source inference results of the take-off and landing points of the flight trajectory, a structured early warning analysis report is generated.

[0010] Optionally, the drone flight path early warning method for no-fly zones further includes: the construction and monitoring deployment of no-fly zones. Based on regional functions and security needs, the no-fly zone is divided into three levels: core control zone, buffer early warning zone, and peripheral monitoring zone, with each zone configured with a corresponding security level. Different security levels correspond to different deployment densities of monitoring equipment, early warning response times, and handling authority. Static boundary electronic fences and dynamic temporary fences are constructed using polygon vector modeling. The static boundary fences are constructed based on the coordinates of the area's legal boundaries or physical walls, while the dynamic temporary fences are demarcated in real time according to temporary security needs and associated with time validity periods. Based on the regional security level and geographical characteristics, high-density radar and optical identification equipment are deployed around the core control area, radio frequency detection and acoustic monitoring equipment are deployed in the buffer early warning area, and long-range radar equipment is deployed in the outer monitoring area. Data interaction protocols and collaborative working mechanisms are configured between the various devices to achieve real-time sharing and correlation analysis of detection data. When a device fails, the detection range of the surrounding devices is adjusted and computing power is supplemented.

[0011] Secondly, the present invention also provides a drone flight path early warning system for no-fly zones, comprising: The construction unit is used to establish a spatial database of no-fly zones, storing the electronic fence boundaries and security level attributes of each no-fly zone; based on the spatial database, detection equipment is deployed within the corresponding geographical area to form an air-ground collaborative monitoring network; The positioning unit is used to collect detection data in real time through the monitoring network, identify, locate and track drones that enter the no-fly zone, and generate real-time flight trajectories; The primary warning unit is used to verify the compliance of real-time flight trajectories based on the reported drone planned routes, mark drones that deviate from the planned routes as suspicious targets, and associate drone identity information and pilot information with the real-time broadcast ADS-B messages, while triggering a primary warning. The advanced early warning unit is used to perform spatial overlay calculations on the flight trajectory of the suspicious target and the electronic fence of the no-fly zone, and determine the intrusion risk level of the suspicious target based on the security level attributes of the electronic fence, and generate intrusion event and advanced early warning information. The synchronization unit is used to synchronize the primary warning information, advanced warning information, UAV identity information, pilot information, flight trajectory and intrusion event records to the spatiotemporal database, wherein the spatiotemporal database supports composite indexes based on time, space and target ID; The early warning analysis unit is used to backtrack the historical flight trajectory of the drone that triggered the early warning based on the spatiotemporal database, obtain the complete flight trajectory of the drone before, during and after the intrusion, and perform multi-dimensional data analysis to generate an early warning analysis report.

[0012] Optionally, the primary early warning unit is specifically used for: By interfacing with radio frequency spectrum data, radar point cloud data, and optical image data, a timestamp alignment algorithm is used to synchronize the same UAV data collected by different devices to a unified time reference, and a spatial coordinate registration algorithm is used to convert the data to the same geographic coordinate system. The extended Kalman filter algorithm is used to fuse radio frequency spectrum data, radar point cloud data, and optical image data to output the estimated position of the UAV and form a trajectory point stream. The system extracts the radio frequency fingerprint features of the UAV from radio frequency spectrum data, the fuselage appearance features of the UAV from optical image data, and the flight attitude features and flight trajectory of the UAV from radar point cloud data. These features are then matched against the UAV's reported planned flight route information and the identity identifier in the real-time broadcast ADS-B message. If the match is successful, the UAV's legal identity information is marked; if the match fails, it is marked as an unreported target. Based on the real-time distance, flight speed, heading angle, and identity attributes of the drone and the no-fly zone, the primary warning level is dynamically adjusted, and the marked drones are continuously tracked to generate real-time flight trajectories. If the drone has been registered, the planned flight path is used as the basis, and the corresponding primary warning level is triggered according to the deviation between the real-time distance and the planned flight path threshold, and the comparison between the speed and the planned threshold. If the drone has not been registered, it is determined whether it has entered the outer monitoring area, the buffer warning area, or the core control area to trigger the corresponding primary warning level.

[0013] Thirdly, the present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of the above-described method for early warning of unmanned aerial vehicle routes in no-fly zones.

[0014] Fourthly, the present invention also provides a storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the above-described method for early warning of unmanned aerial vehicle routes in no-fly zones.

[0015] The above technical solutions enable compliance assessment and tiered risk warning and control of drones in key areas, thereby improving the accuracy of drone safety prevention and control in the region.

[0016] Other features and advantages of the embodiments of the present invention will be described in detail in the following detailed description section. Attached Figure Description

[0017] The accompanying drawings are provided to further illustrate embodiments of the present invention and form part of the specification. They are used together with the following detailed description to explain the embodiments of the present invention, but do not constitute a limitation thereof. In the drawings: Figure 1 This is a flowchart of a method for early warning of unmanned aerial vehicle (UAV) flight paths in no-fly zones, provided by an embodiment of the present invention. Figure 2 This is a structural diagram of a drone flight path early warning system for no-fly zones provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0018] Various embodiments of this disclosure will be described more fully in the following detailed description. This disclosure may have various embodiments, and adjustments and changes may be made therein. However, it should be understood that there is no intention to limit the various embodiments of this disclosure to the specific embodiments disclosed herein, but rather this disclosure should be understood to cover all adjustments, equivalents, and / or alternatives falling within the spirit and scope of the various embodiments of this disclosure.

[0019] In the following, the terms “comprising” or “may include”, which may be used in various embodiments of this disclosure, indicate the presence of the disclosed functions or operations and do not limit the addition of one or more functions or operations. Furthermore, as used in various embodiments of this disclosure, the terms “comprising,” “having,” and their cognates are intended only to indicate a specific feature, number, step, operation, or combination of the foregoing and should not be construed as primarily excluding the presence of one or more other features, numbers, steps, operations, or combinations of the foregoing, or the possibility of adding one or more features, numbers, steps, operations, or combinations of the foregoing.

[0020] In various embodiments of this disclosure, the expression "or" or "at least one of A and / or B" includes any combination or all combinations of the words listed simultaneously. For example, the expression "A or B" or "at least one of A and / or B" may include A, may include B, or may include both A and B.

[0021] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0022] See Figure 1 The diagram shows a flowchart of a drone flight path warning method for no-fly zones in a specific embodiment, including the following execution steps: Step 100: Establish a no-fly zone spatial database to store the electronic fence boundaries and security level attributes of each no-fly zone; based on the spatial database, deploy detection equipment within the corresponding geographical area to form an air-ground collaborative monitoring network.

[0023] Preferably, the detection equipment includes, but is not limited to, drone radio frequency detection, radar detection, and optical recognition equipment.

[0024] In some implementations, the construction and monitoring deployment of no-fly zones include: dividing the no-fly zone into three levels—core control zone, buffer warning zone, and peripheral monitoring zone—based on regional functions and security needs, and configuring a corresponding security level for each zone; different security levels correspond to different deployment densities of monitoring equipment, warning response timeliness, and handling authority; constructing static boundary electronic fences and dynamic temporary fences using polygon vector modeling; wherein the static boundary fence is constructed based on the coordinates of the region's legal boundaries or physical walls, and the dynamic temporary fence is demarcated in real time according to temporary security needs and associated with a time validity period; based on the regional security level and geographical characteristics, deploying high-density radar and optical identification equipment around the core control zone, deploying radio frequency detection and acoustic monitoring equipment in the buffer warning zone, and deploying long-range radar equipment in the peripheral monitoring zone, and configuring data interaction protocols and collaborative working mechanisms between the devices to achieve real-time sharing and correlation analysis of detection data; when a device malfunctions, it triggers adjustments to the detection range of surrounding devices and computing power supplementation.

[0025] Step 101: Collect detection data in real time through the monitoring network, identify, locate and track drones that enter the no-fly zone, and generate real-time flight trajectories.

[0026] Specifically, when executing step 101, the following steps can be performed: S1010: Unify the spatiotemporal reference based on the detection data obtained from the monitoring network, the reported UAV planned routes, and the real-time broadcast ADS-B messages.

[0027] S1011: Assign dynamic weights to detection data, conditional weights to planned routes, and trust weights to ADS-B messages.

[0028] S1012: The adaptive Kalman filter algorithm is used for dynamic weighted fusion calculation. The current time data of the detection data, the planned route, and the ADS-B message are used as the filter input. Based on the dynamic weight assigned to the detection data, the conditional weight assigned to the planned route, and the trust weight assigned to the ADS-B message, the filter gain of each data source is dynamically adjusted to obtain the initial flight trajectory.

[0029] S1013: The initial trajectory is smoothed using cubic B-spline curves, and a confidence value is labeled for each trajectory point of each initial trajectory.

[0030] S1014: Select trajectory points with high confidence, connect them sequentially, and generate a real-time flight trajectory.

[0031] Step 102: Based on the reported drone flight plan, verify the compliance of the real-time flight trajectory, mark drones that deviate from the planned flight path as suspicious targets, and associate the drone identity information and pilot information with the ADS-B message broadcast in real time, while triggering a primary warning.

[0032] S1020: Interacts with radio frequency spectrum data, radar point cloud data, and optical image data. It uses a timestamp alignment algorithm to synchronize the same UAV data collected by different devices to a unified time reference, and uses a spatial coordinate registration algorithm to convert the data to the same geographic coordinate system.

[0033] S1021: Based on the extended Kalman filter algorithm, it performs fusion calculations on radio frequency spectrum data, radar point cloud data, and optical image data to output the estimated position of the UAV and form a trajectory point stream.

[0034] In some implementations, the state vector of the UAV is defined as Where (x,y,z) are three-dimensional spatial coordinates, (v... x ,v y ,v z ) represents three-dimensional velocity, (a x ,a y ,a z ( ) represents three-dimensional acceleration. A uniform acceleration motion model is used to describe the dynamic characteristics of the UAV. The state transition equation is: F k Let w be the state transition matrix. k-1 This is for process noise. When the UAV target is detected for the first time, the initial state is set based on the initial localization result of the radar point cloud data. Initial covariance matrix The diagonal elements are set to the square of the initial positioning error. The UAV's carrier frequency, angle of arrival (AOA), and signal strength (RSSI) are extracted from the radio frequency data, and the horizontal azimuth is estimated using the AOA. and vertical elevation angle Combined with RSSI based on the path loss model, distance is estimated. Convert to measurement coordinates The measurement equation is:

[0035] in, This refers to radio frequency measurement noise.

[0036] Target detection is performed on optical images to obtain the pixel coordinates of the UAV in the images. By combining camera intrinsic parameters, the model is converted into three-dimensional coordinates through perspective projection. The measurement equation is: , This refers to noise in optical measurements.

[0037] Extract the sound pressure level and time difference of arrival of the UAV from the acoustic data to estimate the horizontal azimuth. and distance Convert to two-dimensional horizontal coordinates The measurement equation is:

[0038] In the formula, For acoustic measurement of noise.

[0039] State estimation based on the current time k-1 Covariance Matrix Predict the prior state at time k: ; Calculate the prior covariance matrix: .

[0040] Linear interpolation is used to align sensor data from different sampling frequencies to a unified timestamp. Find the Jacobian matrix for the nonlinear measurement equation. linear model For the coefficient matrix in the measurement equation; for each sensor s, calculate the gain: Update the status sequentially according to the sensor reliability weights: in, For sensor weights, To measure the residuals, the covariance update formula is as follows: .

[0041] A 3σ test is performed on the measurement residuals of each sensor. If the residual exceeds a threshold, the weight ws of that sensor is temporarily reduced to 0.05 to avoid interference from abnormal data. From the updated state... The three-dimensional coordinates (x, y, z) are extracted, and a timestamp tk and confidence level are appended to form trajectory points. The trajectory points at each time point are then stitched together in timestamp order. When data from a certain type of sensor is lost, the predicted state is used as the basis for the prediction. Supplement trajectory points and correct them through update steps after data recovery to ensure continuous and stable trajectory, and finally output trajectory point stream with sampling interval ≤ 1 second.

[0042] S1022: Extract the radio frequency fingerprint features of the UAV from the radio frequency spectrum data, extract the fuselage appearance features of the UAV from the optical image data, and extract the flight attitude features and flight trajectory of the UAV from the radar point cloud data. Perform multi-dimensional matching with the reported UAV planned flight route information and the identity identifier in the real-time broadcast ADS-B message. If the match is successful, mark the legitimate identity information of the UAV; if the match fails, mark it as an unreported target.

[0043] S1023: Based on the real-time distance, flight speed, heading angle, and identity attributes of the drone and the no-fly zone, the warning level is dynamically adjusted, and the marked drones are continuously tracked to generate real-time flight trajectories. If the drone has been registered, the planned flight path is used as the basis, and the corresponding primary warning level is triggered according to the deviation between the real-time distance and the planned flight path threshold, and the comparison between the speed and the planned threshold. If the drone has not been registered, it is determined whether it has entered the outer monitoring area, the buffer warning area, or the core control area to trigger the corresponding primary warning level.

[0044] Step 103: For the suspicious target, perform spatial overlay calculations on its flight trajectory and the electronic fence of the no-fly zone, and determine the intrusion risk level of the suspicious target based on the security level attributes of the electronic fence, and generate intrusion event and advanced early warning information.

[0045] Step 104: Synchronize the primary warning information, advanced warning information, drone identity information, pilot information, flight trajectory, and intrusion event records to the spatiotemporal database.

[0046] This spatiotemporal database supports composite indexes based on time, space, and target ID.

[0047] Step 105: Based on the spatiotemporal database, the historical flight trajectory of the drone that triggered the warning is traced back to obtain the complete flight trajectory of the drone before, during and after the intrusion. Multidimensional data analysis is then performed to generate a warning analysis report.

[0048] Specifically, when executing step 105, the following steps can be performed: S1050: Predefined intrusion behavior patterns and their spatial judgment rules.

[0049] S1051: Match the real-time flight trajectory with the electronic fence and behavior pattern rules. When any pattern rule is met, create an intrusion event record. The intrusion event record includes at least the event type, occurrence time, location, associated drone ID, and trajectory segment ID.

[0050] S1052: Based on the trajectory segment ID and the event that occurred in the intrusion event record, retrieve and load the complete trajectory data within a preset time window before and after the intrusion behavior from the spatiotemporal database, as well as the environmental data and device status data within that time period, to form a retrospective analysis context.

[0051] Specifically, when performing multidimensional data analysis and generating an early warning analysis report in step 105, the following steps can be executed: S1: Perform trajectory point density analysis on the traced flight path to identify the clustering areas and common routes of drones around the no-fly zone.

[0052] S2: Draw speed and altitude profiles, analyze the maneuvering behavior of suspicious targets during the set phase, and perform behavior pattern matching on the backtracked flight trajectory to determine whether the flight behavior of suspicious targets conforms to predefined typical reconnaissance, mapping, or logistics patterns.

[0053] S3: Based on the degree of abnormality of the flight behavior, the security level of the intrusion area, and the credibility of the suspicious target's identity, the intrusion behavior is assessed to determine its level. Combined with the starting point of the flight trajectory, the take-off and landing areas of the suspicious target are traced and inferred.

[0054] S4: Based on the clustering areas and common routes of suspicious targets around the no-fly zone, the maneuvering behavior of suspicious targets during the set phase, whether the flight behavior of suspicious targets conforms to the predefined typical reconnaissance, mapping or logistics patterns, the degree of abnormality of flight behavior, the security level attributes of the intrusion area, the credibility of the identity of suspicious targets, the level assessment, and the source inference results of the take-off and landing areas of the flight trajectory, a structured analysis report is generated.

[0055] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0056] like Figure 2As shown, the following are embodiments of the UAV flight path warning system for no-fly zones provided by this disclosure. These embodiments belong to the same inventive concept as the UAV flight path warning methods for no-fly zones described in the above embodiments. For details not described in detail in the embodiments of the UAV flight path warning system for no-fly zones, please refer to the embodiments of the UAV flight path warning methods for no-fly zones described above.

[0057] A drone flight path early warning system for no-fly zones includes: The construction unit is used to establish a spatial database of no-fly zones, storing the electronic fence boundaries and security level attributes of each area; based on the spatial database, detection equipment is deployed within the corresponding geographical area to form an air-ground collaborative monitoring network; The positioning unit is used to collect detection data in real time through the monitoring network, identify, locate and track drones that enter the no-fly zone, and generate real-time flight trajectories; The primary warning unit is used to verify the compliance of real-time flight trajectories based on the reported drone planned routes, mark drones that deviate from the planned routes as suspicious targets, and associate drone identity information and pilot information with the real-time broadcast ADS-B messages, while triggering a primary warning. The advanced early warning unit is used to perform spatial overlay calculations on the flight trajectory of the suspicious target and the electronic fence of the no-fly zone, and determine the intrusion risk level of the suspicious target based on the security level attributes of the electronic fence, and generate intrusion event and advanced early warning information. The synchronization unit is used to synchronize the primary warning information, advanced warning information, UAV identity information, pilot information, flight trajectory and intrusion event records to the spatiotemporal database, wherein the spatiotemporal database supports composite indexes based on time, space and target ID; The early warning analysis unit is used to backtrack the historical flight trajectory of the drone that triggered the early warning based on the spatiotemporal database, obtain the complete flight trajectory of the drone before, during and after the intrusion, and perform multi-dimensional data analysis to generate an early warning analysis report.

[0058] In some implementations, the primary early warning unit is specifically used for: By interfacing with radio frequency spectrum data, radar point cloud data, and optical image data, a timestamp alignment algorithm is used to synchronize the same UAV data collected by different devices to a unified time reference, and a spatial coordinate registration algorithm is used to convert the data to the same geographic coordinate system. The extended Kalman filter algorithm is used to fuse radio frequency spectrum data, radar point cloud data, and optical image data to output the estimated position of the UAV and form a trajectory point stream. The system extracts the UAV's radio frequency fingerprint features from radio frequency spectrum data, the UAV's fuselage appearance features from optical image data, and the UAV's flight attitude features and flight path trajectory from radar point cloud data. These features are then matched against the UAV's reported planned flight path information and the identity identifier in the real-time broadcast ADS-B message. If the match is successful, the UAV's legitimate identity information is marked; if the match fails, it is marked as an unreported target. Based on the real-time distance, flight speed, heading angle, and identity attributes of the drone and the no-fly zone, the primary warning level is dynamically adjusted, and the marked drones are continuously tracked to generate real-time flight trajectories. If the drone has been registered, the planned flight path is used as the basis, and the corresponding primary warning level is triggered according to the deviation between the real-time distance and the planned flight path threshold, and the comparison between the speed and the planned threshold. If the drone has not been registered, it is determined whether it has entered the outer monitoring area, the buffer warning area, or the core control area to trigger the corresponding primary warning level.

[0059] Figure 3 This is a schematic diagram of the hardware structure of an electronic device that implements various embodiments of the present invention.

[0060] The drone flight path warning method for no-fly zones provided in this application can be applied to electronic devices. Those skilled in the art will understand that the electronic device structure involved in the embodiments of this invention does not constitute a limitation on the electronic device. An electronic device may include more or fewer components than illustrated, or combine certain components, or have different component arrangements. In the embodiments of this invention, the electronic device includes, but is not limited to, laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the embodiments of this application described and / or claimed herein.

[0061] Electronic devices may include processors, external memory interfaces, internal memory, universal serial bus (USB) interfaces, charging management modules, power management modules, batteries, wireless communication modules, audio modules, speakers, microphones, sensor modules, buttons, cameras, displays, and SIM card interfaces, etc.

[0062] It is understood that the structures illustrated in the embodiments of this application do not constitute a specific limitation on the electronic device. In other embodiments of this application, the electronic device may include more or fewer components than illustrated, or combine some components, or split some components, or have different component arrangements. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0063] A processor may include one or more processing units, such as: a central processing unit (CPU), an application processor (AP), a modem processor, a graphics processing unit (GPU), an image signal processor (ISP), a controller, memory, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural network processing unit (NPU). Different processing units may be independent devices or integrated into one or more processors.

[0064] The processor can serve as the nerve center and command center of an electronic device. The controller can generate operation control signals based on the instruction opcode and timing signals to control the fetching and execution of instructions.

[0065] The processor may also include memory for storing instructions and data. In some embodiments, the memory in the processor is a cache memory. This memory can store instructions or data that the processor has just used or that are used repeatedly. If the processor needs to use the instruction or data again, it can retrieve it directly from this memory. This avoids repeated accesses, reduces processor latency, and thus improves system efficiency.

[0066] An external storage interface (ESI) can be used to connect external memory cards, such as microSD cards, to expand the storage capacity of electronic devices. The external memory card communicates with the processor through the ESI to perform data storage functions, such as saving music and video files on the external memory card.

[0067] Internal memory can be used to store computer executable program code, which includes instructions. The processor executes various functional applications and data processing of electronic devices by running the instructions stored in internal memory. Internal memory can include a program storage area and a data storage area. Internal memory can include high-speed random access memory, and can also include non-volatile memory, such as at least one disk storage device, flash memory device, universal flash storage (UFS), etc.

[0068] Wireless communication functionality in electronic devices can be achieved through antennas, wireless communication modules, modem processors, and baseband processors.

[0069] Wireless communication modules can provide solutions for wireless communication applications in electronic devices, including wireless local area networks (WLANs) (such as wireless fidelity (Wi-Fi) networks), Bluetooth (BT), global navigation satellite system (GNSS), frequency modulation (FM), near field communication (NFC), and infrared (IR) technologies.

[0070] Electronic devices can implement audio functions through audio modules, speakers, receivers, microphones, headphone jacks, and application processors.

[0071] Electronic devices can achieve shooting functions through ISPs, cameras, video codecs, GPUs, displays, and application processors.

[0072] Electronic devices can achieve display functions through GPUs, displays, and application processors.

[0073] A GPU is a microprocessor for image processing, connected to the display screen and application processor. GPUs are used to perform mathematical and geometric calculations for graphics rendering. A processor may include one or more GPUs, which execute program instructions to generate or modify display information.

[0074] A display screen is used to display images, videos, etc. A display screen includes a display panel.

[0075] The storage medium provided in this application stores a program product capable of implementing a method for early warning of unmanned aerial vehicle (UAV) flight paths in no-fly zones.

[0076] In some possible implementations, the subject matter of this disclosure, namely, "Method and System for Early Warning of Unmanned Aerial Vehicle Flight Paths in No-Fly Zones," can be implemented as a program product comprising program code that, when run on a terminal device, causes the terminal device to perform the steps described in the "Exemplary Methods" section of this specification according to various exemplary embodiments of this disclosure.

[0077] The storage medium disclosed herein may be any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof.

[0078] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for early warning of unmanned aerial vehicle (UAV) flight paths in no-fly zones, characterized in that, include: Establish a spatial database for no-fly zones to store the electronic fence boundaries and security level attributes of each no-fly zone; Based on the aforementioned spatial database, detection equipment is deployed within the corresponding geographical area to form an air-ground collaborative monitoring network; The monitoring network collects detection data in real time, identifies, locates, and tracks drones entering the no-fly zone, and generates real-time flight trajectories. Based on the reported drone flight plans, the real-time flight trajectory is verified for compliance. Drones that deviate from the planned flight path are marked as suspicious targets. The drone identity information and pilot information are associated with the real-time broadcast ADS-B message, and a primary warning is triggered. For the suspicious target, its flight trajectory is spatially superimposed with the electronic fence of the no-fly zone, and the intrusion risk level of the suspicious target is determined according to the security level attribute of the electronic fence, generating intrusion events and advanced early warning information; The primary warning information, advanced warning information, drone identity information, pilot information, flight trajectory, and intrusion event records are synchronized to a spatiotemporal database, which supports composite indexes based on time, space, and target ID. Based on the aforementioned spatiotemporal database, the historical flight trajectories of the drones that triggered the early warning are traced back to obtain the complete flight trajectories of the drones before, during, and after the intrusion. Multidimensional data analysis is then performed to generate an early warning analysis report.

2. The method for UAV flight path early warning in no-fly zones according to claim 1, characterized in that, The monitoring network collects detection data in real time to identify, locate, and track drones entering the no-fly zone, generating real-time flight trajectories, including: The spatiotemporal reference will be unified based on the detection data obtained from the monitoring network, the reported UAV flight plans, and the real-time broadcast ADS-B messages. Dynamic weights are assigned to the detected data, conditional weights are assigned to the planned flight routes, and trust weights are assigned to the ADS-B messages. An adaptive Kalman filter algorithm is used for dynamic weighted fusion calculation. The current time data of the detection data, the planned route, and the ADS-B message are used as the filter input. Based on the dynamic weight assigned to the detection data, the conditional weight assigned to the planned route, and the trust weight assigned to the ADS-B message, the filter gain of each data source is dynamically adjusted to obtain the initial flight trajectory. The initial trajectory was smoothed using cubic B-spline curves, and a confidence value was labeled for each trajectory point of each initial trajectory. The trajectory points with high confidence are selected and connected sequentially to generate a real-time flight trajectory.

3. The method for early warning of unmanned aerial vehicle (UAV) flight paths in no-fly zones according to claim 1, characterized in that, Based on the reported drone flight plans, the real-time flight trajectories are verified for compliance. Drones deviating from the planned flight paths are marked as suspicious targets. The drone's identity information and pilot information are linked to the real-time broadcast ADS-B messages, triggering a primary warning, including: By interfacing with radio frequency spectrum data, radar point cloud data, and optical image data, a timestamp alignment algorithm is used to synchronize the same UAV data collected by different devices to a unified time reference, and a spatial coordinate registration algorithm is used to convert the data to the same geographic coordinate system. The extended Kalman filter algorithm is used to fuse radio frequency spectrum data, radar point cloud data, and optical image data to output the estimated position of the UAV and form a trajectory point stream. The system extracts the radio frequency fingerprint features of the UAV from radio frequency spectrum data, the fuselage appearance features of the UAV from optical image data, and the flight attitude features and flight trajectory of the UAV from radar point cloud data. These features are then matched against the UAV's reported planned flight route information and the identity identifier in the real-time broadcast ADS-B message. If the match is successful, the UAV's legal identity information is marked; if the match fails, it is marked as an unreported target. Based on the real-time distance, flight speed, heading angle, and identity attributes of the drone and the no-fly zone, the primary warning level is dynamically adjusted, and the marked drones are continuously tracked to generate real-time flight trajectories. If the drone has been registered, the planned flight path is used as the basis, and the corresponding primary warning level is triggered according to the deviation between the real-time distance and the planned flight path threshold, and the comparison between the speed and the planned threshold. If the drone has not been registered, it is determined whether it has entered the outer monitoring area, the buffer warning area, or the core control area to trigger the corresponding primary warning level.

4. The method for early warning of unmanned aerial vehicle (UAV) flight paths in no-fly zones according to claim 1, characterized in that, Based on the aforementioned spatiotemporal database, the historical flight trajectories of the drones that triggered the early warning are traced back to obtain the complete flight trajectories of the drones before, during, and after the intrusion, including: Predefine an intrusion behavior pattern and its spatial judgment rules; The real-time flight trajectory is matched with electronic fences and behavior pattern rules. When any pattern rule is met, an intrusion event record is created. The intrusion event record includes at least the event type, occurrence time, location, associated drone ID, and trajectory segment ID. Based on the trajectory segment ID and the event in the intrusion event record, the complete trajectory data within a preset time window before and after the intrusion behavior is retrieved from the spatiotemporal database, as well as the environmental data and device status data within that time period, to form a retrospective analysis context.

5. The method for UAV flight path early warning in no-fly zones according to claim 1, characterized in that, Perform multi-dimensional data analysis on the recalled flight trajectory and generate an early warning analysis report, including: Track point density analysis is performed on the traced flight trajectories to identify clusters and common routes of suspicious targets around the no-fly zone; Draw speed and altitude profiles, analyze the maneuvering behavior of suspicious targets during the set phase, and perform behavior pattern matching on the backtracked flight trajectory to determine whether the flight behavior of suspicious targets conforms to predefined typical reconnaissance, mapping, or logistics patterns. By comprehensively considering the degree of abnormality of flight behavior, the security level attributes of the intrusion area, and the credibility of the identity information of suspicious targets, the intrusion behavior is assessed at a certain level, and the take-off and landing areas of suspicious targets are inferred by combining the starting point of the flight trajectory. Based on the clustering areas and common routes of suspicious targets around the no-fly zone, the maneuvering behavior of suspicious targets during the set phase, whether the flight behavior of suspicious targets conforms to predefined typical reconnaissance, mapping or logistics patterns, the degree of abnormality of flight behavior, the security level attributes of the intrusion area, the credibility of the identity of suspicious targets, the level assessment, and the source inference results of the take-off and landing areas of the flight trajectory, a structured early warning analysis report is generated.

6. The method for early warning of unmanned aerial vehicle (UAV) flight paths in no-fly zones according to claim 1, characterized in that, The drone flight path early warning method for no-fly zones also includes: the construction and monitoring deployment of no-fly zones. Based on regional functions and security needs, the no-fly zone is divided into three levels: core control zone, buffer early warning zone, and peripheral monitoring zone, with each zone configured with a corresponding security level. Different security levels correspond to different deployment densities of monitoring equipment, early warning response times, and handling authority. Static boundary electronic fences and dynamic temporary fences are constructed using polygon vector modeling. The static boundary fences are constructed based on the coordinates of the area's legal boundaries or physical walls, while the dynamic temporary fences are demarcated in real time according to temporary security needs and associated with time validity periods. Based on the regional security level and geographical characteristics, high-density radar and optical identification equipment are deployed around the core control area, radio frequency detection and acoustic monitoring equipment are deployed in the buffer early warning area, and long-range radar equipment is deployed in the outer monitoring area. Data interaction protocols and collaborative working mechanisms are configured between the various devices to achieve real-time sharing and correlation analysis of detection data. When a device fails, the detection range of the surrounding devices is adjusted and computing power is supplemented.

7. A drone flight path early warning system for no-fly zones, characterized in that, include: The building unit is used to establish a no-fly zone spatial database, storing the electronic fence boundaries and security level attributes of each no-fly zone; Based on the aforementioned spatial database, detection equipment is deployed within the corresponding geographical area to form an air-ground collaborative monitoring network; The positioning unit is used to collect detection data in real time through the monitoring network, identify, locate and track drones that enter the no-fly zone, and generate real-time flight trajectories; The primary warning unit is used to verify the compliance of real-time flight trajectories based on the reported drone planned routes, mark drones that deviate from the planned routes as suspicious targets, and associate drone identity information and pilot information with the real-time broadcast ADS-B messages, while triggering a primary warning. The advanced early warning unit is used to perform spatial overlay calculations on the flight trajectory of the suspicious target and the electronic fence of the no-fly zone, and determine the intrusion risk level of the suspicious target based on the security level attributes of the electronic fence, and generate intrusion event and advanced early warning information. The synchronization unit is used to synchronize the primary warning information, advanced warning information, UAV identity information, pilot information, flight trajectory and intrusion event records to the spatiotemporal database, wherein the spatiotemporal database supports composite indexes based on time, space and target ID; The early warning analysis unit is used to backtrack the historical flight trajectory of the drone that triggered the early warning based on the spatiotemporal database, obtain the complete flight trajectory of the drone before, during and after the intrusion, and perform multi-dimensional data analysis to generate an early warning analysis report.

8. The UAV flight path early warning system for no-fly zones according to claim 7, characterized in that, The primary early warning unit is specifically used for: By interfacing with radio frequency spectrum data, radar point cloud data, and optical image data, a timestamp alignment algorithm is used to synchronize the same UAV data collected by different devices to a unified time reference, and a spatial coordinate registration algorithm is used to convert the data to the same geographic coordinate system. The extended Kalman filter algorithm is used to fuse radio frequency spectrum data, radar point cloud data, and optical image data to output the estimated position of the UAV and form a trajectory point stream. The radio frequency fingerprint features of the UAV are extracted from radio frequency spectrum data, the fuselage appearance features of the UAV are extracted from optical image data, and the flight attitude features and flight trajectory of the UAV are extracted from radar point cloud data. These features are then matched with the reported UAV planned flight route information and the identity identifier in the real-time broadcast ADS-B message in multiple dimensions. If a match is successful, the drone's legal identity information will be marked; if a match fails, it will be marked as an unreported target. Based on the real-time distance, flight speed, heading angle, and identity attributes of the drone and the no-fly zone, the primary warning level is dynamically adjusted, and the marked drones are continuously tracked to generate real-time flight trajectories. If the drone is a registered drone, the planned flight path is used as the basis, and the corresponding primary warning level is triggered according to the deviation between the real-time distance and the planned flight path threshold, and the comparison between the speed and the planned threshold. If the drone is unregistered, it will be determined whether it entered the outer monitoring area, the buffer warning area, or the core control area, triggering the corresponding primary warning level.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps of the unmanned aerial vehicle (UAV) flight path warning method for no-fly zones as described in any one of claims 1 to 6.

10. A storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the unmanned aerial vehicle (UAV) flight path warning method for no-fly zones as described in any one of claims 1 to 6.

Images