A method, apparatus, equipment and medium for detecting unmanned aerial vehicles (UAVs).

Abstract

This invention discloses a method, apparatus, device, and medium for detecting unmanned aerial vehicles (UAVs). The method includes: collecting raw audio data generated by a UAV operating within a substation; transforming the raw audio data to obtain transformed audio data; inputting the transformed audio data into a sound generator to generate pseudo-audio data; determining first audio data based on the pseudo-audio data and the transformed audio data; and identifying uncertified UAVs based on the first audio data and a predefined audio database. The predefined audio database is determined based on a passive audio generator and includes certified audio data from certified UAVs. This technical solution improves the efficiency of uncertified UAV detection by generating audio data using a passive audio generator, and the use of a passive audio generator eliminates the need for battery power, significantly reducing the load weight.

Description

Technical Field

[0001] This invention relates to the field of signal processing technology, and in particular to a method, apparatus, equipment and medium for detecting unmanned aerial vehicles (UAVs). Background Technology

[0002] A drone is an aircraft that is remotely controlled or autonomously managed by a control station. With technological advancements and cost reductions, drones have been widely used in various fields such as military, agriculture, power line inspection, law enforcement, environmental monitoring, and film and television production.

[0003] While drone technology has brought convenience, inadequate management has also led to some security problems. For example, unauthorized drone flights pose security risks in sensitive areas such as airports, nuclear power plants, and borders. Currently, the main methods of drone detection include radar detection, radio signal detection, acoustic signal detection, photoelectric detection, and the coordinated detection of multiple methods.

[0004] Currently, sound-based drone detection and identification technology faces a challenge: drones of the same or opposing brands may have very similar sound characteristics, posing a significant challenge to drone sound recognition. To address this issue, an active sound generator can be mounted on the drone to differentiate it from the propeller airflow sound, giving the drone a unique sonic character. However, this method has two drawbacks: firstly, the active sound generator is relatively large, affecting the drone's stable flight; secondly, its power supply requires batteries, which can lead to battery life issues for the sound generator. Summary of the Invention

[0005] This invention provides a method, apparatus, device, and medium for detecting unmanned aerial vehicles (UAVs). It uses a passive audio generator to generate audio data to identify uncertified UAVs, thereby improving the efficiency of uncertified UAV detection. The passive audio generator does not require battery power, which greatly reduces the load weight.

[0006] According to one aspect of the present invention, a method for detecting unmanned aerial vehicles (UAVs) is provided, comprising:

[0007] Collect raw audio data generated by drones operating inside the substation;

[0008] The original audio data is transformed to obtain the transformed audio data;

[0009] The transformed audio data is input into a sound generator to generate pseudo-audio data;

[0010] The first audio data is determined based on the pseudo-audio data and the transformed audio data;

[0011] Uncertified drones are identified based on the first audio data and a set audio database; wherein, the set audio database is determined based on a passive audio generator, and the set audio database includes certified audio data of certified drones.

[0012] Optionally, before collecting the raw audio data generated by the drone during its operation within the substation, the following steps are also included:

[0013] Collect audio data from certified drones; wherein, a passive audio generator is installed on the certified drones, and the audio data is generated by the passive audio generator;

[0014] The audio data is encoded to obtain encoded audio data;

[0015] The specified audio database is constructed based on the encoded audio data.

[0016] Optionally, the audio data is ultrasonic data;

[0017] The audio data is encoded to obtain encoded audio data, including:

[0018] The ultrasonic data is encoded by setting a frequency to obtain encoded audio data.

[0019] Optionally, the set audio database includes at least one certified audio data;

[0020] Based on the first audio data and the established audio database, uncertified drones are identified, including:

[0021] The first audio data is compared with the at least one certified audio data, and the audio data that is different from the certified audio data is taken as the second audio data;

[0022] The drone corresponding to the second audio data is identified as an uncertified drone.

[0023] Optionally, the original audio data is transformed to obtain transformed audio data, including:

[0024] The original audio data is preprocessed to obtain preprocessed audio data;

[0025] The preprocessed audio data is subjected to a Fast Fourier Transform to obtain the transformed audio data.

[0026] Optionally, the transformed audio data is input into a sound generator to generate pseudo-audio data, including:

[0027] The frequency characteristics of the transformed audio data are input into a sound generator to generate pseudo-audio data.

[0028] Optionally, determining the first audio data based on the pseudo-audio data and the transformed audio data includes:

[0029] The audio data to be recovered is determined based on the pseudo-audio data and the transformed audio data;

[0030] The inverse fast Fourier transform is performed on the audio data to be recovered to obtain the first audio data.

[0031] According to another aspect of the present invention, a drone detection device is provided, comprising:

[0032] The data acquisition module is used to collect raw audio data generated by drones operating within the substation.

[0033] The data transformation and processing module is used to transform the original audio data to obtain the transformed audio data.

[0034] The pseudo-audio data generation module is used to input the transformed audio data into the sound generator to generate pseudo-audio data;

[0035] The first audio data determination module is used to determine first audio data based on the pseudo audio data and the transformed audio data;

[0036] The uncertified drone identification module is used to identify uncertified drones based on the first audio data and a set audio database; wherein, the set audio database is determined based on a passive audio generator, and the set audio database includes certified audio data of certified drones.

[0037] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0038] At least one processor; and

[0039] A memory communicatively connected to the at least one processor; wherein,

[0040] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the UAV detection method according to any embodiment of the present invention.

[0041] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the unmanned aerial vehicle detection method according to any embodiment of the present invention.

[0042] The technical solution of this invention involves collecting raw audio data generated by a drone operating within a substation; transforming the raw audio data to obtain transformed audio data; inputting the transformed audio data into a sound generator to generate pseudo-audio data; determining first audio data based on the pseudo-audio data and the transformed audio data; and identifying uncertified drones based on the first audio data and a predefined audio database. The predefined audio database is determined based on a passive audio generator and includes certified audio data from certified drones. This technical solution improves the efficiency of uncertified drone detection by generating audio data using a passive audio generator, and by eliminating the need for battery power, it significantly reduces the load weight.

[0043] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0044] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0045] Figure 1 This is a flowchart of a drone detection method provided according to Embodiment 1 of the present invention;

[0046] Figure 2 This is a flowchart of a drone detection method provided according to Embodiment 2 of the present invention;

[0047] Figure 3 This is a circuit diagram of a passive audio generator according to Embodiment 2 of the present invention;

[0048] Figure 4 This is a schematic diagram of the structure of a drone detection device according to Embodiment 3 of the present invention;

[0049] Figure 5 This is a schematic diagram of the structure of an electronic device provided according to Embodiment 4 of the present invention. Detailed Implementation

[0050] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0051] It should be noted that the terms "first," "second," and "target," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0052] Example 1

[0053] Figure 1 This is a flowchart of a drone detection method according to Embodiment 1 of the present invention. This embodiment is applicable to the detection of drones within substations. The method can be executed by a drone detection device, which can be implemented in hardware and / or software and can be configured in an electronic device with data processing capabilities. Figure 1 As shown, the method includes:

[0054] S110: Collect raw audio data generated by drones operating within the substation.

[0055] Here, the raw audio data can be understood as the audio data generated by all drones operating within the substation. In this embodiment, the raw audio data generated by the drones can refer to the sound data generated by the drones during flight. In this embodiment, the raw audio data generated by the drones operating within the substation can be collected using the drone's microphone array or a dedicated acoustic sensor.

[0056] Understandably, the audio data of drones is primarily generated by their rotors (for multi-rotor drones) or engines (for fixed-wing or hybrid-powered drones). These sound characteristics vary depending on the type, size, design, and operating mode of the drone. For drone identification, this embodiment can specially process its own drones within the substation to emit ultrasonic audio information at a specific frequency for authentication. This facilitates identification during subsequent drone sound processing. When an external drone approaches the substation's defense range, the system can reliably identify its approach and the lack of distinctive audio data, thereby triggering the targeted countermeasure system. This embodiment can collect sound data generated by all drones currently in flight within the substation.

[0057] S120. Transform the original audio data to obtain the transformed audio data.

[0058] Transformation processing can be understood as the process of converting the original audio data from the time domain to the frequency domain. In this embodiment, transformation processing may include preprocessing and audio signal transformation operations.

[0059] Specifically, in this embodiment, since the acquired raw audio data may contain noise and unnecessary information, it is necessary to preprocess the raw audio data first, and then transform the raw audio data from the time domain to the frequency domain by using Fast Fourier Transform (FFT) to obtain the transformed audio data.

[0060] In this embodiment, optionally, the original audio data is transformed to obtain transformed audio data, including: preprocessing the original audio data to obtain preprocessed audio data; and performing a fast Fourier transform on the preprocessed audio data to obtain transformed audio data.

[0061] Preprocessing can include filtering, noise reduction, and audio signal segmentation. Preprocessed audio data can be understood as data processed through filtering, noise reduction, and audio signal segmentation. The Fast Fourier Transform (FFT) is an efficient algorithm of the Discrete Fourier Transform (DFT) that can be used to convert the time-domain signal of an audio signal to the frequency-domain signal, thereby enabling the analysis and processing of the frequency components of the audio signal. The transformed audio data can be understood as the frequency-domain audio signal obtained through the Fast Fourier Transform.

[0062] Specifically, in this embodiment, preprocessing operations such as filtering, noise reduction, and sound signal segmentation can be performed on the original audio data to obtain preprocessed audio data. Then, a Fast Fourier Transform (FFT) is performed on the preprocessed audio data to transform the audio data from the time domain to the frequency domain, thus obtaining the transformed audio data. The FFT algorithm can quickly calculate the spectrum of the sound signal, that is, the amplitude and phase of different frequency components. In the frequency domain signal of the audio, sound features such as frequency distribution, energy distribution, and frequency peaks can be extracted. These features can be used to distinguish the sounds of different types of drones.

[0063] In this embodiment, by using this setting, time-dependent audio data can be converted into frequency-dependent audio data, so as to facilitate subsequent recognition of drone sounds.

[0064] S130. Input the transformed audio data into the sound generator to generate pseudo-audio data.

[0065] The sound generator can be understood as a pre-trained neural network that generates sound. In this embodiment, the sound generator can be a trained Generative Adversarial Network (GAN). A GAN consists of two neural networks (NNs): a generator NN model (called the generator) and a discriminator NN (called the discriminator). Through adversarial training of the two neural networks, the GAN achieves the generation and simulation of transformed audio data. The pseudo-audio data can be understood as simulated sound data mimicking a drone. In this embodiment, the transformed audio data can be input into the sound generator to generate simulated sound data mimicking a drone.

[0066] In this embodiment, optionally, the transformed audio data is input into a sound generator to generate pseudo-audio data, including: inputting the frequency characteristics of the transformed audio data into a sound generator to generate pseudo-audio data.

[0067] The transformed audio data packet contains frequency characteristics. Specifically, the frequency characteristics can include frequency data and the level value at that frequency time point. In this embodiment, the frequency data and the level value at that frequency time point can be input into the sound generator, enabling the sound generator to generate pseudo-audio data for the drone.

[0068] In this embodiment, the purpose of using a sound generator trained by a generative adversarial network to generate pseudo-drone sounds is to process the audio captured by the actual microphone and improve the accuracy of the drone audio data.

[0069] S140. Determine the first audio data based on the pseudo-audio data and the transformed audio data.

[0070] The first audio data can be understood as audio data obtained by processing pseudo-audio data and transformed audio data. In this embodiment, the specific method for determining the first audio data based on pseudo-audio data and transformed audio data can be to subtract the absolute value of the sound data of each frequency of the transformed audio data from the sound level data of each frequency of the pseudo-audio data to obtain the audio data to be recovered. The audio data obtained by performing recovery processing on the audio data to be recovered is the first audio data.

[0071] S150: Identify uncertified drones based on the first audio data and the established audio database.

[0072] The audio database is determined based on a passive audio generator and includes certified audio data from certified drones. A certified drone can be understood as a drone that has undergone identity verification. In this embodiment, a certified drone refers to a drone that can be trusted. Uncertified audio data can be audio data generated by a certified drone. Uncertified drones can be understood as drones that have not undergone identity verification. The passive audio generator can be a sound generator installed on our certified drone, used to generate corresponding audio data for our certified drone. In this embodiment, the passive audio generator can provide power to the entire device through a passive design.

[0073] In this embodiment, audio data from our certified drones within the substation is collected and processed to establish an audio database, facilitating the differentiation between certified and uncertified drones. It is understood that the audio database contains the certified audio data corresponding to each certified drone. In this embodiment, the specific method for determining uncertified drones based on the first audio data and the established audio database is to compare the first audio data with the certified audio data in the established audio database. If the first audio data matches any certified audio data in the established audio database, the drone corresponding to the first audio data is considered a certified drone; if the first audio data does not match any certified audio data in the established audio database, the drone corresponding to the first audio data is considered an uncertified drone.

[0074] The technical solution of this invention involves collecting raw audio data generated by a drone operating within a substation; transforming the raw audio data to obtain transformed audio data; inputting the transformed audio data into a sound generator to generate pseudo-audio data; determining first audio data based on the pseudo-audio data and the transformed audio data; and identifying uncertified drones based on the first audio data and a predefined audio database. This technical solution improves the efficiency of uncertified drone detection by generating audio data using a passive audio generator, and the use of a passive audio generator eliminates the need for battery power, significantly reducing the load weight.

[0075] Example 2

[0076] Figure 2 This is a flowchart of a drone detection method according to Embodiment 2 of the present invention. This embodiment is based on the above embodiment and optimized. Specifically, the optimization includes: before collecting the raw audio data generated by the drone during operation in the substation, the method further includes: collecting audio data of a certified drone; wherein a passive audio generator is installed on the certified drone, and the audio data is generated by the passive audio generator; encoding the audio data to obtain encoded audio data; and constructing a set audio database based on the encoded audio data. Figure 2 As shown, the method includes:

[0077] S210: Collects audio data from certified drones.

[0078] In this embodiment, a passive audio generator is installed on the certified drone, and the audio data is generated by the passive audio generator. The audio data of the certified drone can be the sound signals generated by the certified drone during flight. In this embodiment, the audio data of the certified drone during flight can be generated based on the passive audio generator installed on the certified drone. The audio data of the certified drone in this embodiment can be ultrasonic audio data.

[0079] For example, the circuit diagram of the passive audio generator in this embodiment is as follows: Figure 3 As shown, the entire passive audio generator comprises a piezoelectric vibration energy harvesting module, an ultrasonic wave transmission module, and an ultrasonic wave frequency encoding module. The piezoelectric vibration energy harvesting module generates electricity by capturing the airflow during the rotation of the drone's propellers, causing the thin film to vibrate. The ultrasonic wave transmission module emits ultrasonic waves. Therefore, ultrasonic waves are more difficult to mimic for drone identification. Figure 3 This circuit uses a 555 timer to generate frequencies above 20kHz and drive a buzzer to produce ultrasonic waves. The ultrasonic frequency encoding module can be used to change the value of resistor Rx, thereby altering the frequency generated by the 555 timer; for example... Figure 3 As shown, different generating frequencies can be selected via an external switch, enabling the use of ultrasonic encoding at different frequencies for different drones. This embodiment employs a passive audio generator with a passive design, eliminating the need for an additional battery module and significantly reducing the load weight.

[0080] Furthermore, in this embodiment, the passive audio generator utilizes the piezoelectric effect generated by the airflow from the drone causing the thin film to vibrate, thus powering the ultrasonic wave generation circuit. By using ultrasonic frequency encoding, the entire ultrasonic wave transmission frequency can be changed, effectively encoding the drone itself. Therefore, the drone only vibrates to generate electricity and emits ultrasonic waves while in flight; it has no audio characteristics when not in flight, making it difficult for the enemy to decipher.

[0081] S220. Encode the audio data to obtain the encoded audio data.

[0082] Encoding can be understood as the process of encoding different frequencies of ultrasound onto different audio data. The encoded audio data can be understood as sound signals obtained by applying different frequencies of ultrasound to the audio data corresponding to different certified drones. The audio data is ultrasonic data, which can be generated using a passive audio generator. Ultrasonic waves typically refer to sound waves with frequencies greater than 20kHz, which are inaudible to the human ear.

[0083] In this embodiment, optionally, the audio data is encoded to obtain encoded audio data, including: encoding the ultrasonic data by setting a frequency to obtain encoded audio data.

[0084] The set frequency can be a pre-set ultrasonic frequency. In this embodiment, there can be one or more set frequencies, which can be set according to actual needs. In this embodiment, encoding ultrasonic data by setting a frequency can set the same frequency for ultrasonic data corresponding to different certified drones, or different ultrasonic frequencies can be set for ultrasonic data corresponding to different certified drones to obtain encoded audio data.

[0085] For example, if there are three certified drones in the current substation, namely certified drone 1, certified drone 2, and certified drone 3; the set frequency can be three different ultrasonic frequencies. In this embodiment, the ultrasonic data corresponding to these three certified drones can be encoded at different frequencies by setting the frequency. For example, certified drone 1 can be assigned a 25kHz ultrasonic frequency, certified drone 2 a 30kHz ultrasonic frequency, and certified drone 3 a 40kHz ultrasonic frequency. In this embodiment, since ultrasonic waves are not easily heard by the human ear, they can serve as encryption. Moreover, by encoding the ultrasonic data, only the certified drone knows the encrypted sound wave frequency, while uncertified drones do not have this ultrasonic frequency characteristic.

[0086] In this embodiment, the audio data of the certified drone can be encoded using different preset frequencies, which is more conducive to the identification of one's own drone.

[0087] S230. Construct and set up an audio database based on the encoded audio data.

[0088] In this embodiment, the encoded audio data corresponding to all certified drones can be used to create a set audio database.

[0089] S240: Collect raw audio data generated by drones operating within the substation.

[0090] S250. Transform the original audio data to obtain the transformed audio data.

[0091] S260. Input the transformed audio data into the sound generator to generate pseudo-audio data.

[0092] In this embodiment, a conditional generative adversarial network (CGAN) method can be used to learn the sound of a drone. The CGAN consists of two neural networks (NNs): a generator NN model (called the generator) and a discriminator NN (called the discriminator). The training process for the initial sound generator can be as follows: the training data sample set can include two dimensions: the frequency of the audio data and the level value at that frequency at a given time point. Furthermore, the correlation can be determined by authenticating the drone's sound features. Therefore, the use of CGAN in this study is efficient in terms of training data volume and required training time. However, to learn the changes in drone sound generated by the motor according to varying flight states, a model based in part on a CGAN method called image-to-image translation is established. In the CGAN method, the input layer or input data of the generator can be pre-conditionalized to produce arbitrary output results based on conditions. The objective function of the GAN is given by (1) below.

[0093] min G max D V(D,G)=E x～pdata(x) [logD(x, C)] + E x～pz(x) [log(1-D)(z, c)] (1);

[0095] Among them, E x～pdata(x) Let represent the expected value of the real drone audio data used for training, and let represent the discriminator's evaluation of this real data; on the other hand, D(x) represents the discriminator's evaluation of this real data, and E... x～pz(x) G(z) represents the expected value when the pseudo-drone sound (synthesized by the generator) is input to the discriminator. G(z) refers to the pseudo-drone sound created by the generator from the noise input z, while D(G(z)) represents the discriminator's evaluation of the generated sound. Essentially, D(x) evaluates the real audio data, while D(G(z)) evaluates the realism of the pseudo-drone sound generated by the generator. Furthermore, in this embodiment, to ensure that the drone audio output generated by the generator is very close to the real value, the generator's loss function is expressed in formula (2). Here, G(x) represents the generator's output when given noise x as input, while D(G(x)) represents the discriminator's output given G(x), i.e., the generator's output.

[0096] L(G) = E x～pz(x) [log(xD(G(x)))] (2);

[0097] In this embodiment, a sound generator is obtained by training an initial sound generator. Pseudo-audio data can be generated by inputting the frequency of the transformed audio data and the corresponding time level value of that frequency into the sound generator. This embodiment utilizes a Generative Adversarial Network (GAN) to suppress audio noise from the drone, retaining only sound waves of specific ultrasonic frequencies, which can greatly improve the accuracy of drone detection and recognition.

[0098] S270. Determine the first audio data based on the pseudo-audio data and the transformed audio data.

[0099] In this embodiment, optionally, determining the first audio data based on the pseudo-audio data and the transformed audio data includes: determining the audio data to be recovered based on the pseudo-audio data and the transformed audio data; and performing an inverse fast Fourier transform on the audio data to be recovered to obtain the first audio data.

[0100] The audio data to be recovered can be obtained by subtracting the pseudo-audio data from the transformed audio data. The Inverse Fast Fourier Transform (IFFT) is the inverse operation of the Fourier Transform, which remaps a signal from the frequency domain to the time domain. The first audio data can be the audio data obtained by performing an IFFT operation on the audio data to be recovered. It can be understood that the first audio data is time-domain based audio data.

[0101] Specifically, in this embodiment, the microphone captures audio data per second, which is then processed to obtain transformed audio data. The absolute value of the sound level data for each frequency can be expressed as |X n |=[X0, X1, X2, ..., X n Similarly, the absolute value of the sound level data for each frequency per second of pseudo-audio data generated by the sound generator is represented as |Z]. n |=[Z0, Z1, Z2, ..., Z n ,]. From |X n |Subtract|Z n The audio data to be recovered is represented as |ω|. n |=[ω0,ω1,ω2,...,ω n The subtraction process is shown in formula (3) below:

[0102]

[0103] In this embodiment, the purpose of using a sound generator trained with a generative adversarial network to generate pseudo-audio data is to process the audio captured by the actual microphone. The purpose of the subtraction operation, performed by subtracting the pseudo-audio data from the transformed audio data, is to suppress ambient noise, thereby enhancing the clarity of the drone's sound in the recording.

[0104] In this embodiment, after suppressing other drone sounds and surrounding noise from the frequency data, the audio data to be recovered is subjected to an inverse fast Fourier transform (IFFT). Since the transformed audio data is time-based audio data, it is converted to frequency-based data through a fast Fourier transform (FFT). In order to convert these frequency-based data back to the time domain, an inverse fast Fourier transform (IFFT) is used. This transformation is crucial for reconstructing the original audio characteristics, while eliminating noise components identified and suppressed in the early stages. The process of performing an inverse fast Fourier transform (IFFT) on the audio data to be recovered in this embodiment is shown in formula (4):

[0105]

[0106] Where F(t) represents the discrete FFT; Z(t) represents the complex frequency domain representation of the audio data signal to be recovered obtained from the subtraction result.

[0107] Furthermore, due to the audio data ω to be recovered n The value of ω is taken as its absolute value during processing, and the sign of the original audio data is lost. In this situation, sound recovery using IFFT is difficult. Maintaining the correct sign (positive or negative) of each audio data point is crucial during sound recovery. To overcome this problem, this embodiment also employs U-Net technology, where the audio data to be recovered ω... n The integration process yields Z(t). Specifically, the U-Net method can reintegrate certain information at both the input and output stages, bypassing the training and learning phase of the GAN neural network. This characteristic is crucial for preventing the loss of important data during the input process. Therefore, the U-Net method plays a key role in ensuring the integrity of the symbol, phase, and volume of the data.

[0108] It should be noted that in this embodiment, due to the linear symmetry of frequency values ​​around the 0 axis in FFT, the values ​​on the positive frequency spectrum axis are trained. The results are then linearly copied to the negative axis, simplifying the process while maintaining the accuracy of the audio data. Therefore, only half of the total training dataset can be used during the training phase, significantly reducing training time and processing requirements.

[0109] This embodiment, through such a setting, can effectively reduce the amount of drone and ambient noise mixed in the audio data captured by the drone microphone, thereby improving the reliability and accuracy of the audio data.

[0110] S280: Identify uncertified drones based on the first audio data and the set audio database.

[0111] The audio database is set based on a passive audio generator and includes certified audio data of certified drones.

[0112] In this embodiment, optionally, the audio database includes at least one certified audio data; determining an uncertified drone based on the first audio data and the audio database includes: comparing the first audio data with at least one certified audio data, and using the audio data that is different from the certified audio data as the second audio data; determining the drone corresponding to the second audio data as an uncertified drone.

[0113] The audio database is configured to include at least one certified audio data set, the specific number of which can be determined based on the number of certified drones. The second audio data set can be understood as audio data not present in the audio database, i.e., uncertified audio data.

[0114] In this embodiment, the first audio data is compared with at least one certified audio data contained in the set audio database. If the first audio data is the same as at least one certified audio data contained in the set audio database, then the first audio data is the certified audio data corresponding to the certified drone. If the first audio data is different from at least one certified audio data contained in the set audio database, then the audio data that is different from the certified audio data is taken as the second audio data, indicating that the second audio data is the uncertified audio data corresponding to the uncertified drone. Therefore, the drone corresponding to the second audio data can be identified as an uncertified drone.

[0115] In this embodiment, by comparing the authenticated audio data with the collected drone audio data, the system can reliably identify the approach of the drone and audio information without identification features, thereby triggering the operation of the targeted countermeasure system.

[0116] Example 3

[0117] Figure 4 This is a schematic diagram of the structure of a drone detection device according to Embodiment 3 of the present invention. Figure 4 As shown, the device includes:

[0118] Data acquisition module 410 is used to acquire raw audio data generated by drones operating inside the substation;

[0119] The data transformation and processing module 420 is used to transform the original audio data to obtain the transformed audio data.

[0120] The pseudo-audio data generation module 430 is used to input the transformed audio data into the sound generator to generate pseudo-audio data.

[0121] The first audio data determination module 440 is used to determine the first audio data based on the pseudo audio data and the transformed audio data.

[0122] The uncertified drone identification module 450 is used to identify uncertified drones based on first audio data and a set audio database; wherein, the set audio database is determined based on a passive audio generator and includes certified audio data of certified drones.

[0123] Optionally, the device may also include:

[0124] The audio data collection module is used to collect audio data from certified drones before collecting the raw audio data generated by drones during operation within the substation; wherein, a passive audio generator is installed on the certified drone, and the audio data is generated by the passive audio generator;

[0125] The encoding module is used to encode audio data to obtain encoded audio data;

[0126] The database construction module is used to build and configure the audio database based on the encoded audio data.

[0127] Optionally, the audio data is ultrasonic data;

[0128] The encoding module is specifically used to encode ultrasonic data by setting a frequency to obtain encoded audio data.

[0129] Optionally, the audio database may include at least one certified audio data set;

[0130] The uncertified drone identification module 450 is specifically used to compare the first audio data with at least one certified audio data, take the audio data that is different from the certified audio data as the second audio data, and identify the drone corresponding to the second audio data as an uncertified drone.

[0131] Optionally, the data transformation and processing module 420 is specifically used to preprocess the original audio data to obtain preprocessed audio data; and to perform a fast Fourier transform on the preprocessed audio data to obtain transformed audio data.

[0132] Optionally, the pseudo-audio data generation module 430 is specifically used to input the frequency characteristics of the transformed audio data into the sound generator to generate pseudo-audio data.

[0133] Optionally, the first audio data determination module 440 is specifically used to determine the audio data to be recovered based on the pseudo audio data and the transformed audio data; and to perform an inverse fast Fourier transform on the audio data to be recovered to obtain the first audio data.

[0134] The drone detection device provided in this embodiment of the invention can execute a drone detection method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0135] Example 4

[0136] Figure 5 This is a schematic diagram of an electronic device according to 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 processors, cellular phones, smartphones, 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 illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0137] like Figure 5 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0138] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0139] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as drone detection methods.

[0140] In some embodiments, the drone detection method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the drone detection method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the drone detection method by any other suitable means (e.g., by means of firmware).

[0141] Various embodiments 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-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0142] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0143] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0144] To provide interaction with a user, the systems and techniques described herein can 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 pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0145] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0146] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0147] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0148] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for detecting unmanned aerial vehicles (UAVs), characterized in that, include: Collect raw audio data generated by drones operating inside the substation; The original audio data is transformed to obtain the transformed audio data; The transformed audio data is input into a sound generator to generate pseudo-audio data; wherein, the pseudo-audio data is simulated sound data that mimics that of a drone; The first audio data is determined based on the pseudo-audio data and the transformed audio data; Uncertified drones are identified based on the first audio data and a set audio database; wherein, the set audio database is determined based on a passive audio generator, and the set audio database includes certified audio data of certified drones; Before collecting the raw audio data generated by the drones operating inside the substation, the following steps are also included: Collect audio data from certified drones; wherein, a passive audio generator is installed on the certified drones, and the audio data is generated by the passive audio generator; The audio data is encoded to obtain encoded audio data; The specified audio database is constructed based on the encoded audio data; The audio data is ultrasonic data; The audio data is encoded to obtain encoded audio data, including: The ultrasonic data is encoded by setting a frequency to obtain encoded audio data; Determining the first audio data based on the pseudo-audio data and the transformed audio data includes: The audio data to be recovered is determined based on the pseudo-audio data and the transformed audio data; Perform an inverse fast Fourier transform on the audio data to be recovered to obtain the first audio data; The audio data to be recovered is determined based on the pseudo-audio data and the transformed audio data, including: The absolute value of the transformed audio data is subtracted from the absolute value of the pseudo-audio data to obtain the audio data to be recovered.

2. The method according to claim 1, characterized in that, The specified audio database includes at least one certified audio data; Based on the first audio data and the established audio database, uncertified drones are identified, including: The first audio data is compared with the at least one certified audio data, and the audio data that is different from the certified audio data is taken as the second audio data; The drone corresponding to the second audio data is identified as an uncertified drone.

3. The method according to claim 1, characterized in that, The original audio data is transformed to obtain the transformed audio data, including: The original audio data is preprocessed to obtain preprocessed audio data; The preprocessed audio data is subjected to a Fast Fourier Transform to obtain the transformed audio data.

4. The method according to claim 3, characterized in that, The transformed audio data is input into a sound generator to generate pseudo-audio data, including: The frequency characteristics of the transformed audio data are input into a sound generator to generate pseudo-audio data.

5. A drone detection device, characterized in that, include: The data acquisition module is used to collect raw audio data generated by drones operating within the substation. The data transformation and processing module is used to transform the original audio data to obtain the transformed audio data. The pseudo-audio data generation module is used to input the transformed audio data into the sound generator to generate pseudo-audio data; wherein, the pseudo-audio data is simulated sound data imitating a drone; The first audio data determination module is used to determine first audio data based on the pseudo audio data and the transformed audio data; The uncertified drone identification module is used to identify uncertified drones based on the first audio data and a set audio database; wherein, the set audio database is determined based on a passive audio generator, and the set audio database includes certified audio data of certified drones; An audio data collection module is used to collect audio data of a certified drone before collecting the raw audio data generated by the drone during its operation within the substation; wherein, a passive audio generator is installed on the certified drone, and the audio data is generated by the passive audio generator; An encoding module is used to encode the audio data to obtain encoded audio data; The database construction module is used to construct the specified audio database based on the encoded audio data; The audio data is ultrasonic data; The encoding module is specifically used to encode the ultrasonic data by setting a frequency to obtain encoded audio data; The first audio data determination module is specifically used to subtract the absolute value of the pseudo-audio data from the absolute value of the transformed audio data to obtain the audio data to be recovered; and to perform an inverse fast Fourier transform on the audio data to be recovered to obtain the first audio data.

6. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the UAV detection method according to any one of claims 1-4.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that are used to cause a processor to execute the UAV detection method according to any one of claims 1-4.

Images