CN115809422B - Unmanned aerial vehicle RF signal identification method and system based on SVM - Google Patents
Unmanned aerial vehicle RF signal identification method and system based on SVM Download PDFInfo
- Publication number
- CN115809422B CN115809422B CN202111069092.5A CN202111069092A CN115809422B CN 115809422 B CN115809422 B CN 115809422B CN 202111069092 A CN202111069092 A CN 202111069092A CN 115809422 B CN115809422 B CN 115809422B
- Authority
- CN
- China
- Prior art keywords
- unmanned aerial
- aerial vehicle
- signal
- data
- training
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000007781 pre-processing Methods 0.000 claims abstract description 14
- 238000012549 training Methods 0.000 claims description 47
- 238000012360 testing method Methods 0.000 claims description 26
- 239000013598 vector Substances 0.000 claims description 18
- 238000010276 construction Methods 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 4
- 238000012795 verification Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000013145 classification model Methods 0.000 claims description 3
- 238000002372 labelling Methods 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 claims description 3
- 238000001514 detection method Methods 0.000 abstract description 20
- 238000005286 illumination Methods 0.000 abstract description 4
- 230000005540 biological transmission Effects 0.000 description 9
- 230000000694 effects Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 239000002360 explosive Substances 0.000 description 1
- 230000009545 invasion Effects 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The application discloses an unmanned aerial vehicle RF signal identification method and system based on SVM. The method comprises the following steps: step 1: collecting unmanned aerial vehicle RF signal data, background noise data and WiFi signal data; step 2: performing data preprocessing on the acquired unmanned aerial vehicle RF signal data, background noise data and WiFi signal data; step 3: constructing an SVM classifier; step 4: and inputting the unmanned aerial vehicle RF signal data to be identified into the trained classifier model. According to the unmanned aerial vehicle signal recognition method, unmanned aerial vehicle signals can be recognized through the unmanned aerial vehicle signal recognition model, and the unmanned aerial vehicle signals emitted autonomously are received and collected, so that the detection signals do not need to be emitted actively, the cost is saved, the interference of the environment such as birds is avoided, the false detection caused by the physical condition of the unmanned aerial vehicle is avoided, meanwhile, the influence of weather and illumination does not need to be considered, and the adaptability of the unmanned aerial vehicle signal recognition method is enhanced.
Description
Technical Field
The application relates to the technical field of unmanned aerial vehicles, in particular to an unmanned aerial vehicle RF signal identification method and system based on SVM.
Background
In recent years, unmanned aerial vehicles (unmanned aerial vehicle, UAV) are increasingly widely applied, and are applied to professional photography, shooting, agricultural application and disaster search and rescue, so that great convenience is brought to work and life of people, but a great deal of personal privacy and public safety problems are caused, such as UAV is used for criminal activities of invasion, reconnaissance and transportation of explosives. Thus, a series of accidents caused by UAVs alert individuals to the need for rapid and effective countering unmanned "black flight" behavior.
Currently, the most commonly used UAV signal detection methods include radar detection, acoustic detection, video detection, radio Frequency (RF) detection, and the like. Among them, in terms of radar detection, for detection of a low-low slow target such as an unmanned aerial vehicle, it has been a major difficulty in radar target detection; in terms of acoustic detection, is sensitive to ambient noise; in the aspect of video detection, weather, illumination, birds and the like can also greatly influence the detection performance. The RF signal belongs to a passive signal, so that RF detection is not transmitted by signals, is not influenced by physical characteristics of the UAV and weather illumination, has relatively good detection conditions, and completely depends on the RF signal reception of the target UAV.
A typical drone has two types of RF signals: the remote control and the image transmission are carried out, wherein the former is an uplink signal for controlling the unmanned aerial vehicle, and the latter is a downlink signal for data transmission. The graphic signal typically operates at either 2.4GHz or 5.8GHz OFDM signals. There are three methods commonly used for UAV signal analysis: (1) Classifying and identifying the UAV remote controller signals, and detecting the signals by extracting the characteristics of signal time domains, frequency domains, periods and the like; (2) extracting and identifying the MAC address of the drone; (3) The unmanned aerial vehicle is identified by extracting graphical signal features of the unmanned aerial vehicle. However, these methods have drawbacks: (1) The remote control signal is easy to report by mistake, for example, a part of remote controllers of the unmanned aerial vehicle still can send out a signal when the unmanned aerial vehicle does not fly; (2) If the unmanned aerial vehicle does not use WiFi communication, the MAC address database cannot be created; (3) The condition of the image transmission signal detection is relatively good, but because the WiFi and the image transmission work in similar frequency bands, the image transmission signal detection is still interfered by external WiFi signals.
Disclosure of Invention
Aiming at the problem that the WiFi signals and the image transmission signals work in similar frequency bands and are easily interfered by external WiFi signals, the application aims to provide an unmanned aerial vehicle RF signal identification method and system based on SVM.
In a first aspect of the present application,
the application provides an unmanned aerial vehicle RF signal identification method based on SVM, which comprises the following steps:
step 1: acquiring unmanned aerial vehicle RF signal data, background noise data and WiFi signal data, determining that unmanned aerial vehicle signal recognition tasks are classified into two categories, wherein two conditions of unmanned aerial vehicles exist and unmanned aerial vehicles do not exist;
step 2: performing data preprocessing on the acquired unmanned aerial vehicle RF signal data, background noise data and WiFi signal data, wherein the preprocessing comprises sample data segmentation, time-frequency domain feature extraction and data set construction;
step 3: constructing an SVM classifier, training the SVM classifier through the constructed data set, and storing a classifier model after training;
step 4: and inputting the unmanned aerial vehicle RF signal data to be identified into a trained classifier model, outputting the corresponding category, and completing the identification of the unmanned aerial vehicle signal.
In the step 1, the unmanned aerial vehicle RF signal data are orthogonal frequency division multiplexing modulation signals, and the bandwidth range is 10-20MHz; the background noise data and the WiFi signal data are of IEEE 802.11.N standard protocol, and the bandwidth is 20-40MHz; the background noise includes ambient noise and a remote control signal.
In step 2, the sample data is segmented into continuous unmanned aerial vehicle RF time domain signal data, and preprocessed into one sample in sequence.
Wherein in step 2, the extracting the time-frequency domain features includes:
time domain signal mean value characteristics:
mean characteristic of absolute values of time domain signals:
time domain signal standard deviation feature:
cross entropy value feature:
root mean square value characteristics:
root-value characteristics:
variance value characteristics:
peak characteristics:
x max ＝Max(x i ),i＝1,2,...N (8)
max-min value characteristics:
x max-min ＝Max(x i )-Min(x i ),i＝1,2,...N (9)
creatfactor value feature:
clearance factor value feature:
the frequency domain is the time domain signal, and the characteristics of the (1) (2) (3) (4) (5) (6) (7) (8) (9) (10) (11) are extracted after FFT.
Wherein 22 features are extracted in total, each feature is combined into a vector to form a feature vector of a single sample, then a plurality of samples are arranged to construct a sample data set, and the sample data set is processed according to 0.8: the ratio of 0.2 is divided into training and test sets.
Wherein, in step 3, the constructing and training the SVM classifier includes: training, testing and evaluating the constructed unmanned aerial vehicle signal classification model adopts a cross-test verification method: the training data set is divided into n groups, one group is selected as a test set each time, the other groups are used as training sets, the training data in the training sets are used for training the SVM classifier, and then the epoch theory is trained sequentially. The data in the test set do not participate in training, and are mainly used for evaluating the trained unmanned aerial vehicle signal recognition model, and if the accuracy of the test set reaches an expected value, the model is saved and used for detecting a subsequent single sample.
In step 4, the identifying the unmanned aerial vehicle signal includes: the preprocessing of the signal to be detected comprises the following steps: and collecting, segmenting and extracting 22 time-frequency domain features to form feature vectors, inputting the feature vectors into a trained SVM classifier model, and performing forward calculation to determine whether an unmanned aerial vehicle exists in an output result, so as to complete the identification of unmanned aerial vehicle signals.
In a second aspect of the present application,
correspondingly to the method, the embodiment of the application provides an unmanned aerial vehicle RF signal identification system based on SVM, which comprises the following modules:
the first module is used for collecting unmanned aerial vehicle RF signal data, background noise data and WiFi signal data, classifying and labeling according to whether the unmanned aerial vehicle has a label type for defining the unmanned aerial vehicle signal data, obtaining a sample data set, and further dividing the sample data set into a training set and a testing set, wherein each training data in the sample data set comprises the unmanned aerial vehicle signal data and the label type thereof;
the second module is used for constructing an SVM classifier according to the unmanned aerial vehicle signal recognition task, training the constructed SVM classifier by using a training data set, and finally evaluating the constructed SVM classifier by using a test data set to obtain the trained unmanned aerial vehicle signal recognition SVM classifier;
and the third module is used for preprocessing unmanned aerial vehicle signal data to be detected to construct a feature vector, inputting the feature vector into a trained unmanned aerial vehicle signal recognition SVM classifier, outputting a corresponding label type of the SVM classifier and completing recognition of unmanned aerial vehicle signals.
Compared with the prior art, the application has the beneficial effects that:
according to the unmanned aerial vehicle RF signal recognition method and system based on the SVM, unmanned aerial vehicle signals can be recognized through the unmanned aerial vehicle signal recognition model, the unmanned aerial vehicle autonomous transmitted signals are received and collected, the active transmission of detection signals is not needed, the cost is saved, the interference of environment such as birds is avoided, the false detection caused by the physical condition of the unmanned aerial vehicle is avoided, meanwhile, the influence of weather and illumination is not needed to be considered, and the adaptability of the unmanned aerial vehicle RF signal recognition method is enhanced. In addition, the method and the device can well relieve the problem of difficult detection caused by similar bandwidths of the unmanned aerial vehicle image transmission signal and the WiFi signal, particularly when the unmanned aerial vehicle image transmission signal and the WiFi signal are overlapped in a frequency domain, and achieve good recognition rate. In addition, a cross verification method is adopted, so that all training data can be trained and verified, and finally, test evaluation is carried out through a test set, thereby ensuring the precision of the model.
Drawings
Fig. 1 is a schematic diagram of the overall operation flow of the present application.
FIG. 2 is a flow chart of the present application for constructing a sample dataset.
Detailed Description
The application is described in further detail below with reference to the drawings and the specific examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.
As shown in fig. 1, the method for identifying the RF signal of the unmanned aerial vehicle based on the SVM provided in the embodiment includes the following steps:
step 1: acquiring unmanned aerial vehicle RF signal data, background noise data and WiFi signal data, and determining that unmanned aerial vehicle signal recognition tasks are classified into two categories, wherein one category is: RF, rf+noise, rf+wifi, rf+wifi+noise is the case with drones; the other is noise, wiFi+noise is the absence of unmanned aerial vehicle.
Step 2: performing data preprocessing on the acquired unmanned aerial vehicle RF signal data, background noise data and WiFi signal data, wherein the preprocessing comprises sample data segmentation, time-frequency domain feature extraction and data set construction;
step 3: constructing an SVM classifier, training the SVM classifier through the constructed data set, and storing a classifier model after training;
step 4: and inputting the unmanned aerial vehicle RF signal data to be identified into a trained unmanned aerial vehicle signal identification model, outputting the corresponding category, and completing the identification of the unmanned aerial vehicle signal.
In a preferred embodiment, in step 1, the acquired RF signal data of the unmanned aerial vehicle is an Orthogonal Frequency Division Multiplexing (OFDM) modulated signal with a bandwidth ranging from 10 MHz to 20MHz;
the WiFi signal data is of an IEEE 802.11.N standard protocol, and the bandwidth is 20-40MHz;
the background noise data includes ambient noise and a remote control signal.
The collected signals relate to six conditions of RF, RF+noise, RF+wifi, RF+wifi+ noise, noise, wifi +noise, and then the signals are divided into two types, so that a data base is provided for unmanned aerial vehicle signal recognition tasks, namely recognition of whether unmanned aerial vehicles exist.
In a preferred embodiment, in step 2, as shown in fig. 2, the data preprocessing includes sample data slicing, time-frequency domain feature extraction, sample data and construction.
Wherein extracting the time domain features as shown in fig. 2 comprises:
time domain signal mean value characteristics:
mean characteristic of absolute values of time domain signals:
time domain signal standard deviation feature:
cross entropy value feature:
root mean square value characteristics:
root-value characteristics:
variance value characteristics:
peak characteristics:
x max ＝Max(x i ),i＝1,2,...N (8)
max-min value characteristics:
x max-min ＝Max(x i )-Min(x i ),i＝1,2,...N (9)
creatfactor value feature:
clearance factor value feature:
the frequency domain is the time domain signal, and the characteristics of the (1) (2) (3) (4) (5) (6) (7) (8) (9) (10) (11) are extracted after FFT. A total of 22 features are extracted, the features are combined into a vector to form a feature vector of a single sample, then a plurality of samples are arranged to construct a sample data set, and the sample data set is processed according to 0.8: the ratio of 0.2 is divided into training and test sets.
In a preferred embodiment, in step 3, the constructing and training of the SVM classifier includes:
training, testing and evaluating the constructed unmanned aerial vehicle signal classification model adopts a cross-test verification method: the training data set is divided into n groups, one group is selected as a test set each time, the other groups are used as training sets, the training data in the training sets are used for training the SVM classifier, and then the epoch theory is trained sequentially. The data in the test set do not participate in training, and are mainly used for evaluating the trained unmanned aerial vehicle signal recognition model, and if the accuracy of the test set reaches an expected value, the model is saved and used for detecting a subsequent single sample.
In a preferred embodiment, in step 4, performing the identification of the drone signal includes:
the preprocessing of the signal to be detected comprises the following steps: and collecting, segmenting and extracting 22 time-frequency domain features to form feature vectors, inputting the feature vectors into a trained SVM classifier model, and performing forward calculation to determine whether an unmanned aerial vehicle exists in an output result, so as to complete the identification of unmanned aerial vehicle signals.
Correspondingly to the method, the embodiment of the application provides an unmanned aerial vehicle RF signal identification system based on SVM, which comprises the following modules:
the first module is used for collecting unmanned aerial vehicle RF signal data, background noise data and WiFi signal data, classifying and labeling according to whether the unmanned aerial vehicle has a label type for defining the unmanned aerial vehicle signal data, obtaining a sample data set, and further dividing the sample data set into a training set and a testing set, wherein each training data in the sample data set comprises the unmanned aerial vehicle signal data and the label type thereof;
the second module is used for constructing an SVM classifier according to the unmanned aerial vehicle signal recognition task, training the constructed SVM classifier by using a training data set, and finally evaluating the constructed SVM classifier by using a test data set to obtain the trained unmanned aerial vehicle signal recognition SVM classifier;
and the third module is used for preprocessing unmanned aerial vehicle signal data to be detected to construct a feature vector, inputting the feature vector into a trained unmanned aerial vehicle signal recognition SVM classifier, outputting a corresponding label type of the SVM classifier and completing recognition of unmanned aerial vehicle signals.
It should be noted that, the details and effects of the system according to the embodiment of the present application are the same as or similar to those of the method according to the above embodiment, and are not described herein again.
The foregoing details of the optional implementation of the embodiment of the present application have been described in detail with reference to the accompanying drawings, but the embodiment of the present application is not limited to the specific details of the foregoing implementation, and various simple modifications may be made to the technical solution of the embodiment of the present application within the scope of the technical concept of the embodiment of the present application, and these simple modifications all fall within the protection scope of the embodiment of the present application.
In addition, the specific features described in the above embodiments may be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, various possible combinations of embodiments of the present application are not described in detail.
Claims (8)
1. An unmanned aerial vehicle RF signal recognition method based on an SVM, the method comprising the steps of:
step 1: acquiring unmanned aerial vehicle RF signal data, background noise data and WiFi signal data, and determining that unmanned aerial vehicle signal recognition tasks are classified into two categories, wherein unmanned aerial vehicle situations exist and unmanned aerial vehicle situations do not exist;
step 2: performing data preprocessing on the acquired unmanned aerial vehicle RF signal data, background noise data and WiFi signal data, wherein the preprocessing comprises sample data segmentation, time-frequency domain feature extraction and data set construction;
step 3: constructing an SVM classifier, training the SVM classifier through the constructed data set, and storing a classifier model after training;
step 4: and inputting the unmanned aerial vehicle RF signal data to be identified into a trained classifier model, outputting the corresponding category, and completing the identification of the unmanned aerial vehicle signal.
2. The unmanned aerial vehicle RF signal recognition method based on SVM according to claim 1, wherein in step 1, the unmanned aerial vehicle RF signal data is an orthogonal frequency division multiplexing modulation signal, and the bandwidth range is 10-20MHz; the background noise data and the WiFi signal data are of IEEE 802.11.N standard protocol, and the bandwidth is 20-40MHz; the background noise includes ambient noise and a remote control signal.
3. The method for identifying RF signals of unmanned aerial vehicle based on SVM according to claim 1, wherein in step 2, the sample data is sliced into continuous RF time domain signal data of unmanned aerial vehicle, which is collected, and preprocessed into one sample in sequence.
4. The method for identifying RF signals of an unmanned aerial vehicle based on SVM according to claim 1, wherein in step 2, the extracting time-frequency domain features includes:
time domain signal mean value characteristics:
mean characteristic of absolute values of time domain signals:
time domain signal standard deviation feature:
cross entropy value feature:
root mean square value characteristics:
root-value characteristics:
variance value characteristics:
peak characteristics:
x max ＝Max(x i ),i＝1,2,...N (8)
max-min value characteristics:
x max-min ＝Max(x i )-Min(x i ),i＝1,2,...N (9)
creatfactor value feature:
clearance factor value feature:
the frequency domain is the time domain signal, and the characteristics of the (1) (2) (3) (4) (5) (6) (7) (8) (9) (10) (11) are extracted after FFT.
5. The method of claim 4, wherein 22 features are extracted in total, each feature is combined into a vector to form a feature vector of a single sample, then a plurality of samples are sorted, a sample data set is constructed, and the sample data set is processed according to 0.8: the ratio of 0.2 is divided into training and test sets.
6. The method of claim 1, wherein in step 3, the constructing and training the SVM classifier comprises: training, testing and evaluating the constructed unmanned aerial vehicle signal classification model adopts a cross-test verification method: dividing a training data set into n groups, selecting one group as a test set each time, selecting other groups as training sets, using training data in the training sets for training an SVM classifier, then training an epoch theory in sequence, wherein the data in the test set are not involved in training, and are mainly used for evaluating a trained unmanned aerial vehicle signal recognition model, and if the accuracy of the test set reaches an expected value, storing the model for detecting a subsequent single sample.
7. The method of claim 1, wherein in step 4, performing the identification of the unmanned aerial vehicle signal comprises: the preprocessing of the signal to be detected comprises the following steps: and collecting, segmenting and extracting 22 time-frequency domain features to form feature vectors, inputting the feature vectors into a trained SVM classifier model, and performing forward calculation to determine whether an unmanned aerial vehicle exists in an output result, so as to complete the identification of unmanned aerial vehicle signals.
8. An unmanned aerial vehicle RF signal recognition system based on SVM, comprising the following modules:
the first module is used for collecting unmanned aerial vehicle RF signal data, background noise data and WiFi signal data, classifying and labeling according to whether the unmanned aerial vehicle has a label type for defining the unmanned aerial vehicle signal data, obtaining a sample data set, and further dividing the sample data set into a training set and a testing set, wherein each training data in the sample data set comprises the unmanned aerial vehicle signal data and the label type thereof;
the second module is used for constructing an SVM classifier according to the unmanned aerial vehicle signal recognition task, training the constructed SVM classifier by using a training data set, and finally evaluating the constructed SVM classifier by using a test data set to obtain the trained unmanned aerial vehicle signal recognition SVM classifier;
and the third module is used for preprocessing unmanned aerial vehicle signal data to be detected to construct a feature vector, inputting the feature vector into a trained unmanned aerial vehicle signal recognition SVM classifier, outputting a corresponding label type of the SVM classifier and completing recognition of unmanned aerial vehicle signals.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111069092.5A CN115809422B (en) | 2021-09-13 | 2021-09-13 | Unmanned aerial vehicle RF signal identification method and system based on SVM |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111069092.5A CN115809422B (en) | 2021-09-13 | 2021-09-13 | Unmanned aerial vehicle RF signal identification method and system based on SVM |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115809422A CN115809422A (en) | 2023-03-17 |
| CN115809422B true CN115809422B (en) | 2023-11-21 |
Family
ID=85481134
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111069092.5A Active CN115809422B (en) | 2021-09-13 | 2021-09-13 | Unmanned aerial vehicle RF signal identification method and system based on SVM |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115809422B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106197424A (en) * | 2016-06-28 | 2016-12-07 | 哈尔滨工业大学 | The unmanned plane during flying state identification method that telemetry drives |
| CN107682109A (en) * | 2017-10-11 | 2018-02-09 | 北京航空航天大学 | A kind of interference signal classifying identification method suitable for UAV Communication system |
| CN107993648A (en) * | 2017-11-27 | 2018-05-04 | 北京邮电大学 | A kind of unmanned plane recognition methods, device and electronic equipment |
| CN110087233A (en) * | 2019-03-28 | 2019-08-02 | 东南大学 | A kind of unmanned plane identity identifying method based on radio-frequency fingerprint |
| CN112270680A (en) * | 2020-11-20 | 2021-01-26 | 浙江科技学院 | Low altitude unmanned detection method based on sound and image fusion |
| CN112348006A (en) * | 2021-01-11 | 2021-02-09 | 湖南星空机器人技术有限公司 | Unmanned aerial vehicle signal identification method, system, medium and equipment |
| CN112801003A (en) * | 2021-02-05 | 2021-05-14 | 江苏方天电力技术有限公司 | Unmanned aerial vehicle radiation source modulation pattern recognition method and device |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10558186B2 (en) * | 2016-10-13 | 2020-02-11 | Farrokh Mohamadi | Detection of drones |
| US10699585B2 (en) * | 2018-08-02 | 2020-06-30 | University Of North Dakota | Unmanned aerial system detection and mitigation |
| US20200158822A1 (en) * | 2018-09-06 | 2020-05-21 | Airspace Systems, Inc. | Unmanned aerial vehicle radar detection |
-
2021
- 2021-09-13 CN CN202111069092.5A patent/CN115809422B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106197424A (en) * | 2016-06-28 | 2016-12-07 | 哈尔滨工业大学 | The unmanned plane during flying state identification method that telemetry drives |
| CN107682109A (en) * | 2017-10-11 | 2018-02-09 | 北京航空航天大学 | A kind of interference signal classifying identification method suitable for UAV Communication system |
| CN107993648A (en) * | 2017-11-27 | 2018-05-04 | 北京邮电大学 | A kind of unmanned plane recognition methods, device and electronic equipment |
| CN110087233A (en) * | 2019-03-28 | 2019-08-02 | 东南大学 | A kind of unmanned plane identity identifying method based on radio-frequency fingerprint |
| CN112270680A (en) * | 2020-11-20 | 2021-01-26 | 浙江科技学院 | Low altitude unmanned detection method based on sound and image fusion |
| CN112348006A (en) * | 2021-01-11 | 2021-02-09 | 湖南星空机器人技术有限公司 | Unmanned aerial vehicle signal identification method, system, medium and equipment |
| CN112801003A (en) * | 2021-02-05 | 2021-05-14 | 江苏方天电力技术有限公司 | Unmanned aerial vehicle radiation source modulation pattern recognition method and device |
Non-Patent Citations (1)
| Title |
|---|
| "遥测数据驱动的无人机飞行状态识别方法";贺思捷等;《仪器仪表学报》;第37卷(第9期);2004-2013 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115809422A (en) | 2023-03-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ezuma et al. | Micro-UAV detection and classification from RF fingerprints using machine learning techniques | |
| US10529241B2 (en) | Unmanned vehicle recognition and threat management | |
| Zhao et al. | Classification of small UAVs based on auxiliary classifier Wasserstein GANs | |
| US10699585B2 (en) | Unmanned aerial system detection and mitigation | |
| Medaiyese et al. | Wavelet transform analytics for RF-based UAV detection and identification system using machine learning | |
| Ozturk et al. | RF-based low-SNR classification of UAVs using convolutional neural networks | |
| CN108055094B (en) | Unmanned aerial vehicle manipulator frequency spectrum feature identification and positioning method | |
| US11915602B2 (en) | Drone detection, classification, tracking, and threat evaluation system employing field and remote identification (ID) information | |
| CN108280395B (en) | Efficient identification method for flight control signals of low-small-slow unmanned aerial vehicle | |
| US10558186B2 (en) | Detection of drones | |
| US20210197967A1 (en) | Uas detection and negation | |
| CN111709329B (en) | Unmanned aerial vehicle measurement and control signal high-speed recognition method based on deep learning | |
| WO2020209918A2 (en) | Detection of cyber attacks targeting avionics systems | |
| KR20190019713A (en) | System and method for classifying based on support vector machine for uav sound identification | |
| CN111474955B (en) | Identification method, device and equipment for unmanned aerial vehicle graph signaling system and storage medium | |
| Zuo et al. | Recognition of UAV video signal using RF fingerprints in the presence of WiFi interference | |
| CN110087233B (en) | Unmanned aerial vehicle identity authentication method based on radio frequency fingerprint | |
| Cai et al. | Reliable UAV monitoring system using deep learning approaches | |
| CN113518374B (en) | Radio frequency identification method for unmanned aerial vehicle image transmission signals under WIFI interference | |
| CN115809422B (en) | Unmanned aerial vehicle RF signal identification method and system based on SVM | |
| CN114154532A (en) | Unmanned aerial vehicle individual multi-dimensional domain electromagnetic signal feature deep learning identification method | |
| CN109669170B (en) | Method for reducing false alarm rate of signal detection system of unmanned aerial vehicle | |
| CN109815773A (en) | A kind of low slow small aircraft detection method of view-based access control model | |
| CN114415726B (en) | Unmanned aerial vehicle obstacle avoidance control system and method based on image analysis | |
| CN111339816B (en) | Multi-unmanned aerial vehicle radio frequency signal identification method based on wavelet neural network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |