Unmanned aerial vehicle identification method, device and equipment and readable storage medium

Abstract

The invention discloses an unmanned aerial vehicle identification method, device and equipment and a readable storage medium, and the method comprises the steps: converting a to-be-identified signal, determining a frequency domain where an unmanned aerial vehicle image transmission signal is located when the to-be-identified signal is judged to have the unmanned aerial vehicle image transmission signal based on the conversion data, and processing the conversion data based on the frequency domain. And calculating the sum of each column of the processed data, dividing the sum of each column into two sets, determining a target set from the two sets, calculating all continuous sequence sets of the target set, calculating to obtain a duration set and a time interval set, and inputting the duration set and the time interval set into a model to obtain an unmanned aerial vehicle identification result. According to the method, the frequency domain where the unmanned aerial vehicle image transmission signals are located in the to-be-recognized signals with the unmanned aerial vehicle image transmission signals is determined, the data are processed based on the frequency domain, the duration set and the time interval set are obtained through calculation, finally, the model is used for processing the duration set and the time interval set, and the unmanned aerial vehicle recognition result is obtained. And identification of the unmanned aerial vehicle is realized.

Description

Technical Field

[0001] The present application relates to the technical field of unmanned aerial vehicles, and particularly to a method, device, equipment and readable storage medium for identifying unmanned aerial vehicles. Background Art

[0002] In recent years, the unmanned aerial vehicle industry has developed rapidly and the technology has become increasingly mature. The characteristics of small size, flexible movement and easy operation of unmanned aerial vehicles have enabled them to show great potential in many fields such as civil use and scientific research. For example, in fields such as aerial photography, environmental monitoring, geographical mapping and power line inspection, unmanned aerial vehicles play an important role. However, with the wide application of unmanned aerial vehicle technology, the number of unmanned aerial vehicles has increased rapidly. The improper and illegal use of unmanned aerial vehicles has also led to frequent public safety and privacy security problems, posing a serious threat to society and people's lives, attracting wide attention. Therefore, how to identify unmanned aerial vehicles has been a problem that people have been concerned about. Summary of the Invention

[0003] In view of this, the present application provides a method, device, equipment and readable storage medium for identifying unmanned aerial vehicles, so as to facilitate the identification of unmanned aerial vehicles.

[0004] In order to achieve the above object, the following solutions are proposed:

[0005] A method for identifying an unmanned aerial vehicle, comprising:

[0006] Obtaining a signal to be identified;

[0007] Performing time-frequency conversion on the signal to be identified to obtain conversion data;

[0008] Based on the conversion data, determining whether there is an unmanned aerial vehicle video transmission signal in the signal to be identified;

[0009] If it exists, based on the conversion data, determining the frequency domain where the unmanned aerial vehicle video transmission signal is located, and taking the determined frequency domain as a selected frequency domain;

[0010] Based on the selected frequency domain, processing the conversion data to obtain processed data;

[0011] Calculating the sum of each column of the processed data, and using a clustering algorithm to divide the sum of each column into two non-overlapping sets;

[0012] Respectively determining the maximum values in the two non-overlapping sets, and comparing the determined two maximum values, and taking the set corresponding to the larger maximum value as a target set;

[0013] Calculating to obtain the entire continuous sequence set of the target set;

[0014] Based on the set of all continuous sequences, a set of durations and a set of time intervals of the UAV video transmission signal are calculated;

[0015] The set of durations and the set of time intervals are input into the UAV recognition model to obtain the UAV recognition result;

[0016] The UAV recognition model is obtained by pre-training with a set of duration training samples and a set of time interval training samples, and using the corresponding UAV recognition results of the set of duration training samples and the set of time interval training samples as training labels.

[0017] Optionally, the determining whether there is a UAV video transmission signal in the signal to be recognized based on the conversion data includes:

[0018] Calculate the maximum value of each row in the conversion data to obtain a first set;

[0019] Use a clustering algorithm to divide the first set into two non-overlapping sets;

[0020] Respectively determine the maximum values in the two non-overlapping sets, compare the two determined maximum values, and determine the smaller maximum value as the noise value;

[0021] Determine the number of data in the conversion data that is greater than the noise value as the comparison value;

[0022] Based on the sampling frequency and sampling time, calculate a reference value;

[0023] Compare the comparison value with the reference value;

[0024] If the comparison value is greater than the reference value, there is a UAV video transmission signal in the signal to be recognized.

[0025] Optionally, the determining the frequency domain where the UAV video transmission signal is located based on the conversion data, and using the determined frequency domain as the selected frequency domain includes:

[0026] Calculate the sum of each row in the conversion data to obtain a second set;

[0027] Use a clustering algorithm to divide the second set into two non-overlapping sets;

[0028] Respectively determine the maximum values in the two non-overlapping sets, compare the two determined maximum values, and use the set corresponding to the larger maximum value as the preselected set;

[0029] Based on the preselected set, determine the frequency domain where the UAV video transmission signal is located, and use the determined frequency domain as the selected frequency domain.

[0030] Optionally, determining the frequency domain where the UAV video transmission signal is located based on the preselected set, and using the determined frequency domain as the selected frequency domain includes:

[0031] Calculating the longest continuous sequence of the preselected set;

[0032] Determining the frequency domain where the UAV video transmission signal is located as the frequency domain where the longest continuous sequence is located, and using the determined frequency domain as the selected frequency domain.

[0033] Optionally, performing time-frequency conversion on the signal to be recognized to obtain conversion data includes:

[0034] Processing the signal to be recognized through short-time Fourier transform to obtain transformed data;

[0035] Processing the transformed data to obtain conversion data.

[0036] A UAV recognition device includes:

[0037] A signal acquisition module, configured to acquire a signal to be recognized;

[0038] A signal conversion module, configured to perform time-frequency conversion on the signal to be recognized to obtain conversion data;

[0039] A signal judgment module, configured to judge whether there is a UAV video transmission signal in the signal to be recognized based on the conversion data; if so, determining the frequency domain where the UAV video transmission signal is located based on the conversion data, and using the determined frequency domain as the selected frequency domain;

[0040] A data processing module, configured to process the conversion data based on the selected frequency domain to obtain processed data;

[0041] A data calculation module, configured to calculate the sum of each column of the processed data, and use a clustering algorithm to divide the sum of each column into two non-overlapping sets;

[0042] A target set determination module, configured to respectively determine the maximum values in the two non-overlapping sets, compare the determined two maximum values, and use the set corresponding to the larger maximum value as the target set;

[0043] A continuous sequence calculation module, configured to calculate the entire continuous sequence set of the target set;

[0044] A time data analysis module, configured to calculate the duration set and time interval set of the UAV video transmission signal based on the entire continuous sequence set;

[0045] The UAV recognition module is configured to input the duration set and the time interval set into a UAV recognition model to obtain a UAV recognition result. The UAV recognition model is pre-trained with a duration training set and a time interval training set as training samples, and the corresponding UAV recognition results of the duration training set and the time interval training set as training labels.

[0046] Optionally, the signal judgment module executes a process of judging whether there is a UAV video transmission signal in the signal to be recognized based on the conversion data, including:

[0047] Calculate the maximum value of each row in the conversion data to obtain a first set;

[0048] Use a clustering algorithm to divide the first set into two non-overlapping sets;

[0049] Respectively determine the maximum values in the two non-overlapping sets, compare the two determined maximum values, and determine the smaller maximum value as the noise value;

[0050] Determine the number of data in the conversion data that is greater than the noise value as a comparison value;

[0051] Based on the sampling frequency and sampling time, calculate a reference value;

[0052] Compare the comparison value with the reference value;

[0053] If the comparison value is greater than the reference value, there is a UAV video transmission signal in the signal to be recognized.

[0054] Optionally, the signal judgment module executes a process of determining the frequency domain where the UAV video transmission signal is located based on the conversion data, and using the determined frequency domain as the selected frequency domain, including:

[0055] Calculate the sum of each row in the conversion data to obtain a second set;

[0056] Use a clustering algorithm to divide the second set into two non-overlapping sets;

[0057] Respectively determine the maximum values in the two non-overlapping sets, compare the two determined maximum values, and use the set corresponding to the larger maximum value as a preselected set;

[0058] Based on the preselected set, determine the frequency domain where the UAV video transmission signal is located, and use the determined frequency domain as the selected frequency domain.

[0059] A UAV recognition device includes: a memory and a processor;

[0060] The memory is used to store programs;

[0061] The processor is configured to execute the program to implement each step of the UAV recognition method as described in any one of the foregoing items.

[0062] A readable storage medium stores a computer program thereon. When the computer program is executed by a processor, each step of the UAV recognition method as described in any one of the foregoing items is implemented.

[0063] As can be seen from the above technical solutions, a UAV recognition method, device, equipment, and readable storage medium provided in an embodiment of the present application obtain a signal to be recognized, perform time-frequency conversion on the signal to be recognized to obtain conversion data, and based on the conversion data, determine whether there is a UAV video transmission signal in the signal to be recognized. If so, based on the conversion data, determine the frequency domain where the UAV video transmission signal is located, use the determined frequency domain as the selected frequency domain, process the conversion data based on the selected frequency domain to obtain processed data, calculate the sum of each column of the processed data, and use a clustering algorithm to divide the sum of each column into two non-overlapping sets, respectively determine the maximum values in the two non-overlapping sets, compare the determined two maximum values, use the set corresponding to the larger maximum value as the target set, calculate the entire continuous sequence set of the target set, based on the entire continuous sequence set, calculate the duration set and the time interval set of the UAV video transmission signal, and input the duration set and the time interval set into a UAV recognition model to obtain a UAV recognition result. The UAV recognition model is pre-trained with a duration training set and a time interval training set as training samples and the UAV recognition results corresponding to the duration training set and the time interval training set as training labels. The present application determines whether there is a UAV video transmission signal in the signal to be recognized, determines the frequency domain where the UAV video transmission signal is located, processes the data based on the selected frequency domain, calculates the duration set and the time interval set of the UAV video transmission signal, and finally uses the model to process the duration set and the time interval set of the UAV video transmission signal to obtain a UAV recognition result, thereby realizing the recognition of the UAV. Further, after determining that there is a UAV video transmission signal in the signal to be recognized, by determining the frequency domain where the UAV video transmission signal is located and processing the conversion data based on the frequency domain, interference from other data can be excluded to a certain extent, making the UAV recognition more accurate. Description of the Drawings

[0064] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only the embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained according to the provided drawings without creative efforts.

[0065] Figure 1 Flow chart of an unmanned aerial vehicle (UAV) recognition method provided by an embodiment of the present application;

[0066] Figure 2 Spectrum diagram obtained by processing a signal to be recognized provided by an embodiment of the present application;

[0067] Figure 3 Schematic structural diagram of an UAV recognition device provided by an embodiment of the present application;

[0068] Figure 4 Hardware structure block diagram of an UAV recognition device disclosed by an embodiment of the present application. Specific embodiments

[0069] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the protection scope of the present application.

[0070] Figure 1 Flow chart of an UAV recognition method provided by an embodiment of the present application, which may include the following steps:

[0071] Step S100: Obtain a signal to be recognized.

[0072] Specifically, software can be used to collect the signal. During the collection process, the sampling frequency r is set to be greater than 40 MHz, the signal is received with a fixed gain, and the signal to be recognized is obtained according to the preset sampling time t.

[0073] Step S101: Perform time-frequency conversion on the signal to be recognized to obtain conversion data.

[0074] Specifically, the size of each sampling window of the signal to be recognized is s, and the number of sampling times w can be calculated according to the following formula:

[0075] w = r × t / s

[0076] After performing time-frequency conversion on the signal to be recognized, conversion data x(i, j) is obtained, where 0 ≤ i ≤ s and 0 ≤ j ≤ w.

[0077] Step S102: Based on the conversion data, determine whether there is an UAV video transmission signal in the signal to be recognized.

[0078] Specifically, based on the converted data, it is determined whether there is a drone video transmission signal in the signal to be recognized. If there is a drone video transmission signal in the signal to be recognized, step S103 is executed. If there is no drone video transmission signal in the signal to be recognized, return to step S100.

[0079] Step S103: Based on the converted data, determine the frequency domain where the drone video transmission signal is located, and use the determined frequency domain as the selected frequency domain.

[0080] Specifically, based on the converted data x(i, j), the frequency domain where the drone video transmission signal is located can be determined as the selected frequency domain. After determining that there is a drone video transmission signal in the signal to be recognized, by determining the frequency domain where the drone video transmission signal is located, the signals in the determined frequency domain can be analyzed.

[0081] Step S104: Based on the selected frequency domain, process the converted data to obtain the processed data.

[0082] Specifically, after determining the selected frequency domain, the converted data can be processed based on the selected frequency domain to obtain the processed data, and the processed data is associated with the selected frequency domain.

[0083] Step S105: Calculate the sum of each column of the processed data, and use the clustering algorithm to divide the sum of each column into two non - overlapping sets.

[0084] Specifically, the K - means clustering algorithm can be used as the clustering algorithm, where the value of K can be set to 2.

[0085] Step S106: Respectively determine the maximum values in the two non - overlapping sets, compare the two determined maximum values, and use the set corresponding to the larger maximum value as the target set.

[0086] Step S107: Calculate the set of all continuous sequences of the target set.

[0087] Specifically, calculate the set of all continuous sequences seqlist of the target set wj t . Two data wj1 and wj2 in the target set wj t can be selected. If |wj1 - wj2| ≤ conn, it is considered that wj1 and wj2 are continuous, where con > 1, and con can be set to 3.

[0088] Step S108: Based on the set of all continuous sequences, calculate the set of the duration and the set of the time intervals of the drone video transmission signal.

[0089] Step S109: Input the set of the duration and the set of the time intervals into the drone recognition model to obtain the drone recognition result.

[0090] Specifically, the UAV recognition model will identify and analyze data such as the maximum value, number, average value, median, mode, and bandwidth of the duration set and the time interval set. The UAV recognition model can be a Support Vector Machine (SVM), a Convolutional Neural Network, etc. The UAV recognition model is obtained by pre-training with the duration training set and the time interval training set as training samples and the corresponding UAV recognition results of the duration training set and the time interval training set as training labels. Among them, the UAV recognition results can include data such as the type and quantity of UAVs.

[0091] As can be seen from the above technical solutions, a UAV recognition method provided by an embodiment of the present application includes: obtaining a signal to be recognized, performing time-frequency conversion on the signal to be recognized to obtain conversion data, based on the conversion data, determining whether there is a UAV video transmission signal in the signal to be recognized. If so, based on the conversion data, determining the frequency domain where the UAV video transmission signal is located, using the determined frequency domain as the selected frequency domain, based on the selected frequency domain, processing the conversion data to obtain processed data, calculating the sum of each column of the processed data, and using a clustering algorithm to divide the sum of each column into two non-overlapping sets, respectively determining the maximum values in the two non-overlapping sets, comparing the two determined maximum values, using the set corresponding to the larger maximum value as the target set, calculating the entire continuous sequence set of the target set, based on the entire continuous sequence set, calculating the duration set and the time interval set of the UAV video transmission signal, inputting the duration set and the time interval set into the UAV recognition model to obtain the UAV recognition result. The UAV recognition model is obtained by pre-training with the duration training set and the time interval training set as training samples and the corresponding UAV recognition results of the duration training set and the time interval training set as training labels. The present application determines whether there is a UAV video transmission signal in the signal to be recognized, determines the frequency domain where the UAV video transmission signal is located, processes the data based on the selected frequency domain, calculates the duration set and the time interval set of the UAV video transmission signal, and finally uses the model to process the duration set and the time interval set of the UAV video transmission signal to obtain the UAV recognition result, realizing the recognition of UAVs. Further, after determining that there is a UAV video transmission signal in the signal to be recognized, by determining the frequency domain where the UAV video transmission signal is located and processing the conversion data based on the frequency domain, the interference of other data can be excluded to a certain extent, making the UAV recognition more accurate.

[0092] In some embodiments of the present application, step S101, performing time-frequency conversion on the signal to be recognized to obtain conversion data, may include:

[0093] S11, processing the signal to be recognized through short-time Fourier transform to obtain the transformed data.

[0094] Specifically, the signal to be recognized is processed by short-time Fourier transform, and each resulting transformed data is x f (i, j).

[0095] S12. Process the transformed data to obtain transformed data.

[0096] Specifically, the transformed data can be processed through the following formula to obtain the transformed data x(i, j):

[0097] x(i, j) = 10log 10 (x f (i, j) 2 )

[0098] where 0 ≤ i ≤ s, 0 ≤ j ≤ w, s is the size of each sampling window, w is the number of sampling times, Figure 2 is the spectrogram obtained after processing the signal to be recognized.

[0099] In some embodiments of the present application, step S102. Based on the transformed data, determine whether there is a drone video transmission signal in the signal to be recognized, which may include the following steps:

[0100] S21. Calculate the maximum value of each row in the transformed data to obtain a first set.

[0101] Specifically, the maximum value of each row in the transformed data x(i, j) can be calculated according to the following formula:

[0102] x smax (si) = max{x(i, j)|i = si, 0 ≤ j ≤ w}

[0103] where 0 ≤ si ≤ s, si ≠ s / 2, s is the size of each sampling window, w is the number of sampling times.

[0104] S22. Use a clustering algorithm to divide the first set into two non-overlapping sets.

[0105] Specifically, the clustering algorithm K-means can be used to divide the first set x smax (si) into two non-overlapping sets, and at this time k = 2 for the clustering algorithm K-means.

[0106] S23. Determine the maximum values in the two non-overlapping sets respectively, compare the two determined maximum values, and determine the smaller maximum value as the noise value.

[0107] Specifically, from the two disjoint sets obtained in S22, find the maximum value in each set respectively, compare the maximum values corresponding to the two sets, and determine the smaller maximum value as the noise value.

[0108] S24. Determine the number of data in the converted data that is greater than the noise value as the comparison value.

[0109] Specifically, compare the determined noise value with the data in the converted data, determine the number of data greater than the noise value, and use this number as the comparison value a.

[0110] S25. Calculate the reference value based on the sampling frequency and sampling time.

[0111] Specifically, the reference value b can be calculated according to the following formula using the sampling frequency r and the sampling time t:

[0112] b = λ × r × t

[0113] Specifically, λ is a coefficient, and λ can be selected as 0.1.

[0114] S26. Compare the comparison value with the reference value.

[0115] Specifically, compare the obtained comparison value a with the reference value b. If the comparison value a is greater than the reference value b, it can be considered that there is a drone video transmission signal in the signal to be recognized.

[0116] In some embodiments of the present application, step S103. Based on the converted data, determine the frequency domain where the drone video transmission signal is located, and use the determined frequency domain as the selected frequency domain, which may include:

[0117] S31. Calculate the sum of each row in the converted data to obtain the second set.

[0118] Specifically, the maximum value of each row in the converted data x(i, j) can be calculated according to the following formula:

[0119]

[0120] where 0 ≤ si ≤ s, s is the size of each sampling window, and w is the number of sampling times.

[0121] S32. Use the clustering algorithm to divide the second set into two disjoint sets.

[0122] Specifically, the clustering algorithm K-means can be used to divide the first set x ssum (si) into two disjoint sets. At this time, k = 2 for the clustering algorithm K-means.

[0123] S33. Determine the maximum values in two non - intersecting sets respectively, compare the two determined maximum values, and use the set corresponding to the larger maximum value as the pre - selected set.

[0124] Specifically, from the two non - intersecting sets obtained in S22, find the maximum value in each set respectively, compare the maximum values corresponding to the two sets, and use the set corresponding to the larger maximum value as the pre - selected set.

[0125] S34. Based on the pre - selected set, determine the frequency domain where the UAV video transmission signal is located, and use the determined frequency domain as the selected frequency domain.

[0126] Specifically, after determining the pre - selected set, the frequency domain where the UAV video transmission signal is located can be predicted based on the pre - selected set, and the predicted and determined frequency domain is used as the selected frequency domain.

[0127] In some embodiments of the present application, S34. Based on the pre - selected set, determine the frequency domain where the UAV video transmission signal is located, and use the determined frequency domain as the selected frequency domain, which may include:

[0128] S41. Calculate the longest continuous sequence of the pre - selected set.

[0129] Specifically, the pre - selected set si obtained above t is the range where the UAV video transmission signal may exist. For the pre - selected set si t find the longest continuous sequence seq. Among them, the process of finding the longest continuous sequence seq for the pre - selected set si t can be to select two data si1 and si2 in the pre - selected set si t If |si1 - si2|≤con, then si1 and si2 are considered continuous, where con>1, and con can be set to 5.

[0130] S42. Determine the frequency domain where the longest continuous sequence is located as the frequency domain where the UAV video transmission signal is located, and use the determined frequency domain as the selected frequency domain.

[0131] Specifically, the frequency domain where the longest continuous sequence seq obtained in the above steps is located can be considered as the frequency domain where the UAV video transmission signal is located. Among them, seqf is the head of seq and seql is the tail of seq.

[0132] Furthermore, the bandwidth bw = r / s×(seql - seqf) and the center frequency point cf=(seql + seqf) / 2×r / s - r / 2 + tlo can be determined, where tlo is the local oscillator frequency point set by the software radio.

[0133] Based on this, in step S104, the converted data is processed based on the selected frequency domain to obtain the processed data, which may include: using the head seqf and tail seql of the longest continuous sequence seq in the selected frequency domain, and processing the converted data x(i, j) according to the following formula to obtain the processed data x l (i, j):

[0134]

[0135] In the above processing process, the data within the selected frequency domain remains unchanged. Since the data outside the selected frequency domain is considered not to be the UAV signal, it is all changed to the minimum value, so that the data outside the selected frequency domain has an impact on the subsequent calculations.

[0136] In addition, in the process of processing the converted data based on the selected frequency domain to obtain the processed data, the data in the selected frequency domain can also be extracted separately, and only the extracted data is used for subsequent calculations.

[0137] Based on this, in step S105, the sum of each column of the processed data is calculated, and the sum of each column is divided into two non - overlapping sets using a clustering algorithm, which may include: calculating the sum x l (i, j) of each column of the processed data x lwsum (wj):

[0138]

[0139] where 0 ≤ wj ≤ w, s is the size of each sampling window, and w is the number of sampling times.

[0140] Based on this, in step S108, based on the set of all continuous sequences, the duration set and time interval set of the UAV video transmission signal are calculated, which may include:

[0141] The duration set dt of the UAV video transmission signal is calculated according to the following formula:

[0142] dt = {dti|(seql i - seqf i ) / r × s}

[0143] where seqf is the head of the i - th continuous sequence in the set of all continuous sequences seqlist, seql i is the tail of the i - th continuous sequence in the set of all continuous sequences seqlist, r is the sampling frequency, and s is the size of each sampling window.

[0144] The time interval set int of the UAV video transmission signal is calculated according to the following formula:

[0145] int = {inti | (seqf i+1 -seql i ) / r × s}

[0146] where seqf i+1 is the head of the (i + 1)-th continuous sequence in the set seqlist of all continuous sequences, seql i is the tail of the i-th continuous sequence in the set seqlist of all continuous sequences, r is the sampling frequency, and s is the size of each sampling window.

[0147] Next, a drone recognition device provided by an embodiment of the present application will be described. The drone recognition device described below can be correspondingly referred to the drone recognition method described above.

[0148] Referring to Figure 3 as shown Figure 3 is a schematic structural diagram of a drone recognition device provided by an embodiment of the present application. The drone recognition device may include:

[0149] A signal acquisition module 10, configured to acquire a signal to be recognized;

[0150] A signal conversion module 20, configured to perform time-frequency conversion on the signal to be recognized to obtain conversion data;

[0151] A signal judgment module 30, configured to determine whether there is a drone video transmission signal in the signal to be recognized based on the conversion data; if so, determine the frequency domain where the drone video transmission signal is located based on the conversion data, and use the determined frequency domain as the selected frequency domain;

[0152] A data processing module 40, configured to process the conversion data based on the selected frequency domain to obtain processed data;

[0153] A data calculation module 50, configured to calculate the sum of each column of the processed data, and use a clustering algorithm to divide the sum of each column into two non-overlapping sets;

[0154] A target set determination module 60, configured to respectively determine the maximum values in the two non-overlapping sets, compare the two determined maximum values, and use the set corresponding to the larger maximum value as the target set;

[0155] A continuous sequence calculation module 70, configured to calculate the set of all continuous sequences of the target set;

[0156] A time data analysis module 80, configured to calculate the set of durations and the set of time intervals of the drone video transmission signal based on the set of all continuous sequences;

[0157] The UAV recognition module 90 is used to input the duration set and the time interval set into the UAV recognition model to obtain the UAV recognition result. The UAV recognition model is trained in advance with the duration training set and the time interval training set as training samples and the corresponding UAV recognition results of the duration training set and the time interval training set as training labels.

[0158] As can be seen from the above technical solution, a UAV recognition device provided by an embodiment of the present application includes: The signal acquisition module 10 acquires the signal to be recognized. The signal conversion module 20 performs time-frequency conversion on the signal to be recognized to obtain conversion data. The signal judgment module 30 determines whether there is a UAV video transmission signal in the signal to be recognized based on the conversion data. If so, based on the conversion data, it determines the frequency domain where the UAV video transmission signal is located and uses the determined frequency domain as the selected frequency domain. The data processing module 40 processes the conversion data based on the selected frequency domain to obtain processed data. The data calculation module 50 calculates the sum of each column of the processed data and uses a clustering algorithm to divide the sum of each column into two non-overlapping sets. The target set determination module 60 determines the maximum value in each of the two non-overlapping sets respectively, compares the two determined maximum values, and uses the set corresponding to the larger maximum value as the target set. The continuous sequence calculation module 70 calculates all the continuous sequence sets of the target set. The time data analysis module 80 calculates the duration set and the time interval set of the UAV video transmission signal based on all the continuous sequence sets. The UAV recognition module 90 inputs the duration set and the time interval set into the UAV recognition model to obtain the UAV recognition result. The UAV recognition model is trained in advance with the duration training set and the time interval training set as training samples and the corresponding UAV recognition results of the duration training set and the time interval training set as training labels. Through the present application, it is determined whether there is a UAV video transmission signal in the signal to be recognized, the frequency domain where the UAV video transmission signal is located is determined, the data is processed based on the selected frequency domain, the duration set and the time interval set of the UAV video transmission signal are calculated, and finally the model is used to process the duration set and the time interval set of the UAV video transmission signal to obtain the UAV recognition result, realizing the recognition of the UAV. Further, after it is determined that there is a UAV video transmission signal in the signal to be recognized, by determining the frequency domain where the UAV video transmission signal is located and processing the conversion data based on the frequency domain, the interference of other data can be excluded to a certain extent, making the UAV recognition more accurate.

[0159] In some embodiments of the present application, the process of the signal judgment module 30 determining whether there is a UAV video transmission signal in the signal to be recognized based on the conversion data may include:

[0160] Calculate the maximum value of each row in the conversion data to obtain the first set;

[0161] Using a clustering algorithm, divide the first set into two non - overlapping sets;

[0162] Determine the maximum values in the two non - overlapping sets respectively, compare the two determined maximum values, and determine the smaller maximum value as the noise value;

[0163] Determine the number of data in the converted data that is greater than the noise value as the comparison value;

[0164] Based on the sampling frequency and sampling time, calculate the reference value;

[0165] Compare the comparison value with the reference value;

[0166] If the comparison value is greater than the reference value, there is a UAV video transmission signal in the signal to be recognized.

[0167] In some embodiments of the present application, the signal judgment module 30 executes the process of determining the frequency domain where the UAV video transmission signal is located based on the converted data and taking the determined frequency domain as the selected frequency domain, which may include:

[0168] Calculate the sum of each row in the converted data to obtain the second set;

[0169] Using a clustering algorithm, divide the second set into two non - overlapping sets;

[0170] Determine the maximum values in the two non - overlapping sets respectively, compare the two determined maximum values, and take the set corresponding to the larger maximum value as the pre - selected set;

[0171] Based on the pre - selected set, determine the frequency domain where the UAV video transmission signal is located and take the determined frequency domain as the selected frequency domain.

[0172] In some embodiments of the present application, the signal judgment module 30 executes the process of determining the frequency domain where the UAV video transmission signal is located based on the pre - selected set and taking the determined frequency domain as the selected frequency domain, which may include:

[0173] Calculate the longest continuous sequence of the pre - selected set;

[0174] Determine the frequency domain where the longest continuous sequence is located as the frequency domain where the UAV video transmission signal is located and take the determined frequency domain as the selected frequency domain.

[0175] In some embodiments of the present application, the signal conversion module 20 executes the process of performing time - frequency conversion on the signal to be recognized to obtain the converted data, which may include:

[0176] Process the signal to be recognized through short - time Fourier transform to obtain the transformed data;

[0177] Process the transformed data to obtain the converted data.

[0178] An embodiment of the present application further provides a drone identification device. Figure 4 The hardware structure block diagram of the training device of the lane line annotation model is shown. Refer to Figure 4 , the hardware structure of the drone identification device may include: at least one processor 1, at least one communication interface 2, at least one memory 3, and at least one communication bus 4;

[0179] In the embodiment of the present application, the number of the processor 1, the communication interface 2, the memory 3, and the communication bus 4 is at least one, and the processor 1, the communication interface 2, and the memory 3 complete mutual communication through the communication bus 4;

[0180] The processor 1 may be a central processing unit CPU, or a specific integrated circuit ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of the present invention, etc.;

[0181] The memory 3 may include a high-speed RAM memory, and may also include a non-volatile memory, etc., such as at least one disk memory;

[0182] Among them, the memory stores a program, and the processor can call the program stored in the memory. The program is used to: implement each processing flow in the foregoing drone identification method.

[0183] An embodiment of the present application further provides a storage medium. The storage medium can store a program suitable for being executed by a processor. The program is used to: implement each processing flow in the foregoing drone identification method.

[0184] Finally, it should also be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover a non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "including a..." does not exclude the presence of additional identical elements in the process, method, article or device including the element.

[0185] The various embodiments in this specification are described in a progressive manner. Each embodiment focuses on the differences from other embodiments. The various embodiments can be combined with each other, and the same or similar parts can be referred to each other.

[0186] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be obvious to those skilled in the art. The general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but rather will be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for identifying an unmanned aerial vehicle, characterized in that, Including: Obtain the signal to be recognized; Perform time-frequency conversion on the signal to be recognized to obtain conversion data; Based on the conversion data, determine whether there is a UAV video transmission signal in the signal to be recognized; If it exists, based on the conversion data, determine the frequency domain where the UAV video transmission signal is located, and use the determined frequency domain as the selected frequency domain; Based on the selected frequency domain, process the conversion data to obtain processed data; Calculate the sum of each column of the processed data, and use a clustering algorithm to divide the sum of each column into two non-overlapping sets; Respectively determine the maximum values in the two non-overlapping sets, compare the determined two maximum values, and use the set corresponding to the larger maximum value as the target set; Calculate the set of all continuous sequences of the target set; Based on the set of all continuous sequences, calculate the set of durations and the set of time intervals of the UAV video transmission signal; Input the set of durations and the set of time intervals into the UAV recognition model to obtain the UAV recognition result; The UAV recognition model is obtained by pre-training with a duration training set and a time interval training set as training samples and the corresponding UAV recognition results of the duration training set and the time interval training set as training labels.

2. The method according to claim 1, wherein The determining whether there is a UAV video transmission signal in the signal to be recognized based on the conversion data includes: Calculate the maximum value of each row in the conversion data to obtain a first set; Use a clustering algorithm to divide the first set into two non-overlapping sets; Respectively determine the maximum values in the two non-overlapping sets, compare the determined two maximum values, and determine the smaller maximum value as the noise value; Determine the number of data in the conversion data that is greater than the noise value as the comparison value; Based on the sampling frequency and sampling time, calculate a reference value; Compare the comparison value with the reference value; If the comparison value is greater than the reference value, there is a UAV video transmission signal in the signal to be recognized.

3. The method according to claim 1, wherein The determining the frequency domain where the UAV video transmission signal is located based on the conversion data and using the determined frequency domain as the selected frequency domain includes: Calculate the sum of each row in the conversion data to obtain a second set; Use a clustering algorithm to divide the second set into two non-overlapping sets; Respectively determine the maximum values in the two non-overlapping sets, compare the determined two maximum values, and use the set corresponding to the larger maximum value as the preselected set; Based on the preselected set, determine the frequency domain where the UAV video transmission signal is located, and use the determined frequency domain as the selected frequency domain.

4. The method according to claim 3, wherein The determining the frequency domain where the UAV video transmission signal is located based on the preselected set and using the determined frequency domain as the selected frequency domain includes: Calculate the longest continuous sequence of the preselected set; Determine the frequency domain where the longest continuous sequence is located as the frequency domain where the UAV video transmission signal is located, and use the determined frequency domain as the selected frequency domain.

5. The method according to claim 1, wherein The performing time-frequency conversion on the signal to be recognized to obtain conversion data includes: Process the signal to be recognized through short-time Fourier transform to obtain transformed data; Process the transformed data to obtain conversion data.

6. An unmanned aerial vehicle recognition device, characterized in that, Comprising: A signal acquisition module, configured to acquire a signal to be recognized; A signal conversion module, configured to perform time-frequency conversion on the signal to be recognized to obtain conversion data; A signal judgment module, configured to judge whether there is a UAV video transmission signal in the signal to be recognized based on the conversion data; If it exists, based on the conversion data, determine the frequency domain where the UAV video transmission signal is located, and use the determined frequency domain as the selected frequency domain; A data processing module, configured to process the conversion data based on the selected frequency domain to obtain processed data; A data calculation module, configured to calculate the sum of each column of the processed data, and use a clustering algorithm to divide the sum of each column into two non-overlapping sets; A target set determination module, configured to respectively determine the maximum values in the two non-overlapping sets, compare the determined two maximum values, and use the set corresponding to the larger maximum value as the target set; A continuous sequence calculation module, configured to calculate the entire continuous sequence set of the target set; A time data analysis module, configured to calculate the duration set and time interval set of the UAV video transmission signal based on the entire continuous sequence set; A UAV recognition module, configured to input the duration set and time interval set into a UAV recognition model to obtain a UAV recognition result, where the UAV recognition model is pre-trained with a duration training set and a time interval training set as training samples and the corresponding UAV recognition results of the duration training set and the time interval training set as training labels.

7. The device according to claim 6, characterized in that, The process of the signal judgment module performing the judgment on whether there is a UAV video transmission signal in the signal to be recognized based on the conversion data includes: Calculating the maximum value of each row in the conversion data to obtain a first set; Using a clustering algorithm to divide the first set into two non-overlapping sets; Respectively determining the maximum values in the two non-overlapping sets, comparing the determined two maximum values, and determining the smaller maximum value as the noise value; Determining the number of data in the conversion data that is greater than the noise value as a comparison value; Calculating a reference value based on the sampling frequency and sampling time; Comparing the comparison value with the reference value; If the comparison value is greater than the reference value, there is a UAV video transmission signal in the signal to be recognized.

8. The device according to claim 6, characterized in that The process of the signal judgment module performing the determination of the frequency domain where the UAV video transmission signal is located based on the conversion data and using the determined frequency domain as the selected frequency domain includes: Calculating the sum of each row in the conversion data to obtain a second set; Using a clustering algorithm to divide the second set into two non-overlapping sets; Respectively determining the maximum values in the two non-overlapping sets, comparing the determined two maximum values, and using the set corresponding to the larger maximum value as a preselected set; Based on the preselected set, determining the frequency domain where the UAV video transmission signal is located, and using the determined frequency domain as the selected frequency domain.

9. An unmanned aerial vehicle identification device, characterized in that, Comprising: A memory and a processor; The memory is used to store programs; The processor is used to execute the programs to implement each step of the UAV recognition method according to any one of claims 1-5.

10. A readable storage medium, on which a computer program is stored, characterized in that, When the computer program is executed by a processor, each step of the UAV recognition method according to any one of claims 1-5 is implemented.

Images