Unmanned aerial vehicle detection method and device, electronic equipment and storage medium

Abstract

The invention relates to the technical field of flyer anti-reconnaissance, and discloses a detection method and device of an unmanned aerial vehicle, electronic equipment and a storage medium, and the method comprises the steps: collecting the data of a flyer, the data at least comprising the motion data and communication data of the flyer, and the timestamp and signal data of data collection; performing data fusion on the acquired data based on the timestamp of data acquisition; carrying out flyer identification on the fused data; and if the flying object is the unmanned aerial vehicle, performing early warning. Through the above mode, before the flyer is identified, fusion processing is performed on the acquired data based on the timestamp of data acquisition, so that the identification efficiency can be improved.

Description

Technical Field

[0001] The embodiments of the present application relate to the technical field of anti-detection of flying objects, and specifically to a detection method and device for an unmanned aerial vehicle, an electronic device, and a storage medium. Background Art

[0002] With the popularization of the country's low-altitude economy, especially the rapid development and popularization of drone technology, drones are increasingly widely used in civil and military fields for reconnaissance and counter-reconnaissance. At the same time, the abuse of drones has also brought many security issues, such as airport interference, privacy infringement and illegal transportation. Therefore, how to effectively detect, intercept and counter illegal intrusion drones has become an urgent problem to be solved.

[0003] Traditional anti-drone technologies mainly rely on a single type of sensor, such as radar, optical, radio spectrum, etc., but each sensor has its limitations. Radar is susceptible to clutter interference, optical equipment performance degrades in bad weather conditions, and RF signal detection is unstable in complex electromagnetic environments. Therefore, a new type of drone detection method is needed to improve the accuracy and reliability of drone detection. Summary of the invention

[0004] In view of the above problems, the embodiments of the present application provide a method and device for detecting a drone, an electronic device and a storage medium, which are used to solve the problem of low drone detection accuracy in the prior art.

[0005] According to one aspect of an embodiment of the present application, a method for detecting a drone is provided, the method comprising:

[0006] Collecting data of the flying object, the data including at least: motion data, image data, a timestamp of data collection, and communication signal data of the flying object;

[0007] fusing the collected data based on the timestamp of the data collection;

[0008] Identify the flying object based on the fused data;

[0009] If the flying object is a drone, an early warning is issued.

[0010] In an optional manner, the fusing the collected data based on the timestamp of the data collection includes:

[0011] Performing spatiotemporal fusion on the collected data based on the timestamp of the data collection;

[0012] The collected data is subjected to feature fusion based on the timestamp of the data collection.

[0013] In an optional manner, before fusing the collected data based on the timestamp of data collection, the method further includes:

[0014] De-noising the collected data;

[0015] Perform data alignment on the denoised data;

[0016] Performing coordinate transformation on the aligned data;

[0017] The data after coordinate transformation is smoothed based on the Bayesian algorithm.

[0018] In an optional manner, the performing spatiotemporal fusion on the collected data based on the timestamp of the data collection includes:

[0019] Get the motion data with the earliest timestamp;

[0020] The acquired motion data is used as fused spatiotemporal data;

[0021] The performing feature fusion on the collected data based on the timestamp of the data collection includes:

[0022] Respectively obtain the image data and communication signal data with the earliest timestamp;

[0023] The acquired communication data and communication signal data are used as fused feature data.

[0024] In an optional manner, if the flying object is a drone, issuing an early warning includes:

[0025] Calculate the distance between the UAV and the target core area in real time;

[0026] Issue corresponding warnings based on the currently calculated distance.

[0027] In an optional manner, the corresponding warning based on the currently calculated distance includes:

[0028] Compare the currently calculated distance with the warning comparison table;

[0029] Output a warning corresponding to the comparison result according to the comparison result.

[0030] In an optional manner, the corresponding warning based on the currently calculated distance includes:

[0031] When the UAV flies in a direction close to the target core area, comparing the currently calculated distance with the first preset distance;

[0032] If the currently calculated distance is greater than the first preset distance, a first level warning is issued;

[0033] If the currently calculated distance is equal to the first preset distance, a second level warning is issued;

[0034] If the currently calculated distance is less than the first preset distance and greater than the second preset distance, a third level warning is issued, and the first preset distance is greater than the second preset distance;

[0035] If the currently calculated distance is equal to the second preset distance, a fourth level warning is issued;

[0036] If the currently calculated distance is less than the second preset distance, a fifth level warning is issued; and

[0037] When the UAV flies in a direction away from the target core area, comparing the currently calculated distance with the second preset distance;

[0038] If the currently calculated distance is less than the second preset distance, the fifth level warning is issued;

[0039] If the currently calculated distance is equal to the second preset distance, the fourth level warning is issued;

[0040] If the currently calculated distance is greater than the second preset distance and less than the first preset distance, the third level warning is issued;

[0041] If the currently calculated distance is equal to the first preset distance, the second level warning is issued;

[0042] If the currently calculated distance is greater than the first preset distance, the first level warning is issued.

[0043] According to another aspect of the embodiment of the present application, there is also provided a detection device for a drone, including:

[0044] A collection module, used to collect data of the flying object, the data at least including: motion data, image data, a timestamp of data collection and communication signal data of the flying object;

[0045] A fusion module, used for fusing the collected data based on the timestamp of the data collection;

[0046] Identification module, used to identify flying objects based on the fused data;

[0047] The early warning module is used to issue an early warning when the flying object is a drone.

[0048] According to another aspect of an embodiment of the present application, an electronic device is provided, comprising: a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the above-mentioned drone detection method.

[0049] According to another aspect of the embodiments of the present application, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the above-mentioned drone detection method is implemented.

[0050] The embodiment of the present application can improve the recognition efficiency by fusing the various collected data based on the timestamps of data collection before identifying the flying object.

[0051] The above description is only an overview of the technical solution of the embodiment of the present application. In order to more clearly understand the technical means of the embodiment of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the embodiment of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] The accompanying drawings are only used to illustrate the embodiments and are not to be considered as limiting the present application. In addition, the same reference symbols are used to represent the same components throughout the accompanying drawings. In the accompanying drawings:

[0053] Figure 1 A schematic diagram of the flow of a drone detection method provided in an embodiment of the present application is shown;

[0054] Figure 2 A schematic diagram of a flow chart of a method for detecting a drone provided by another embodiment of the present application is shown;

[0055] Figure 3 A schematic diagram of the structure of a detection device for a drone provided in an embodiment of the present application is shown;

[0056] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0057] The exemplary embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present application are shown in the drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments set forth herein.

[0058] Figure 1 A flowchart of a method for detecting a drone provided in an embodiment of the present application is shown, and the method is performed by an electronic device. The electronic device can be any server configured with a machine learning model.

[0059] like Figure 1 As shown, the method comprises the following steps:

[0060] Step S110: Collect data of the flying object.

[0061] Among them, real-time detection of the area to be detected (such as a specific area in the sky) can be performed by setting various sensors to collect data, such as setting a radar sensor to collect the motion data of flying objects in the air (including the location and speed data), and using a light sensor (such as a camera or infrared sensor) to collect the picture of the flying object for subsequent target identification. For another example, a signal detector (such as an RF signal detector) is set to detect various control signals and communication signals for subsequent target identification or positioning. Preferably, the collected data can include: the motion data of the flying object, image data, the timestamp of data collection, and the communication signal data.

[0062] Step S120: performing data fusion on the collected data based on the timestamp of data collection.

[0063] Among them, various collected data are fused based on the timestamp of data collection to facilitate subsequent identification.

[0064] Step S130: Identify the flying object based on the fused data.

[0065] The fused data is input into a machine learning model to identify flying objects, and the identification results are output. The machine learning model can adopt existing structures, such as logistic regression models, naive Bayes models, support vector machine models, etc., and there is no limitation on this here.

[0066] Step S140: If the flying object is a drone, issue an early warning.

[0067] Among them, if the flying object is identified as a drone, an early warning will be issued.

[0068] In this embodiment, before the flying object is identified, various collected data are fused based on the timestamp to improve the identification efficiency.

[0069] Figure 2 A flowchart of a drone detection method provided by another embodiment of the present application is shown, and the method is performed by an electronic device. The electronic device can be any server (or terminal) configured with a machine learning model. Figure 2 As shown, the method comprises the following steps:

[0070] Step S210: Collect data of the flying object.

[0071] The collected data at least includes: the motion data, image data and communication signal data of the flying object, and the area to be detected is detected in real time. Various sensors can be set to collect data, such as setting a radar sensor to collect the motion data of the flying object in the air (including the location data and speed data, such as acceleration data, horizontal speed, vertical speed, etc.), wherein the location data may include the latitude and longitude data of the flying object, and using a light sensor (such as a camera or infrared sensor) to collect the image screen (image data) where the flying object is located, for subsequent target identification. For another example, a signal detector (such as an RF signal detector) is set to detect various control signals and communication signals for subsequent target identification or positioning, and also includes the timestamp of the collection.

[0072] In this embodiment, the process of collecting data of flying objects is as follows:

[0073] Collect the motion data of the flying object.

[0074] Among them, radar sensors are used to collect movement data of flying objects (such as current location and speed data).

[0075] Collect image data of flying objects.

[0076] Among them, a camera or an infrared sensor is used to collect image data of the flying object.

[0077] Collect signal data of flying objects.

[0078] Among them, an RF signal detector is used to collect the flying object's own receiving and transmitting signals (such as control signals and communication signals).

[0079] Step S220: denoising the collected data.

[0080] Among them, a moving average filter is used for denoising. The signal is smoothed by calculating the average value of the data points in the sliding window, and its expression is: Where x[n] is the raw data from the sensor, y[n] is the output data after filtering, the window size is N, and i is the label of any data point.

[0081] Step S230: performing data alignment processing on the denoised data.

[0082] Among them, using interpolation method to perform data alignment processing can effectively fill the missing values ​​in the sensor data, making the data more complete and continuous. Preferably, linear interpolation method (such as using numpy and pandas interpolation tools) or polynomial interpolation can be used, such as calling the polyfit and polyval functions of the numpy interpolation tool to achieve it.

[0083] Step S240: performing coordinate transformation on the aligned data.

[0084] Among them, various methods are used to realize coordinate conversion according to the actual situation of the data, such as coordinate translation, coordinate rotation, scaling, etc.

[0085] The specific transformation matrix can be as follows:

[0086] Translation matrix:

[0087] Rotation matrix:

[0088] Rotate the angle θ around the X axis:

[0089]

[0090] Rotate the angle θ around the Y axis:

[0091]

[0092] Rotate the angle θ around the Z axis:

[0093]

[0094] Scaling matrix:

[0095]

[0096] In this embodiment, the collected data is firstly subjected to the aforementioned data preprocessing, which can improve the reliability and synchronization of the data.

[0097] In a further preferred solution of this embodiment, after step S240 and before step S260, the following steps are further included:

[0098] The data after coordinate transformation is smoothed based on Bayesian algorithm;

[0099] Among them, the data after coordinate transformation is smoothed by Bayesian algorithm, and the Bayesian formula is: Among them, P(θ|D) represents the posterior probability, P(D|θ) represents the likelihood function, P(θ) represents the prior probability, and P(D) represents the evidence (normalization function). The above data can be smoothed by the Bayesian algorithm to improve the reliability of the data.

[0100] Step S250: performing data fusion on the aligned data based on the timestamp of data acquisition.

[0101] The aligned data are fused based on the timestamp of data acquisition to improve the reliability of the data.

[0102] Furthermore, the collected data includes: feature data and spatiotemporal data, the spatiotemporal data may include the aforementioned motion data (speed data, position data, etc.), and the feature data may include the aforementioned signal data, image data, and the collected timestamp, etc. Data fusion mainly fuses spatiotemporal data and feature data.

[0103] The data fusion process can include:

[0104] Perform spatiotemporal fusion of the collected data.

[0105] Among them, when collecting or receiving data, there will be a corresponding collection timestamp. The timestamp of each data is analyzed to obtain the spatiotemporal data with the earliest timestamp (i.e., motion data). The spatiotemporal data with the earliest timestamp is used as the fused spatiotemporal data (communication signal data and image data) for subsequent identification.

[0106] Perform feature fusion on the collected data.

[0107] Among them, when collecting or receiving data, there will be a corresponding collection timestamp. The timestamp of each data is analyzed to obtain the feature data with the earliest timestamp (communication signal data and image data). The feature data with the earliest timestamp is used as the fused feature data for subsequent recognition.

[0108] For example, when multiple detection devices detect the same flying object, the maximum timestamp is calculated and the data with a timestamp lower than the last maximum timestamp is discarded, that is, the earliest timestamp is retained. In a specific scenario, the signal sent by the same flying object is a timestamp attribute (t1). After the two devices detect it, it is transmitted to the processor. Due to the sequence of network transmission, the processor receives the two signals in sequence. At this time, the first received data is processed first, and the next one is duplicate data and is not processed. Reducing data processing can reduce unnecessary losses and improve efficiency.

[0109] It should be noted that the data collected by any device adopts the same data fusion method, and there is no limitation on the device for data collection.

[0110] For example: For a drone with a DroneID protocol, use the reported timestampRid timestamp. For a drone with a RemoteID protocol, use the reported gps_clock timestamp.

[0111] It should be noted that the spatiotemporal fusion of the collected data and the feature fusion of the collected data need to be performed simultaneously.

[0112] Step S260: Identify the flying object based on the fused data.

[0113] Among them, the fused data is used to identify the flying object and input into the machine learning model for identification of the flying object. If the identification result is not a drone, the tracking process is stopped and returns to step S210. If the identification result is a drone, go to step S270.

[0114] Step S270: If the flying object is a drone, issue an early warning.

[0115] If the current flying object is identified as a drone, a corresponding warning will be issued based on the location of the drone. The specific warning process is as follows:

[0116] Calculate the distance between the drone and the target core area in real time;

[0117] Among them, when detecting drones, a target core area is pre-set. When a drone is found, the distance from the drone to the target core area is calculated. A circle can be drawn with the center point of the drone's location, and the circle tangent to the target core area (a circle with a preset radius) and the circle where the target core area is located is the target circle. The radius corresponding to the circle is the distance between the drone and the target core area (the shortest distance). Or the distance between the center of the circle corresponding to the drone's location and the target core area minus the radius of the circle where the target core area is located is directly calculated to obtain the distance between the drone and the target core area. Further, the core area is a circle with a preset radius, and an early warning area is also set outside the core area (the early warning area and the target core area are concentric circle structures). The radius of the early warning area and the target core area are also set according to actual needs, and there is no restriction on this here. It is also necessary to calculate the distance (shortest distance) from the drone to the early warning area. The calculation method can refer to the calculation process of the distance between the drone and the target core area mentioned above.

[0118] Issue corresponding warnings based on the currently calculated distance.

[0119] Among them, an early warning can be issued based on the currently calculated distance and the flight direction of the drone, or the currently calculated distance can be compared with an early warning comparison table, and an early warning can be issued based on the comparison result.

[0120] In a preferred solution of this embodiment, a distance-level warning comparison table can be set in advance, as shown in Table 1:

[0121] Table 1

[0122]

[0123] In Table 1, the first preset distance is greater than the second preset distance.

[0124] The currently calculated distance is matched with Table 1 to obtain the warning result, and then the corresponding warning is issued.

[0125] In another preferred embodiment of this embodiment, an early warning may be issued based on the currently calculated distance and the flight direction of the drone.

[0126] Among them, when the drone flies in the direction close to the target core area, the process of issuing corresponding warnings based on the currently calculated distance is as follows:

[0127] Compare the currently calculated distance with the first preset distance; if the currently calculated distance is greater than the first preset distance, issue a first level warning; if the currently calculated distance is equal to the first preset distance, issue a second level warning; if the currently calculated distance is less than the first preset distance and greater than the second preset distance, issue a third level warning; if the currently calculated distance is equal to the second preset distance, issue a fourth level warning; if the currently calculated distance is less than the second preset distance, issue a fifth level warning. Further, the higher the level, the more urgent the situation. Alternatively, first compare with the radius of the warning area, if the currently calculated distance is greater than the radius of the warning area, issue a level 1 warning, if the currently calculated distance is equal to the radius of the warning area, it means that the drone begins to enter the warning area, and a level 2 warning is issued at this time, if the calculated distance is less than the radius of the warning area, it means that the drone has entered the warning area, and a level 3 warning is issued, if the currently calculated distance is equal to the radius of the target core area, it means that the drone begins to enter the target core area, and a level 4 warning is issued, if the currently calculated distance is less than the radius of the target core area, it means that the drone is already in the target core area, and a level 5 warning (the highest level warning) is issued. It should be noted that the first preset distance is the radius of the warning area, and the second preset distance is the radius of the target core area. The specific level setting can be set according to actual needs, and there is no limitation on this here.

[0128] When the drone flies in a direction away from the target core area, the process of issuing a corresponding warning based on the currently calculated distance is as follows:

[0129] The currently calculated distance is first compared with the second preset distance; if the currently calculated distance is less than the second preset distance, a fifth level warning is issued; if the currently calculated distance is equal to the second preset distance, a fourth level warning is issued; if the currently calculated distance is greater than the second preset distance and less than the first preset distance, a third level warning is issued; if the currently calculated distance is equal to the first preset distance, a second level warning is issued; if the currently calculated distance is greater than the first preset distance, a first level warning is issued.

[0130] In the embodiment of the present invention, different processing recommendations can be triggered according to different drone warning levels, such as recommending strikes, recommending remote capture of pilots, and other countermeasures.

[0131] Furthermore, the detection and interception results can be displayed in real time on the console interface of the electronic device, providing a visual target path, classification information and processing status.

[0132] Furthermore, historical data and comprehensive analysis process data can also be stored to facilitate comprehensive evaluation based on historical data and comprehensive analysis process data in the future, and provide statistical and analysis reports on drone intrusions.

[0133] In the embodiment of the present invention, before the flying object is identified, various collected data are first fused based on the timestamp, which can improve the identification efficiency and reduce the loss.

[0134] Secondly, using multiple sensors to collect data and fuse them to achieve fusion processing of heterogeneous data can improve recognition accuracy.

[0135] Based on the above method embodiment, Figure 3 FIG. 1 is a schematic diagram showing the structure of a detection device for a drone provided in an embodiment of the present application. Figure 3 As shown, the device 300 includes: a collection module 310, a fusion module 320 connected to the collection module 310, an identification module 330 connected to the fusion module 320, and an early warning module 340 connected to the identification module 330, wherein:

[0136] The acquisition module 310 is used to acquire data of flying objects.

[0137] Real-time detection of the area to be detected. The acquisition module 310 may include various sensors, signal detectors, etc., for collecting data, such as setting a radar sensor to collect the motion data of flying objects in the air (including the location and speed data), and using a light sensor (such as a camera or infrared sensor) to collect the image of the flying object for subsequent target identification. Another example is setting a signal detector (such as an RF signal detector) to detect various control signals and communication signals for subsequent target identification or positioning. Preferably, the collected data may include: the motion data of the flying object, image data, the timestamp of data collection, and the communication signal data.

[0138] The fusion module 320 is used to perform data fusion on the collected data based on the timestamp of data collection.

[0139] Among them, the fusion module 320 performs data fusion on the collected data based on the timestamp of data collection to facilitate subsequent drone identification.

[0140] The identification module 330 is used to identify the flying object based on the fused data.

[0141] Among them, the recognition module 330 can be a machine learning model, which inputs the fused data into the machine learning model to identify the flying object and outputs the recognition result. Among them, the machine learning model can adopt an existing structure, such as a logistic regression model, a naive Bayes model, a support vector machine model, etc., and there is no limitation on this here.

[0142] The early warning module 340 is used to issue an early warning when the flying object is a drone.

[0143] If the flying object is identified as a drone, the warning module 340 is used to issue a corresponding warning.

[0144] In this embodiment, before the flying object is identified, various collected data are fused based on the timestamp to improve the identification efficiency.

[0145] In an optional manner, the fusion module 320 is used to:

[0146] Perform spatiotemporal fusion of the collected data based on the timestamp of data collection;

[0147] The collected data is feature fused based on the timestamp of data collection.

[0148] In an optional manner, the device further includes:

[0149] The preprocessing module is used to preprocess the collected data, wherein the preprocessing module is specifically used to:

[0150] De-noising the collected data;

[0151] Perform data alignment on the denoised data;

[0152] Performing coordinate transformation on the aligned data;

[0153] The data after coordinate transformation is smoothed based on the Bayesian algorithm.

[0154] In an optional manner, the fusion module 330 is used to:

[0155] Get the motion data with the earliest timestamp;

[0156] The acquired motion data is used as fused spatiotemporal data; and

[0157] Respectively obtain the image data and communication signal data with the earliest timestamp;

[0158] The acquired image data and communication signal data are used as fused feature data.

[0159] In an optional manner, the early warning module 340 is used to:

[0160] Calculate the distance between the drone and the target core area in real time;

[0161] Issue corresponding warnings based on the currently calculated distance.

[0162] In an optional manner, the early warning module 340 is used to:

[0163] Compare the currently calculated distance with the warning comparison table;

[0164] According to the comparison result, a warning corresponding to the comparison result is output.

[0165] In an optional manner, the early warning module 340 is used to:

[0166] When the drone flies in the direction close to the target core area, a corresponding warning is issued based on the currently calculated distance, including:

[0167] comparing the currently calculated distance with a first preset distance;

[0168] If the currently calculated distance is greater than the first preset distance, a first level warning is issued;

[0169] If the currently calculated distance is equal to the first preset distance, a second level warning is issued;

[0170] If the currently calculated distance is less than the first preset distance but greater than the second preset distance, a third level warning is issued, and the first preset distance is greater than the second preset distance;

[0171] If the currently calculated distance is equal to the second preset distance, a fourth level warning is issued;

[0172] If the currently calculated distance is less than the second preset distance, a fifth level warning is issued; and

[0173] When the drone flies in a direction away from the target core area, a corresponding warning is issued based on the currently calculated distance, including:

[0174] comparing the currently calculated distance with a second preset distance;

[0175] If the currently calculated distance is less than the second preset distance, a fifth level warning is issued;

[0176] If the currently calculated distance is equal to the second preset distance, a fourth level warning is issued;

[0177] If the currently calculated distance is greater than the second preset distance and less than the first preset distance, a third level warning is issued;

[0178] If the currently calculated distance is equal to the first preset distance, a second level warning is issued;

[0179] If the currently calculated distance is greater than the first preset distance, a first level warning is issued.

[0180] In the embodiment of the present invention, before the flying object is identified, the various collected data are first fused and processed, which can improve the identification efficiency.

[0181] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application is shown, and the specific embodiment of the present application does not limit the specific implementation of the electronic device.

[0182] like Figure 4 As shown, the electronic device 400 may include: a processor (processor) 402 and a memory (memory) 404.

[0183] The memory 404 is used to store a computer program 406. The memory 404 may include a high-speed RAM memory, and may also include a non-volatile memory, such as at least one disk memory. The computer program 406 may include computer executable instructions.

[0184] The processor 402 is used to execute the computer program 406 to implement the above-mentioned drone detection method embodiment.

[0185] The processor 402 may be a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application. The one or more processors included in the electronic device 400 may be processors of the same type, such as one or more CPUs, or may be processors of different types, such as one or more CPUs and one or more ASICs.

[0186] The computer program 406 can be specifically called by the processor 402 to enable the electronic device to execute the drone detection method proposed in the embodiment of the present application.

[0187] An embodiment of the present application provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the above-mentioned drone detection method embodiment is implemented.

[0188] An embodiment of the present application provides a computer program that can be executed by a processor to implement an embodiment of the detection method of the drone.

[0189] An embodiment of the present application provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the above-mentioned drone detection method embodiment is implemented.

[0190] In the embodiment of the present invention, before the flying object is identified, various collected data are fused based on the timestamp, which can improve the identification efficiency.

[0191] In several embodiments provided in the present application, if any function is implemented in the form of a software function module / unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the technical solution of the present application can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, server or other electronic device) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (RandomAccess Memory, RAM), disk or optical disk and other media that can store computer program codes.

[0192] The algorithm or display provided here are not inherently related to any specific computer, virtual system or other equipment. Various general systems can also be used together with the teaching based on this. According to the above description, it is obvious to construct the structure required for this type of system. In addition, the present application embodiment is not directed to any specific programming language yet. It should be understood that various programming languages ​​can be utilized to realize the content of the present application described here, and the above description of specific languages ​​is to disclose the best mode of implementation of the present application.

[0193] It should be noted that the above embodiments illustrate the present application rather than limit the present application, and that those skilled in the art may design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference symbol between brackets shall not be constructed as a limitation on the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "one" or "an" preceding an element does not exclude the presence of multiple such elements. The present application may be implemented by means of hardware including several different elements and by means of a suitably programmed computer. In the claims that list several devices, several units or modules in these devices may be embodied by the same hardware item. The use of the words first, second, and third, etc. does not indicate any order. These words may be interpreted as names. The steps in the above embodiments, unless otherwise specified, should not be understood as limitations on the order of execution.

[0194] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for detecting a drone, characterized in that: The method comprises: Collecting data of the flying object, the data including at least: motion data, image data, a timestamp of data collection, and communication signal data of the flying object; fusing the collected data based on the timestamp of the data collection; Identify the flying object based on the fused data; If the flying object is a drone, an early warning is issued.

2. The method according to claim 1, characterized in that The fusing the collected data based on the timestamp of the data collection includes: Performing spatiotemporal fusion on the collected data based on the timestamp of the data collection; The collected data is subjected to feature fusion based on the timestamp of the data collection.

3. The method according to claim 1, characterized in that Before fusing the collected data based on the timestamp of the data collection, the method further includes: De-noising the collected data; Perform data alignment on the denoised data; Performing coordinate transformation on the aligned data; The data after coordinate transformation is smoothed based on the Bayesian algorithm.

4. The method according to claim 2, characterized in that: The performing spatiotemporal fusion of the collected data based on the timestamp of the data collection includes: Get the motion data with the earliest timestamp; The acquired motion data is used as fused spatiotemporal data; The performing feature fusion on the collected data based on the timestamp of the data collection includes: Respectively obtain the image data and communication signal data with the earliest timestamp; The acquired communication data and communication signal data are used as fused feature data.

5. The method according to claim 1, characterized in that If the flying object is a drone, issuing an early warning includes: Calculate the distance between the UAV and the target core area in real time; Issue corresponding warnings based on the currently calculated distance.

6. The method according to claim 5, characterized in that The corresponding warning based on the currently calculated distance includes: Compare the currently calculated distance with the warning comparison table; Output a warning corresponding to the comparison result according to the comparison result.

7. The method according to claim 5, characterized in that The corresponding warning based on the currently calculated distance includes: When the UAV flies in a direction close to the target core area, comparing the currently calculated distance with the first preset distance; If the currently calculated distance is greater than the first preset distance, a first level warning is issued; If the currently calculated distance is equal to the first preset distance, a second level warning is issued; If the currently calculated distance is less than the first preset distance and greater than the second preset distance, a third level warning is issued, and the first preset distance is greater than the second preset distance; If the currently calculated distance is equal to the second preset distance, a fourth level warning is issued; If the currently calculated distance is less than the second preset distance, a fifth level warning is issued; and When the UAV flies in a direction away from the target core area, comparing the currently calculated distance with the second preset distance; If the currently calculated distance is less than the second preset distance, the fifth level warning is issued; If the currently calculated distance is equal to the second preset distance, the fourth level warning is issued; If the currently calculated distance is greater than the second preset distance and less than the first preset distance, the third level warning is issued; If the currently calculated distance is equal to the first preset distance, the second level warning is issued; If the currently calculated distance is greater than the first preset distance, the first level warning is issued.

8. A detection device for an unmanned aerial vehicle, characterized in that: The device comprises: A collection module, used to collect data of the flying object, the data at least including: motion data, image data, a timestamp of data collection and communication signal data of the flying object; A fusion module, used for fusing the collected data based on the timestamp of the data collection; Identification module, used to identify flying objects based on the fused data; The early warning module is used to issue an early warning when the flying object is a drone.

9. An electronic device comprising a memory, a processor and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the drone detection method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for detecting a drone as claimed in any one of claims 1 to 7 is implemented.

Images