CN108280395B - Efficient identification method for flight control signals of low-small-slow unmanned aerial vehicle - Google Patents
Efficient identification method for flight control signals of low-small-slow unmanned aerial vehicle Download PDFInfo
- Publication number
- CN108280395B CN108280395B CN201711400796.XA CN201711400796A CN108280395B CN 108280395 B CN108280395 B CN 108280395B CN 201711400796 A CN201711400796 A CN 201711400796A CN 108280395 B CN108280395 B CN 108280395B
- Authority
- CN
- China
- Prior art keywords
- unmanned aerial
- flight control
- low
- identification
- aerial vehicle
- 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 46
- RZVHIXYEVGDQDX-UHFFFAOYSA-N 9,10-anthraquinone Chemical group C1=CC=C2C(=O)C3=CC=CC=C3C(=O)C2=C1 RZVHIXYEVGDQDX-UHFFFAOYSA-N 0.000 title claims abstract description 36
- 238000001514 detection method Methods 0.000 claims abstract description 13
- 238000005457 optimization Methods 0.000 claims abstract description 12
- 238000013528 artificial neural network Methods 0.000 claims abstract description 10
- 230000004927 fusion Effects 0.000 claims abstract description 10
- 238000012545 processing Methods 0.000 claims abstract description 10
- 238000004458 analytical method Methods 0.000 claims abstract description 7
- 238000004364 calculation method Methods 0.000 claims abstract description 4
- 238000005070 sampling Methods 0.000 claims description 7
- 239000013598 vector Substances 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 5
- 238000012937 correction Methods 0.000 claims description 3
- 238000000354 decomposition reaction Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 230000003111 delayed effect Effects 0.000 claims description 2
- 238000010606 normalization Methods 0.000 claims description 2
- 238000012549 training Methods 0.000 claims description 2
- 230000003595 spectral effect Effects 0.000 claims 1
- 230000000694 effects Effects 0.000 abstract description 3
- 230000007123 defense Effects 0.000 abstract description 2
- 238000005516 engineering process Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 3
- 238000001228 spectrum Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 241000592183 Eidolon Species 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000008054 signal transmission Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
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
- G06F2218/12—Classification; Matching
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Radar Systems Or Details Thereof (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention discloses a high-efficiency identification method for flight control signals of a low-small-slow unmanned aerial vehicle, which comprises the following steps: firstly, carrying out primary detection on flight control link signals; extracting key features and constructing a target feature database; thirdly, performing feature fusion and optimization; analyzing the signal according to the new feature after the fusion optimization, acquiring the signal type, the frame format and the key field, and storing the analysis result into a target feature database; and fifthly, realizing accurate classification and identification of the target by adopting a learning algorithm based on a neural network to obtain a correct identification result. The method can solve the problem of identifying the flight control signals of the low-small-slow unmanned aerial vehicle, realizes the identification and control of a specific airspace, and achieves the high-efficiency early warning defense effect on various low-small-slow unmanned aerial vehicles in illegal invasion-involved and sensitive airspaces; the method has the advantages of high correct recognition rate, reduced calculation amount, improved processing efficiency and strong applicability.
Description
Technical Field
The invention relates to a high-efficiency identification method for flight control signals of a low-speed unmanned aerial vehicle.
Background
A slow-low drone generally refers to an airborne drone target with a flying height below 1000 meters, a speed below 300 km/h, and a radar reflection area below 2 square meters. The low-small-slow unmanned aerial vehicle is small in size, light in weight, convenient to carry and simple in operation, and various small-sized devices such as navigation equipment, communication equipment, infrared camera equipment and the like can be additionally arranged on the unmanned aerial vehicle body to expand functions of the unmanned aerial vehicle and complete various tasks. Meanwhile, as the technical threshold and the cost of the low-small-slow unmanned aerial vehicle are relatively low, a plurality of companies at home and abroad research and produce the type of unmanned aerial vehicle, and the low-small-slow unmanned aerial vehicle is widely used in the civil and military market.
The identification of the low, small and slow unmanned aerial vehicle is a research hotspot problem, and the difficulty of identifying the low, small and slow unmanned aerial vehicle by the traditional radar-based method is mainly embodied as that the accurate identification of the target of the low, small and slow unmanned aerial vehicle is the basis for realizing an efficient denial system. Because the flight height of the low-small-slow unmanned aerial vehicle is low, on one hand, the radar waves can not irradiate the target under the influence of the curvature of the earth and the shielding of ground objects. On the other hand, a large amount of ground clutter enters the radar receiver at the same time, so that the radar is difficult to find the target of the unmanned aerial vehicle, even if the target can be found in real time, the target is difficult to form continuous flight paths. The low-small slow unmanned aerial vehicle has a slow flying speed, and some unmanned aerial vehicles are even lower than a general radar speed detection threshold, so that the radar of a pulse Doppler system cannot detect a target. The radar reverse area of the target is small, the echo signal is weak, and the detection probability of the radar to the target is obviously reduced. On one hand, the target is easy to form slow-moving clutter confusion with slowness targets such as meteorological clutter and bird groups due to the low flying speed of the target, and the target identification is difficult. On the other hand, at present, most unmanned aerial vehicles do not have identity recognition equipment similar to that installed on civil aircraft, and cannot perform identity verification in a signal inquiry/response mode.
At present, through patent retrieval, a solution for identifying the low, small and slow unmanned aerial vehicle based on flight control signal multi-dimensional features is not found. Similar methods of the retrieved, filed patent application are: an unmanned aerial vehicle ID identification method (publication No. 106998224A, application No. 201710149118.4, applicant: Hangzhou electronic technology university, inventor: Yuekang, Shang Jun, Liu Shen, etc.). The method designs an unmanned aerial vehicle ID identification method, and realizes real-time monitoring of the unmanned aerial vehicle and ID identification between unmanned aerial vehicles by regularly sending the self ID, the MAC address and current flight state data by the unmanned aerial vehicle. The method is not based on the identification of the characteristics of flight control signals, and cannot be applied to identifying the low-small-slow unmanned aerial vehicle which is not provided with the identity identification module in the patent and flies in black; an unmanned aerial vehicle identification method and system (publication No. 106774422A, application No. 201710111012.5, applicant: Doudou Qingyun aerospace technologies, Inc., inventor: Zhang Van, Rotao, Hainan, etc.). This patent has designed an unmanned aerial vehicle identification method, through judging the flight characteristic that detects the flight thing target around the interfering signal transmission right to judge this flight thing whether be unmanned aerial vehicle. The method does not utilize the characteristics of the unmanned aerial vehicle flight control signals for rapid identification, and an interference signal needs to be additionally transmitted to further identify the target.
The unmanned aerial vehicle target can be further identified on the basis of successful identification of the low-small-slow unmanned aerial vehicle flight control signal. The existing unmanned aerial vehicle identification technology comprises a development technology based on joint multi-sensing; identification detection technology based on sound wave; low-cost acoustic array-based recognition techniques, and the like. However, no method for identifying the low-small-slow unmanned aerial vehicle based on flight control signal features exists at present.
Disclosure of Invention
In order to overcome the defects in the prior art, the invention provides an efficient identification method for flight control signals of low-small-slow unmanned aerial vehicles.
The technical scheme adopted by the invention for solving the technical problems is as follows: a high-efficiency identification method for a low-small-slow unmanned aerial vehicle flight control signal comprises the following steps:
firstly, carrying out primary detection on flight control link signals;
extracting key features and constructing a target feature database;
thirdly, performing feature fusion and optimization;
analyzing the signal according to the new feature after the fusion optimization, acquiring the signal type, the frame format and the key field, and storing the analysis result into a target feature database;
and fifthly, realizing accurate classification and identification of the target by adopting a learning algorithm based on a neural network to obtain a correct identification result.
Compared with the prior art, the invention has the following positive effects:
the method can solve the problem of identifying the flight control signals of the low-small-slow unmanned aerial vehicle, can be applied to densely populated places such as government agencies, military units, security-related units, squares and the like, realizes the identification and control of specific airspaces, and achieves the high-efficiency early warning and defense effects on various low-small-slow unmanned aerial vehicles illegally invading the security-related and sensitive airspaces. Meanwhile, the identification method has higher correct identification rate for the flight control signals of the low-speed and small-speed unmanned aerial vehicles through a large number of tests in the actual environment, reduces the calculated amount, improves the processing efficiency and embodies better engineering practicability through further optimization of the algorithm, and is an identification method with superior performance. The method can be applied to the identification of other types of target measurement and control communication signals by slight improvement, and has strong applicability.
Drawings
The invention will now be described, by way of example, with reference to the accompanying drawings, in which:
fig. 1 is a flow chart of flight control signal identification and analysis for a low, small and slow unmanned aerial vehicle;
FIG. 2 is a flow chart of a decision algorithm for unmanned aerial vehicle flight control signal identification based on a neural network;
FIG. 3 is a graph of the identification performance of the method of the present invention.
Detailed Description
The invention provides a method for identifying flight control signals of a low-small-slow unmanned aerial vehicle. The identification of low-small slow unmanned aerial vehicle signals is an important precondition for realizing efficient rejection. The flight control signal of the low-small-slow unmanned aerial vehicle has wide bandwidth, variability and unknown property, taking the flight control signal of a genius series unmanned aerial vehicle product of the company of great Xinjiang as an example, signal systems of different models have various modes such as adaptive frequency hopping, direct sequence spread spectrum, spread/hop combination and the like, and modulation modes comprise FSK, BPSK, QPSK, 8PSK and the like, so that the problem that the key characteristic of extracting the flight control signal of the unmanned aerial vehicle in a complex electromagnetic environment is required to be solved.
The identification process for the flight control signals of the low, small and slow unmanned aerial vehicle is as follows:
(1) the primary detection of flight control link signals is carried out, and a first-level judgment result is obtained in real time through a channelized parallel processing algorithm;
(2) extracting multi-dimensional characteristics of the signals and constructing a target characteristic database;
(3) performing feature fusion and optimization based on optimization algorithms such as a self-organizing incremental novel neural network algorithm, a D-S evidence theory and the like;
(4) further analyzing the signals according to the characteristics, acquiring signal type characteristics, frame format characteristics, key field characteristics and the like, and storing analysis results into a characteristic database to enrich data domain characteristics;
(5) and (4) realizing decision judgment by adopting ideas such as a neural network machine learning algorithm and the like to obtain a correct recognition result.
As shown in fig. 1, the identification and analysis process specifically includes the following steps:
the preliminary detection algorithm for the unmanned aerial vehicle flight control link signals needs to sort the broadband data signals in real time, and is a premise for obtaining accurate signal analysis results later. The flight control link signal of the unmanned aerial vehicle is generally a broadband self-adaptive frequency hopping system, and takes a Professional unmanned aerial vehicle of a typical product eidolon 3 series of the Dajiang company as an example, the frequency range of the flight control link signal is 2.402 GHz-2.482 GHz, the frequency hopping bandwidth is 80MHz, the number of frequency hopping points is 39, and the interval of each frequency point is about 1.2 MHz. A structure based on multi-stage channelization processing can be adopted, and the accuracy of signal detection is improved by combining the idea of background noise. Firstly, the channelized data is carrier frequency corrected to align the instantaneous frequency of the signal to the center of the channel, and the IQ data of each channelized sampling point is modulo-operated, that is
Then, accumulating and summing the IQ data of the M sampling points to obtain X, accumulating and summing the delayed M sampling points to obtain Y, and then carrying out background calculation on X, Y and a background value Z of the previous period: x + Y + (1+ α). times.Z. And then the weighting coefficient alpha is selected from 0 to 1 according to the actual background change degree. The algorithm can be equivalent to performing smooth filtering on the background value within a certain timeAnd obtaining the background noise value of each channel. And subtracting the previously estimated background noise value from the channelized data to obtain background-removed channelized data, and performing maximum value holding and occurrence frequency statistical processing on all channel data. The maximum value is kept to obtain the amplitude information of the frequency hopping signal, and the frequency statistics is to obtain the frequency information of the occurrence of the signal. When the signal amplitude is larger than a certain amplitude threshold, the occurrence of a frequency hopping signal can be judged, and M-point smooth filtering is carried out on the obtained value to prepare for signal detection. And finally, comparing the maximum value and the occurrence frequency of the filtered signal with a hopping threshold and a frequency threshold, and judging as a frequency hopping channel when the maximum value of the signal is greater than the hopping threshold and the occurrence probability is less than the frequency threshold. Because the frequency hopping channels are generally continuously distributed, the actual frequency hopping channel distribution can be obtained after manual intervention is carried out to remove part of false alarm channels, and other channels except the frequency hopping channels can be shielded accordingly. And carrying out jump detection in the frequency hopping bandwidth to improve the accuracy of signal detection. In order to extract key characteristics of an unmanned aerial vehicle flight control link signal as accurately as possible from a complex electromagnetic environment, an improved envelope extraction idea based on signal complex modulation and low-pass filtering is adopted, and spectrum symmetry characteristics of the signal are analyzed by combining an idea based on Empirical Mode Decomposition (EMD). Since the basis functions of the EMD method are obtained by self-adaptation in the signals, a good decomposition effect can be obtained. The method has better adaptability in processing complex signals such as spread spectrum signals, and can enhance the anti-noise performance of the feature extraction algorithm more than the traditional mode in the past. And then fusing target signal features extracted from different angles, namely straightening and combining various kinds of feature vectors into a single feature vector through a D-S evidence algorithm, and then carrying out normalization processing on the single feature vector to form new features after fusion optimization. In the decision making process, learning calculation based on neural network can be adoptedThe method realizes the accurate classification and identification of the target, and the thought flow chart is shown in figure 2 and comprises the following steps:
(1) setting an initial connection weight;
(2) reading a multi-dimensional characteristic data sample of the unmanned aerial vehicle target;
(3) calculating each layer of neural network output;
(4) calculating a weight coefficient correction value;
(5) adjusting the weight coefficient;
(6) judging whether a new sample exists: if yes, returning to the step (2); if not, entering the step (7);
(7) judging whether the error meets the requirement: if yes, judging the network convergence, completing the identification and classification, and then returning to the step (2); if not, entering the step (8);
(8) judging whether the number of times of recognition training is greater than or not: if so, judging that the network can not be converged, correcting the connection weight and the samples, and then retraining; if not, returning to the step (2).
In practical application, generally, the actually obtained observation data samples are few, and the recognizer based on the machine learning idea has very superior classification capability and popularization capability on small sample data, and can solve the problem of local extremum which cannot be avoided in a general neural network method and improve the recognition processing efficiency.
Selecting a low-small-slow unmanned aerial vehicle flight control signal actually measured in an external field as an experimental object, setting the central frequency of a receiver to be 70MHz, sampling frequency to be 100MHz and experimental times to be 1000 times, simulating the performance of the identification method in the patent application, testing the accuracy of identification when the signal-to-noise ratio is in a range of-4 dB to 10dB, and obtaining a performance curve shown in fig. 3. As can be seen from fig. 3, the demodulation method in the present application can achieve an identification accuracy of more than 95% when the signal-to-noise ratio is about 4dB, which embodies better engineering practicability and is an identification method with superior performance.
Claims (6)
1. A high-efficiency identification method for low, small and slow unmanned aerial vehicle flight control signals is characterized by comprising the following steps: the method comprises the following steps:
step one, carrying out preliminary detection on a flight control signal:
firstly, carrying out carrier frequency correction on channelized data to enable the instantaneous frequency of a signal to be aligned to the center of a channel, and then calculating the background noise value of each channel; subtracting the background noise value from the channelized data to obtain background-removed channelized data; carrying out maximum value holding and occurrence frequency statistical processing on all channel data to obtain amplitude information of frequency hopping signals and frequency information of occurrence of the signals, judging whether the channel is a frequency hopping channel according to the amplitude and frequency information, obtaining actual frequency hopping channel distribution, and shielding other channels except the frequency hopping channel so as to carry out hopping detection in a frequency hopping bandwidth;
extracting multidimensional key features and constructing a target feature database;
thirdly, performing feature fusion and optimization;
analyzing the signals according to various new characteristics after fusion optimization to obtain signal type characteristics, frame format characteristics and key field characteristics, and storing analysis results into a target characteristic database;
step five, realizing accurate classification and identification of the target by adopting a learning algorithm based on a neural network to obtain a correct identification result:
(1) setting an initial connection weight;
(2) reading a multi-dimensional characteristic data sample of the unmanned aerial vehicle target;
(3) calculating each layer of neural network output;
(4) calculating a weight coefficient correction value;
(5) adjusting the weight coefficient;
(6) judging whether a new sample exists: if yes, returning to the step (2); if not, entering the step (7);
(7) judging whether the error meets the requirement: if yes, judging the network convergence, completing the identification and classification, and then returning to the step (2); if not, entering the step (8);
(8) judging whether the number of times of recognition training is greater than or not: if so, judging that the network can not be converged, correcting the connection weight and the samples, and then retraining; if not, returning to the step (2).
2. The method for efficiently identifying the flight control signals of the low and small slow unmanned aerial vehicles according to claim 1, is characterized in that: the method for calculating the background noise value of each channel comprises the following steps: performing modulus operation on IQ data of each channelized sampling point
Then, accumulating and summing the IQ data of the M sampling points to obtain X, accumulating and summing the delayed M sampling points to obtain Y, and then carrying out background calculation on X, Y and a background value Z of the previous period: and X + Y + (1+ alpha) multiplied by Z, wherein alpha is a weighting coefficient, and the background noise value of each channel is obtained.
3. The method for efficiently identifying the flight control signals of the low and small slow unmanned aerial vehicles according to claim 2, is characterized in that: the weighting factor alpha is selected from 0 to 1 depending on the actual degree of background variation.
4. The method for efficiently identifying the flight control signals of the low and small slow unmanned aerial vehicles according to claim 1, is characterized in that: the method for judging the frequency hopping channel according to the amplitude and frequency information comprises the following steps: when the signal amplitude is larger than the set amplitude threshold, the occurrence of a frequency hopping signal is judged, M-point smooth filtering is carried out on the obtained value, then the maximum value and the occurrence frequency of the filtered signal are compared with the set amplitude threshold and the set frequency threshold, and when the maximum value of the signal is larger than the set amplitude threshold and the occurrence probability is smaller than the set frequency threshold, the frequency hopping channel is judged.
5. The method for efficiently identifying the flight control signals of the low and small slow unmanned aerial vehicles according to claim 1, is characterized in that: and secondly, when the key features are extracted, an improved envelope extraction method based on signal complex modulation and low-pass filtering is adopted, and the spectral symmetry features of the signals are decomposed by combining an empirical mode decomposition method.
6. The method for efficiently identifying the flight control signals of the low and small slow unmanned aerial vehicles according to claim 1, is characterized in that: step three, the method for performing fusion optimization on the features comprises the following steps: and straightening and combining the various kinds of feature vectors into a single feature vector through a D-S evidence algorithm, and then carrying out normalization processing on the single feature vector to form new features after fusion optimization.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711400796.XA CN108280395B (en) | 2017-12-22 | 2017-12-22 | Efficient identification method for flight control signals of low-small-slow unmanned aerial vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711400796.XA CN108280395B (en) | 2017-12-22 | 2017-12-22 | Efficient identification method for flight control signals of low-small-slow unmanned aerial vehicle |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108280395A CN108280395A (en) | 2018-07-13 |
| CN108280395B true CN108280395B (en) | 2021-12-17 |
Family
ID=62802135
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711400796.XA Active CN108280395B (en) | 2017-12-22 | 2017-12-22 | Efficient identification method for flight control signals of low-small-slow unmanned aerial vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108280395B (en) |
Families Citing this family (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109243486A (en) * | 2018-09-13 | 2019-01-18 | 西安电子科技大学 | A kind of winged acoustic detection method of cracking down upon evil forces based on machine learning |
| CN109375204B (en) * | 2018-10-26 | 2021-04-13 | 中电科思仪科技股份有限公司 | Target detection method, system, equipment and medium based on radar |
| CN109669170B (en) * | 2018-12-12 | 2021-03-23 | 北航（四川）西部国际创新港科技有限公司 | Method for reducing false alarm rate of signal detection system of unmanned aerial vehicle |
| CN110084094B (en) * | 2019-03-06 | 2021-07-23 | 中国电子科技集团公司第三十八研究所 | Unmanned aerial vehicle target identification and classification method based on deep learning |
| CN110991531A (en) * | 2019-12-02 | 2020-04-10 | 中电科特种飞机系统工程有限公司 | Training sample library construction method, device and medium based on air-to-ground small and slow target |
| CN111817794B (en) * | 2020-05-29 | 2021-04-13 | 中南民族大学 | Multi-domain cooperative unmanned aerial vehicle detection method and system based on deep learning |
| CN111652183B (en) * | 2020-06-19 | 2022-03-29 | 桂林电子科技大学 | Unmanned aerial vehicle detection and identification method based on image-transmission signal multi-feature fusion |
| CN111709385B (en) * | 2020-06-22 | 2023-07-25 | 电子科技大学 | A low, small and slow aircraft target detection system and its identification method |
| CN111935044B (en) * | 2020-08-20 | 2021-03-09 | 金陵科技学院 | PSK (phase Shift keying) and QAM (Quadrature amplitude modulation) signal modulation identification method based on EMD (empirical mode decomposition) |
| CN114169367A (en) * | 2021-11-25 | 2022-03-11 | 成都大公博创信息技术有限公司 | Low-slow and small UAV identification method and system based on deep learning |
| CN114111456B (en) * | 2021-11-25 | 2023-05-09 | 北京睿空未来信息技术有限公司 | Unmanned aerial vehicle defense system for power transformer substation and important facilities |
| CN115859056B (en) * | 2022-12-29 | 2023-09-15 | 华诺星空技术股份有限公司 | Unmanned aerial vehicle target detection method based on neural network |
| CN118468125B (en) * | 2024-05-15 | 2025-03-11 | 哈尔滨工程大学 | Channel-DeepIQ-based radar signal intelligent detection model construction method, radar signal intelligent detection method, computer equipment and storage medium |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104950906A (en) * | 2015-06-15 | 2015-09-30 | 中国人民解放军国防科学技术大学 | Unmanned aerial vehicle remote measuring and control system and method based on mobile communication network |
| CN105516031A (en) * | 2015-12-18 | 2016-04-20 | 北京航空航天大学 | Channel estimation and channel equalization method of fast frequency hopping system |
| CN105550636A (en) * | 2015-12-04 | 2016-05-04 | 中国电子科技集团公司第三研究所 | Method and device for identifying target types |
| CN105912980A (en) * | 2016-03-31 | 2016-08-31 | 深圳奥比中光科技有限公司 | Unmanned plane and unmanned plane system |
| CN105929845A (en) * | 2016-05-18 | 2016-09-07 | 中国计量大学 | Unmanned aerial vehicle network-based river channel cruise system and cruise method |
| CN106452716A (en) * | 2016-11-15 | 2017-02-22 | 厦门大学 | Unmanned aerial vehicle signal recognition and detection algorithm based on Hash fingerprint |
| CN106714166A (en) * | 2016-12-23 | 2017-05-24 | 成都赫尔墨斯科技有限公司 | Anti-UAV method based on user authentication |
| CN106788480A (en) * | 2017-03-20 | 2017-05-31 | 上海资誉电子科技有限公司 | The winged control signal testing method and system of unmanned plane |
| CN106959753A (en) * | 2017-03-21 | 2017-07-18 | 西安交通大学 | Unmanned plane dummy control method and system based on Mental imagery brain-computer interface |
| CN107231427A (en) * | 2017-06-19 | 2017-10-03 | 中国人民解放军理工大学 | MAC protocol recognition methods based on SVMs |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8867418B2 (en) * | 2013-02-17 | 2014-10-21 | Parallel Wireless, Inc. | Methods of incorporating an ad hoc cellular network into a fixed cellular network |
| CN108353081B (en) * | 2015-09-28 | 2021-01-19 | 13部门有限公司 | Device and method for detecting and confronting remote-controlled vehicle and storage medium |
-
2017
- 2017-12-22 CN CN201711400796.XA patent/CN108280395B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104950906A (en) * | 2015-06-15 | 2015-09-30 | 中国人民解放军国防科学技术大学 | Unmanned aerial vehicle remote measuring and control system and method based on mobile communication network |
| CN105550636A (en) * | 2015-12-04 | 2016-05-04 | 中国电子科技集团公司第三研究所 | Method and device for identifying target types |
| CN105516031A (en) * | 2015-12-18 | 2016-04-20 | 北京航空航天大学 | Channel estimation and channel equalization method of fast frequency hopping system |
| CN105912980A (en) * | 2016-03-31 | 2016-08-31 | 深圳奥比中光科技有限公司 | Unmanned plane and unmanned plane system |
| CN105929845A (en) * | 2016-05-18 | 2016-09-07 | 中国计量大学 | Unmanned aerial vehicle network-based river channel cruise system and cruise method |
| CN106452716A (en) * | 2016-11-15 | 2017-02-22 | 厦门大学 | Unmanned aerial vehicle signal recognition and detection algorithm based on Hash fingerprint |
| CN106714166A (en) * | 2016-12-23 | 2017-05-24 | 成都赫尔墨斯科技有限公司 | Anti-UAV method based on user authentication |
| CN106788480A (en) * | 2017-03-20 | 2017-05-31 | 上海资誉电子科技有限公司 | The winged control signal testing method and system of unmanned plane |
| CN106959753A (en) * | 2017-03-21 | 2017-07-18 | 西安交通大学 | Unmanned plane dummy control method and system based on Mental imagery brain-computer interface |
| CN107231427A (en) * | 2017-06-19 | 2017-10-03 | 中国人民解放军理工大学 | MAC protocol recognition methods based on SVMs |
Non-Patent Citations (3)
| Title |
|---|
| "Drone Classification Using Convolutional Neural Networks With Merged Doppler Images";Byung Kwan Kim;《IEEE Geoscience & Remote Sensing Letters》;20161118;第14卷(第1期);第38-42页 * |
| "四旋翼无人机防冲突系统设计";王永升;《中国优秀硕士学位论文全文数据库 工程科技II辑》;20170315(第03期);第C031-1485页 * |
| "无人机自动识别、定位和压制系统";R&S罗德与施瓦茨中国;《https://news.eeworld.com.cn/mp/rs/a83144.jspx》;20161107;第1-4页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108280395A (en) | 2018-07-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108280395B (en) | Efficient identification method for flight control signals of low-small-slow unmanned aerial vehicle | |
| Basak et al. | Combined RF-based drone detection and classification | |
| Ozturk et al. | RF-based low-SNR classification of UAVs using convolutional neural networks | |
| Zhao et al. | Classification of small UAVs based on auxiliary classifier Wasserstein GANs | |
| CN110084094B (en) | Unmanned aerial vehicle target identification and classification method based on deep learning | |
| CN107015205B (en) | False target elimination method for distributed MIMO radar detection | |
| CN109270497B (en) | Multidimensional parameter pre-sorting method for radar pulse signals | |
| CN110334591A (en) | A UAV Frequency Hopping Signal Detection and Recognition Method Based on Cluster Analysis | |
| CN111709329B (en) | Unmanned aerial vehicle measurement and control signal high-speed recognition method based on deep learning | |
| CN116866129A (en) | Wireless communication signal detection method | |
| CN105259541A (en) | Method of confronting active deception jamming by multi-station radar | |
| CN102879767A (en) | Detection method of interference target for space-time adaptive processing | |
| CN119179055A (en) | Unmanned aerial vehicle detection method based on frequency modulation continuous wave radar | |
| Sinha et al. | Estimation of Doppler profile using multiparameter cost function method | |
| CN109669170B (en) | Method for reducing false alarm rate of signal detection system of unmanned aerial vehicle | |
| CN113608193A (en) | Radar multi-target distance and speed estimation method based on UNet | |
| CN117421543A (en) | Flight target recognition system based on intelligent group cooperation | |
| Xu et al. | Radar modulation recognition of intra-pulse overlapping signals based on object detection | |
| CN107589409B (en) | Distributed low-traffic detection fusion method for MIMO radar with separate antennas | |
| CN106019250A (en) | Repeating false target discriminating method based on angular glint | |
| CN111339816B (en) | Multi-unmanned aerial vehicle radio frequency signal identification method based on wavelet neural network | |
| CN113534132A (en) | Adaptive unmanned aerial vehicle direction of arrival estimation method | |
| CN117572091B (en) | Airborne detection high-performance miniaturized alarm system | |
| Yang et al. | SNR estimation of UAV control signal based on convolutional neural network | |
| Wang et al. | Research on UAV remote control signal recognition based on time-frequency map |
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 |