Drone Locking Monitoring Method and System Based on Cloud Control Platform

Abstract

The present invention relates to the technical field of UAV monitoring, and discloses a UAV locking and monitoring method and system based on a cloud control platform. The method includes the following steps: collecting the characteristic data of the UAV and transmitting the characteristic data to the cloud control platform; preprocessing the characteristic data by the cloud control platform; extracting the behavior characteristic parameters of the UAV based on the preprocessed characteristic data; detecting the abnormal behavior of the UAV based on the behavior characteristic parameters; obtaining the environmental data and performing behavior pattern matching on the UAV with abnormal behavior; taking illegal UAV response and management measures for the UAV with an illegal matching result. The present invention significantly improves the efficiency and effect of illegal UAV identification, provides a systematic and intelligent solution for the UAV supervision field, and has important value for promoting the standardized development of the UAV industry.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned aerial vehicle (UAV) monitoring, and particularly to a UAV locking and monitoring method and system based on a cloud control platform. Background Art

[0002] With the rapid development of technology, UAV technology has become a booming field globally, and is widely used in multiple industries such as agricultural monitoring, topographic mapping, cargo transportation, film shooting, emergency rescue, and environmental monitoring. UAVs, with their advantages of flexibility, high cost-effectiveness, and the ability to perform dangerous tasks, have greatly expanded the boundaries of human activities and promoted the diversified development of the social economy. However, the popularization of UAV technology has also brought many safety hazards and regulatory challenges. Unauthorized UAV flights may interfere with aviation order and cause air traffic accidents. For example, illegal approach of UAVs to airport runways may force flight delays or even cancellations, posing a serious threat to aviation safety. In addition, UAVs may also be used for illegal activities. In view of this, various regions have strengthened the formulation of UAV management regulations, requiring UAVs to be registered and comply with specific flight rules, while increasing the crackdown on illegal UAV activities. However, most of the existing regulatory means and technologies rely on manual visual observation, ground radar monitoring, or simple electronic fence technology. These methods have obvious deficiencies in coverage, accuracy, response speed, and the ability to identify illegal UAVs, and are difficult to effectively cope with the increasing number of UAVs and complex and changeable usage scenarios. UAVs are small in size, low in flight altitude, and fast in moving speed. Traditional radar systems often have difficulty accurately capturing their dynamics, especially in complex urban environments, where the occlusion of buildings and terrain increases the identification difficulty. Relying solely on a single data source (such as GPS position information) is difficult to comprehensively evaluate whether the flight behavior of UAVs is abnormal, lacking the ability to analyze multi-dimensional data comprehensively. The existing monitoring systems do not adequately consider environmental factors, such as the impact of weather changes and geographical environment diversity on UAV flight characteristics, resulting in high false alarm rates and missed alarm rates. In summary, although the wide application of UAV technology has brought great value to society, the accompanying safety and regulatory issues cannot be ignored.

[0003] As disclosed in the Chinese patent with the authorization announcement number CN108291952B, a drone and its flight status supervision method and monitoring system are provided. The method includes: generating an offline flight certificate for the drone according to the offline flight declaration information, and providing the offline flight certificate to the drone, so as to restrict the flight behavior of the drone in the offline flight mode through the offline flight certificate; or, reporting the flight information of the drone, judging whether the flight information of the drone conforms to the flight safety regulations according to the preset safe flight parameters, and when it is judged that the flight information of the drone violates the flight safety regulations, generating a corresponding flight restriction instruction and sending the flight restriction instruction to the drone for execution to restrict the flight behavior of the drone in the online flight mode.

[0004] As disclosed in the patent application with the publication number CN105912288A, a comprehensive processing and display method and system for monitoring the flight status of drones are provided. A comprehensive processing and display interface is established. The comprehensive processing and display interface is divided into a fixed display bar interface and a switching display bar interface. The fixed display bar interface is divided into: a drone attitude display sub-interface, a basic flight control sub-interface, and a basic flight status display sub-interface. The switching display bar interface switches among a route planning and photo-taking setting sub-interface, a flight monitoring display sub-interface, and a data analysis sub-interface. Compared with the prior art, the invention can intuitively display the key flight status data of the drone in the flight monitoring display sub-interface in the form of graphics, animations, etc., which is convenient for the monitoring personnel to find the required information in time. At the same time, it also has a route planning function combined with photo-taking settings and flight settings and a data comprehensive analysis function.

[0005] The above technical solutions all have the problems raised in this background technology: insufficient consideration of environmental factors, resulting in relatively high false alarm rates and missed alarm rates.

[0006] The information disclosed in this background technology section is only intended to increase the understanding of the overall background of the present invention, and should not be regarded as an admission or any form of implication that this information constitutes the prior art already known to those of ordinary skill in the art. Summary of the Invention

[0007] The technical problem to be solved by the present invention is to overcome the defects of the prior art, and provide a drone locking and monitoring method and system based on a cloud control platform, so as to improve the efficiency and effect of illegal drone identification and provide a systematic and intelligent solution for the field of drone supervision.

[0008] To solve the above technical problems, the present invention provides the following technical solutions:

[0009] In a first aspect, the present invention provides a drone locking and monitoring method based on a cloud control platform, including the following steps:

[0010] S1: Collect the characteristic data of the drone and transmit the characteristic data to the cloud control platform;

[0011] S2: The cloud control platform preprocesses the characteristic data;

[0012] S3: Based on the preprocessed characteristic data, extract the behavior characteristic parameters of the drone;

[0013] S4: Detect abnormal behaviors of the drone based on the behavior characteristic parameters;

[0014] S5: Obtain environmental data and perform behavior pattern matching on the drones with abnormal behaviors;

[0015] S6: Take illegal drone response and management measures for the drones with illegal matching results.

[0016] As a preferred solution of the drone locking and monitoring method based on the cloud control platform of the present invention, wherein: the characteristic data includes three-dimensional coordinate data, communication signal data, and drone images;

[0017] The three-dimensional coordinate data is obtained by lidar; the communication signal data is the communication signal between the drone and the remote controller or the ground station, and is collected by a wireless signal detector; the drone images are obtained by an optoelectronic sensor.

[0018] As a preferred solution of the drone locking and monitoring method based on the cloud control platform of the present invention, wherein: the preprocessing is specifically as follows:

[0019] Perform data cleaning on the characteristic data;

[0020] Perform format calibration and coordinate alignment on each type of characteristic data;

[0021] Organize the three-dimensional coordinate data into a time series as a coordinate sequence, and draw a flight trajectory map based on the coordinate sequence; the flight trajectory map is the drone flight trajectory composed of the coordinate points of the drone, and each coordinate point corresponds to a three-dimensional coordinate data and the corresponding timestamp;

[0022] Perform frequency domain analysis on the communication signal data to obtain a communication signal spectrogram;

[0023] Perform image enhancement on the drone images.

[0024] As a preferred solution of the drone locking and monitoring method based on the cloud control platform of the present invention, wherein: the behavior characteristic parameters include flight trajectory characteristic parameters, flight mode characteristic parameters, communication behavior characteristic parameters, and target shape characteristic parameters;

[0025] The flight trajectory characteristic parameters include the average flight speed, the maximum acceleration, and the average flight altitude; the extraction method is as follows:

[0026] Based on the three-dimensional coordinate data, calculate the distance between any two adjacent coordinate points in the flight trajectory diagram and divide it by the time difference between the two adjacent coordinate points to obtain the average speed between any two adjacent coordinate points; find the average value of the average speeds between all adjacent coordinate points to obtain the average flight speed; perform two differentiations of the three-dimensional coordinate data of each coordinate point in the flight trajectory characteristic parameters with respect to time to obtain the acceleration of each coordinate point and extract the maximum value of the acceleration of the coordinate points as the maximum acceleration; extract the flight altitude of each coordinate point in the flight trajectory diagram and find the average value to obtain the average flight altitude.

[0027] As a preferred embodiment of the UAV locking and monitoring method based on the cloud control platform of the present invention, wherein: the flight mode characteristic parameters include the frequency and duration of each flight mode; the flight modes include straight flight, turning, hovering, ascending, descending, and hovering; the extraction method of the flight mode characteristic parameters is as follows:

[0028] Use a machine learning model to identify the trajectory segments corresponding to each flight model from the flight trajectory diagram; count the number of times each flight model appears per unit time as the frequency of each flight mode; count the total duration of each flight mode per unit time as the duration of each flight mode.

[0029] As a preferred embodiment of the UAV locking and monitoring method based on the cloud control platform of the present invention, wherein: the communication behavior characteristic parameters include the signal strength characteristic and the signal frequency characteristic, and the extraction method is as follows:

[0030] Calculate the mean and variance of the signal strength of the communication signal data as the signal strength characteristic; extract the frequency range and center frequency of the communication signal from the communication signal spectrogram as the signal frequency characteristic.

[0031] The target shape characteristic parameters include the model and color of the UAV, and the extraction method is as follows:

[0032] Perform target detection on the UAV image, mark the UAV area in the UAV image, and crop a feature map of a fixed size containing the UAV area;

[0033] Input the feature map into a trained convolutional neural network model to output the model and color of the UAV.

[0034] As a preferred embodiment of the UAV locking and monitoring method based on the cloud control platform of the present invention, wherein: the method for detecting abnormal behavior is as follows:

[0035] Collect normal UAV feature data and extract behavioral feature parameters as normal samples; normalize and encode the behavioral feature parameters of the normal samples to form a behavioral feature vector; the form of any behavioral feature vector is as follows:

[0036] ;

[0037] Among them, represents the behavioral feature vector of the i-th normal sample, where the value range of i is 1, 2, ……, m, and m is the number of normal samples; represents the j-th normalized and encoded behavioral feature parameter of the i-th normal sample, where the value range of j is 1, 2, ……, n, and n is the total number of behavioral feature parameters of any UAV;

[0038] Construct an abnormal probability model based on Gaussian distribution, and the equation is as follows:

[0039] ;

[0040] Among them, represents the abnormal probability density function of; represents the weight coefficient of the k-th Gaussian distribution, where the value range of k is 1, 2, ……, K, and K is the number of Gaussian distributions in the abnormal probability model;

[0041] represents the covariance matrix of the k-th Gaussian distribution; represents the determinant of; represents the inverse matrix of; represents the mean vector of the k-th Gaussian distribution; represents the transpose of the matrix in the parentheses;

[0042] Perform the training of the abnormal probability model, and the method is as follows: Use the EM algorithm for parameter estimation to determine the weight coefficient of each Gaussian distribution , covariance matrix , mean vector values, and determine the number K of Gaussian distributions through the AIC criterion; Save the trained abnormal probability model;

[0043] Normalize and encode the behavioral feature parameters of the UAV to be detected for abnormal behavior, form a behavioral feature vector, denoted as , and input the behavioral feature vector into the trained abnormal probability model to obtain the abnormal behavior detection result.

[0044] As a preferred solution of the UAV locking and monitoring method based on the cloud control platform of the present invention, wherein: the specific manner of obtaining the abnormal behavior detection result is as follows:

[0045] Calculate based on the equation of the abnormal probability model of the abnormal probability density function, denoted as ;

[0046] Calculate of the logarithmic probability function , and the formula is as follows:

[0047] ;

[0048] If , then the UAV has no abnormal behavior; otherwise, the UAV has abnormal behavior;

[0049] Among them, represents the first abnormal threshold, and the calculation formula is as follows:

[0050] ;

[0051] Among them, represents the logarithmic probability function of the behavior feature vector of the i-th normal sample , and the calculation formula is as follows:

[0052] ;

[0053] represents the mean value of the logarithmic probability functions of the behavior feature vectors of m normal samples, represents the variance of the logarithmic probability functions of the behavior feature vectors of m normal samples;

[0054] represents the second abnormal threshold, and the calculation formula is as follows:

[0055] .

[0056] As a preferred solution of the method for locking and monitoring an unmanned aerial vehicle (UAV) based on a cloud control platform according to the present invention, wherein: the cloud control platform is configured with a behavior pattern database of the UAV; the behavior pattern database contains M reference samples, and the reference samples include legal samples and illegal samples; each reference sample corresponds to a behavior pattern vector, and the behavior pattern vector is formed by splicing a behavior feature vector and an environmental feature vector; the environmental feature vector of each reference sample is composed of the environmental data corresponding to the reference sample after normalization and encoding processing; the environmental data includes wind speed, wind direction, temperature, relative humidity, visibility, cloud thickness, flight environment; the flight environment is the geographical environment corresponding to the area where the UAV flies, including mountains, hills, plains, plateaus, basins, waters, and urban areas.

[0057] As a preferred solution of the method for locking and monitoring an unmanned aerial vehicle (UAV) based on a cloud control platform according to the present invention, wherein: the method for behavior pattern matching is as follows:

[0058] Collect the environmental data of the UAV to be matched, form an environmental feature vector after normalization and encoding processing, and splice it with the behavior feature vector to form the behavior pattern vector of the UAV to be matched;

[0059] Calculate the similarity between the behavior pattern vector of the UAV to be matched and the behavior pattern vector of each reference sample in the behavior pattern database;

[0060] Select the N reference samples with the highest similarity as the similar samples of the UAV to be matched;

[0061] Calculate the legal matching degree of the UAV to be matched, and the formula is as follows:

[0062] ;

[0063] Wherein, R represents the legal matching degree; represents the similarity between the behavior pattern vector of the UAV to be matched and the behavior pattern vector of the p-th similar sample, and the value range of p is 1, 2,..., N; represents the similarity between the behavior pattern vector of the UAV to be matched and the behavior pattern vector of the q-th similar sample with the sample type of legal sample, and the value range of q is 1, 2,..., Q, and Q represents the number of legal samples in the similar samples;

[0064] If the legal matching degree R is higher than the legal threshold, the matching result of the UAV to be matched is legal; otherwise, the matching result of the UAV to be matched is illegal.

[0065] In a second aspect, the present invention provides a drone locking and monitoring system based on a cloud control platform, including a monitoring and locking module, a preprocessing module, a feature extraction module, an anomaly detection module, a data acquisition module, a behavior matching module, and a control module; wherein:

[0066] The monitoring and locking module is used to locate the drone and continuously collect the feature data of the drone;

[0067] The preprocessing module is used to preprocess the feature data of the drone;

[0068] The feature extraction module is used to extract the behavior feature parameters of the drone based on the preprocessed feature data;

[0069] The anomaly detection module is used to detect the abnormal behavior of the drone based on the behavior feature parameters;

[0070] The data acquisition module is used to collect the environmental data of the flight environment of the drone;

[0071] The behavior matching module is used to match the behavior patterns of the drones with abnormal behaviors;

[0072] The control module is used to take illegal drone response and management measures for the drones with illegal matching results.

[0073] In a third aspect, the present invention provides an electronic device, including: a memory for storing instructions; a processor for executing the instructions, so that the device performs the operations of implementing the drone locking and monitoring method based on the cloud control platform of the present invention.

[0074] In a fourth aspect, the present invention provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the drone locking and monitoring method based on the cloud control platform of the present invention.

[0075] Compared with the prior art, the beneficial effects achieved by the present invention are as follows:

[0076] By comprehensively collecting the three-dimensional coordinate data, communication signal data, and image information of the drone, this solution constructs a multi-dimensional feature data set, providing a solid foundation for subsequent precise analysis. Through in-depth analysis of the feature data and extraction of multi-dimensional behavior feature parameters such as flight trajectories, patterns, communication behaviors, and target shapes, this solution can more deeply understand the flight patterns and intentions of the drone and can effectively identify even complex flight strategies.

[0077] The combined anomaly behavior detection that incorporates multiple characteristic parameters can handle the complex distributions in the data, effectively distinguish normal and abnormal flight patterns, and improve the sensitivity and accuracy of detection; incorporating environmental data for behavior pattern matching makes the judgment process closer to the actual situation, reduces false positives caused by environmental factors, and enhances the robustness and adaptability of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0078] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings. Among them:

[0079] Figure 1 is a flowchart of a method for locking and monitoring an unmanned aerial vehicle based on a cloud control platform provided by the present invention;

[0080] Figure 2 is a schematic structural diagram of a system for locking and monitoring an unmanned aerial vehicle based on a cloud control platform provided by the present invention;

[0081] Figure 3 is a logic diagram for judging the legality of an unmanned aerial vehicle provided by the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0082] The following will elaborate on the technical solutions of the present invention through the drawings and specific embodiments. It should be understood that the embodiments of the present invention and the specific features in the embodiments are detailed descriptions of the technical solutions of the present invention, rather than limitations on the technical solutions of the present invention. Without conflict, the technical features in the embodiments of the present invention and the embodiments can be combined with each other.

[0083] Embodiment 1

[0084] This embodiment introduces a method for locking and monitoring an unmanned aerial vehicle based on a cloud control platform. Referring to Figure 1 , the method includes the following steps:

[0085] S1: Collect the characteristic data of the unmanned aerial vehicle and transmit the characteristic data to the cloud control platform;

[0086] The characteristic data includes three-dimensional coordinate data, communication signal data, and unmanned aerial vehicle images;

[0087] The three-dimensional coordinate data is obtained through a lidar and can be used to accurately track the position and movement trajectory of the unmanned aerial vehicle, providing a data basis for subsequent analysis of the speed, direction, altitude, speed, heading, etc. of the unmanned aerial vehicle;

[0088] The communication signal data is the communication signal between the drone and the remote controller or the ground station, which is collected by a wireless signal detector and can assist in identifying the identity of the drone, control instructions, etc.;

[0089] The drone images are obtained by optoelectronic sensors, such as visible light cameras, infrared cameras, thermal imagers, etc., and can identify the shape, color, thermal characteristics, etc. of the drone.

[0090] S2: The cloud control platform preprocesses the feature data; specifically as follows:

[0091] Perform data cleaning on the feature data; remove noise points, outliers, and invalid data, such as incorrect radar echoes or interference signals;

[0092] Perform format calibration and coordinate alignment on each type of feature data; convert feature data from different sources to a unified time series and coordinate system to ensure the synchronization and alignment of feature data from different sources in time and space, facilitating subsequent analysis;

[0093] Organize the three-dimensional coordinate data into a time series as a coordinate sequence, and draw a flight trajectory map based on the coordinate sequence; the flight trajectory map is the drone flight trajectory composed of the coordinate points of the drone, and each coordinate point corresponds to a three-dimensional coordinate data and the corresponding timestamp;

[0094] Perform frequency domain analysis on the communication signal data to obtain a communication signal spectrum diagram;

[0095] Perform image enhancement on the drone images; such as adjusting brightness and contrast to better identify features such as the size, model, and color of the drone.

[0096] S3: Based on the preprocessed feature data, extract the behavioral feature parameters of the drone;

[0097] The behavioral feature parameters include flight trajectory feature parameters, flight mode feature parameters, communication behavior feature parameters, and target shape feature parameters;

[0098] The flight trajectory feature parameters include average flight speed, maximum acceleration, and average flight altitude; the extraction method is as follows:

[0099] Calculate the distance between any two adjacent coordinate points in the flight trajectory map based on the three-dimensional coordinate data and divide it by the time difference between the two adjacent coordinate points to obtain the average speed between any two adjacent coordinate points; find the mean value of the average speeds between all adjacent coordinate points to obtain the average flight speed; perform double differentiation of the three-dimensional coordinate data of each coordinate point in the flight trajectory characteristic parameters with respect to time to obtain the acceleration of each coordinate point and extract the maximum value of the acceleration of the coordinate points as the maximum acceleration; extract the flight altitude of each coordinate point in the flight trajectory map and find the mean value to obtain the average flight altitude.

[0100] The flight mode characteristic parameters include the frequency and duration of each flight mode; the flight modes include straight flight, turning, hovering, ascending, descending, and hovering; the extraction method of the flight mode characteristic parameters is as follows:

[0101] Through machine learning models, such as convolutional neural networks, YOLO, SSD, etc., identify the trajectory segments corresponding to each flight model from the flight trajectory map; count the number of times each flight model appears per unit time as the frequency of each flight mode; count the total duration of each flight mode per unit time as the duration of each flight mode.

[0102] The communication behavior characteristic parameters include signal strength characteristics and signal frequency characteristics, and the extraction method is as follows:

[0103] Calculate the mean value and variance of the signal strength of the communication signal data as the signal strength characteristics; extract the frequency range and center frequency of the communication signal from the communication signal spectrogram as the signal frequency characteristics.

[0104] The target appearance characteristic parameters include the model and color of the unmanned aerial vehicle, and the extraction method is as follows:

[0105] Perform object detection on the unmanned aerial vehicle image, mark the unmanned aerial vehicle area in the unmanned aerial vehicle image, and crop out a feature map of a fixed size containing the unmanned aerial vehicle area;

[0106] Input the feature map into a trained convolutional neural network model to output the model and color of the unmanned aerial vehicle.

[0107] The convolutional neural network model is obtained by fine-tuning and training a pre-trained model (such as VGG, ResNet, etc.) on an unmanned aerial vehicle image set; the unmanned aerial vehicle image set is a large number of feature maps containing unmanned aerial vehicle areas, covering various models and colors of unmanned aerial vehicles.

[0108] S4: Perform abnormal behavior detection on the unmanned aerial vehicle based on the behavior characteristic parameters; the method is as follows:

[0109] Collect normal UAV feature data and extract behavior feature parameters as normal samples; normalize and encode the behavior feature parameters of the normal samples to form behavior feature vectors; the form of any behavior feature vector is as follows:

[0110] ;

[0111] Among them, represents the behavior feature vector of the i-th normal sample, and the value range of i is 1, 2,..., m, where m is the number of normal samples; represents the j-th behavior feature parameter of the i-th normal sample after normalization and encoding, and the value range of j is 1, 2,..., n, where n is the total number of behavior feature parameters of any UAV;

[0112] Construct an abnormal probability model based on the Gaussian distribution, and the equation is as follows:

[0113] ;

[0114] Among them, represents the abnormal probability density function of; represents the weight coefficient of the k-th Gaussian distribution, and the value range of k is 1, 2,..., K, where K is the number of Gaussian distributions in the abnormal probability model;

[0115] represents the covariance matrix of the k-th Gaussian distribution; represents the determinant of; represents the inverse matrix of; represents the mean vector of the k-th Gaussian distribution; represents the transpose of the matrix in the parentheses;

[0116] Perform training on the abnormal probability model, and the method is as follows: use the EM algorithm for parameter estimation to determine the weight coefficient , covariance matrix , mean vector of the values, and determine the number K of Gaussian distributions through the AIC criterion; save the trained abnormal probability model;

[0117] Normalize and encode the behavior feature parameters of the UAV to be detected for abnormal behavior, form a behavior feature vector, denoted as , and input the behavior feature vector into the trained abnormal probability model to obtain the abnormal behavior detection result; specifically as follows:

[0118] Calculate based on the equation of the abnormal probability model The abnormal probability density function, denoted as ;

[0119] Calculate The logarithmic probability function of , and the formula is as follows:

[0120] ;

[0121] If , then the UAV has no abnormal behavior; otherwise, the UAV has abnormal behavior;

[0122] Among them, Represents the first abnormal threshold, and the calculation formula is as follows:

[0123] ;

[0124] Among them, Represents the behavior feature vector of the i-th normal sample The logarithmic probability function of, and the calculation formula is as follows:

[0125] ;

[0126] Represents the mean value of the logarithmic probability functions of the behavior feature vectors of m normal samples, Represents the variance of the logarithmic probability functions of the behavior feature vectors of m normal samples;

[0127] Represents the second abnormal threshold, and the calculation formula is as follows:

[0128] .

[0129] S5: Obtain environmental data and perform behavior pattern matching on the UAVs with abnormal behavior;

[0130] The cloud control platform is configured with a behavior pattern database of UAVs; the behavior pattern database contains M reference samples, and the reference samples include legal samples and illegal samples; each reference sample corresponds to a behavior pattern vector, and the behavior pattern vector is composed of a behavior feature vector and an environmental feature vector spliced together; the environmental feature vector of each reference sample is composed of the environmental data corresponding to the reference sample after normalization and encoding processing; the environmental data includes wind speed, wind direction, temperature, relative humidity, visibility, cloud thickness, flight environment; the flight environment is the geographical environment corresponding to the area where the UAV flies, including mountains, hills, plains, plateaus, basins, waters, urban areas.

[0131] Since the behavior patterns and characteristics of drones can be interfered by environmental factors. For example, when flying in mountainous areas, the drone will fly at a relatively high altitude and has a high frequency of ascending and descending to avoid mountain obstacles. Therefore, the abnormal behavior of the drone may be caused by environmental factors, and it is necessary to combine environmental data to further judge the legality of the drone with abnormal behavior.

[0132] The method for matching the behavior patterns is as follows:

[0133] Collect the environmental data of the drone to be matched, and after normalization and encoding, form an environmental feature vector, and splice it with the behavior feature vector to form the behavior pattern vector of the drone to be matched;

[0134] Calculate the similarity between the behavior pattern vector of the drone to be matched and the behavior pattern vectors of each reference sample in the behavior pattern database; methods such as Euclidean distance and cosine similarity can be selected to calculate the similarity between behavior pattern vectors;

[0135] Select the N reference samples with the highest similarity as the similar samples of the drone to be matched;

[0136] Calculate the legal matching degree of the drone to be matched. The formula is as follows:

[0137] ;

[0138] Where R represents the legal matching degree; represents the similarity between the behavior pattern vector of the drone to be matched and the behavior pattern vector of the p-th similar sample, and the value range of p is 1, 2,..., N; represents the similarity between the behavior pattern vector of the drone to be matched and the behavior pattern vector of the q-th similar sample whose sample type is a legal sample, and the value range of q is 1, 2,..., Q, and Q represents the number of legal samples in the similar samples;

[0139] If the legal matching degree R is higher than the legal threshold, the matching result of the drone to be matched is legal; otherwise, the matching result of the drone to be matched is illegal. The legal threshold is set by those skilled in the art according to experience and actual needs. The judgment logic of the legality of the drone in this embodiment is as Figure 3 shown.

[0140] S6: Take illegal drone response and management measures for the drone with an illegal matching result.

[0141] The illegal drone response and management measures are specifically as follows:

[0142] Activate the alarm system and send an illegal drone alarm signal, the flight trajectory map, and the behavior characteristic parameters of the illegal drone to the relevant departments;

[0143] Send a notice to illegal drones to decelerate or land; apply electromagnetic interference technology to block the communication between drones and ground control consoles, cut off the remote control signals, data transmission, and video transmission signals of drones, and force drones to enter the self-protection state after signal loss, achieving the purpose of forced landing or driving away; interfere with the satellite navigation signals of drones to make them unable to accurately locate and restrict the flight of drones.

[0144] The position of the drone is displayed in real time through a visual interface, facilitating continuous tracking and monitoring management of illegal drones.

[0145] Embodiment 2

[0146] This embodiment is the second embodiment of the present invention; based on the same inventive concept as Embodiment 1, referring to Figure 2 , this embodiment introduces a drone locking and monitoring system based on a cloud control platform, including a monitoring and locking module, a preprocessing module, a feature extraction module, an anomaly detection module, a data acquisition module, a behavior matching module, and a control module; among them:

[0147] The monitoring and locking module is used to locate the drone and continuously collect the characteristic data of the drone; it includes a lidar, a wireless signal detector, and an optoelectronic sensor, which are respectively used to collect the three-dimensional coordinate data, communication signal data, and drone images of the drone.

[0148] The preprocessing module is used to preprocess the characteristic data of the drone, including data cleaning, format calibration, and coordinate alignment; and organize the coordinate sequence, draw a flight trajectory map; draw a spectrogram of the communication signal.

[0149] The feature extraction module is used to extract the behavior characteristic parameters of the drone, including flight trajectory characteristic parameters, flight mode characteristic parameters, communication behavior characteristic parameters, and target shape characteristic parameters.

[0150] The anomaly detection module is used to detect the abnormal behavior of the drone; an anomaly probability model is used to detect the abnormal behavior of the behavior feature vector of the drone to determine whether the drone has abnormal behavior.

[0151] The data acquisition module is used to collect the environmental data of the flight environment of the drone, including wind speed, wind direction, temperature, relative humidity, visibility, cloud thickness, and flight environment.

[0152] The behavior matching module is used to match the behavior patterns of drones with abnormal behavior; by measuring the similarity between the behavior pattern vector of the drone and the behavior pattern vector of the reference sample in the behavior pattern database and calculating the legal matching degree, the legality of the drone is determined.

[0153] The control module is used to respond to and manage illegal drones; including but not limited to sending alarm information of illegal drones, sending control signals to the drones, such as interference signals that interfere with the flight of illegal drones or notifications for decelerated landing; continuously tracking and real-time displaying the position information of illegal drones through the monitoring and locking module.

[0154] For the specific function implementation of each of the above modules, refer to the relevant content in the method for locking and monitoring drones based on a cloud control platform described in Embodiment 1, which will not be elaborated here.

[0155] Embodiment 3

[0156] Based on the same inventive concept as other embodiments, this embodiment introduces an electronic device, including a memory and a processor. The memory is used to store instructions, and the processor is used to execute the instructions, so that the computer device executes the method for locking and monitoring drones based on the cloud control platform provided in the above embodiments.

[0157] Since the electronic device introduced in this embodiment is the electronic device used to implement the method for locking and monitoring drones based on the cloud control platform in the embodiments of the present application, based on the method for locking and monitoring drones based on the cloud control platform introduced in the embodiments of the present application, those skilled in the art can understand the specific implementation manners and various variations of the electronic device in this embodiment. Therefore, the specific implementation of how this electronic device implements the method in the embodiments of the present application will not be described in detail here. As long as those skilled in the art implement the electronic device used to implement the method for locking and monitoring drones based on the cloud control platform in the embodiments of the present application, it falls within the scope of protection of the present application.

[0158] Embodiment 4

[0159] Based on the same inventive concept as other embodiments, this embodiment introduces a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements the method for locking and monitoring drones based on the cloud control platform provided in the above embodiments.

[0160] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0161] The embodiments of the present invention have been described above in conjunction with the accompanying drawings. However, the present invention is not limited to the above specific embodiments. The above specific embodiments are merely illustrative and not restrictive. Under the inspiration of the present invention, those of ordinary skill in the art can also make many forms without departing from the purpose and scope of the present invention. All of these fall within the protection scope of the present invention.

Claims

1. A method for locking and monitoring an unmanned aerial vehicle based on a cloud control platform, characterized in that, It includes the following steps: S1: Collect the characteristic data of the drone and transmit the characteristic data to the cloud control platform; S2: The cloud control platform preprocesses the characteristic data; S3: Based on the preprocessed characteristic data, extract the behavior characteristic parameters of the drone; S4: Detect the abnormal behavior of the drone based on the behavior characteristic parameters; S5: Obtain the environmental data and perform behavior pattern matching on the drones with abnormal behavior; Specifically including: The cloud control platform is configured with a behavior pattern database of drones; The behavior pattern database contains M reference samples, and the reference samples include legal samples and illegal samples; Each reference sample corresponds to a behavior pattern vector, and the behavior pattern vector is composed of a behavior feature vector and an environmental feature vector spliced together; The environmental feature vector of each reference sample is composed of the environmental data corresponding to the reference sample after normalization and encoding processing; Collect the environmental data of the drone to be matched, and after normalization and encoding processing, form an environmental feature vector, and splice it with the behavior feature vector to form the behavior pattern vector of the drone to be matched; Calculate the similarity between the behavior pattern vector of the drone to be matched and the behavior pattern vector of each reference sample in the behavior pattern database; Select the N reference samples with the highest similarity as the similar samples of the drone to be matched; Calculate the legal matching degree of the drone to be matched; If the legal matching degree R is higher than the legal threshold, the matching result of the drone to be matched is legal; Otherwise, the matching result of the drone to be matched is illegal; S6: Take illegal drone response and management measures for the drones with illegal matching results.

2. The method for locking and monitoring an unmanned aerial vehicle based on a cloud control platform according to claim 1, wherein The characteristic data includes three-dimensional coordinate data, communication signal data, and drone images; The three-dimensional coordinate data is obtained by lidar; The communication signal data is the communication signal between the drone and the remote controller or the ground station, and is collected by a wireless signal detector; The drone image is obtained by an optoelectronic sensor.

3. The method for locking and monitoring an unmanned aerial vehicle based on a cloud control platform according to claim 2, wherein, The preprocessing is specifically as follows: Perform data cleaning on the characteristic data; Perform format calibration and coordinate alignment on each type of characteristic data; Organize the three-dimensional coordinate data into a time series as a coordinate sequence, and draw a flight trajectory map based on the coordinate sequence; The flight trajectory map is the drone flight trajectory composed of the coordinate points of the drone, and each coordinate point corresponds to a three-dimensional coordinate data and the corresponding timestamp; Perform frequency domain analysis on the communication signal data to obtain a communication signal spectrogram; Perform image enhancement on the drone image.

4. The method for locking and monitoring an unmanned aerial vehicle based on a cloud control platform according to claim 3, wherein The behavior characteristic parameters include flight trajectory characteristic parameters, flight mode characteristic parameters, communication behavior characteristic parameters, and target shape characteristic parameters; The flight trajectory characteristic parameters include average flight speed, maximum acceleration, and average flight height; The extraction method is as follows: Calculate the distance between any two adjacent coordinate points in the flight trajectory map based on the three-dimensional coordinate data and divide it by the time difference between the two adjacent coordinate points to obtain the average speed between any two adjacent coordinate points; find the mean value of the average speeds between all adjacent coordinate points to obtain the average flight speed; perform double differentiation of the three-dimensional coordinate data of each coordinate point in the flight trajectory characteristic parameters with respect to time to obtain the acceleration of each coordinate point and extract the maximum value of the acceleration of the coordinate point as the maximum acceleration; extract the flight altitude of each coordinate point in the flight trajectory map and find the mean value to obtain the average flight altitude.

5. The method for locking and monitoring an unmanned aerial vehicle based on a cloud control platform according to claim 4, wherein The flight mode characteristic parameters include the frequency and duration of each flight mode; the flight modes include straight flight, turning, hovering, ascending, descending, and hovering; the extraction method of the flight mode characteristic parameters is as follows: Identify the trajectory segments corresponding to each flight model from the flight trajectory map through a machine learning model; count the number of occurrences of each flight model per unit time as the frequency of each flight mode; count the total duration of each flight mode per unit time as the duration of each flight mode.

6. The method for locking and monitoring an unmanned aerial vehicle based on a cloud control platform according to claim 5, wherein, The communication behavior characteristic parameters include signal strength characteristics and signal frequency characteristics, and the extraction method is as follows: Calculate the mean value and variance of the signal strength of the communication signal data as the signal strength characteristics; extract the frequency range and center frequency of the communication signal from the communication signal spectrogram as the signal frequency characteristics; The target appearance characteristic parameters include the model and color of the drone, and the extraction method is as follows: Perform object detection on the drone image, mark the drone area in the drone image and crop a feature map of a fixed size containing the drone area; Input the feature map into the trained convolutional neural network model to output the model and color of the drone.

7. The method for locking and monitoring an unmanned aerial vehicle based on a cloud control platform according to claim 6, characterized in that, The method for abnormal behavior detection is as follows: Collect normal drone feature data and extract behavior characteristic parameters as normal samples; normalize and encode the behavior characteristic parameters of the normal samples to form behavior feature vectors; the form of any behavior feature vector is as follows: ； Among them, represents the behavior feature vector of the i-th normal sample, where the value range of i is 1, 2, ……, m, and m is the number of normal samples; represents the j-th behavior feature parameter of the i-th normal sample after normalization and encoding, where the value range of j is 1, 2, ……, n, and n is the total number of behavior feature parameters of any unmanned aerial vehicle; Construct an abnormal probability model based on the Gaussian distribution, and the equation is as follows: ； Among them, represents the abnormal probability density function; represents the weight coefficient of the k-th Gaussian distribution, where the value range of k is 1, 2, ……, K, and K is the number of Gaussian distributions in the abnormal probability model; represents the covariance matrix of the k-th Gaussian distribution; represents the determinant of; represents the inverse matrix of; represents the mean vector of the k-th Gaussian distribution; represents the transpose of the matrix within the parentheses; Train the anomaly probability model as follows: Use the EM algorithm for parameter estimation to determine the weight coefficients of each Gaussian distribution , covariance matrix , and mean vector values, and determine the number of Gaussian distributions K through the AIC criterion; Save the trained anomaly probability model; Normalize and encode the behavior feature parameters of the drone to be detected for abnormal behavior, and form a behavior feature vector, denoted as , and input the behavior feature vector into the trained abnormal probability model to obtain the abnormal behavior detection result.

8. The method for locking and monitoring an unmanned aerial vehicle based on a cloud control platform according to claim 7, characterized in that, The specific way to obtain the abnormal behavior detection result is as follows: Equation calculation based on the abnormal probability model The abnormal probability density function of is denoted as ; Calculation log probability function of is as follows: ； If , then the drone has no abnormal behavior; Otherwise, the drone has abnormal behavior; Among them, represents the first abnormal threshold, and the calculation formula is as follows: ； Among them, represents the behavioral feature vector of the i-th normal sample of the logarithmic probability function, and the calculation formula is as follows: ； represents the mean of the logarithmic probability functions of the behavioral feature vectors of m normal samples, represents the variance of the logarithmic probability functions of the behavioral feature vectors of m normal samples; Indicates the second abnormal threshold, and the calculation formula is as follows: 。 9. The method for locking and monitoring an unmanned aerial vehicle based on a cloud control platform according to claim 8, wherein, The environmental data includes wind speed, wind direction, temperature, relative humidity, visibility, cloud thickness, and flight environment; the flight environment is the geographical environment corresponding to the area where the drone flies, including mountains, hills, plains, plateaus, basins, waters, and urban areas.

10. The method for locking and monitoring an unmanned aerial vehicle based on a cloud control platform according to claim 9, characterized in that, The calculation formula for the legal matching degree of the drone to be matched is as follows: ； wherein, R represents the legal matching degree; represents the similarity between the behavior pattern vector of the UAV to be matched and the behavior pattern vector of the p-th similar sample, and the value range of p is 1, 2,..., N; represents the similarity between the behavior pattern vector of the UAV to be matched and the behavior pattern vector of the q-th similar sample whose sample type is a legal sample, the value range of q is 1, 2,..., Q, and Q represents the number of legal samples in the similar samples.

11. A drone locking and monitoring system based on a cloud control platform, which is used to implement the drone locking and monitoring method based on the cloud control platform described in any one of claims 1-10, characterized in that, Including a monitoring and locking module, a preprocessing module, a feature extraction module, an abnormal detection module, a data acquisition module, a behavior matching module, and a control module; among them: The monitoring and locking module is used to locate the drone and continuously collect the feature data of the drone; the preprocessing module is used to preprocess the feature data of the drone; The feature extraction module is used to extract the behavior characteristic parameters of the drone based on the preprocessed feature data; The anomaly detection module is used to detect abnormal behaviors of the UAV based on the behavioral feature parameters; The data acquisition module is used to acquire environmental data of the flight environment of the UAV; The behavior matching module is used to perform behavior pattern matching on the UAV with abnormal behaviors; The control module is used to take illegal UAV response and management measures for the UAV with an illegal matching result.

12. An electronic device, characterized in that, Comprising: A memory for storing instructions; A processor for executing the instructions, so that the device performs the operations of implementing the UAV locking and monitoring method based on the cloud control platform as described in any one of claims 1-10.

13. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the UAV locking and monitoring method based on the cloud control platform as described in any one of claims 1-10.

Images