CN112884003A - Radar target sample expansion generation method based on sample expander - Google Patents
Radar target sample expansion generation method based on sample expander Download PDFInfo
- Publication number
- CN112884003A CN112884003A CN202110060821.4A CN202110060821A CN112884003A CN 112884003 A CN112884003 A CN 112884003A CN 202110060821 A CN202110060821 A CN 202110060821A CN 112884003 A CN112884003 A CN 112884003A
- Authority
- CN
- China
- Prior art keywords
- sample
- target
- radar
- expansion
- processing
- 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
- 238000000034 method Methods 0.000 title claims abstract description 51
- 238000012545 processing Methods 0.000 claims abstract description 45
- 238000005094 computer simulation Methods 0.000 claims abstract description 20
- 238000005070 sampling Methods 0.000 claims abstract description 12
- 238000001228 spectrum Methods 0.000 claims abstract description 9
- 238000013519 translation Methods 0.000 claims abstract description 8
- 238000003672 processing method Methods 0.000 claims description 13
- 238000004088 simulation Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000007792 addition Methods 0.000 claims description 3
- 238000012217 deletion Methods 0.000 claims description 3
- 230000037430 deletion Effects 0.000 claims description 3
- 238000013461 design Methods 0.000 claims description 3
- 238000012986 modification Methods 0.000 claims description 3
- 230000004048 modification Effects 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 238000004422 calculation algorithm Methods 0.000 claims description 2
- 230000010354 integration Effects 0.000 claims 1
- 238000005516 engineering process Methods 0.000 description 6
- 238000002592 echocardiography Methods 0.000 description 4
- 238000010801 machine learning Methods 0.000 description 4
- 238000011161 development Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000003190 augmentative effect Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000010287 polarization Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
Images
Classifications
-
- 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
- G06F18/2148—Generating training patterns; Bootstrap methods, e.g. bagging or boosting characterised by the process organisation or structure, e.g. boosting cascade
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The invention discloses a radar target sample expansion generating method based on a sample expander, and provides a radar target sample expansion method, which comprises the following steps: firstly, a radar target sample expander is constructed, the expander integrates methods such as distance image and modulation spectrum signal simulation modeling, noise superposition, pulse adjustment, variable sampling, signal translation, generation of a countermeasure network and the like, four sample expansion modes represented by simulation modeling, parameter adjustment, generation of countermeasures and comprehensive treatment are designed, and multiple means are provided for radar target sample expansion; then calculating to obtain an available processing mode according to input radar parameters, target parameters and sample information, and setting the number of samples to be generated and a sample expansion mode; and finally, calling different methods according to the processing mode, automatically expanding and generating the sample, obtaining sample data under different target parameters and different radar parameters, and providing data support for target identification.
Description
Technical Field
The method is applied to the field of radar target identification.
Technical Field
With the continuous progress of radar technology, radar signal parameters are changeable and waveforms are various, and rich characteristic information of a target can be extracted, so that target identification based on radar becomes possible. The radar target identification technology also becomes one of research hotspots in academic and engineering circles, and is an important support technology of an intelligent weapon system. If the size of the target is larger than the radar range resolution, the echo strengths of the radar echoes on different range units are different; the high-resolution range profile of the target is just the vector sum amplitude waveform of the projection of the target scattering point sub-echo on the radar ray acquired by using the broadband radar signal, reflects the fine geometric structural characteristics of the target on the radar sight line, and is very valuable for target identification and classification. Some targets, especially aerial targets, have periodic rotational motion while moving, and within a certain range of attitude angles of the targets, the micro motion causes doppler modulation in radar echoes, and the characteristics are studied in the document "Chen, v.c. radar micro doppler effect [ M ]. electronic industry press, 2013: 92-108", which can be used for target identification. The two common radar target identification technologies are established on the basis of radar echo data, and template matching is carried out by establishing a sample library during identification so as to identify a target; with the development of machine learning, a data-driven neural network brings new development to radar target identification, a large number of data samples are used for training, and a model is constructed for target identification. Both template matching and machine learning are not separated from reliable and valid radar target data and samples.
The method is limited by the influence of multiple factors such as environment, equipment, opportunity and the like, the data acquisition capability under non-ideal and unconventional conditions is limited, and the data often does not have completeness and scale; the amount of data samples actually accumulated is far from meeting the requirements of deep learning on training data. The key problem is how to utilize limited data, even a small amount of data, to mine the value and realize the traditional large-scale data machine learning function. Currently, sample expansion techniques have become one direction in the field of identification. Related research mainly focuses on expansion and transformation of pictures, for example, patent "an image processing method for expanding a data set under a small sample", CN201811087771.3, 2019-02-12 "discloses an image processing method for expanding a data set under a small sample, the expansion and generation of radar target samples are relatively less, more simulation modeling is performed, and the sample expansion technology for radar target identification is less. Parameters such as radar and targets are comprehensively considered, a multi-mode radar target data processing method is researched, sample data under different parameter conditions are generated, the problem of radar target data expansion can be solved, and the method has important significance for further radar target classification and identification.
Disclosure of Invention
The invention provides a radar target sample expansion generation method based on a sample expander, which enriches the number of samples and provides data support for target identification and machine learning.
The solution for realizing the invention is as follows: aiming at the problems of difficult data acquisition and small quantity in the process of identifying a radar target by a broadband one-dimensional image and a narrowband modulation spectrum of the target, the method provided by the invention provides a radar target sample expansion method, which comprises the following steps:
step 1: constructing a sample expander, wherein the sample expander consists of an input parameter layer, a method model layer, a processing mode layer and an output sample layer, integrating methods such as distance image and modulation spectrum signal simulation modeling, noise superposition, pulse adjustment, variable sampling and signal translation, generating a countermeasure network and the like, and designing four processing modes such as simulation modeling, parameter adjustment, countermeasure generation and comprehensive processing;
step 2: inputting radar parameters, target parameters or target samples;
and step 3: automatically analyzing and calculating to obtain an available sample expansion mode according to the input quantity and parameters of the sample expander;
and 4, step 4: selecting a mode, judging whether the mode is selectable according to the expansion processing mode of the available samples calculated in the step 3, and if not, ending the processing or selecting the mode again;
and 5: setting expansion parameters of a target sample, namely setting the number N of expansion samples and parameters of a processing method;
step 6: carrying out sample expansion generation, and processing by applying different methods according to different processing modes;
and 7: and expanding to obtain N samples, and outputting the samples to obtain a sample library.
Finally, sample generation and expansion under the condition of adding different target parameters and different radar parameters are realized, the problem of radar target data expansion is solved, and basic data support is provided for radar target identification.
The sample expander machine structure provided by the invention integrates four processing modes of multiple methods, can meet the expansion requirements of different radar target sample data, and has a wide application range. Compared with the traditional radar target sample acquisition means, the method has the following remarkable advantages:
1. the sample acquisition efficiency is high, and the sample acquisition is not restricted by equipment state conditions;
2. by the multi-method combined sample expansion technology, not only can the target sample detected by the current equipment be enriched, but also the target sample under different radar technical parameters can be obtained by expansion, and the sample data contains more characteristic information;
3. the processing flow is simple, only input parameters need to be concerned, the sample is automatically generated, and repeated parameter adjustment is not needed.
The invention can effectively expand the information of the interested target and provide data support for further target identification.
The present invention is described in further detail below with reference to the attached drawing figures.
Drawings
FIG. 1 is a block diagram of a sample expander architecture.
FIG. 2 is a block diagram of a radar target sample expansion flow.
Fig. 3 is a schematic of the sample generation results.
Detailed Description
The specific implementation method of the invention is as follows:
step 1: constructing a sample expander, wherein the sample expander consists of an input parameter layer, a method model layer, a processing mode layer and an output sample layer, integrating methods such as distance image and modulation spectrum signal simulation modeling, noise superposition, pulse adjustment, variable sampling and signal translation, generating a countermeasure network and the like, and designing four processing modes such as simulation modeling, parameter adjustment, generation countermeasure and comprehensive processing, which are shown in the attached figure 1;
the sample expander adopts a four-layer expandable hierarchical structure, and the input parameter layer obtains sample expansion parameters and sample data to provide data for further calculation processing; the method model layer can integrate and expand the sample processing method and support modifying, adding and deleting the method model; the processing mode layer calls a method model layer algorithm and a method to perform sample expansion calculation according to the mode design rule, and supports modification, addition and deletion of processing modes; outputting a sample layer to obtain a final expanded sample result; each layer can be adjusted and configured according to the business needs and the sample expansion requirements.
Step 2: inputting radar parameters, target parameters or target samples; the radar parameters comprise carrier frequency, repetition frequency, pulse width, bandwidth, polarization mode and signal waveform; the target parameters comprise motion characteristics, structural characteristics, scattering characteristics, micromotion information and material, and the radar target sample mainly comprises a target range profile, video data in a modulation spectrum and a characteristic sequence;
and step 3: and analyzing and calculating to obtain an available sample expansion processing mode according to the input quantity and the parameters of the sample expander. Further, the available processing pattern analysis calculation method is as follows:
3.1: if no target parameter or radar parameter is input, a simulation modeling mode cannot be used;
3.2: if no radar target sample data is input, the generated countermeasure mode cannot be used;
3.3: if radar parameters, target parameters and sample data are input, four processing modes of simulation modeling, parameter adjustment, generation countermeasure and comprehensive processing can be used;
and 4, step 4: selecting a mode, judging whether the mode is selectable according to the expansion processing mode of the available samples calculated in the step 3, and if not, ending the processing or selecting the mode again;
and 5: setting expansion parameters of a target sample, setting the number of the expansion samples and parameters of a processing method;
step 6: and carrying out sample expansion generation. Further, in different modes, the specific method of sample expansion is as follows:
step 6.1: if simulation modeling is selected, the basic processing method is as follows:
step 6.1.1: aiming at the broadband range profile simulation of a target, a target scattering model is constructed, so that radar echoes are simulated, and echo vector sums are obtained;
according to the scattering point model, the echoes of the targets in range unit i are:
Niis the number of scattering points of the object within the distance, σinIs the echo emphasis of the nth scattering point in the range unit i, riIs the scattering point range radar distance.
The range profile is represented as: ([ | X (1) |, | X (2) |. |)]T。
And acquiring one-dimensional target image simulation data according to the radar parameters and the target scattering model.
Step 6.1.1: aiming at the narrow-band modulation spectrum simulation of a target, acquiring a main echo component and micro-motion modulation information of the target by using micro-motion parameters of the target; and constructing a coordinate system taking the target as a center, modeling to obtain the motion information of the target, and further obtaining the target echo. Taking a helicopter as an example, the echo model complex envelope of the N blades is as follows:
wherein n ismNumber of blades of mth rotary member, ωrmFor the m-th rotating part, the length from the root of the blade to the center of the rotor is L1mThe length from the top of the blade to the center of the rotor is L2mEffective blade length of L1m－L1m. Beta 'beta, perpendicular beta' pi/2-beta, theta when the plane of rotation is parallel to the direction of flightkm＝θ0m+2πk/nm，θ0mIs the initial phase angle of the m-th rotating component blade.
Frequency domain characteristics of ideal JEM:
wherein if the blade is a double blade, q ism1, otherwise, qm＝2。
Thus, obtaining radar target modulation spectrum sample data;
step 6.2: if parameter adjustment is selected, the basic processing method is as follows:
echo information under different conditions is obtained by methods of noise superposition, pulse length adjustment, pulse frequency sampling setting, signal translation and the like, so that samples are expanded.
Noise superposition: by adding different degrees of noise, multiple groups of samples are obtained, for example, appropriate signal-to-noise ratio can be set to superpose white gaussian noise: n is S/(10)σ/10)；
Adjusting the pulse length: the number of pulses affects the spectral resolution, and different numbers of pulses are obtained by a truncation method;
pulse frequency sampling setting: different sampling frequencies can be set, and different data can be obtained by sparse sampling or interpolation;
signal translation: and circularly shifting the samples to perform sample transformation.
Step 6.3: if generation of the countermeasure is selected, the basic processing method is as follows:
and constructing a generation countermeasure network based on the input target sample data, generating a radar target sample by using the discrimination model D and the generation model G, and outputting radar target data.
Step 6.4: if comprehensive processing is selected, joint processing is carried out by utilizing various methods in modes such as simulation modeling, parameter adjustment, generation countermeasure and the like, and the basic processing method is as follows:
step 6.4.1: distributing the sample numbers expanded by the method in the simulation modeling, parameter adjustment, generated countermeasure mode according to the requirement of the expansion number of the radar sample data in the step 5 according to a certain proportion, and determining that the sample numbers expanded by the method in the simulation modeling, parameter adjustment, generated countermeasure mode are N1, N2 and N3 respectively, wherein N is N1+ N2+ N3; step 6.4.2: according to the result of the sample expansion quantity distribution in the step 6.4.1, carrying out the processing in the steps 6.1 and 6.2 to obtain a sample data set S1; then, taking the data set S1 and the original data as input, and carrying out the processing of step 6.3 to obtain a sample set S2; finally obtaining an output sample set S-S1 + S2;
and 7, expanding N samples, outputting the samples to obtain a sample library, and realizing target sample acquisition under the conditions of different radar parameters and different target types, thereby solving the problem of sample shortage. FIG. 3 shows sample data augmented by simulation and parameter tuning.
Claims (4)
1. A radar target sample expansion generation method based on a sample expander is characterized by comprising the following steps:
step 1: constructing a sample expander, wherein the sample expander consists of an input parameter layer, a method model layer, a processing mode layer and an output sample layer, integrates distance image and modulation spectrum signal simulation modeling, noise superposition, pulse adjustment, variable sampling and signal translation, generates a countermeasure network method, and designs four processing modes of simulation modeling, parameter adjustment, generation countermeasure and comprehensive processing;
step 2: inputting radar parameters, target parameters or target samples;
and step 3: automatically analyzing and calculating to obtain an available sample expansion processing mode according to the input quantity and parameters of the sample expander;
and 4, step 4: selecting a mode, and judging whether the mode is selectable according to the available sample expansion processing mode, if not, ending the processing or selecting the mode again;
and 5: setting expansion parameters of a target sample, namely setting the number N of expansion samples and parameters of a processing method;
step 6: carrying out sample expansion generation, and processing by applying different methods according to different processing modes;
and 7: and expanding to obtain N samples, and outputting the samples to obtain a sample library.
2. The method of claim 1, wherein the sample expander-based radar target sample expansion generation method comprises: the sample expander adopts a four-layer expandable hierarchical structure, the input parameter layer obtains sample expansion parameters and sample data, the method model layer can carry out sample processing method integration and expansion, and supports modification, addition and deletion method models, the processing mode layer calls a method model layer algorithm and a method to carry out sample expansion calculation according to mode design rules, supports modification, addition and deletion processing modes, outputs the sample layer to obtain a final expanded sample result, and each layer can be adjusted and configured according to business needs and sample expansion requirements.
3. The method of claim 1, wherein the sample expander-based radar target sample expansion generation method comprises: aiming at the radar sample expansion requirements under different conditions, the requirements of different processing modes on input parameters are analyzed, and the available processing modes are automatically calculated according to the types of the input parameters: if no target parameter or radar parameter is input, no simulation modeling mode exists; if no radar target sample data is input, the generated countermeasure mode cannot be used; if radar parameters, target parameters and sample data are input, four processing modes of simulation modeling, parameter adjustment, generation countermeasure and comprehensive processing can be used.
4. The method for generating radar target sample expansion based on sample expander as claimed in claim 1, wherein said step 6 comprises the steps of:
step 6.1: if the simulation modeling is selected, the processing method is as follows: simulating radar echo by constructing a target scattering model aiming at the broadband range profile simulation of a target to obtain an echo vector sum, and acquiring a main echo component and micro-motion modulation information of the target by utilizing micro-motion parameters of the target aiming at the narrow-band modulation spectrum simulation of the target;
step 6.2: if parameter adjustment is selected, echo information under different conditions is obtained by adopting methods of noise superposition, pulse length adjustment, pulse frequency sampling and signal translation, so that samples are expanded; noise superposition: obtaining a plurality of groups of samples by adding noises with different degrees; adjusting the pulse length, and obtaining the pulse numbers with different numbers by a truncation method; sampling pulse frequency, setting different sampling rates, and obtaining different data by a sparse sampling or interpolation method; signal translation, carrying out circular circumferential shift on the sample, and carrying out sample transformation;
step 6.3: if the generation of the countermeasure is selected, a generated countermeasure network is constructed based on input target sample data, a radar target sample is generated by using the discrimination model D and the generation model G, and radar target data are output;
step 6.4: if comprehensive processing is selected, multi-mode combined processing is carried out by utilizing various methods in simulation modeling, parameter adjustment and countermeasure mode generation, firstly, the number of samples expanded by the methods in the simulation modeling, parameter adjustment and countermeasure mode generation is determined according to the requirement of the number of the radar sample data expansion and the distribution in a certain proportion; then, carrying out the processing of the steps 6.1 and 6.2 to obtain a sample data set S1, and carrying out the processing of the step 6.3 by taking the data set S1 and the original data as input to obtain a sample set S2; and finally obtaining an output sample set S which is S1+ S2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110060821.4A CN112884003A (en) | 2021-01-18 | 2021-01-18 | Radar target sample expansion generation method based on sample expander |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110060821.4A CN112884003A (en) | 2021-01-18 | 2021-01-18 | Radar target sample expansion generation method based on sample expander |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112884003A true CN112884003A (en) | 2021-06-01 |
Family
ID=76048857
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110060821.4A Pending CN112884003A (en) | 2021-01-18 | 2021-01-18 | Radar target sample expansion generation method based on sample expander |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112884003A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115525786A (en) * | 2022-10-11 | 2022-12-27 | 中国传媒大学 | Method for constructing ionospheric frequency high-graph classification sample library |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107679465A (en) * | 2017-09-20 | 2018-02-09 | 上海交通大学 | A kind of pedestrian's weight identification data generation and extending method based on generation network |
| CN108881807A (en) * | 2017-05-09 | 2018-11-23 | 富士通株式会社 | Method and apparatus for being expanded the data in monitor video |
| US20200167941A1 (en) * | 2018-11-27 | 2020-05-28 | GM Global Technology Operations LLC | Systems and methods for enhanced distance estimation by a mono-camera using radar and motion data |
| CN111291560A (en) * | 2020-03-06 | 2020-06-16 | 深圳前海微众银行股份有限公司 | Sample expansion method, terminal, device and readable storage medium |
| CN111814875A (en) * | 2020-07-08 | 2020-10-23 | 西安电子科技大学 | Method for expanding ship samples in infrared image based on pattern generation countermeasure network |
| CN111914555A (en) * | 2019-05-09 | 2020-11-10 | 中国人民大学 | Automatic relation extraction system based on Transformer structure |
| CN112132179A (en) * | 2020-08-20 | 2020-12-25 | 中国人民解放军战略支援部队信息工程大学 | Incremental learning method and system based on small number of labeled samples |
| CN112149755A (en) * | 2020-10-12 | 2020-12-29 | 自然资源部第二海洋研究所 | Small sample seabed underwater sound image substrate classification method based on deep learning |
-
2021
- 2021-01-18 CN CN202110060821.4A patent/CN112884003A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108881807A (en) * | 2017-05-09 | 2018-11-23 | 富士通株式会社 | Method and apparatus for being expanded the data in monitor video |
| CN107679465A (en) * | 2017-09-20 | 2018-02-09 | 上海交通大学 | A kind of pedestrian's weight identification data generation and extending method based on generation network |
| US20200167941A1 (en) * | 2018-11-27 | 2020-05-28 | GM Global Technology Operations LLC | Systems and methods for enhanced distance estimation by a mono-camera using radar and motion data |
| CN111914555A (en) * | 2019-05-09 | 2020-11-10 | 中国人民大学 | Automatic relation extraction system based on Transformer structure |
| CN111291560A (en) * | 2020-03-06 | 2020-06-16 | 深圳前海微众银行股份有限公司 | Sample expansion method, terminal, device and readable storage medium |
| CN111814875A (en) * | 2020-07-08 | 2020-10-23 | 西安电子科技大学 | Method for expanding ship samples in infrared image based on pattern generation countermeasure network |
| CN112132179A (en) * | 2020-08-20 | 2020-12-25 | 中国人民解放军战略支援部队信息工程大学 | Incremental learning method and system based on small number of labeled samples |
| CN112149755A (en) * | 2020-10-12 | 2020-12-29 | 自然资源部第二海洋研究所 | Small sample seabed underwater sound image substrate classification method based on deep learning |
Non-Patent Citations (1)
| Title |
|---|
| 潘宗序 等: "基于深度学习的雷达图像目标识别研究进展", 《中国科学:信息科学》, vol. 49, no. 12, pages 1626 - 1639 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115525786A (en) * | 2022-10-11 | 2022-12-27 | 中国传媒大学 | Method for constructing ionospheric frequency high-graph classification sample library |
| CN115525786B (en) * | 2022-10-11 | 2024-02-20 | 中国传媒大学 | Method for constructing ionospheric frequency high-graph classification sample library |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109164428A (en) | Digital radar analogue system and method | |
| Nichols et al. | A simple algorithm for generating spectrally colored, non-Gaussian signals | |
| CN108008385A (en) | Interference environment ISAR high-resolution imaging methods based on management loading | |
| CN109683147B (en) | Method and device for generating chaotic pulse stream signal in real time and electronic equipment | |
| CN112835009B (en) | Data set expanding method based on RAI (radar-ranging) of FMCW (frequency modulated continuous wave) | |
| Shandarin et al. | Origin of the cosmic network in Λ CDM: Nature vs nurture | |
| CN108459308A (en) | A kind of analogue echoes method and device based on time-varying RCS data | |
| Zhang et al. | Serial-EMD: Fast empirical mode decomposition method for multi-dimensional signals based on serialization | |
| CN112884003A (en) | Radar target sample expansion generation method based on sample expander | |
| Kubicek et al. | Sonar target representation using two-dimensional Gabor wavelet features | |
| Wang et al. | Space precession target classification based on radar high-resolution range profiles | |
| CN112836674B (en) | Underwater target identification method based on micro Doppler characteristics | |
| CN111654264B (en) | Method and system for generating signal pulse sequence by signal data simulator | |
| Lovtsov et al. | Automated special purpose optical electronic system’s functional diagnosis | |
| JP2005181153A (en) | Calculation method for radar reflection cross section | |
| CN105158746A (en) | FPGA-based rotary micro Doppler signal generation method of target | |
| CN106680791A (en) | Radar echo simulating method based on broadband sweep frequency data | |
| Venkatasubramanian et al. | Toward data-driven stap radar | |
| CN104820214A (en) | Field programmable gate array (FPGA)-based point target vibration micro Doppler signal generation method | |
| Tran et al. | Generative adversarial networks for recovering missing spectral information | |
| Haywood et al. | ISARLAB-inverse synthetic aperture radar simulation and processing tool | |
| CN107728126B (en) | Phased-array radar signal imitation method based on multitask template | |
| Venkatasubramanian et al. | Data-driven target localization using adaptive radar processing and convolutional neural networks | |
| Ran et al. | A data block partition based fast factorized BP algorithm for bistatic SAR | |
| Liu et al. | Energy and spectrum efficient radio frequency fingerprint intelligent blind identification |
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 | ||
| CB02 | Change of applicant information |
Address after: 210003 No. 346, Zhongshan North Road, Jiangsu, Nanjing Applicant after: 724 Research Institute of China Shipbuilding Corp. Address before: 210003 No. 346, Zhongshan North Road, Jiangsu, Nanjing Applicant before: 724TH RESEARCH INSTITUTE OF CHINA SHIPBUILDING INDUSTRY Corp. |
|
| CB02 | Change of applicant information | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20210601 |
|
| WD01 | Invention patent application deemed withdrawn after publication |