Method and device for determining security of target area and electronic equipment

Abstract

The invention discloses a method and device for determining the safety of a target area and electronic equipment. According to the specific scheme, unmanned aerial vehicle data of at least one to-be-detected unmanned aerial vehicle in a target area under multiple dimensions are acquired, and the multiple dimensions comprise a radio signal dimension, an unmanned aerial vehicle vibration audio dimension and an image acquisition dimension of the to-be-detected unmanned aerial vehicle; determining the unmanned aerial vehicle type of the to-be-detected unmanned aerial vehicle based on the unmanned aerial vehicle data of the at least one to-be-detected unmanned aerial vehicle; in response to the event of which the unmanned aerial vehicle type is not the preset type, determining flight data of the target unmanned aerial vehicle, and determining a safety attribute of a preset detection point according to the flight data and position data of the preset detection point of the target area; wherein the target unmanned aerial vehicle is an unmanned aerial vehicle in the at least one to-be-detected unmanned aerial vehicle. According to the invention, accurate detection and positioning of the unmanned aerial vehicle are realized, and whether the unmanned aerial vehicle will threaten the preset detection point is determined.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a method, a device and an electronic device for determining the safety of a target area. Background Art

[0002] With the continuous advancement of drone technology, the scope and number of drones are also increasing. Drones are widely used in many fields such as commercial filming, agricultural monitoring, emergency rescue, etc. However, the widespread use of drones also brings potential security threats.

[0003] Currently, drones are usually located through radar or radio wave detection to determine whether they pose a threat to a safe area. However, the above methods only rely on a single sensor or signal source, which is easily interfered with during the drone positioning process and cannot accurately locate the drone, making it impossible to accurately assess whether the drone poses a potential threat. Summary of the invention

[0004] The present invention provides a method, device and electronic equipment for determining the safety of a target area, which realizes accurate detection and positioning of drones and determines whether the drones will pose a threat to preset detection points.

[0005] According to one aspect of the present invention, there is provided a method for determining the safety of a target area, the method comprising:

[0006] Acquire drone data of at least one drone to be detected in a target area in multiple dimensions, wherein the multiple dimensions include a radio signal dimension, a drone vibration audio dimension, and an image acquisition dimension of the drone to be detected;

[0007] Determining a drone type of the drone to be detected based on drone data of at least one drone to be detected;

[0008] In response to an event that the type of the drone is not a preset type, determining flight data of the target drone, and determining a safety attribute of the preset detection point based on the flight data and position data of the preset detection point in the target area;

[0009] The target drone is a drone among at least one drone to be detected.

[0010] According to another aspect of the present invention, there is provided a device for determining the safety of a target area, the device comprising:

[0011] A data acquisition module, used to acquire drone data of at least one drone to be detected in a target area in multiple dimensions, wherein the multiple dimensions include a radio signal dimension, a drone vibration audio dimension, and an image acquisition dimension of the drone to be detected;

[0012] A drone type determination module, configured to determine the drone type of the drone to be detected based on the drone data of at least one drone to be detected;

[0013] A safety attribute determination module, for determining flight data of a target UAV in response to an event that the type of the UAV is not a preset type, and determining safety attributes of a preset detection point based on the flight data and position data of a preset detection point in a target area;

[0014] The target drone is a drone among at least one drone to be detected.

[0015] According to another aspect of the present invention, there is provided an electronic device, the electronic device comprising:

[0016] at least one processor; and

[0017] a memory communicatively connected to at least one processor; wherein,

[0018] The memory stores a computer program that can be executed by at least one processor. The computer program is executed by the at least one processor so that the at least one processor can execute the method for determining the safety of a target area according to any embodiment of the present invention.

[0019] According to another aspect of the present invention, a computer-readable storage medium is provided. The computer-readable storage medium stores computer instructions, which are used to enable a processor to implement the method for determining the safety of a target area according to any embodiment of the present invention when the computer instructions are executed.

[0020] According to another aspect of the present invention, a computer program product is provided, including a computer program, wherein the computer program implements the method for determining the safety of a target area according to any embodiment of the present invention when executed by a processor.

[0021] The technical solution of the embodiment of the present invention obtains drone data of at least one drone to be detected in a target area in multiple dimensions, wherein the multiple dimensions include a radio signal dimension, a drone vibration audio dimension, and an image acquisition dimension of the drone to be detected. By obtaining drone data in multiple dimensions, the accuracy of subsequent determination of the type of drone is improved. The drone type of the drone to be detected is determined according to the drone data of at least one drone to be detected. In response to an event that the drone type is not a preset type, the flight data of the target drone is determined, and the safety attribute of the preset detection point is determined according to the flight data and the position data of the preset detection point in the target area. Based on this, it can be determined whether the target drone will pose a threat to the preset detection point in the target area, so as to determine whether to take measures against the target drone according to the safety attribute of the preset detection point to ensure the safety of the preset detection point. The present invention solves the problem of inaccurate detection and positioning caused by detecting drones through a single sensor or signal source in the prior art, and improves the accuracy and reliability of drone detection and positioning by performing feature analysis and processing on drone data in multiple dimensions. Moreover, when the drone type is not a preset type, it is determined whether the target drone will pose a threat to the preset detection point according to the position of the target drone at a preset time, thereby ensuring the safety of the preset detection point in the target area.

[0022] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0024] Figure 1 is a flow chart of a method for determining the safety of a target area provided by an embodiment of the present invention;

[0025] Figure 2 is a flow chart of a method for determining the safety of a target area provided by an embodiment of the present invention;

[0026] Figure 3 is an example diagram of a signal time-frequency characteristic diagram provided by an embodiment of the present invention;

[0027] Figure 4 is an example diagram of a sound time-frequency feature diagram provided by an embodiment of the present invention;

[0028] Figure 5 is a schematic structural diagram of a device for determining the safety of a target area provided by an embodiment of the present invention;

[0029] Figure 6 It is a structural schematic diagram of an electronic device for implementing the method for determining the safety of a target area according to an embodiment of the present invention. DETAILED DESCRIPTION

[0030] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0031] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0032] Embodiment 1

[0033] Figure 1 This is a flow chart of a method for determining the safety of a target area provided by the first embodiment of the present invention. This embodiment can be applied to detect the type of drones to be detected in the target area, and evaluate drones that are not of the preset type to ensure the safety of preset detection points in the target area. The method can be executed by a device for determining the safety of the target area. The device for determining the safety of the target area can be implemented in the form of hardware and / or software. The device for determining the safety of the target area can be configured in electronic devices such as mobile phones, computers or servers. Figure 1 As shown, the method includes:

[0034] S110, obtaining drone data of at least one drone to be detected in the target area in multiple dimensions, wherein the multiple dimensions include a radio signal dimension, a drone vibration audio dimension, and an image acquisition dimension of the drone to be detected.

[0035] In an embodiment of the present invention, by detecting the drone in the target area, it is determined whether the drone poses a potential threat. The target area may be a pre-divided area. For example, the target area may be a circular area with a radius of three kilometers. The drone in the target area is the drone to be detected. In order to improve the accuracy of drone type detection, drone data of the drone to be detected in multiple dimensions may be obtained. The multiple dimensions may be a radio signal dimension, a drone vibration audio dimension, and an image acquisition dimension. Optionally, the drone data under the radio signal dimension may be information such as the signal frequency and bandwidth of the drone image transmission signal of the drone to be detected. The drone data under the drone vibration audio dimension may be understood as information such as the frequency and intensity of the sound of the drone to be detected during flight. The drone data under the image acquisition dimension may be a drone image obtained by image acquisition of the drone to be detected.

[0036] Specifically, the drone data of at least one drone to be detected in the target area in the radio signal dimension, the drone vibration audio dimension and the image acquisition dimension of the drone to be detected are obtained, so as to determine the drone type of the drone to be detected through these drone data, and to determine whether the drone to be detected has potential threats based on the drone type.

[0037] S120: Determine the drone type of the drone to be detected based on the drone data of at least one drone to be detected.

[0038] The drone type can be understood as the type of the drone to be detected. For example, the drone type of the drone to be detected can be type A, type B, or type C.

[0039] Specifically, the drone type of each drone to be detected is determined according to the drone data of each drone to be detected in multiple dimensions, so as to determine whether the drone to be detected is a drone type allowed to fly in the target area according to the drone type of the drone to be detected.

[0040] S130. In response to an event that the drone type is not a preset type, determining flight data of the target drone, and determining safety attributes of the preset detection points based on the flight data and position data of the preset detection points in the target area.

[0041] Among them, the target drone is a drone among at least one drone to be detected. The preset type can be understood as the type of drones allowed to fly in the target area. For example, if the drone type of the drone to be detected is type A, and the preset type is type B, it means that the drone to be detected is prohibited from flying in the target area. The target drone may be a drone to be detected whose drone type is not the preset type. The flight data may be various flight data of the target drone when it flies in the target area. For example, the flight position, flight speed and flight direction of the target drone. The preset detection point may be a place or area pre-set in the target area that needs to be protected. The position data may be the height data of the preset detection point, or it may be the three-dimensional coordinate data in a three-dimensional coordinate system with the center of the earth as the origin. The safety attribute can be used to characterize whether the preset detection point is safe.

[0042] Specifically, in response to an event that the drone type of the drone to be detected is not a preset type, the drone to be detected that is not of the preset type is taken as a target drone, and the flight data of the target drone is determined. Based on the flight data and the position data of the preset detection point in the target area, it is determined whether the target drone will pose a threat to the preset detection point, that is, whether the preset detection point is safe.

[0043] In an embodiment of the present invention, the preset type is a type of drone that is not banned from flying in the target area. The method for determining the safety attribute of the preset detection point can be: if the drone type of the drone to be detected is a type of drone that is banned from flying in the target area, then the drone to be detected is determined to be a target drone; the control signal of the target drone is intercepted and processed, and the intercepted control signal is analyzed to obtain the flight data of the target drone; the flight data is substituted into the preset position determination function to obtain the predicted position information corresponding to the target drone at the preset time; the safety attribute of the preset detection point is determined according to the predicted position information and the position data of the preset detection point in the target area.

[0044] The target UAV may be a UAV to be detected that is prohibited from flying in the target area. The control signal may be understood as a signal used to control the flight of the target UAV. The flight data includes at least the current flight position, current flight speed, current flight direction, and current flight acceleration of the target UAV. The preset position determination function is:

[0045]

[0046] Among them, (x0, y0, z0) represents the three-dimensional coordinate data corresponding to the current flight position in the three-dimensional coordinate system with the center of the earth as the origin, v represents the current flight speed, t represents the preset time, θ represents the angle between the current flight direction and the horizontal plane, a represents the current flight acceleration, and (x, y, z) represents the predicted position information corresponding to the preset time.

[0047] The preset time may be a pre-set time for detecting the flight position of the target UAV. The predicted position information may be the flight position of the target UAV in a three-dimensional coordinate system with the center of the earth as the origin at the preset time.

[0048] Specifically, if the drone type of the drone to be detected is not the preset type, it means that the drone type of the drone to be detected is a drone type that is prohibited from flying in the target area, and the drone to be detected is used as the target drone. The control signal of the target drone is analyzed and processed to obtain flight data such as the current flight position, current flight speed, current flight direction, and current flight acceleration of the target drone. The above flight data is substituted into the above preset position determination function to obtain the predicted position information of the target drone at the preset time. According to the three-dimensional coordinate data corresponding to the predicted position information and the three-dimensional coordinate data corresponding to the preset detection point in the target area, it is determined whether the preset detection point in the target area is safe.

[0049] Optionally, the flight data of the target UAV may be acquired by decoding and analyzing the UAV image transmission signal of the target UAV to obtain the flight data of the target UAV.

[0050] Exemplary. The drone data in the radio signal dimension is used as the drone image transmission signal for illustration. The drone image transmission signal and the control signal are decoded and processed to extract the Global Navigation Satellite System (GNSS) positioning data and other flight data of the target drone. Among them, the GNSS positioning data contains three coordinates, namely, the latitude coordinate (Latitude, lat), the longitude coordinate (Longitude, lon) and the altitude coordinate (Altitude, alt). The positioning data and other flight data are filtered and denoised to obtain the denoised flight data, so as to determine the predicted position information of the target drone at the preset time through the denoised flight data.

[0051] Optionally, the flight data is substituted into a preset position determination function to obtain the position information of the target UAV at multiple moments. The flight trajectory of the target UAV can be determined based on the position information of the target UAV at multiple moments. The predicted position information of the target UAV at the preset moment can be determined based on the flight trajectory of the target UAV.

[0052] Optionally, the safety attribute of the preset detection point is determined based on the predicted position information and the position data of the preset detection point in the target area, including: determining the distance information between the predicted position information and the preset detection point based on the predicted position information and the position data of the preset detection point; if the distance information does not fall within the preset distance range, determining the safety attribute of the preset detection point as unsafe.

[0053] The distance information can be understood as the distance between the predicted position information and the position data of the preset detection point. The distance information can be determined by the three-dimensional coordinate data corresponding to the predicted position information and the three-dimensional coordinate data corresponding to the preset detection point. The preset distance range can be a pre-set safe distance range between the target drone and the preset detection point.

[0054] Specifically, the distance information between the target drone and the preset detection point is determined based on the three-dimensional coordinate data corresponding to the predicted position information and the three-dimensional coordinate data of the predicted detection point. When the distance information does not fall within the preset distance range, the safety attribute of the preset detection point is determined to be unsafe.

[0055] Optionally, multiple distance ranges may be set, and the drone threat level corresponding to each distance range may be determined. According to the distance information between the target drone and the preset detection point, the distance range to which the distance information belongs is determined, and according to the distance range, the drone threat level of the target drone is determined. Based on this, it may be determined whether to interfere with the target drone according to the drone threat level to ensure the safety of the preset detection points in the target area.

[0056] Optionally, when the security attribute of the preset detection point is unsafe, interference processing or inductive deception processing is performed on the target drone to update the security attribute of the preset detection point.

[0057] The interference processing may be to perform radio signal interference processing on the target UAV. The inductive deception processing may be to send a false Global Positioning System (GPS) signal to the target UAV so as to shift the flight position of the target UAV to ensure the safety of the predicted detection point.

[0058] Specifically, when it is determined that the security attribute of the preset detection point is unsafe, interference processing or inductive deception processing is performed on the target drone to cause the predicted position information of the target drone to shift. The distance information between the predicted position information after the shift and the preset detection point is determined. When the distance information is within the preset distance range, the security attribute of the preset detection point is updated to be safe.

[0059] The technical solution of this embodiment obtains drone data of at least one drone to be detected in the target area in multiple dimensions, wherein the multiple dimensions include a radio signal dimension, a drone vibration audio dimension, and an image acquisition dimension of the drone to be detected. By obtaining drone data in multiple dimensions, the accuracy of subsequent determination of the drone type is improved. The drone type of the drone to be detected is determined according to the drone data of at least one drone to be detected. In response to an event that the drone type is not a preset type, the flight data of the target drone is determined, and the safety attributes of the preset detection points are determined according to the flight data and the position data of the preset detection points in the target area. Based on this, it can be determined whether the target drone will pose a threat to the preset detection points in the target area, so as to determine whether to take measures against the target drone according to the safety attributes of the preset detection points to ensure the safety of the preset detection points. The present invention solves the problem of inaccurate detection and positioning caused by detecting drones through a single sensor or signal source in the prior art, and improves the accuracy and reliability of drone detection and positioning by performing feature analysis and processing on drone data in multiple dimensions. Moreover, when the drone type is not a preset type, it is determined whether the target drone will pose a threat to the preset detection points according to the position of the target drone at a preset time, thereby ensuring the safety of the preset detection points in the target area.

[0060] Embodiment 2

[0061] Figure 2 This is a flow chart of a method for determining the safety of a target area provided by the second embodiment of the present invention. This embodiment is based on the above embodiment and refines the step of "determining the type of the drone to be detected based on the drone data of at least one drone to be detected". The specific implementation method can be found in the technical solution of this embodiment. Among them, the technical terms that are the same as or corresponding to the above embodiment are not repeated here. Figure 2 As shown, the method includes:

[0062] S210, obtaining drone data of at least one drone to be detected in the target area in multiple dimensions, wherein the multiple dimensions include a radio signal dimension, a drone vibration audio dimension, and an image acquisition dimension of the drone to be detected.

[0063] S220: For at least one drone to be detected, obtain a signal time-frequency feature graph in a radio signal dimension from drone data of the drone to be detected, and determine at least one signal feature of the drone to be detected based on the signal time-frequency feature graph.

[0064] The signal time-frequency characteristic graph may be an image determined based on the image transmission signal of the drone to be detected and the time. The image transmission signal of the drone may be understood as the signal used when the drone to be detected transmits image data to the receiving device. For example, the signal time-frequency characteristic graph may be as follows: Figure 3 As shown in the figure. The signal time-frequency characteristic diagram can be used to determine how the frequency of the drone image transmission signal changes over time. The signal characteristics can include the spectrum characteristics, modulation mode characteristics, instantaneous characteristics, pulse width characteristics, and data transmission interval characteristics of the drone to be detected.

[0065] Specifically, at least one radio signal in the airspace corresponding to the target area is obtained according to the radio wave detection technology. According to the frequency, modulation mode and time domain characteristics of the radio signal, the radio signal related to the drone image transmission is determined. That is, the drone image transmission signal is obtained. The signal time-frequency feature diagram of the drone to be detected is determined through the drone image transmission signal. And the signal time-frequency feature diagram is used as the drone data of the current drone to be detected in the radio signal dimension. For at least one drone to be detected, the signal time-frequency feature diagram of the current drone to be detected is determined from the drone data of the current drone to be detected. Signal feature extraction is performed on the signal time-frequency feature diagram and the drone image transmission signal of the drone to be detected to determine at least one signal feature of the current drone to be detected.

[0066] S230: Obtain a sound time-frequency feature graph in the drone vibration audio dimension from the drone data, and determine the voiceprint feature of the drone to be detected based on the sound time-frequency feature graph.

[0067] The sound time-frequency feature graph may be an image determined according to the sound frequency and time of the drone to be detected. For example, the sound time-frequency feature graph may be as follows: Figure 4 As shown. The sound time-frequency characteristic diagram can be used to determine how the sound frequency of the drone to be detected changes over time. The voiceprint feature can be a characteristic value used to characterize the sound frequency and sound intensity of the drone to be detected.

[0068] Specifically, audio data in the target area is collected according to the audio sensors deployed in the target area. The sound time-frequency feature graph of the drone to be detected in the drone vibration audio dimension is determined according to the audio data. The sound time-frequency feature graph is extracted to determine the voiceprint features of the drone to be detected.

[0069] It should be noted that different drone types have different corresponding voiceprint features. Voiceprint features can be expressed as V = [v1, v2, v3, ..., v m ], where v i Indicates the sound frequency f i and time t iThe voiceprint feature value corresponding to the time, i∈[1,m].

[0070] S240: Acquire an image to be processed in an image acquisition dimension from the drone data, and determine at least one image feature of the drone to be detected based on the image to be processed.

[0071] The image to be processed may be a drone image obtained by collecting images of the drone to be detected.

[0072] Specifically, an image to be processed of the drone to be detected in the image acquisition dimension is obtained from the drone data. The image to be processed is processed using a deep learning algorithm, such as a convolutional neural network algorithm (CNN), to extract at least one image feature of the drone to be detected. The image feature may be an appearance feature of the drone to be detected, such as the shape, color, and texture of the drone.

[0073] It should be noted that before obtaining the image to be processed from the drone data, the method also includes: determining the distance difference between the drone to be detected at two preset signal receiving points based on the arrival time difference technology, so as to determine the positioning information of the drone to be detected based on the distance difference. Based on the positioning information of the drone to be detected, an image acquisition device with a telephoto lens is called to perform image acquisition and processing on the drone to be detected to obtain the image to be processed of the drone to be detected, wherein the positioning information is used to characterize the current position information of the drone to be detected.

[0074] The calculation formula of the distance difference can be expressed as follows:

[0075] d ij =c×(t i -t j )

[0076] Among them, d ij represents the distance difference between the drone to be detected and the two preset signal receiving points, c represents the propagation speed of the radio signal of the drone to be detected in the air, and t i It represents the time when the radio signal of the drone to be detected reaches the preset signal receiving point i, t j Indicates the time when the radio signal of the drone to be detected reaches the preset signal receiving point j.

[0077] S250: When at least one signal feature, voiceprint feature, and at least one image feature all satisfy corresponding constraint conditions, determine that the drone type of the drone to be detected is a target type.

[0078] The corresponding constraint condition may be a pre-set condition that the features in different dimensions need to satisfy. Optionally, the constraint condition may be used to characterize the degree of match between the features in different dimensions and the corresponding preset features. The target type may be understood as the type of drone corresponding to the drone to be detected.

[0079] Specifically, when at least one signal feature satisfies the constraint condition under the radio signal dimension, at least one drone type corresponding to the signal feature is determined. When the voiceprint feature satisfies the constraint condition under the drone vibration audio dimension, at least one drone type corresponding to the voiceprint feature is determined. When at least one image feature satisfies the constraint condition under the image acquisition dimension, at least one drone type corresponding to the image feature is determined. Based on multiple drone types corresponding to features of different dimensions, the drone type of the drone to be detected is determined as the target type.

[0080] In an embodiment of the present invention, the method for determining the type of the drone may be: determining the similarity of the features to be fused corresponding to each signal feature according to at least one signal feature and a preset feature under the radio signal dimension, and determining the signal feature similarity based on the weight coefficient of each signal feature and the similarity of the features to be fused; determining the voiceprint feature similarity corresponding to the voiceprint feature according to the voiceprint feature and the preset feature under the drone vibration audio dimension; obtaining at least one feature difference according to the feature value corresponding to at least one image feature and the feature value of the preset feature under the image acquisition dimension; determining the drone type of the drone to be detected as the target type when the signal feature similarity belongs to the preset signal similarity range, the voiceprint feature similarity is greater than the preset sound similarity threshold, and the feature difference is less than the preset value.

[0081] Among them, the preset features under the radio signal dimension can be standard signal features corresponding to different types of drones pre-stored in a database or a corresponding file. The similarity of the features to be fused can be understood as the feature similarity between the current signal feature and the corresponding preset feature. Optionally, the similarity of the features to be fused can be determined by at least one of the methods such as Euclidean distance, Manhattan distance, cosine similarity and spectrum similarity measurement method. For example, if the signal feature is a numerical feature, the Euclidean distance or Manhattan distance calculation method can be used. If the signal feature is a vector feature, the feature similarity can be determined by using the cosine similarity method. If the signal feature is a spectral feature, the feature similarity can be determined by using the spectral similarity measurement method. The weight coefficient can be predetermined and used to characterize the importance of the signal feature. The signal feature similarity can be determined based on the weight coefficient of each signal feature and the similarity of the features to be fused. Optionally, the method for determining the signal feature similarity can be:

[0082]

[0083] Where D represents the signal feature similarity, w i Represents the signal feature x i The weight coefficient, y i Indicates the preset characteristics, Indicates the similarity of features to be fused.

[0084] The preset features in the drone vibration audio dimension may be standard voiceprint features corresponding to different drone types pre-stored in a database or a corresponding file. The voiceprint feature similarity may be used to characterize the similarity between the preset features and the voiceprint features. Optionally, the voiceprint feature similarity may be determined in the following manner:

[0085]

[0086] Among them, S(V,V′) represents the similarity between the voiceprint feature V and the preset feature V′, which usually ranges from -1 to 1. V represents the voiceprint feature of the drone to be detected, defined as V=[v1,v2,...,v m ], where v i Indicates the sound frequency f i and time t i V' represents the preset feature in the drone vibration audio dimension, defined as V' = [v1', v2', ..., v m ']. V·V' represents the product of the voiceprint feature and the preset feature, that is, ‖V‖ represents the Euclidean norm of the voiceprint feature V, that is, ‖V′‖ represents the Euclidean norm of the preset feature V′. It should be noted that, by determining the voiceprint feature similarity in the above manner, when the voiceprint feature similarity is closer to 1, it means that the voiceprint feature and the preset feature are more similar.

[0087] The feature value of the preset feature under the image acquisition dimension may be a feature value corresponding to the standard image feature corresponding to different drone types that is pre-stored in a database or a corresponding file. The feature difference may be the difference between the feature value of the image feature and the feature value of the preset feature. The smaller the feature difference, the more similar the image feature is to the preset feature.

[0088] The preset signal similarity range may be a preset standard range for characterizing signal feature similarity. The preset sound similarity threshold may be a preset standard value for voiceprint feature similarity. The preset value may be a preset standard value for feature difference.

[0089] Specifically, for at least one signal feature, determine the similarity of the features to be fused between each signal feature and the preset features in the radio signal dimension. Calculate and determine the signal feature similarity based on the similarity of the features to be fused and the weight coefficient of each signal feature. Determine the voiceprint feature similarity between the voiceprint feature and the preset features in the drone vibration audio dimension. For at least one image feature, calculate the feature difference between each image feature and the preset feature in the image acquisition dimension. When the signal feature similarity falls within the preset signal similarity range, the voiceprint feature similarity is greater than the preset sound similarity threshold, and each feature difference is less than the corresponding preset value, determine that the drone to be detected is a drone of the target type.

[0090] Optionally, when the signal feature similarity belongs to a preset signal similarity range, the voiceprint feature similarity is greater than a preset sound similarity threshold, and the feature difference is less than a preset value, the drone type of the drone to be detected is determined to be a target type, including: when the signal feature similarity belongs to the preset signal similarity range, determining the first candidate type corresponding to the drone to be detected; when the voiceprint feature similarity is greater than the preset sound similarity threshold, determining the second candidate type corresponding to the drone to be detected; when the feature difference is less than a preset value, determining the third candidate type corresponding to the drone to be detected; and determining the drone to be detected as the target type based on the first candidate type, the second candidate type and the third candidate type.

[0091] The first candidate type may be a possible drone type of the drone to be detected, determined based on the signal characteristics. The second candidate type may be a possible drone type of the drone to be detected, determined based on the voiceprint characteristics. The third candidate type may be a possible drone type of the drone to be detected, determined based on the image characteristics. For example, the first candidate type is type A, type B, and type C. The second candidate type is type B and type C, and the third candidate type is type B, then the target type may be type B.

[0092] Specifically, when the signal feature similarity falls within the preset signal feature similarity range, the drone type corresponding to the preset feature of the radio signal dimension is used as the first candidate type of the drone to be detected. When the voiceprint feature similarity is greater than the preset sound similarity threshold, the drone type corresponding to the preset feature of the drone vibration audio dimension is used as the second candidate type corresponding to the drone to be detected. When each feature difference is less than a preset value, the drone type corresponding to the preset feature of the image acquisition dimension is used as the third candidate type. The drone type of the drone to be detected is comprehensively determined based on the first candidate type, the second candidate type, and the third candidate type, that is, the drone to be detected is determined to be a drone of the target type.

[0093] S260: In response to an event that the drone type is not a preset type, determine the flight data of the target drone, and determine the safety attributes of the preset detection points based on the flight data and the position data of the preset detection points in the target area.

[0094] The target drone is a drone among at least one drone to be detected.

[0095] The technical solution of this embodiment is to obtain drone data of at least one drone to be detected in the target area in multiple dimensions, wherein the multiple dimensions include a radio signal dimension, a drone vibration audio dimension, and an image acquisition dimension of the drone to be detected. By obtaining drone data in multiple dimensions, the accuracy of subsequent determination of the type of drone is improved. For at least one drone to be detected, a signal time-frequency feature map, a sound time-frequency feature map, and an image to be processed are obtained from the drone data, so as to obtain at least one signal feature by extracting features from the signal time-frequency feature map. A voiceprint feature is obtained by extracting features from the sound time-frequency feature map. And at least one image feature is obtained by extracting features from the image to be processed. When at least one signal feature, a voiceprint feature, and at least one image feature all meet corresponding constraints, the drone type of the drone to be detected is determined to be the target type. Based on this, the drone type of the drone to be detected can be accurately determined. In response to an event that the drone type is not a preset type, the flight data of the target drone is determined, and the safety attributes of the preset detection point are determined based on the flight data and the position data of the preset detection point in the target area. Based on this, it is possible to determine whether the target drone will pose a threat to the preset detection points in the target area, so as to determine whether to take measures against the target drone based on the security attributes of the preset detection points to ensure the safety of the preset detection points. The present invention solves the problem of inaccurate detection and positioning caused by detecting drones through a single sensor or signal source in the prior art, and improves the accuracy and reliability of drone detection and positioning by performing feature analysis and processing on drone data in multiple dimensions. In addition, when the drone type is not the preset type, it is determined whether the target drone will pose a threat to the preset detection points based on the position of the target drone at the preset time, thereby ensuring the safety of the preset detection points in the target area.

[0096] Embodiment 3

[0097] Figure 5 FIG. 1 is a schematic diagram of a structure of a device for determining the safety of a target area provided by Embodiment 3 of the present invention. Figure 5 As shown, the device includes: a data acquisition module 310, a drone type determination module 320 and a safety attribute determination module 330.

[0098] The data acquisition module 310 is used to obtain drone data of at least one drone to be detected in the target area in multiple dimensions, wherein the multiple dimensions include a radio signal dimension, a drone vibration audio dimension, and an image acquisition dimension of the drone to be detected; the drone type determination module 320 is used to determine the drone type of the drone to be detected based on the drone data of at least one drone to be detected; the security attribute determination module 330 is used to determine the flight data of the target drone in response to an event that the drone type is not a preset type, and determine the security attributes of the preset detection point based on the flight data and the position data of the preset detection point in the target area; wherein the target drone is a drone among the at least one drone to be detected.

[0099] The technical solution of this embodiment obtains drone data of at least one drone to be detected in the target area in multiple dimensions, wherein the multiple dimensions include a radio signal dimension, a drone vibration audio dimension, and an image acquisition dimension of the drone to be detected. By obtaining drone data in multiple dimensions, the accuracy of subsequent determination of the drone type is improved. The drone type of the drone to be detected is determined according to the drone data of at least one drone to be detected. In response to an event that the drone type is not a preset type, the flight data of the target drone is determined, and the safety attributes of the preset detection points are determined according to the flight data and the position data of the preset detection points in the target area. Based on this, it can be determined whether the target drone will pose a threat to the preset detection points in the target area, so as to determine whether to take measures against the target drone according to the safety attributes of the preset detection points to ensure the safety of the preset detection points. The present invention solves the problem of inaccurate detection and positioning caused by detecting drones through a single sensor or signal source in the prior art, and improves the accuracy and reliability of drone detection and positioning by performing feature analysis and processing on drone data in multiple dimensions. Moreover, when the drone type is not a preset type, it is determined whether the target drone will pose a threat to the preset detection points according to the position of the target drone at a preset time, thereby ensuring the safety of the preset detection points in the target area.

[0100] On the basis of the above embodiment, optionally, the drone type determination module includes: a signal feature determination unit, which is used to obtain a signal time-frequency feature graph in the radio signal dimension from the drone data of the drone to be detected for at least one drone to be detected, and determine at least one signal feature of the drone to be detected based on the signal time-frequency feature graph; a voiceprint feature determination unit, which is used to obtain a sound time-frequency feature graph in the drone vibration audio dimension from the drone data, and determine the voiceprint feature of the drone to be detected based on the sound time-frequency feature graph; an image feature determination unit, which is used to obtain an image to be processed in the image acquisition dimension from the drone data, and determine at least one image feature of the drone to be detected based on the image to be processed; a drone type determination unit, which is used to determine that the drone type of the drone to be detected is a target type when at least one signal feature, voiceprint feature and at least one image feature all meet corresponding constraints.

[0101] Optionally, the drone type determination unit includes: a signal feature similarity determination subunit, used to determine the similarity of the features to be fused corresponding to each signal feature based on at least one signal feature and a preset feature under the radio signal dimension, and determine the signal feature similarity based on the weight coefficient of each signal feature and the similarity of the features to be fused; a voiceprint feature similarity determination subunit, used to determine the voiceprint feature similarity corresponding to the voiceprint feature based on the voiceprint feature and the preset feature under the drone vibration audio dimension; a feature difference determination subunit, used to obtain at least one feature difference based on the feature value corresponding to at least one image feature and the feature value of the preset feature under the image acquisition dimension; a target type determination subunit, used to determine that the drone type of the drone to be detected is a target type when the signal feature similarity belongs to the preset signal similarity range, the voiceprint feature similarity is greater than the preset sound similarity threshold, and the feature difference is less than the preset value.

[0102] Optionally, a target type determination subunit is used to determine a first candidate type corresponding to the drone to be detected when the signal feature similarity falls within a preset signal similarity range; to determine a second candidate type corresponding to the drone to be detected when the voiceprint feature similarity is greater than a preset sound similarity threshold; to determine a third candidate type corresponding to the drone to be detected when the feature difference is less than a preset value; and to determine that the drone to be detected is a target type based on the first candidate type, the second candidate type and the third candidate type.

[0103] Optionally, the preset type is a type of drone that is not banned from flying in the target area, and the safety attribute determination module includes: a target drone determination unit, which is used to determine that the drone to be detected is a target drone if the drone type of the drone to be detected is a type of drone that is banned from flying in the target area; a flight attribute determination unit, which is used to intercept and process the control signal of the target drone, and parse the intercepted control signal to obtain the flight data of the target drone; a position information determination unit, which is used to substitute the flight data into a preset position determination function to obtain the predicted position information corresponding to the target drone at a preset time; and a safety attribute determination unit, which is used to determine the safety attribute of a preset detection point based on the predicted position information and the position data of a preset detection point in the target area.

[0104] Optionally, the flight data includes at least the current flight position, current flight speed, current flight direction and current flight acceleration of the target UAV, and the preset position determination function is:

[0105]

[0106] Among them, (x0, y0, z0) represents the three-dimensional coordinate data corresponding to the current flight position in the three-dimensional coordinate system with the center of the earth as the origin, v represents the current flight speed, t represents the preset time, θ represents the angle between the current flight direction and the horizontal plane, a represents the current flight acceleration, and (x, y, z) represents the predicted position information corresponding to the preset time.

[0107] Optionally, a safety attribute determination unit is used to determine the distance information between the predicted position information and the preset detection point based on the predicted position information and the position data of the preset detection point; if the distance information does not fall within the preset distance range, the safety attribute of the preset detection point is determined to be unsafe.

[0108] Optionally, the security attribute determination module also includes: a security attribute updating unit, which is used to perform interference processing or induced deception processing on the target drone when the security attribute of the preset detection point is unsafe, so as to update the security attribute of the preset detection point.

[0109] The device for determining the safety of a target area provided by an embodiment of the present invention can execute the method for determining the safety of a target area provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0110] Embodiment 4

[0111] Figure 61 is a schematic diagram of the structure of an electronic device provided in Embodiment 4 of the present invention. The electronic device 10 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0112] like Figure 6 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0113] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0114] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a method for determining the safety of a target area.

[0115] In some embodiments, the method for determining the safety of the target area may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the method for determining the safety of the target area described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the method for determining the safety of the target area in any other appropriate manner (e.g., by means of firmware).

[0116] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0117] The computer program for implementing the method for determining the safety of a target area of ​​the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program can be executed entirely on the machine, partially on the machine, partially on the machine as an independent software package and partially on a remote machine, or entirely on a remote machine or server.

[0118] Embodiment 5

[0119] Embodiment 5 of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to cause a processor to execute a method for determining the safety of a target area, the method comprising:

[0120] Obtain drone data of at least one drone to be detected in a target area in multiple dimensions, wherein the multiple dimensions include a radio signal dimension, a drone vibration audio dimension, and an image acquisition dimension of the drone to be detected; determine the drone type of the drone to be detected based on the drone data of at least one drone to be detected; in response to an event that the drone type is not a preset type, determine the flight data of the target drone, and determine the safety attributes of the preset detection point based on the flight data and the position data of the preset detection point in the target area; wherein the target drone is a drone among the at least one drone to be detected.

[0121] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0122] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0123] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0124] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0125] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0126] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for determining the safety of a target area, characterized in that: include: Acquire drone data of at least one drone to be detected in a target area in multiple dimensions, wherein the multiple dimensions include a radio signal dimension, a drone vibration audio dimension, and an image acquisition dimension of the drone to be detected; Determining the drone type of the drone to be detected based on the drone data of the at least one drone to be detected; In response to the event that the type of the drone is not a preset type, determining flight data of the target drone, and determining a safety attribute of the preset detection point based on the flight data and position data of the preset detection point in the target area; The target drone is a drone among the at least one drone to be detected.

2. The method according to claim 1, characterized in that The determining the drone type of the drone to be detected based on the drone data of the at least one drone to be detected includes: For at least one of the unmanned aerial vehicles to be detected, a signal time-frequency feature graph in a radio signal dimension is obtained from the unmanned aerial vehicle data of the unmanned aerial vehicle to be detected, and at least one signal feature of the unmanned aerial vehicle to be detected is determined based on the signal time-frequency feature graph; Acquire a sound time-frequency feature graph in the drone vibration audio dimension from the drone data, and determine the voiceprint feature of the drone to be detected based on the sound time-frequency feature graph; Acquire an image to be processed in an image acquisition dimension from the drone data, and determine at least one image feature of the drone to be detected based on the image to be processed; When the at least one signal feature, the voiceprint feature, and the at least one image feature all satisfy corresponding constraint conditions, the drone type of the drone to be detected is determined to be a target type.

3. The method according to claim 2, characterized in that When the at least one signal feature, the voiceprint feature, and the at least one image feature all satisfy corresponding constraint conditions, determining the drone type of the drone to be detected as a target type includes: Determine the similarity of the features to be fused corresponding to each of the signal features according to at least one of the signal features and the preset features under the radio signal dimension, and determine the signal feature similarity based on the weight coefficient of each of the signal features and the similarity of the features to be fused; Determining the voiceprint feature similarity corresponding to the voiceprint feature according to the voiceprint feature and the preset features under the vibration audio dimension of the drone; Obtain at least one feature difference value according to a feature value corresponding to at least one of the image features and a feature value of a preset feature under the image acquisition dimension; When the signal feature similarity belongs to a preset signal similarity range, the voiceprint feature similarity is greater than a preset sound similarity threshold, and the feature difference is less than a preset value, the drone type of the drone to be detected is determined to be a target type.

4. The method according to claim 3, characterized in that When the signal feature similarity belongs to a preset signal similarity range, the voiceprint feature similarity is greater than a preset sound similarity threshold, and the feature difference is less than a preset value, determining that the drone type of the drone to be detected is a target type includes: When the signal feature similarity falls within a preset signal similarity range, determining a first candidate type corresponding to the to-be-detected drone; When the voiceprint feature similarity is greater than a preset voice similarity threshold, determining a second candidate type corresponding to the drone to be detected; When the feature difference is less than a preset value, determining a third candidate type corresponding to the to-be-detected drone; According to the first candidate type, the second candidate type and the third candidate type, the unmanned aerial vehicle to be detected is determined to be a target type.

5. The method according to claim 1, characterized in that: The preset type is a type of drone that is not prohibited from flying in the target area, and in response to the event that the drone type is not the preset type, determining flight data of the target drone, and determining the safety attribute of the preset detection point based on the flight data and the position data of the preset detection point in the target area, includes: If the drone type of the drone to be detected is a drone type that is prohibited from flying in the target area, determining that the drone to be detected is a target drone; Intercepting and processing the control signal of the target UAV, and analyzing the intercepted control signal to obtain the flight data of the target UAV; Substituting the flight data into a preset position determination function to obtain the predicted position information corresponding to the target UAV at a preset time; The safety attribute of the preset detection point is determined according to the predicted position information and the position data of the preset detection point in the target area.

6. The method according to claim 5, characterized in that The flight data at least includes the current flight position, current flight speed, current flight direction and current flight acceleration of the target UAV, and the preset position determination function is: Among them, (x0, y0, z0) represents the three-dimensional coordinate data corresponding to the current flight position in the three-dimensional coordinate system with the center of the earth as the origin, v represents the current flight speed, t represents the preset time, θ represents the angle between the current flight direction and the horizontal plane, a represents the current flight acceleration, and (x, y, z) represents the predicted position information corresponding to the preset time.

7. The method according to claim 5, characterized in that The determining the safety attribute of the preset detection point according to the predicted position information and the position data of the preset detection point in the target area includes: Determine the distance between the predicted location information and the preset detection point according to the predicted location information and the location data of the preset detection point; If the distance information does not belong to the preset distance range, the safety attribute of the preset detection point is determined to be unsafe.

8. The method according to claim 7, characterized in that Also includes: When the security attribute of the preset detection point is unsafe, interference processing or inductive deception processing is performed on the target drone to update the security attribute of the preset detection point.

9. A device for determining the safety of a target area, characterized in that: include: A data acquisition module, used to acquire drone data of at least one drone to be detected in a target area in multiple dimensions, wherein the multiple dimensions include a radio signal dimension, a drone vibration audio dimension, and an image acquisition dimension of the drone to be detected; A drone type determination module, configured to determine the drone type of the drone to be detected based on the drone data of the at least one drone to be detected; a safety attribute determination module, configured to determine, in response to an event that the type of the drone is not a preset type, flight data of the target drone, and determine the safety attribute of the preset detection point based on the flight data and position data of the preset detection point in the target area; The target drone is a drone among the at least one drone to be detected.

10. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so as to enable the at least one processor to perform the method for determining the safety of a target area according to any one of claims 1 to 8.

Images