CN114494819B - Anti-interference infrared target identification method based on dynamic Bayesian network - Google Patents
Anti-interference infrared target identification method based on dynamic Bayesian network Download PDFInfo
- Publication number
- CN114494819B CN114494819B CN202111200199.9A CN202111200199A CN114494819B CN 114494819 B CN114494819 B CN 114494819B CN 202111200199 A CN202111200199 A CN 202111200199A CN 114494819 B CN114494819 B CN 114494819B
- Authority
- CN
- China
- Prior art keywords
- bayesian network
- time slice
- feature
- descriptor
- nodes
- 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 36
- 230000003068 static effect Effects 0.000 claims abstract description 24
- 239000013598 vector Substances 0.000 claims abstract description 18
- 238000012549 training Methods 0.000 claims description 4
- 238000004088 simulation Methods 0.000 claims description 3
- 230000002093 peripheral effect Effects 0.000 claims 2
- 238000010276 construction Methods 0.000 abstract description 7
- 238000013461 design Methods 0.000 abstract description 3
- 230000005855 radiation Effects 0.000 abstract description 2
- 230000007704 transition Effects 0.000 description 7
- 238000012360 testing method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000007476 Maximum Likelihood Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 230000010485 coping Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000005764 inhibitory process Effects 0.000 description 1
- 238000007500 overflow downdraw method Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
- G06F18/24155—Bayesian classification
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Probability & Statistics with Applications (AREA)
- Aiming, Guidance, Guns With A Light Source, Armor, Camouflage, And Targets (AREA)
Abstract
The invention relates to an anti-interference infrared target identification method based on a dynamic Bayesian network, and construction and update of Bayesian feature vectors. The Bayesian feature vector is mainly formed by combining the abstract representation of the features such as the radiation intensity, the outline and the like of the target and the interference, realizes the characteristic definition of the target and the interference, and lays a foundation for accurate identification. Feature vector timing correlations and matches. Based on the completion of feature vector construction, a static Bayesian network is constructed by taking the features as cores, and the association between the features is described. Meanwhile, a static Bayesian network is taken as an initial network, and a dynamic Bayesian network framework is constructed aiming at the same node characteristics at different moments. Reasoning and recognition under the Bayesian network. In the interference projection process, the target and the interference characteristics continuously change, and the characteristic difference between the front moment and the rear moment is small. On the basis of completing the construction of the current dynamic Bayesian network, the target information is identified through reasoning of characteristic time sequence change, the identification precision is improved, and the framework design of the target identification method is completed.
Description
Technical Field
The invention belongs to the field of information processing, and relates to an anti-interference infrared target identification method based on a dynamic Bayesian network.
Background
With the development of modern air combat weaponry, the air combat environment becomes increasingly complex. For the infrared air-to-air missile, the target interferes with the missile guidance system by releasing artificial baits such as point sources, surface sources and the like which are similar to the characteristic information of the target, so that the guidance system cannot make accurate and effective judgment. Therefore, the resistance to artificial interference in a complex scene is a core problem faced by the current infrared air-to-air missile, and the anti-interference capability has important significance for an infrared guidance system.
The traditional aerial infrared target recognition method is mainly characterized in that firstly, the extracted features are used as templates, and then, the templates are matched and verified. Typical features include shape features, local texture features, edge features, and the like. The method can comprehensively analyze and process the image information more comprehensively. However, with the increasing complexity of environmental background and the occurrence of infrared interference, the conventional method has difficulty in coping with contemporary air combat environments.
Only the traditional feature fusion method is considered, so that the application requirements of actual air battlefield countermeasure cannot be met, and the time sequence association among multiple feature frames needs to be comprehensively considered. And in the process of throwing the bait into the target, the bait gradually and semi-or fully shields the target from the target position, and then is separated. In the process, the real-time change of the features is accelerated, and the complex change relation between the features cannot be expressed by using simple feature fusion. Thus, a multi-feature inter-frame timing dependent dynamic Bayesian network is introduced as part of the classification system for recognition targets. The dynamic Bayesian network introduces a time dimension on the basis of static Bayesian, the characteristics of the target on each time node are represented by a group of variables, and the relationship among the variables is utilized to express the rule that the characteristics of the target change continuously along with time.
Therefore, on the basis of intensive research on the anti-interference target identification of the traditional infrared air-to-air missile, the anti-interference infrared target identification method based on the dynamic Bayesian network is provided, and the target identification and anti-interference tracking capacity of the seeker is improved.
Disclosure of Invention
Technical problem to be solved
In order to avoid the defects of the prior art, the invention provides an anti-interference infrared target identification method based on a dynamic Bayesian network, which realizes stable target tracking under the environment of strong interference shielding of infrared point sources.
Technical proposal
An anti-interference infrared target identification method based on a dynamic Bayesian network is characterized by comprising the following steps:
step 1: constructing a Bayesian feature vector of target interference:
step 2: constructing a static Bayesian network, wherein the static Bayesian network consists of a directed acyclic graph and a conditional probability table, the directed acyclic graph qualitatively represents the dependency relationship among variables, and the conditional probability table quantitatively describes the relationship strength among the variables; each node of the network corresponds to a characteristic variable, and a time slice comprises 17 characteristic nodes; according to the feature nodes, the relation among the features and the conditional probability table, the Bayesian network obtains the joint probability distribution of all the feature nodes;
establishing an infrared air-to-air missile anti-interference simulation data set, and respectively extracting positive and negative sample characteristics to form a characteristic vector A i ＝{X 1 ,X 2 ,X 3 ,…,X 17 Form a positive and negative sample library S + ＝{A 1 ,A 2 ,A 3 ,…,A P Sum S - ＝{A 1 ,A 2 ,A 3 ,…,A Q The static bayesian network of 17 features is:
constructing a dynamic Bayesian network according to the time sequence association of the constructed static Bayesian network: the static Bayesian network is used as an initial network, the connection relation of various random variables among time slices is determined by a directed arc, and the initial network is expanded to a dynamic Bayesian network;
training a classifier for anti-interference identification by adopting a dynamic Bayesian network;
step 3: and inputting the received infrared image into a classifier, and carrying out target identification on the infrared image by the classifier.
The static bayesian network structure of step 2 is shown in fig. 3.
The dynamic bayesian network structure of step 2 is shown in fig. 4.
Advantageous effects
The invention provides an anti-interference infrared target identification method based on a dynamic Bayesian network, and construction and update of Bayesian feature vectors. The Bayesian feature vector is mainly formed by combining the abstract representation of the features such as the radiation intensity, the outline and the like of the target and the interference, realizes the characteristic definition of the target and the interference, and lays a foundation for accurate identification. Feature vector timing correlations and matches. Based on the completion of feature vector construction, a static Bayesian network is constructed by taking the features as cores, and the association between the features is described. Meanwhile, a static Bayesian network is taken as an initial network, and a dynamic Bayesian network framework is constructed aiming at the same node characteristics at different moments. Reasoning and recognition under the Bayesian network. In the interference projection process, the target and the interference characteristics continuously change, and the characteristic difference between the front moment and the rear moment is small. On the basis of completing the construction of the current dynamic Bayesian network, the target information is identified through reasoning of characteristic time sequence change, the identification precision is improved, and the framework design of the target identification method is completed.
The invention has the advantages and beneficial effects that: therefore, the target interference characteristic difference starts, the problem of identifying the strong shielding target is solved by constructing a dynamic Bayesian network, the real-time requirement of a guiding system is met, the anti-interference capability of the infrared air-to-air missile is improved, and the accurate guidance and striking capability is effectively improved.
Drawings
Fig. 1: an anti-interference infrared target identification method flow chart based on a dynamic Bayesian network;
fig. 2: an anti-interference infrared target recognition method test chart based on a dynamic Bayesian network;
a:160 ° left turn (# 52);
b:160 ° left turn (# 225);
c:160 ° left turn (# 446);
d:160 ° left turn (# 545);
e:100 degree jump (# 114)
f:100 degree jump (# 377)
g:100 degree jump (# 609)
h:100 degree jump (# 720)
Fig. 3: static bayesian network structure diagram;
fig. 4: dynamic bayesian network structure diagram.
Detailed Description
The invention will now be further described with reference to examples, figures:
the invention mainly constructs the target and the interference feature vector through the dynamic Bayesian network, predicts the position of the target under the strong shielding condition in real time by utilizing the feature difference, obtains the identification method based on the dynamic Bayesian network, and solves the problem of accurate identification of the air combat target. A method for carrying out the invention will be further described with reference to the accompanying drawings:
the method comprises the following specific steps:
step one: and through analysis of the interference characteristics of the target, the variables which can distinguish the target from the interference characteristics are selected and combined to form the characteristic vector. The method selects seventeen characteristics such as length-width ratio, perimeter, energy, area, circularity, gray average value, entropy, fourier descriptor and the like as characteristic vectors, and represents distinguishing the target from the interference characteristic, wherein the specific description of the characteristics is shown in a table 1.
Table 1 characteristics used in the present method
Step two: after determining the features representing the target and the interference, a static Bayesian network is constructed based on the selected features. And then constructing a dynamic Bayesian network according to the time sequence association of the constructed static Bayesian network.
Construction of a static Bayesian network
The Bayesian network is composed of a directed acyclic graph which qualitatively represents the dependency relationship among the variables and a conditional probability table which quantitatively describes the relationship strength among the variables.
In this context, each node of the network corresponds to a characteristic variable, and a time slice contains 17 characteristic nodes. According to the feature nodes, the relation among the features and the conditional probability table, the Bayesian network can obtain the joint probability distribution of all the feature nodes.
Establishing a simulation data set, and respectively extracting positive and negative sample characteristics to form a characteristic vector A i ＝{X 1 ,X 2 ,X 3 ,…,X 17 Form a positive and negative sample library S + ＝{A 1 ,A 2 ,A 3 ,…,A P Sum S - ＝{A 1 ,A 2 ,A 3 ,…,A Q }. The static Bayesian network formed by 17 features of the method is shown in figure 3.
Dynamic Bayesian network structure and parameter learning
The dynamic Bayesian network is generally composed of an initial network and a transition network, wherein the method adopts a static Bayesian network as the initial network, a directed arc is used for determining how various random variables are related among time slices, the initial network is expanded into a dynamic Bayesian network to model a classifier based on anti-interference recognition, and the dynamic Bayesian network structure is shown in figure 4.
On the basis, the parameter learning process needs to be completed, and the method adopts a maximum likelihood estimation method.
Assuming arbitrary feature variable X i (0.ltoreq.i.ltoreq.N) has r i Seed value, parent node pa (X i ) The variable is q i Under the condition of seed value, the parameter vector of the characteristic variable is θ= { θ ijk |i＝1,...,N；j＝1,...,r i ；k＝1,...,q i }, whereinThe sum of probabilities representing the values of arbitrary feature variables is 1. Will satisfy p (X) i |pa(X i ) The parameter vector of =k) is denoted as θ i,k ＝{θ ijk |j＝1,...,r i }. The parameters to be estimated are:
θ ijk ＝p(X i ＝j|pa(X i )＝k)(i＝1,...,N；j＝1,...,r i ；k＝1,...,q i )
from the log likelihood estimation method, the following formula can be obtained, where N ijk Representative of satisfying theta ijk Is the number of samples of (a)。
According to the above parameter learning process, each characteristic node X can be calculated 1 ,X 2 ,X 3 ,…,X 17 Taking area nodes as an example, the conditional probability table of (2) is shown in table 3.
Table 2 on-chip conditional probability tables for area feature nodes
TABLE 3 transition probability tables for area characterization nodes
Note that: the parent node of the probability surface area in the chip is the perimeter; the parent node of the inter-slice transition probability table area is the perimeter at the current time and the area at the previous time. The transition probability table of the area characteristic node is a three-dimensional probability table, and table 3 selects a transition probability table of a father node corresponding to the fifth characteristic interval of the area at the current moment.
Step three: after the dynamic Bayesian network is constructed, parameters in the transfer network are not changed, so that the network is expanded to a T time slice according to the initial distribution and the conditional distribution among adjacent time slices, and the identification of the target is realized.
Because the discrete dynamic Bayesian network meets the conditional independence assumption, the probability distribution of the initial moment of the dynamic Bayesian network can be obtained as follows:
wherein, recordIs-> Representation->Is a parent node set of (c).
Conditional probability tables between two adjacent time slice variables are distributed as follows, wherein,for the ith node on the t-th time slice,/and>is->Is a parent node of (c). />t > 0 represents the conditional probability distribution of each node in the next time slice. Node->Parent node +.>In either of the two time slices.
From the homogeneity assumption, a joint probability distribution across multiple time slices can be obtained:
where T is the number of time slices and m is the number of nodes in a single time slice. From this, the bayesian formula of the dynamic bayesian network is:
wherein,and (3) representing the matching degree of the test data and the class C, wherein P (C) is the prior probability of the class C.
For a set of characteristic valuesCalculating +.about.each based on the intra-chip conditional probability table and inter-chip transition probability table of each attribute node obtained in Table 2 and Table 3>The prior probability P (C) i ) P (c=1) =0.5334, P (c=0) =0.4666 can be calculated from the training samples. And then based on the dynamic Bayesian structure calculation (Q is the category of the first time slice):
the same thing can be calculated:
by comparison ofAnd->Obtaining a sample ofIs a dynamic bayesian network detection result. If it is
The sample belongs to the target and vice versa to the disturbance.
Therefore, the design flow of the target anti-interference recognition method based on the dynamic Bayesian network is as shown in fig. 1:
1)T i and carrying out pretreatment and connected region marking on the frame image, counting the number of connected regions of the current frame, and extracting the characteristics of the connected regions to obtain a characteristic value set.
2) And respectively calculating the probability of each type of the feature value of each connected region according to the conditional probability table in the time slices and the transition probability table among the time slices obtained through training.
3) And comparing to obtain the probability of each type of the single connected region, wherein the type with the highest probability is the type to which the connected region belongs.
Example implementation effects
The method can well construct an anti-interference infrared target identification method based on a dynamic Bayesian network, and can identify the target and the interference with high probability, so that the position of the target is determined, the anti-interference performance of the infrared air-to-air missile is improved, and accurate striking is realized.
The invention is tested based on the image sequence after background inhibition, and the test result is shown in figure 2.
Claims (1)
1. An anti-interference infrared target identification method based on a dynamic Bayesian network is characterized by comprising the following steps:
step 1: constructing a Bayesian feature vector of target interference:
step 2: constructing a static Bayesian network, wherein the static Bayesian network consists of a directed acyclic graph and a conditional probability table, the directed acyclic graph qualitatively represents the dependency relationship among variables, and the conditional probability table quantitatively describes the relationship strength among the variables; each node of the network corresponds to a characteristic variable, and a time slice comprises 17 characteristic nodes; according to the feature nodes, the relation among the features and the conditional probability table, the Bayesian network obtains the joint probability distribution of all the feature nodes;
establishing an infrared air-to-air missile anti-interference simulation data set, and respectively extracting positive and negative sample characteristics to form a characteristic vector A i ＝{X 1 ,X 2 ,X 3 ,…,X 17 Form a positive and negative sample library S + ＝{A 1 ,A 2 ,A 3 ,…,A P Sum S - ＝{A 1 ,A 2 ,A 3 ,…,A Q The static bayesian network of 17 features is:
a. the initial node is an aspect ratio, and the child nodes are circularities;
b. the circularity child nodes are perimeter, descriptor 1 and descriptor 2;
c. the peripheral sub-nodes are areas, the area sub-nodes are energy, the energy sub-nodes are average gray levels, and the average gray level sub-nodes are entropy;
d. the descriptor 1 child node is descriptor 3, and the descriptor 3 child node is descriptor 4 and descriptor 5;
e. the descriptor 5 child nodes are descriptor 6 and descriptor 7;
f. the descriptor 6 child node is a descriptor 8, and the descriptor 8 child node is a descriptor 10;
g. the descriptor 7 child node is descriptor 9;
constructing a dynamic Bayesian network according to the time sequence association of the constructed static Bayesian network: the static Bayesian network is used as an initial network, the connection relation of various random variables among time slices is determined by a directed arc, and the initial network is expanded to a dynamic Bayesian network;
the dynamic Bayesian network structure comprises a first time slice and a second time slice, wherein the first time slice and the second time slice are the same as each other in the network structure and are static Bayesian network structures, and the static Bayesian network structure of the first time slice is as follows: the initial node is an aspect ratio, and the child nodes are circularities; the child nodes of the circularity are perimeter and descriptors; the peripheral sub-nodes are areas, the area sub-nodes are energy, the energy sub-nodes are average gray levels, and the average gray level sub-nodes are entropy;
the network connection mode between the first time slice and the second time slice is corresponding characteristic connection: the method comprises the steps that a time slice I middle length-width ratio feature is connected with a time slice II middle length-width ratio feature, a time slice I middle circularity feature is connected with a time slice II middle circularity feature, a time slice I middle description sub-feature is connected with a time slice II middle description sub-feature, a time slice I middle circumference feature is connected with a time slice II middle circumference feature, a time slice I middle area feature is connected with a time slice II middle area feature, a time slice I middle energy feature is connected with a time slice II middle energy feature, a time slice I middle average gray scale feature is connected with a time slice II middle average gray scale feature, and a time slice I middle entropy feature is connected with a time slice II middle entropy feature;
training a classifier for anti-interference identification by adopting a dynamic Bayesian network;
step 3: and inputting the received infrared image into a classifier, and carrying out target identification on the infrared image by the classifier.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111200199.9A CN114494819B (en) | 2021-10-14 | 2021-10-14 | Anti-interference infrared target identification method based on dynamic Bayesian network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111200199.9A CN114494819B (en) | 2021-10-14 | 2021-10-14 | Anti-interference infrared target identification method based on dynamic Bayesian network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114494819A CN114494819A (en) | 2022-05-13 |
| CN114494819B true CN114494819B (en) | 2024-03-08 |
Family
ID=81492125
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111200199.9A Active CN114494819B (en) | 2021-10-14 | 2021-10-14 | Anti-interference infrared target identification method based on dynamic Bayesian network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114494819B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115169252B (en) * | 2022-09-07 | 2022-12-13 | 哈尔滨工业大学(深圳)(哈尔滨工业大学深圳科技创新研究院) | Structured simulation data generation system and method |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103488886A (en) * | 2013-09-13 | 2014-01-01 | 清华大学 | State threat assessment method based on fuzzy dynamic Bayesian network |
| CN110489898A (en) * | 2019-08-26 | 2019-11-22 | 北京航空航天大学 | A kind of dynamic multilayer grade system modelling and trend prediction method based on mixing cognition |
| CN112016239A (en) * | 2020-07-07 | 2020-12-01 | 中国科学院西安光学精密机械研究所 | Method for rapidly solving system reliability based on dynamic Bayesian network |
| LU102399B1 (en) * | 2019-12-16 | 2021-06-18 | Shandong Technology And Business Univ | Gpr image denoising method and system based on bayesian inference |
-
2021
- 2021-10-14 CN CN202111200199.9A patent/CN114494819B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103488886A (en) * | 2013-09-13 | 2014-01-01 | 清华大学 | State threat assessment method based on fuzzy dynamic Bayesian network |
| CN110489898A (en) * | 2019-08-26 | 2019-11-22 | 北京航空航天大学 | A kind of dynamic multilayer grade system modelling and trend prediction method based on mixing cognition |
| LU102399B1 (en) * | 2019-12-16 | 2021-06-18 | Shandong Technology And Business Univ | Gpr image denoising method and system based on bayesian inference |
| CN112016239A (en) * | 2020-07-07 | 2020-12-01 | 中国科学院西安光学精密机械研究所 | Method for rapidly solving system reliability based on dynamic Bayesian network |
Non-Patent Citations (1)
| Title |
|---|
| 基于离散动态贝叶斯网络的辐射源目标识别研究;唐政;高晓光;;系统仿真学报;20090131(第01期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114494819A (en) | 2022-05-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Chen et al. | Enhancing detection model for multiple hypothesis tracking | |
| Bendale et al. | Towards open set deep networks | |
| CN108846426B (en) | Polarization SAR classification method based on deep bidirectional LSTM twin network | |
| CN108961308B (en) | Residual error depth characteristic target tracking method for drift detection | |
| CN107256017B (en) | Route planning method and system | |
| CN114564982B (en) | Automatic identification method for radar signal modulation type | |
| CN111340076B (en) | Zero sample identification method for unknown mode of radar target of new system | |
| CN110082738B (en) | Radar target identification method based on Gaussian mixture and tensor recurrent neural network | |
| CN112766315A (en) | Method and system for testing robustness of artificial intelligence model | |
| Weber et al. | Single-shot panoptic segmentation | |
| CN115620160A (en) | Remote sensing image classification method based on multi-classifier active transfer learning resistance | |
| CN110716792A (en) | Target detector and construction method and application thereof | |
| Yu et al. | Recognition method of soybean leaf diseases using residual neural network based on transfer learning | |
| CN114494819B (en) | Anti-interference infrared target identification method based on dynamic Bayesian network | |
| CN114818734B (en) | Method and device for analyzing antagonism scene semantics based on target-attribute-relation | |
| Chen et al. | Military image scene recognition based on CNN and semantic information | |
| CN112364747A (en) | Target detection method under limited sample | |
| CN110033043B (en) | Radar one-dimensional range profile rejection method based on condition generation type countermeasure network | |
| CN114818853A (en) | Intention identification method based on bidirectional gating cycle unit and conditional random field | |
| Altundogan et al. | Multiple object tracking with dynamic fuzzy cognitive maps using deep learning | |
| Wang et al. | FCM algorithm and index CS for the signal sorting of radiant points | |
| Zhou et al. | SAR open set recognition based on counterfactual framework | |
| CN111652246B (en) | Image self-adaptive sparsization representation method and device based on deep learning | |
| CN110880012A (en) | Correlation method for frequency information of agile radar radiation source between multiple scout platforms | |
| Du et al. | [Retracted] Application of Improved Interactive Multimodel Algorithm in Player Trajectory Feature Matching |
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 |