CN111222430A - Unmanned aerial vehicle identification method and system based on artificial intelligence - Google Patents
Unmanned aerial vehicle identification method and system based on artificial intelligence Download PDFInfo
- Publication number
- CN111222430A CN111222430A CN201911378364.2A CN201911378364A CN111222430A CN 111222430 A CN111222430 A CN 111222430A CN 201911378364 A CN201911378364 A CN 201911378364A CN 111222430 A CN111222430 A CN 111222430A
- Authority
- CN
- China
- Prior art keywords
- unmanned aerial
- aerial vehicle
- artificial intelligence
- signal
- frequency
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S5/00—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations
- G01S5/02—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations using radio waves
- G01S5/10—Position of receiver fixed by co-ordinating a plurality of position lines defined by path-difference measurements, e.g. omega or decca systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Signal Processing (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The invention discloses an unmanned aerial vehicle identification method and system based on artificial intelligence, and the method comprises the following steps: step S1, receiving radio signals in the surrounding environment; step S2, carrying out Fourier transform operation on the collected radio signals to generate a spectrogram, and then overlapping the multiframe spectrograms to generate a corresponding time-frequency graph; and step S3, judging whether the generated time-frequency picture has the unmanned aerial vehicle communication signal or not by an artificial intelligence method. The system comprises a receiving antenna array, a data acquisition unit, a time-frequency diagram generation unit and a processing unit. The invention has the advantages of simple principle, easy realization, good universality and the like.
Description
Technical Field
The invention mainly relates to the technical field of unmanned aerial vehicles, in particular to an unmanned aerial vehicle identification method and system based on artificial intelligence.
Background
In recent years, civil unmanned aerial vehicles have been rapidly developed, wherein small consumer-grade civil unmanned aerial vehicles exhibit well-jet development, and unmanned aerial vehicles are currently applied to many fields, such as agriculture, personal aerial photography, police reconnaissance and the like. However, as unmanned aerial vehicles grow rapidly, the security threat brought with the unmanned aerial vehicles is also valued by more and more people and even national governments. In order to deal with the huge threat of the black flying abuse of the unmanned aerial vehicle to personal privacy, public security management, national security and the like, the theory and technical research of the relevant anti-unmanned aerial vehicle is more and more paid high attention by governments, academic circles and industrial circles at home and abroad.
The existing popular unmanned aerial vehicle communication signal identification method is that signal key characteristics, such as power spectral density maximum value, signal envelope kurtosis, instantaneous phase standard deviation, phase pulse number, cyclic spectrum, high order moment and the like/frequency domain signal characteristics, are selected by practitioners in the field, and then characteristic parameters are calculated by utilizing a traditional signal processing algorithm. And then, the signals in the environment are acquired and matched with the corresponding characteristics to achieve the detection and identification of the unmanned aerial vehicle.
The existing unmanned aerial vehicle communication signal identification method has some defects:
1. several or even more than ten characteristics in an unmanned aerial vehicle signal model need to be selected as model input, the calculation complexity is very high, and actual deployment and use are difficult.
2. The unmanned aerial vehicle model added with detection is difficult, new characteristic parameters need to be added, and characteristic parameter extraction depends on artificial experience values and does not have universality.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: aiming at the technical problems in the prior art, the invention provides the unmanned aerial vehicle identification method and system based on artificial intelligence, which have the advantages of simple principle, easy realization and good universality.
In order to solve the technical problems, the invention adopts the following technical scheme:
an unmanned aerial vehicle identification method based on artificial intelligence is characterized by comprising the following steps:
step S1, receiving radio signals in the surrounding environment;
step S2, carrying out Fourier transform operation on the collected radio signals to generate a spectrogram, and then overlapping the multiframe spectrograms to generate a corresponding time-frequency graph;
and step S3, judging whether the generated time-frequency picture has the unmanned aerial vehicle communication signal or not by an artificial intelligence method.
As a further improvement of the process of the invention: in step S3, if it is determined that there is a drone signal, the drone position is measured by the direction finding method.
As a further improvement of the process of the invention: in step S3, if it is determined that there is an unmanned aerial vehicle signal, the unmanned aerial vehicle distance is measured by the ranging method.
As a further improvement of the process of the invention: the direction finding method comprises the following steps: firstly, a corresponding model is established according to a directional diagram of an antenna array, the receiving intensity values among all antennas in the receiving antenna array are used for representing in the 0-360-degree direction, and the direction of the unmanned aerial vehicle is obtained in a lookup table mode; when the unmanned aerial vehicle direction finding device is used, a matrix taking the signal intensity value of each antenna at each angle as a row is established according to the signal intensity values of the unmanned aerial vehicle signals of the output channels, then the corresponding signal intensity values are sequentially subjected to difference operation with the rows of the lookup table matrix, and then the variance is calculated, wherein the row with the minimum variance and the direction representing the best matching are obtained, so that the unmanned aerial vehicle direction finding is realized.
As a further improvement of the process of the invention: the distance measuring method comprises the following steps: and according to the signal intensity of the received unmanned aerial vehicle signal, calculating the distance between the unmanned aerial vehicle and the system by using a radio atmospheric attenuation formula.
As a further improvement of the process of the invention: in step S2, first, a single-order spectrogram is generated from the digital radio signal by fourier transform; and then generating a time-frequency picture by overlapping the spectrogram of multiple Fourier transforms.
As a further improvement of the process of the invention: in step S3, the algorithm network is trained by a large number of signals of the unmanned aerial vehicle, the trained algorithm network generates a corresponding weight value file, and when the trained algorithm network is used, the corresponding weight value file is loaded, and then the time-frequency picture input into the algorithm is operated, so that whether the input picture contains the unmanned aerial vehicle signal can be identified.
As a further improvement of the process of the invention: when a new model needs to be added, a time-frequency graph of a new unmanned aerial vehicle signal is collected to train the algorithm network, and a new weight value file is generated.
The invention further provides an unmanned aerial vehicle identification system based on artificial intelligence, which comprises:
a receiving antenna array for receiving radio signals in the surrounding environment;
the data acquisition unit is used for acquiring radio signals;
the time-frequency diagram generating unit is used for carrying out Fourier transform operation on the collected radio signals to generate a frequency spectrum diagram, and then overlapping the multi-frame frequency spectrum diagram to generate a corresponding time-frequency diagram;
and the processing unit is used for judging whether the unmanned aerial vehicle communication signals exist in the generated time-frequency image through an artificial intelligence algorithm, and if the unmanned aerial vehicle communication signals exist, measuring and calculating the direction and the distance of the unmanned aerial vehicle through a direction-finding and distance-measuring method.
As a further improvement of the system of the invention: the antenna array is composed of a plurality of full-band antennas, covers the receiving range of 0-6 Ghz radio signals and covers the horizontal 360-degree receiving direction.
Compared with the prior art, the invention has the advantages that:
1. the unmanned aerial vehicle identification method and the unmanned aerial vehicle identification system based on artificial intelligence are simple in principle, easy to implement and good in universality, and the unmanned aerial vehicle communication signals are detected by adopting the artificial intelligence method. The artificial intelligence method can extract corresponding characteristic weight values only by training with unmanned aerial vehicle signals, and can realize the detection of the unmanned aerial vehicle signals according to the characteristic weight values. No expert is required to pick the characteristics of the signal. For increasing new types of unmanned aerial vehicle models, the artificial intelligence method can increase the models only by providing new types of unmanned aerial vehicle signals for training, and the model increase is simple and convenient.
2. The unmanned aerial vehicle identification method and the unmanned aerial vehicle identification system based on artificial intelligence are a complete unmanned aerial vehicle identification and detection system which can identify the type of the unmanned aerial vehicle and the direction and distance of the unmanned aerial vehicle.
Drawings
FIG. 1 is a schematic flow diagram of the process of the present invention.
Fig. 2 is a schematic diagram of a receiving antenna array in an embodiment of the present invention.
Fig. 3 is a schematic diagram of a time-frequency picture generation process in a specific application example of the present invention.
Fig. 4 is a schematic diagram of time-frequency picture generation in a specific application example of the present invention.
Fig. 5 is a schematic flow chart of identifying the drone signal in a specific application example of the present invention.
Fig. 6 is a schematic diagram of the signal result of the unmanned aerial vehicle of artificial intelligent recognition in a specific application example of the invention.
FIG. 7 is a schematic diagram of an artificial intelligence network training process in an embodiment of the present invention.
FIG. 8 is a block diagram of an artificial intelligence network model in an example embodiment of the present invention.
Detailed Description
The invention will be described in further detail below with reference to the drawings and specific examples.
As shown in fig. 1 to 8, the method for identifying an unmanned aerial vehicle based on artificial intelligence of the present invention includes:
step S1, receiving radio signals in the surrounding environment;
step S2, carrying out Fourier transform operation on the collected radio signals to generate a spectrogram, and then overlapping the multiframe spectrograms to generate a corresponding time-frequency graph;
and step S3, judging whether the generated time-frequency picture has the unmanned aerial vehicle communication signal or not by an artificial intelligence method.
As a preferred embodiment, the present invention further comprises: in step S3, if it is determined that there is an unmanned aerial vehicle signal, the direction and distance of the unmanned aerial vehicle are measured by the direction and distance measuring method.
In a specific application example, the direction-finding and distance-measuring method adopted by the invention is characterized in that when the direction is measured, a corresponding model is firstly established according to the directional diagram of the antenna array, the received intensity values among all antennas in the receiving antenna array are used for representing in the 0-360-degree direction, and the lookup table is shown as table 1. When the unmanned aerial vehicle direction-finding device is used, according to the signal intensity values of the unmanned aerial vehicle signals of 8 channels output by the artificial intelligence algorithm, difference value operation is sequentially carried out on the signal intensity values and rows of a lookup table matrix, then the variance is obtained, the row with the minimum variance and the direction which represents the best matching are obtained, and therefore unmanned aerial vehicle direction finding is achieved. And the unmanned aerial vehicle ranging is to calculate the distance between the unmanned aerial vehicle and the system by utilizing a radio atmosphere attenuation formula according to the signal intensity of the received unmanned aerial vehicle signal.
TABLE 1 Direction finding lookup table
Referring to fig. 3, in a specific application example, in step S2, a single-pass spectrogram is generated by fourier transform on a digital radio signal; and then generating a time-frequency picture by overlapping the spectrogram of multiple Fourier transforms.
Referring to fig. 5, in a specific application example, a schematic diagram of a signal identification result of an unmanned aerial vehicle is shown in fig. 6, an algorithm outputs a signal type signal bandwidth, a signal center frequency point and a confidence coefficient of the unmanned aerial vehicle, and the output result in fig. 6 is an unmanned aerial vehicle type: JL4 (genius 4), signal bandwidth 10M, signal center frequency point 2476M, and confidence of the detection result 0.82. In step S3, it is necessary to train the algorithm network through a large number of signals of the unmanned aerial vehicle in the processing unit in the early stage, the trained algorithm network will generate a corresponding weight value file, and when in use, it is only necessary to load the corresponding weight value file and then operate the time-frequency picture input into the algorithm to identify whether the input picture contains the unmanned aerial vehicle signal. Further, if a new model is required to be added, only a time-frequency graph of a new unmanned aerial vehicle signal is required to be collected to train the algorithm network, and a new weight value file is generated.
Referring to fig. 7, an artificial intelligence network training procedure is shown. The training process comprises the following steps:
data preprocessing: the time spectrogram generated by the acquired unmanned aerial vehicle radio signal is subjected to data calibration to calibrate the position of the unmanned aerial vehicle signal in the picture and classify the type of the unmanned aerial vehicle into a data set.
Network structure and model configuration: the Yolo-V3 network model is used in this example. The structure of the model is shown in FIG. 8.
Training and parameter adjustment: the data set is input into a network model, whether the loss function reaches an expected value or not is observed through continuous iterative operation, the expected fine tuning parameter is not reached, training is continued until the expected value is reached, and finally, a weight value file is output and used for inputting the weight value file in the graph 5.
With reference to fig. 1, the present invention further provides an unmanned aerial vehicle identification system based on artificial intelligence, including:
a receiving antenna array for receiving radio signals in the surrounding environment;
the data acquisition unit is used for acquiring radio signals;
the time-frequency diagram generating unit is used for carrying out Fourier transform operation on the collected radio signals to generate a frequency spectrum diagram, and then overlapping the multi-frame frequency spectrum diagram to generate a corresponding time-frequency diagram;
and the processing unit is used for judging whether the unmanned aerial vehicle communication signals exist in the generated time-frequency image through an artificial intelligence algorithm, and if the unmanned aerial vehicle communication signals exist, measuring and calculating the direction and the distance of the unmanned aerial vehicle through a direction-finding and distance-measuring method.
Referring to fig. 2, a schematic diagram of an antenna array used in an embodiment of the present invention is shown. The antenna array is composed of a plurality of (for example, 8) full-band antennas, covers the receiving range of 0-6 Ghz radio signals, and covers the horizontal 360-degree receiving direction.
In a specific application example, the data acquisition unit adopts an AD chip, and the AD chip is used for converting an analog signal into a digital signal.
Referring to fig. 3, in a specific application example, a schematic flow chart of generating a time-frequency picture in the specific application example is shown. Firstly, generating a single-time spectrogram by a digital radio signal through Fourier change; and then generating a time-frequency picture by overlapping the spectrogram of multiple Fourier transforms. Fig. 4 is a schematic diagram of time-frequency picture generation in a specific application example.
The above is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above-mentioned embodiments, and all technical solutions belonging to the idea of the present invention belong to the protection scope of the present invention. It should be noted that modifications and embellishments within the scope of the invention may be made by those skilled in the art without departing from the principle of the invention.
Claims (10)
1. An unmanned aerial vehicle identification method based on artificial intelligence is characterized by comprising the following steps:
step S1, receiving radio signals in the surrounding environment;
step S2, carrying out Fourier transform operation on the collected radio signals to generate a spectrogram, and then overlapping the multiframe spectrograms to generate a corresponding time-frequency graph;
and step S3, judging whether the generated time-frequency picture has the unmanned aerial vehicle communication signal or not by an artificial intelligence method.
2. The method of claim 1, wherein in step S3, if the drone signal is determined to be present, the drone orientation is measured by a direction-finding method.
3. The method of claim 1, wherein in step S3, if the drone signal is determined to be present, the drone distance is measured by a ranging method.
4. The artificial intelligence based unmanned aerial vehicle identification method of claim 2, wherein the direction-finding method is: firstly, a corresponding model is established according to a directional diagram of an antenna array, the receiving intensity values among all antennas in the receiving antenna array are used for representing in the 0-360-degree direction, and the direction of the unmanned aerial vehicle is obtained in a lookup table mode; when the unmanned aerial vehicle direction finding device is used, a matrix taking the signal intensity value of each antenna at each angle as a row is established according to the signal intensity values of the unmanned aerial vehicle signals of the output channels, then the corresponding signal intensity values are sequentially subjected to difference operation with the rows of the lookup table matrix, and then the variance is calculated, wherein the row with the minimum variance and the direction representing the best matching are obtained, so that the unmanned aerial vehicle direction finding is realized.
5. The artificial intelligence based unmanned aerial vehicle identification method according to claim 3, wherein the ranging method is as follows: and according to the signal intensity of the received unmanned aerial vehicle signal, calculating the distance between the unmanned aerial vehicle and the system by using a radio atmospheric attenuation formula.
6. The artificial intelligence based unmanned aerial vehicle identification method of any one of claims 1-5, wherein in step S2, the digital radio signal is first Fourier transformed to generate a single-time spectrogram; and then generating a time-frequency picture by overlapping the spectrogram of multiple Fourier transforms.
7. The unmanned aerial vehicle identification method based on artificial intelligence of any one of claims 1-5, wherein in step S3, the algorithm network is trained through a large number of unmanned aerial vehicle signals, the trained algorithm network generates a corresponding weight value file, and when in use, the corresponding weight value file is loaded, and then the time-frequency picture input into the algorithm is operated, so that whether the input picture contains the unmanned aerial vehicle signal or not can be identified.
8. The unmanned aerial vehicle identification method based on artificial intelligence of claim 7, wherein when a new model needs to be added, a time-frequency graph of a new unmanned aerial vehicle signal is collected to train an algorithm network, and a new weight value file is generated.
9. An unmanned aerial vehicle identification system based on artificial intelligence, its characterized in that includes:
a receiving antenna array for receiving radio signals in the surrounding environment;
the data acquisition unit is used for acquiring radio signals;
the time-frequency diagram generating unit is used for carrying out Fourier transform operation on the collected radio signals to generate a frequency spectrum diagram, and then overlapping the multi-frame frequency spectrum diagram to generate a corresponding time-frequency diagram;
and the processing unit is used for judging whether the unmanned aerial vehicle communication signals exist in the generated time-frequency image through an artificial intelligence algorithm, and if the unmanned aerial vehicle communication signals exist, measuring and calculating the direction and the distance of the unmanned aerial vehicle through a direction-finding and distance-measuring method.
10. The artificial intelligence based unmanned aerial vehicle identification system of claim 9, wherein the antenna array is composed of a plurality of full-band antennas, covers a 0-6 Ghz radio signal reception range, and covers a horizontal 360 ° reception direction.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911378364.2A CN111222430A (en) | 2019-12-27 | 2019-12-27 | Unmanned aerial vehicle identification method and system based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911378364.2A CN111222430A (en) | 2019-12-27 | 2019-12-27 | Unmanned aerial vehicle identification method and system based on artificial intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111222430A true CN111222430A (en) | 2020-06-02 |
Family
ID=70806103
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911378364.2A Pending CN111222430A (en) | 2019-12-27 | 2019-12-27 | Unmanned aerial vehicle identification method and system based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111222430A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111785004A (en) * | 2020-07-01 | 2020-10-16 | 上海广拓信息技术有限公司 | Line patrol information transmission method and system |
| CN114154545A (en) * | 2021-12-07 | 2022-03-08 | 中国人民解放军32802部队 | Intelligent unmanned aerial vehicle measurement and control signal identification method under strong mutual interference condition |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107122738A (en) * | 2017-04-26 | 2017-09-01 | 成都蓝色起源科技有限公司 | Automatic Communication Signals Recognition based on deep learning model and its realize system |
| CN108055094A (en) * | 2017-12-26 | 2018-05-18 | 成都爱科特科技发展有限公司 | A kind of unmanned plane manipulator spectrum signature identification and localization method |
| WO2018142395A1 (en) * | 2017-01-31 | 2018-08-09 | Arbe Robotics Ltd | A radar-based system and method for real-time simultaneous localization and mapping |
| CN109031185A (en) * | 2018-07-13 | 2018-12-18 | 中睿通信规划设计有限公司 | A kind of fixed point amplitude-comprised direction-finding method based on unmanned plane |
| CN109409225A (en) * | 2018-09-21 | 2019-03-01 | 清华大学 | Unmanned plane classification method and device based on the fusion of radar multipath signal time-frequency characteristics |
| CN110084094A (en) * | 2019-03-06 | 2019-08-02 | 中国电子科技集团公司第三十八研究所 | A kind of unmanned plane target identification classification method based on deep learning |
-
2019
- 2019-12-27 CN CN201911378364.2A patent/CN111222430A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018142395A1 (en) * | 2017-01-31 | 2018-08-09 | Arbe Robotics Ltd | A radar-based system and method for real-time simultaneous localization and mapping |
| CN107122738A (en) * | 2017-04-26 | 2017-09-01 | 成都蓝色起源科技有限公司 | Automatic Communication Signals Recognition based on deep learning model and its realize system |
| CN108055094A (en) * | 2017-12-26 | 2018-05-18 | 成都爱科特科技发展有限公司 | A kind of unmanned plane manipulator spectrum signature identification and localization method |
| CN109031185A (en) * | 2018-07-13 | 2018-12-18 | 中睿通信规划设计有限公司 | A kind of fixed point amplitude-comprised direction-finding method based on unmanned plane |
| CN109409225A (en) * | 2018-09-21 | 2019-03-01 | 清华大学 | Unmanned plane classification method and device based on the fusion of radar multipath signal time-frequency characteristics |
| CN110084094A (en) * | 2019-03-06 | 2019-08-02 | 中国电子科技集团公司第三十八研究所 | A kind of unmanned plane target identification classification method based on deep learning |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111785004A (en) * | 2020-07-01 | 2020-10-16 | 上海广拓信息技术有限公司 | Line patrol information transmission method and system |
| CN111785004B (en) * | 2020-07-01 | 2022-04-26 | 上海广拓信息技术有限公司 | Line patrol information transmission method and system |
| CN114154545A (en) * | 2021-12-07 | 2022-03-08 | 中国人民解放军32802部队 | Intelligent unmanned aerial vehicle measurement and control signal identification method under strong mutual interference condition |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Nie et al. | UAV detection and identification based on WiFi signal and RF fingerprint | |
| Medaiyese et al. | Wavelet transform analytics for RF-based UAV detection and identification system using machine learning | |
| CN108540202B (en) | Satellite communication signal modulation mode identification method and satellite communication system | |
| Zhao et al. | Classification of small UAVs based on auxiliary classifier Wasserstein GANs | |
| CN105824021B (en) | One kind mixing two dimensional phased battle array radio frequency multi-beam intelligence imaging system based on modulus | |
| CN112087774B (en) | Communication radiation source individual identification method based on residual error neural network | |
| CN108280395B (en) | Efficient identification method for flight control signals of low-small-slow unmanned aerial vehicle | |
| US11372086B2 (en) | Radio frequency (RF) object detection using radar and machine learning | |
| CN111981910B (en) | Low latitude prevents imperial system based on artificial intelligence | |
| CN107194936B (en) | Hyperspectral image target detection method based on superpixel combined sparse representation | |
| CN111050315B (en) | Wireless transmitter identification method based on multi-core two-way network | |
| CN107092898B (en) | QPSK signal bispectrum energy entropy and color moment based radio frequency fingerprint identification method | |
| CN111222430A (en) | Unmanned aerial vehicle identification method and system based on artificial intelligence | |
| CN113156439A (en) | SAR wind field and sea wave joint inversion method and system based on data driving | |
| CN111709329A (en) | Unmanned aerial vehicle measurement and control signal high-speed identification method based on deep learning | |
| CN110087233B (en) | Unmanned aerial vehicle identity authentication method based on radio frequency fingerprint | |
| CN116471154A (en) | Modulation signal identification method based on multi-domain mixed attention | |
| CN114757224A (en) | Specific radiation source identification method based on continuous learning and combined feature extraction | |
| CN109446910A (en) | A kind of communication emitter Signals classifying identification method | |
| CN116359836A (en) | Unmanned aerial vehicle target tracking method and system based on super-resolution direction finding | |
| Liu | Unmanned aerial vehicle detection and identification using deep learning | |
| CN112101249A (en) | SAR target type identification method based on deep convolutional memory network | |
| Yang et al. | Power Spectral Density Distribution Based GCN Construction for Through-the-wall Target Detection | |
| CN117523321B (en) | Optical shallow water classification method based on passive remote sensing spectral image application neural network | |
| Tang et al. | Target identification based on diagonal slice of the complex bispectrum |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200602 |