CN112152731A - Fractal dimension-based unmanned aerial vehicle detection and identification method - Google Patents
Fractal dimension-based unmanned aerial vehicle detection and identification method Download PDFInfo
- Publication number
- CN112152731A CN112152731A CN202010932316.XA CN202010932316A CN112152731A CN 112152731 A CN112152731 A CN 112152731A CN 202010932316 A CN202010932316 A CN 202010932316A CN 112152731 A CN112152731 A CN 112152731A
- Authority
- CN
- China
- Prior art keywords
- unmanned aerial
- aerial vehicle
- signal
- signals
- fractal dimension
- 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.)
- Granted
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B17/00—Monitoring; Testing
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B64—AIRCRAFT; AVIATION; COSMONAUTICS
- B64C—AEROPLANES; HELICOPTERS
- B64C39/00—Aircraft not otherwise provided for
- B64C39/02—Aircraft not otherwise provided for characterised by special use
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B1/00—Details of transmission systems, not covered by a single one of groups H04B3/00 - H04B13/00; Details of transmission systems not characterised by the medium used for transmission
- H04B1/0003—Software-defined radio [SDR] systems, i.e. systems wherein components typically implemented in hardware, e.g. filters or modulators/demodulators, are implented using software, e.g. by involving an AD or DA conversion stage such that at least part of the signal processing is performed in the digital domain
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- Electromagnetism (AREA)
- Aviation & Aerospace Engineering (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention discloses an unmanned aerial vehicle detection and identification method based on fractal dimension, which belongs to the technical field of unmanned aerial vehicle detection, comprises a signal receiving module and a signal processing module, is suitable for the field of unmanned aerial vehicle detection and classification identification, and has the main ideas as follows: a software radio frequency sub-board is connected with a 2.4GHz directional antenna to receive wireless signals; judging whether the amplitude of the received signal is stably larger than a preset threshold value or not to detect the unmanned aerial vehicle signal, if so, carrying out Haar wavelet transform on the signal and extracting an effective unmanned aerial vehicle signal, calculating the fractal dimension of the unmanned aerial vehicle signal to serve as the characteristic fingerprint of the unmanned aerial vehicle device, and finally carrying out classification and identification on the unmanned aerial vehicle by using a classification and identification algorithm.
Description
Technical Field
The invention belongs to the field of unmanned aerial vehicle detection and identification, and particularly provides an unmanned aerial vehicle detection and identification method.
Background
Present society, civilian unmanned aerial vehicle have obtained the wide application, when bringing convenience for the society, also become more gradually by the unexpected injury that unmanned aerial vehicle out of control caused, consequently, need a mechanism to detect the discernment to unmanned aerial vehicle, distinguish out illegal unmanned aerial vehicle, improve management and control efficiency.
The current unmanned aerial vehicle detection methods mainly comprise radar detection, audio detection, video detection, infrared detection and the like. The radar detection method is to utilize radar scanning technology, and the reflection wave phenomenon that produces when the electromagnetic wave passes through different transmission media realizes the detection to unmanned aerial vehicle, but this technique has higher equipment requirement, and the cost is great to unmanned aerial vehicle scattering area is less, is difficult for surveying. The audio frequency is surveyed and is utilized when unmanned aerial vehicle flies, and its motor work and the "audio frequency fingerprint" that rotor vibrations produced come discernment unmanned aerial vehicle. The video detection is to acquire unmanned aerial vehicle images by using a high-definition camera and match the images with a database to finish unmanned aerial vehicle detection. The infrared detection is to detect the unmanned aerial vehicle by using the thermal infrared reflection of a target and adopting an infrared thermal imager sensor combination. However, when audio detection, video detection and infrared detection are used, the environment interference is large, and when the environment is severe, the identification accuracy is not high.
The fractal dimension-based unmanned aerial vehicle detection and identification technology provided by the invention has the advantages of simple equipment and high identification precision. The fractal dimension is the similarity of a part to the whole to some extent (form, structure, time, energy, etc.), and can quantitatively describe the degree of signal nonuniformity and distinguish weak differences of signals. It breaks the simple and complex, chaotic and regular, whole and partial, ordered and disordered constraints and provides possibility for signal classification. Therefore, unmanned aerial vehicle detection and identification based on fractal dimension have great feasibility, and therefore the control efficiency of the unmanned aerial vehicle can be improved.
Disclosure of Invention
The invention aims to provide an unmanned aerial vehicle detection and identification method based on fractal dimension, which can effectively solve the problems of complex system and low identification efficiency of unmanned aerial vehicle detection and identification equipment at present.
The invention provides the following technical scheme:
an unmanned aerial vehicle detection and identification method based on fractal dimension comprises the following steps:
and the signal receiving module is connected with the 2.4GHz directional antenna through the software radio sub-board to acquire wireless signals.
The signal processing module carries out analysis processes to the wireless signal of storage, at first realizes unmanned aerial vehicle's detection, secondly draws the fractal dimension of unmanned aerial vehicle signal as unmanned aerial vehicle's characteristic fingerprint, carries out classification to unmanned aerial vehicle at last.
An unmanned aerial vehicle detection and identification method based on fractal dimension comprises the following steps:
And 2, analyzing and processing the signals obtained in the step 1, taking the maximum value of the amplitude of the signals in the environment without the unmanned aerial vehicle as a threshold value sigma, and if the amplitude of the received signals is stably larger than the preset threshold value sigma, taking the signals as the signals of the unmanned aerial vehicle to finish the detection of the unmanned aerial vehicle.
And 3, performing one-dimensional discrete Haar wavelet transform on the unmanned aerial vehicle signal obtained in the step 2, wherein the signal subjected to the Haar wavelet transform can not only keep the waveform characteristics of the original signal, but also reduce the data volume and the calculation amount. And finally, removing the part which is lower than the threshold value sigma in the signal after the wavelet transformation to obtain an effective unmanned aerial vehicle signal.
And 4, acquiring data based on the effective unmanned aerial vehicle signals obtained in the step 3, and dividing the data into an off-line stage and an on-line stage. An off-line stage: extracting fractal dimension characteristics of signals of the unmanned aerial vehicle by using a Higuchi algorithm, and storing the extracted fractal dimension characteristic data and a label representing the type of the unmanned aerial vehicle as training data; an online stage: and (4) extracting the fractal dimension characteristics of the effective unmanned aerial vehicle signals obtained in the step (3), and storing the fractal dimension characteristics as test data.
And 5, based on the training data and the test data obtained in the step 4, carrying out classification and identification on the unmanned aerial vehicle by using a K nearest neighbor algorithm.
Preferably, the Higuchi algorithm of the feature extraction algorithm includes the following steps:
s1: extracting a limited period of drone signal timeThe sequence is as follows: y (1), y (2), …, y (i), …, y (N), where i ═ 1,2, …, N are the number of points in the time series. From this sequence, a new drone signal time sequence y (m, k) { y (m), y (m + k), y (m +2k).. y (m + [ (N-m)% k) is constructed]K), where m is 1,2, …, k, k is 1,2, …, kmaxM represents the initial time, and k represents the interval time.
S2: based on y (m, k) in S1, the length of each curve in y (m, k) is calculated
Where N is the total length of the data sequence, N-1/[ (N-m)% k]K represents the curve length Lm(k) The normalization factor of (1).
S3: calculate the average length per k curves
Where k is 1,2, …, kmax
S4: if L (k). varies.. k-FDAnd then, the curve is a fractal curve with the dimension being FD, at this time, the relation curve of ln (L (k)) and ln (k) should be distributed on a straight line with the slope being FD, and the FD value is calculated by a least square linear best fitting method, that is, the fractal dimension characteristic of the unmanned aerial vehicle signal is successfully extracted.
Preferably, the K nearest neighbor algorithm of the classification and identification algorithm of the unmanned aerial vehicle includes the following steps:
s1: and loading the training data X and the test data Y of the unmanned aerial vehicle, and designating the value of K as K.
S2: based on the data X and Y of S1, the data is normalized to obtain new training data X 'and new test data Y', where the normalization formula is T '═ T-minT)/(maxT-minT), where T is the original data, T' is the data after T normalization, and maxT and minT are the maximum and minimum values in T, respectively.
S3: based on the data X 'and Y' in S2, the data Y in Y 'is selected, and the data X from Y to X' is calculatediOf Euclidean distance diWhere i ═ n (1, 2,. n), n is the total number of data in X'.
S4: based on Euclidean distance d obtained in S3iTo d is pairediSorting in ascending order to obtainSet of distances D ═ D1，d2，…，dn) And n is the total number of data in X'.
S5: based on the distance D in S4, the first k euclidean distances in D are selected to correspond to the data points X "in the training data X', respectively.
S6: based on the data x ″ in S5, the class label with the highest frequency of occurrence in x ″ is set as the class of the test data Y, and the recognition rate is maximized by testing different K values, where K is the optimal K value. And taking the obtained result label as the category of the unmanned aerial vehicle to be tested, namely completing the classification and identification of the unmanned aerial vehicle.
Advantageous effects
The invention has the beneficial effects that: firstly, a software radio frequency sub-board is connected with a 2.4GHz directional antenna to receive wireless signals with different frequency points from 2.412GHz to 2.472GHz, and the received signals are preprocessed; detecting the unmanned aerial vehicle signal by comparing whether the amplitude of the received signal is stably larger than a preset threshold value sigma; performing Haar wavelet transform on the signals, extracting effective unmanned aerial vehicle signals, and extracting signal fractal dimension by using a Higuchi algorithm to serve as the equipment characteristics of the unmanned aerial vehicle; and finally, using a K nearest neighbor algorithm to realize the classification and identification of the unmanned aerial vehicle. The fractal dimension features extracted in the invention can distinguish weak differences of signals, thereby realizing classification and identification of different unmanned aerial vehicles. The Euclidean distance is selected from the K nearest neighbor algorithm as a distance measurement mode, the recognition rate of the algorithm is made to be the highest by setting different K values, and the problems of complex system and low recognition efficiency in the existing unmanned aerial vehicle detection and recognition equipment are solved.
Drawings
FIG. 1 is a schematic flow chart of a method for detecting and identifying an unmanned aerial vehicle according to the present invention;
FIG. 2 is a schematic diagram of the Haar wavelet transform principle of the present invention;
Detailed Description
The invention will be further described with reference to the accompanying drawings in which:
the invention provides an unmanned aerial vehicle detection and identification method based on fractal dimension, which can be applied to an unmanned aerial vehicle detection and identification system, and the system specifically comprises the following steps: signal receiving module, signal processing module.
As shown in fig. 1, an unmanned aerial vehicle detection and identification method based on fractal dimension specifically includes the following steps:
And 2, analyzing and processing the signals obtained in the step 1, taking the maximum value of the amplitude of the signals in the environment without the unmanned aerial vehicle as a threshold value sigma, and if the amplitude of the received signals is stably larger than the preset threshold value sigma, taking the signals as the signals of the unmanned aerial vehicle to finish the detection of the unmanned aerial vehicle.
And 3, performing one-dimensional discrete Haar wavelet transform based on the unmanned aerial vehicle signal obtained in the step 2, wherein a schematic diagram (taking 2-level as an example) of the Haar wavelet transform is shown in FIG. 2: inputting unmanned aerial vehicle signal x [ n ]]In the first stage, the low-pass filters h [ n ] are passed]And a high-pass filter g n]Then down sampling is carried out to obtain detail coefficient d1[n]And approximation coefficient a1[n]In the second stage, a1[n]The detail coefficient d is obtained by performing the same processing as in the first stage as the input signal2[n]And approximation coefficient a2[n]Then a is2[n]I.e. the input signal x n]Output signal y [ n ] after 2-levelHaar wavelet transform]. The signals after Haar wavelet transform not only can keep the waveform characteristics of the original signals, but also can reduce the data volume, thereby reducing the calculation amount. And finally, removing the part which is lower than the threshold value sigma in the signal after the wavelet transformation to obtain an effective unmanned aerial vehicle signal.
And 4, collecting characteristic data based on the effective unmanned aerial vehicle signals obtained in the step 3, and specifically comprising the following steps: (1) extracting a finite time sequence of drone signals: y (1), y (2), …, y (i), …, y (N), where i ═ 1,2, …, N are the number of points in the time series. From this sequence, a new drone signal time sequence y (m, k) { y (m), y (m + k), y (m +2k).. y (m + [ (N-m)% k)]K), where m is 1,2, …, k, k is 1,2, …, kmaxM represents the initial time, and k represents the interval time. (2) Length of each curve in y (m, k)
Where N is the total length of the data sequence, N-1/[ (N-m)% k]K represents the curve length Lm(k) The normalization factor of (1). (3) Calculate the average length per k curves
Drawing a relation curve of ln (L) (k) and ln (k), and calculating the fractal dimension FD of the signal by using a least square linear best fitting method, wherein the value of the FD is the signal characteristic of the unmanned aerial vehicle. (5) And dividing the collected characteristic data into training data and testing data and storing the training data and the testing data respectively.
And 5, based on the unmanned aerial vehicle signal training data and the test data obtained in the step 4, carrying out classification and identification on the unmanned aerial vehicle by using a K nearest neighbor algorithm. The method comprises the following specific steps: (1) and normalizing the data set to obtain new training data X 'and new test data Y', wherein the normalization formula is T '═ T-minT)/(maxT-minT), T is original data, T' is data after T normalization, and maxT and minT are respectively the maximum value and the minimum value in T. (2) Selecting data Y from the test data Y', calculating data X from Y to XiOf Euclidean distance diWhere i is (1, 2, … n), and n is the total number of data in X'. To diSorting in ascending order to obtain a distance set D ═ D1，d2，...，dn) And n is the total number of data in X'. (3) And selecting the first k Euclidean distances in D to respectively correspond to the data points X in the training set X ', taking the class label with the highest occurrence frequency in X' as the class of the test data Y, and testing different k values to enable the recognition rate to reach the highest value, wherein the k at the moment is the optimal k value. And taking the obtained result label as the category of the unmanned aerial vehicle to be tested, namely completing the classification and identification of the unmanned aerial vehicle.
Claims (2)
1. An unmanned aerial vehicle detection and identification method based on fractal dimension is characterized by comprising the following steps:
step 1, connecting a 2.4GHz directional antenna with a software wireless electronic board to acquire and store wireless signals.
And 2, analyzing and processing the signals obtained in the step 1, taking the maximum value of the amplitude of the signals in the environment without the unmanned aerial vehicle as a threshold value sigma, and if the amplitude of the received signals is stably larger than the preset threshold value sigma, taking the signals as the signals of the unmanned aerial vehicle to finish the detection of the unmanned aerial vehicle.
And 3, performing one-dimensional discrete Haar wavelet transform on the unmanned aerial vehicle signal obtained in the step 2, wherein the signal subjected to the Haar wavelet transform can not only keep the waveform characteristics of the original signal, but also reduce the data volume and the calculation amount. And finally, removing the part which is lower than the threshold value sigma in the signal after the wavelet transformation to obtain an effective unmanned aerial vehicle signal.
And 4, acquiring data based on the effective unmanned aerial vehicle signals obtained in the step 3, and dividing the data into an off-line stage and an on-line stage. An off-line stage: extracting fractal dimension characteristics of signals of the unmanned aerial vehicle by using a Higuchi algorithm, and storing the extracted fractal dimension characteristic data and a label representing the type of the unmanned aerial vehicle as training data; an online stage: and (4) extracting the fractal dimension characteristics of the effective unmanned aerial vehicle signals obtained in the step (3), and storing the fractal dimension characteristics as test data.
And 5, based on the training data and the test data obtained in the step 4, carrying out classification and identification on the unmanned aerial vehicle by using a K nearest neighbor algorithm.
2. An unmanned aerial vehicle detection and identification method based on fractal dimension is characterized in that a Higuchi algorithm in the step 4 specifically comprises the following steps:
s1: extracting a finite time sequence of drone signals: y (1), y (2), …, y (i), …, y (N), where i ═ 1,2, …, N are the number of points in the time series. From this sequence, a new drone signal time sequence y (m, k) { y (m), y (m + k), y (m +2k).. y (m + [ (N-m)% k) is constructed]K), where m is 1,2, …, k, k is 1,2, …, kmaxM represents the initial time, and k represents the interval time.
S2: based on y (m, k) in S1, the length of each curve in y (m, k) is calculated
Where N is the total length of the data sequence, N-1/[ (N-m)% k]K represents the curve length Lm(k) The normalization factor of (1).
S3: calculate the average length per k curves
Where k is 1,2, …, kmax
S4: if L (k). varies.. k-FDAnd then, the curve is a fractal curve with the dimension being FD, at this time, the relation curve of ln (L (k)) and ln (k) should be distributed on a straight line with the slope being FD, and the FD value is calculated by a least square linear best fitting method, that is, the fractal dimension characteristic of the unmanned aerial vehicle signal is successfully extracted.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010932316.XA CN112152731B (en) | 2020-09-08 | 2020-09-08 | Fractal dimension-based unmanned aerial vehicle detection and identification method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010932316.XA CN112152731B (en) | 2020-09-08 | 2020-09-08 | Fractal dimension-based unmanned aerial vehicle detection and identification method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112152731A true CN112152731A (en) | 2020-12-29 |
| CN112152731B CN112152731B (en) | 2023-01-20 |
Family
ID=73889422
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010932316.XA Active CN112152731B (en) | 2020-09-08 | 2020-09-08 | Fractal dimension-based unmanned aerial vehicle detection and identification method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112152731B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113593187A (en) * | 2021-07-26 | 2021-11-02 | 吉林大学 | Seismic oscillation abnormity sensing method for regional security |
| CN115225172A (en) * | 2022-06-28 | 2022-10-21 | 珠海云洲智能科技股份有限公司 | Method and device for detecting radio signal, control equipment and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160071529A1 (en) * | 2013-04-11 | 2016-03-10 | Nec Corporation | Signal processing apparatus, signal processing method, signal processing program |
| CN106646165A (en) * | 2016-12-23 | 2017-05-10 | 西安交通大学 | Method and system for classifying and positioning internal insulation defects of GIS |
| CN108353081A (en) * | 2015-09-28 | 2018-07-31 | 13部门有限公司 | Unmanned plane intrusion detection and confrontation |
| CN109165545A (en) * | 2018-07-05 | 2019-01-08 | 上海电机学院 | A kind of new signal characteristic extracting methods based on fractal dimension |
| CN110958199A (en) * | 2019-12-03 | 2020-04-03 | 上海电机学院 | Communication modulation signal identification method based on multi-dimensional feature extraction |
| CN111007871A (en) * | 2019-11-29 | 2020-04-14 | 厦门大学 | Unmanned aerial vehicle dynamic feature identification method, medium, equipment and device |
-
2020
- 2020-09-08 CN CN202010932316.XA patent/CN112152731B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160071529A1 (en) * | 2013-04-11 | 2016-03-10 | Nec Corporation | Signal processing apparatus, signal processing method, signal processing program |
| CN108353081A (en) * | 2015-09-28 | 2018-07-31 | 13部门有限公司 | Unmanned plane intrusion detection and confrontation |
| CN106646165A (en) * | 2016-12-23 | 2017-05-10 | 西安交通大学 | Method and system for classifying and positioning internal insulation defects of GIS |
| CN109165545A (en) * | 2018-07-05 | 2019-01-08 | 上海电机学院 | A kind of new signal characteristic extracting methods based on fractal dimension |
| CN111007871A (en) * | 2019-11-29 | 2020-04-14 | 厦门大学 | Unmanned aerial vehicle dynamic feature identification method, medium, equipment and device |
| CN110958199A (en) * | 2019-12-03 | 2020-04-03 | 上海电机学院 | Communication modulation signal identification method based on multi-dimensional feature extraction |
Non-Patent Citations (3)
| Title |
|---|
| BHARGAVI R等: ""Emotion Classification Using Single-Channel EEG"", 《2019 INTERNATIONAL CONFERENCE ON COMPUTING, POWER AND COMMUNICATION TECHNOLOGIES》 * |
| 严丹莉: ""基于通信信号指纹的无人机个体识别"", 《中国优秀博硕士学位论文全文数据库(硕士)》 * |
| 刘博翰: ""基于脑电信号的导联筛选及可解释情绪分类模型研究"", 《中国优秀博硕士学位论文全文数据库(硕士)》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113593187A (en) * | 2021-07-26 | 2021-11-02 | 吉林大学 | Seismic oscillation abnormity sensing method for regional security |
| CN115225172A (en) * | 2022-06-28 | 2022-10-21 | 珠海云洲智能科技股份有限公司 | Method and device for detecting radio signal, control equipment and storage medium |
| CN115225172B (en) * | 2022-06-28 | 2024-05-03 | 珠海云洲智能科技股份有限公司 | Method, device, control equipment and storage medium for detecting radio signal |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112152731B (en) | 2023-01-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112152731B (en) | Fractal dimension-based unmanned aerial vehicle detection and identification method | |
| CN108768562B (en) | Illegal unmanned aerial vehicle identification method based on remote control and image transmission signals | |
| CN111461037B (en) | End-to-end gesture recognition method based on FMCW radar | |
| US20100061630A1 (en) | Specific Emitter Identification Using Histogram of Oriented Gradient Features | |
| CN111488801A (en) | Ship classification method based on vibration noise identification | |
| CN112364768B (en) | Distributed optical fiber intrusion recognition method based on airspace characteristics and machine learning | |
| CN112367273A (en) | Knowledge distillation-based flow classification method and device for deep neural network model | |
| CN111144522A (en) | Power grid NFC equipment fingerprint authentication method based on hardware intrinsic difference | |
| CN111666848B (en) | Method, device and equipment for detecting arrival of transport vehicle and storage medium | |
| Zhang et al. | Vehicle classification based on feature selection with anisotropic magnetoresistive sensor | |
| CN110764152B (en) | Device and method for rapid detection and identification of unmanned aerial vehicle | |
| CN110599800A (en) | Parking lot parking space state monitoring system and monitoring method | |
| CN115508821A (en) | Multisource fuses unmanned aerial vehicle intelligent detection system | |
| Xun et al. | An experimental study towards driver identification for intelligent and connected vehicles | |
| CN115859078A (en) | Millimeter wave radar fall detection method based on improved Transformer | |
| CN111830321A (en) | Unmanned aerial vehicle detection and identification method based on radio frequency fingerprint | |
| US9354265B2 (en) | Vehicle identification system and method | |
| CN112883895A (en) | Illegal electromagnetic signal detection method based on self-adaptive weighted PCA and realization system thereof | |
| CN111652063A (en) | Gray level stacking chart identification method of ground penetrating radar | |
| CN112162271A (en) | Vehicle type recognition method of microwave radar under multiple scenes | |
| CN116894223A (en) | Airborne underwater anomaly detection method based on self-adaptive cancellation and ResNet neural network | |
| CN108549076B (en) | Method for identifying scenes of various unmanned aerial vehicles based on velocity and rhythm diagram | |
| CN114565841A (en) | Vehicle type recognition method based on image processing | |
| CN114137518A (en) | Radar high-resolution range profile open set identification method and device | |
| CN113033396A (en) | Variable frequency pipeline ball passing indicating device based on feature fusion and ball passing detection method |
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 |