CN112180376A - Identification method for detecting meteorological target based on phased array weather radar - Google Patents

Identification method for detecting meteorological target based on phased array weather radar Download PDF

Info

Publication number
CN112180376A
CN112180376A CN202011013581.4A CN202011013581A CN112180376A CN 112180376 A CN112180376 A CN 112180376A CN 202011013581 A CN202011013581 A CN 202011013581A CN 112180376 A CN112180376 A CN 112180376A
Authority
CN
China
Prior art keywords
polarization
meteorological
gaussian
matrix
clustering
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
Application number
CN202011013581.4A
Other languages
Chinese (zh)
Inventor
乔俊淇
艾未华
刘茂宏
郭朝刚
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
National University of Defense Technology
Original Assignee
National University of Defense Technology
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by National University of Defense Technology filed Critical National University of Defense Technology
Priority to CN202011013581.4A priority Critical patent/CN112180376A/en
Publication of CN112180376A publication Critical patent/CN112180376A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
    • G01S13/88—Radar or analogous systems specially adapted for specific applications
    • G01S13/95—Radar or analogous systems specially adapted for specific applications for meteorological use
    • G01S13/958—Theoretical aspects
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
    • G01S7/02—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00
    • G01S7/41—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section
    • G01S7/418—Theoretical aspects
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
    • Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation

Abstract

The invention discloses a method for identifying a meteorological target detected based on a phased array weather radar, which comprises the following steps: extracting a scattering polarization matrix from phased array weather radar echo data; extracting polarization invariant features from the scattering polarization matrix; inputting the polarization invariant features into a mixed Gaussian clustering model, and identifying to obtain a meteorological target; the Gaussian mixture clustering model comprises a plurality of subclasses, and each subclass model correspondingly identifies a meteorological target. The method solves the problem that the phased array weather radar obtains different polarization scattering matrixes under different beam pointing directions, and improves the accuracy of meteorological target identification.

Description

Identification method for detecting meteorological target based on phased array weather radar
Technical Field
The invention relates to the field of radar polarization, in particular to a method for identifying a meteorological target detected based on a phased array weather radar.
Background
In actual atmosphere, the real meteorological scene is more complicated, and the meteorological target is more various, so the detection of complicated and mixed meteorological targets becomes an important subject in the field of modern aviation. In order to identify different types of meteorological targets, the meteorological targets are detected by the phased array weather radar, and information of the meteorological targets is obtained through polarization data, so that the method is a key technical means for detecting complex meteorological targets. However, the conventional meteorological radar detects a meteorological target on the basis of the assumption that the meteorological target is spherical, and most meteorological targets are actually non-spherical particles, so the conventional meteorological radar has certain limitations. The phased array weather radar is designed aiming at the defect, and can transmit horizontal polarized waves and vertical polarized waves to acquire co-polarized echoes (echoes with the same polarization state as the transmitted waves) and cross-polarized echoes (echoes orthogonal to the polarization state of the transmitted waves) of a weather target, so that polarization detection parameters including differential reflectivity, differential phase shift, linear depolarization ratio and the like are obtained, and the parameters can improve the accuracy of weather target identification. However, the polarization characteristic of the phased array radar antenna changes with the change of the beam scanning angle, so that the polarization scattering matrixes observed on meteorological targets under different beam directions are different, and a large polarization measurement error is inevitably generated, so that how to process polarization data becomes a problem to be solved urgently.
Disclosure of Invention
Aiming at the defects of the prior art, the invention aims to provide an identification method for detecting a meteorological target based on a phased array weather radar, so as to solve the problem of large polarization measurement error in the prior art.
In order to achieve the purpose, the invention provides the following technical scheme:
an identification method for detecting meteorological targets comprises the following steps:
extracting a scattering polarization matrix from phased array weather radar echo data;
extracting polarization invariant features from the scattering polarization matrix;
inputting the polarization invariant features into a mixed Gaussian clustering model, and identifying to obtain a meteorological target;
the Gaussian mixture clustering model comprises a plurality of subclasses, and each subclass model correspondingly identifies a meteorological target.
Further, the scattering polarization matrix is:
Figure BDA0002696147780000021
wherein s isHHPolarization mode, s, for horizontal transmission and horizontal receptionVVPolarization mode, s, for vertical transmission and vertical receptionHVPolarization mode, s, for horizontal transmission and vertical receptionVHA polarization mode for vertical transmission and horizontal reception.
Further, the polarization invariant features include determinant mode, power matrix trace, eigen-polarization ellipticity and invariant coefficient.
Further, the determinant module is as follows:
Figure BDA0002696147780000022
the power matrix trace is:
P1＝|sHH|2+|sVV|2+|sHV|2
the intrinsic polarization ellipticity is:
Figure BDA0002696147780000031
the invariant coefficient is as follows:
Figure BDA0002696147780000032
wherein j is a complex number and S' is an intrinsic polarization ellipticity factor.
Further, the method for constructing the Gaussian mixture clustering model comprises the following steps:
extracting a scattering polarization matrix from historical echo data of the phased array weather radar;
extracting polarization invariant features from the scattering polarization matrix to form a training set and a verification set;
training a mixed Gaussian clustering model consisting of different numbers and subclasses through a training set;
clustering the trained mixed Gaussian clustering models composed of different numbers and subclasses;
and selecting the mixed Gaussian clustering model with the best clustering result as a final mixed Gaussian clustering model according to the average deviation distance and the deviation degree.
Further, the gaussian mixture density function when the mixture gaussian clustering model performs clustering is as follows:
Figure BDA0002696147780000033
wherein x is a three-dimensional characteristic vector of polarization invariant characteristics, pikFor each weight coefficient of the Gaussian distribution, mukAnd σkRespectively the mean value and the variance of each Gaussian distribution;
the formula of the gaussian distribution is:
Figure BDA0002696147780000041
where μ is the mean and is the covariance matrix of the eigenvectors.
Further, the calculation formula of the average deviation distance is as follows:
Figure BDA0002696147780000042
wherein n isjIs the number of scatters, d, in subclass jiThe Euclidean distance from the ith point in the subclass j to the clustering center;
the calculation formula of the deviation degree is as follows:
Figure BDA0002696147780000043
and K is the number of the subclasses of the Gaussian mixture clustering model.
An identification system for detecting a meteorological object, the system comprising:
a first extraction module: the method comprises the steps of extracting a scattering polarization matrix from phased array weather radar echo data;
a second extraction module: for extracting polarization invariant features from the scattering polarization matrix;
an identification module: the polarization invariant feature is input into a mixed Gaussian clustering model, and a meteorological target is identified and obtained;
the Gaussian mixture clustering model comprises a plurality of subclasses, and each subclass model correspondingly identifies a meteorological target.
An identification system for detecting a meteorological object, the system comprising a processor and a storage medium;
the storage medium is used for storing instructions;
the processor is configured to operate according to the instructions to perform the steps of the method described above.
A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method described above.
Compared with the prior art, the invention has the beneficial effects that:
(1) the phased array weather radar is different from the traditional radar in that a large number of individually controlled small antenna units are arranged to form an antenna array surface, and the geometric shape of a meteorological target is determined by processing polarization information in radar echoes, so that the purpose of identifying the meteorological target is achieved; according to the characteristic, firstly, polarization invariant features in a polarization scattering matrix are extracted; secondly, the meteorological target is identified through the Gaussian mixture clustering model, the problem that the polarized scattering matrixes obtained by the phased array weather radar under different beam directions are different is solved, and the accuracy of identifying the meteorological target is improved;
(2) constructing a data set (echo data in different polarization modes) for learning, training and verifying a model, extracting polarization invariant features in a polarization scattering matrix, and providing corresponding data support for identification of a phased array weather radar meteorological target; then, a machine learning model is constructed, data are trained according to a Gaussian mixture clustering method, the polarization degree is defined to verify the accuracy of a clustering result, and then a final clustering result of meteorological target identification is obtained; and finally, verifying the clustering result and identifying the meteorological target by using the clustering result.
Drawings
FIG. 1 is a graph showing the variation of the deviation degree of the present invention.
FIG. 2 is a diagram of the classification results of the present invention.
Fig. 3 is a diagram of the recognition result of the present invention.
Detailed Description
In order to make the technical means, the creation characteristics, the achievement purposes and the effects of the invention easy to understand, the invention is further described with the specific embodiments.
An identification method for detecting meteorological targets comprises the following steps:
extracting a scattering polarization matrix from phased array weather radar echo data;
extracting polarization invariant features from the scattering polarization matrix;
inputting the polarization invariant features into a mixed Gaussian clustering model, and identifying to obtain a meteorological target;
the Gaussian mixture clustering model comprises a plurality of subclasses, and each subclass model correspondingly identifies a meteorological target.
As shown in fig. 1 to 3, a method for identifying a meteorological target detected based on a phased array weather radar includes the following steps:
step 1, extracting scattering polarization matrix s from historical echo data of phase control array weather radarnConstructing a data set S for training a machine learning model, and extracting a scattering polarization matrix S in the data set SnIncluding determinant modulo delta, power matrix trace P1Intrinsic polarization ellipticity τ0And obtaining a new data set S' by the combined invariant coefficient eta. Randomly dividing the data set S' into S1、S2Respectively as a training set and a verification set80% and 20% of the total data;
step 2: will train set S1Selecting different K values as the number of Gaussian models, namely the number of subclasses, and respectively using the average deviation distance DjAnd degree of deviation IKEvaluating the clustering performance of the mixed Gaussian clustering models with different subclass numbers, and selecting the K value with the best performance as the subclass number. Will S1The typical meteorological target in (2) is separated, and each subclass is determined to correspond to the meteorological target.
And step 3: will verify the set S2The method is used for checking the clustering result and checking the accuracy of the meteorological target identification method.
In this embodiment, the step 1 of extracting the scattering polarization matrix in the data set S
Figure BDA0002696147780000071
( n 1,2, 3.) polarization invariant features including determinant mode | Δ |, power matrix trace P1Intrinsic polarization ellipticity τ0And the invariant coefficient eta of the combination, the main formula is as follows:
Figure BDA0002696147780000072
P1＝|sHH|2+|sVV|2+|sHV|2
Figure BDA0002696147780000073
Figure BDA0002696147780000074
wherein s isHH、sVV、sHV、sVHIn the form of a different polarization pattern,
Figure BDA0002696147780000075
direction of intrinsic polarization
Figure BDA0002696147780000076
For meteorological targets, s can be approximatedHV＝sVH。
In the present embodiment: tracing the power matrix P1Intrinsic polarization ellipticity τ0And performing three-feature three-dimensional Gaussian mixed clustering by using the combined invariant coefficient eta as a feature value. K gaussian mixture density functions represented by a combination of gaussian distributions:
Figure BDA0002696147780000077
wherein x is P1、τ0Eta, of three-dimensional feature vector, pikFor each weight coefficient of the Gaussian distribution, mukAnd σkThe mean and variance of each gaussian distribution. The formula for a single gaussian distribution:
Figure BDA0002696147780000081
where μ is the mean and is the covariance matrix of the eigenvectors.
Determining Gaussian mixture model coefficients pi using EM algorithmk、μk、σkMaximum likelihood estimation is required, that is, coefficients of each gaussian model are estimated by assuming that the coefficients of each gaussian model are known (one is initialized or the result of the previous iteration is adopted), and then the coefficients of the gaussian models are determined again after the previous estimation. The first two steps are iterated repeatedly until the value of the likelihood function converges with a small fluctuation.
In this embodiment, the average deviation distance D for evaluating clustering performance of different K values in the step 2jAnd degree of deviation IKThe concrete formula is as follows:
Figure BDA0002696147780000082
wherein n isjIs the number of scatters, d, in subclass jiThe euclidean distance from the ith point in the subclass j to the cluster center. Then the degree of deviation formula for the number K of subclasses is:
Figure BDA0002696147780000083
in this embodiment, an ideal K value is obtained according to the deviation degree, and the point corresponding to the maximum value of the representative probability density of each subclass is determined to be respectively recorded as ψ1、ψ2、ψ3、ψ4. Combined training set S1Known meteorological targets, determining the kind of meteorological target that can be identified, comprising: cloud drops, rain drops, ice crystals, snow crystals, aragonite, hail, and the like.
In the present embodiment, the verification set S2The accuracy of the method is verified. Determining S using Euclidean distance | X |2Sorting of medium data, i.e. comparing with psiiAnd (i ═ 1,2,3,4) euclidean distance | X |.
The method comprises the steps that target backward echo polarization scattering information is received by a phased array weather radar, polarization invariants in the radar polarization information are extracted, namely characteristic signals of information contained in target scattering echoes and irrelevant to radar coordinate system or polarization base selection are extracted, and a machine learning method based on Gaussian mixture clustering is utilized to identify meteorological targets. The method has enough theoretical basis for support, and provides technical support for target identification of the subsequent phased array weather radar.
An identification system for detecting a meteorological object, the system comprising:
a first extraction module: the method comprises the steps of extracting a scattering polarization matrix from phased array weather radar echo data;
a second extraction module: for extracting polarization invariant features from the scattering polarization matrix;
an identification module: the polarization invariant feature is input into a mixed Gaussian clustering model, and a meteorological target is identified and obtained;
the Gaussian mixture clustering model comprises a plurality of subclasses, and each subclass model correspondingly identifies a meteorological target.
An identification system for detecting a meteorological object, the system comprising a processor and a storage medium;
the storage medium is used for storing instructions;
the processor is configured to operate according to the instructions to perform the steps of the method described above.
A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method described above.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The present invention is not limited to the above embodiments, and any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention are included in the scope of the claims of the present invention which are filed as the application.

Claims (10)

1. An identification method for detecting meteorological targets, characterized by comprising the following steps:
extracting a scattering polarization matrix from phased array weather radar echo data;
extracting polarization invariant features from the scattering polarization matrix;
inputting the polarization invariant features into a mixed Gaussian clustering model, and identifying to obtain a meteorological target;
the Gaussian mixture clustering model comprises a plurality of subclasses, and each subclass model correspondingly identifies a meteorological target.
2. An identification method for detecting meteorological targets according to claim 1, wherein the scattering polarization matrix is:
Figure FDA0002696147770000011
wherein s isHHPolarization mode, s, for horizontal transmission and horizontal receptionVVPolarization mode, s, for vertical transmission and vertical receptionHVPolarization mode, s, for horizontal transmission and vertical receptionVHA polarization mode for vertical transmission and horizontal reception.
3. The method of claim 1, wherein the polarization invariant features comprise determinant mode, power matrix trace, eigen-polarization ellipticity, and invariant coefficients.
4. An identification method for detecting meteorological objects according to claim 3, wherein the determinant model is as follows:
Figure FDA0002696147770000012
the power matrix trace is:
P1＝|sHH|2+|sVV|2+|sHV|2
the intrinsic polarization ellipticity is:
Figure FDA0002696147770000021
the invariant coefficient is as follows:
Figure FDA0002696147770000022
wherein j is a complex number and S' is an intrinsic polarization ellipticity factor.
5. The identification method for detecting the meteorological target according to claim 1, wherein the Gaussian mixture clustering model is constructed by the following steps:
extracting a scattering polarization matrix from historical echo data of the phased array weather radar;
extracting polarization invariant features from the scattering polarization matrix to form a training set and a verification set;
training a mixed Gaussian clustering model consisting of different numbers and subclasses through a training set;
clustering the trained mixed Gaussian clustering models composed of different numbers and subclasses;
and selecting the mixed Gaussian clustering model with the best clustering result as a final mixed Gaussian clustering model according to the average deviation distance and the deviation degree.
6. The identification method for detecting the meteorological target according to claim 5, wherein the Gaussian mixture density function of the Gaussian mixture clustering model during clustering is as follows:
Figure FDA0002696147770000023
wherein x is a three-dimensional characteristic vector of polarization invariant characteristics, pikFor each weight coefficient of the Gaussian distribution, mukAnd σkRespectively the mean value and the variance of each Gaussian distribution;
the formula of the gaussian distribution is:
Figure FDA0002696147770000024
where μ is the mean and is the covariance matrix of the eigenvectors.
7. The method for identifying the meteorological target, according to claim 5, wherein the mean deviation distance is calculated by the formula:
Figure FDA0002696147770000031
wherein n isjIs the number of scatters, d, in subclass jiThe Euclidean distance from the ith point in the subclass j to the clustering center;
the calculation formula of the deviation degree is as follows:
Figure FDA0002696147770000032
and K is the number of the subclasses of the Gaussian mixture clustering model.
8. An identification system for detecting meteorological targets, the system comprising:
a first extraction module: the method comprises the steps of extracting a scattering polarization matrix from phased array weather radar echo data;
a second extraction module: for extracting polarization invariant features from the scattering polarization matrix;
an identification module: the polarization invariant feature is input into a mixed Gaussian clustering model, and a meteorological target is identified and obtained;
the Gaussian mixture clustering model comprises a plurality of subclasses, and each subclass model correspondingly identifies a meteorological target.
9. An identification system for detecting meteorological targets, the system comprising a processor and a storage medium;
the storage medium is used for storing instructions;
the processor is configured to operate in accordance with the instructions to perform the steps of the method according to any one of claims 1 to 7.
10. Computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 7.
CN202011013581.4A 2020-09-23 2020-09-23 Identification method for detecting meteorological target based on phased array weather radar Pending CN112180376A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011013581.4A CN112180376A (en) 2020-09-23 2020-09-23 Identification method for detecting meteorological target based on phased array weather radar

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011013581.4A CN112180376A (en) 2020-09-23 2020-09-23 Identification method for detecting meteorological target based on phased array weather radar

Publications (1)

Publication Number Publication Date
CN112180376A true CN112180376A (en) 2021-01-05

Family

ID=73956640

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011013581.4A Pending CN112180376A (en) 2020-09-23 2020-09-23 Identification method for detecting meteorological target based on phased array weather radar

Country Status (1)

Country Link
CN (1) CN112180376A (en)

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20180074224A1 (en) * 2016-09-15 2018-03-15 Kabushiki Kaisha Toshiba Weather data processing apparatus and method using weather radar
CN111239741A (en) * 2020-01-21 2020-06-05 航天新气象科技有限公司 Phased array weather radar polarization control method and phased array weather radar system

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20180074224A1 (en) * 2016-09-15 2018-03-15 Kabushiki Kaisha Toshiba Weather data processing apparatus and method using weather radar
CN111239741A (en) * 2020-01-21 2020-06-05 航天新气象科技有限公司 Phased array weather radar polarization control method and phased array weather radar system

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
李杭 等: "基于高斯混合聚类的阵列干涉SAR三维成像", 《雷达学报》 *
王福友 等: "基于极化不变量特征的雷达目标识别技术", 《雷达科学与技术》 *
薛建儒 等: "基于自适应高斯混合体模型的相控阵雷达TWS跟踪技术", 《电子学报》 *

Similar Documents

Publication Publication Date Title
CN108229404B (en) Radar echo signal target identification method based on deep learning
Chiang et al. Model-based classification of radar images
Ding et al. Target reconstruction based on 3-D scattering center model for robust SAR ATR
CN110298280B (en) Ocean vortex identification method based on MKL multi-feature fusion
CN107688170A (en) A kind of Radar Target Track initial mode based on random forest
CN110516525B (en) SAR image target recognition method based on GAN and SVM
CN102109495A (en) Method for classifying types of mixed seabed sediment based on multi-beam sonar technology
CN109840542B (en) Self-adaptive dimension decision tree classification method based on polarization characteristics
CN109655826A (en) The low slow Small object track filtering method of one kind and device
CN104732224B (en) SAR target identification methods based on two-dimentional Zelnick moment characteristics rarefaction representation
CN106707255A (en) Phased array radar simulation system and method
CN115685096B (en) Secondary radar side lobe suppression method based on logistic regression
CN116087994B (en) Deception jamming detection method based on machine learning
CN112597820A (en) Target clustering method based on radar signal sorting
CN105809113A (en) Three-dimensional human face identification method and data processing apparatus using the same
CN110348310A (en) A kind of Hough ballot 3D colour point clouds recognition methods
CN110703221A (en) Urban low-altitude small target classification and identification system based on polarization characteristics
CN115220007A (en) Radar point cloud data enhancement method aiming at attitude identification
WO2008118706A1 (en) Identifying whether a candidate object is from an object class
CN110109068A (en) Decoy jamming recognition methods based on polarization characteristic vector
CN112213697B (en) Feature fusion method for radar deception jamming recognition based on Bayesian decision theory
CN112180376A (en) Identification method for detecting meteorological target based on phased array weather radar
Yi et al. Target indexing in SAR images using scattering centers and the Hausdorff distance
Gan et al. Hierarchical particle filter tracking algorithm based on multi-feature fusion
Lin et al. The track initiation algorithm based on Hough transform and space accumulation

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20210105