CN108845302A - A kind of true and false target's feature-extraction method of k nearest neighbor transformation - Google Patents

A kind of true and false target's feature-extraction method of k nearest neighbor transformation Download PDF

Info

Publication number
CN108845302A
CN108845302A CN201810964240.1A CN201810964240A CN108845302A CN 108845302 A CN108845302 A CN 108845302A CN 201810964240 A CN201810964240 A CN 201810964240A CN 108845302 A CN108845302 A CN 108845302A
Authority
CN
China
Prior art keywords
nearest neighbor
vector
matrix
feature
sample
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN201810964240.1A
Other languages
Chinese (zh)
Other versions
CN108845302B (en
Inventor
周代英
沈晓峰
冯健
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.)
University of Electronic Science and Technology of China
Original Assignee
University of Electronic Science and Technology of China
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 University of Electronic Science and Technology of China filed Critical University of Electronic Science and Technology of China
Priority to CN201810964240.1A priority Critical patent/CN108845302B/en
Publication of CN108845302A publication Critical patent/CN108845302A/en
Application granted granted Critical
Publication of CN108845302B publication Critical patent/CN108845302B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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
    • 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

Abstract

The invention discloses a kind of k nearest neighbors to convert true and false target's feature-extraction method, belong to Technology of Radar Target Identification neighborhood, the present invention is by reducing the difference between similar sample based on k nearest neighbor constraint rule, and increase the difference between foreign peoples's sample, reduce influence of other samples to building transformation matrix, in the case where target sample data distribution is non-gaussian distribution, it still is able to the degree for indicating to separate between aggregation and class in class well, the shortcomings that conventional contact transformation matrix is suitable only for sample data Gaussian Profile is overcome, to improve target identification performance.

Description

A kind of true and false target's feature-extraction method of k nearest neighbor transformation
Technical field
The invention belongs to Technology of Radar Target Identification neighborhoods, and in particular to a kind of true and false target's feature-extraction of k nearest neighbor transformation Method.
Background technique
In radar target recognition, differentiates that Vector Transformation-based is capable of increasing the difference between heterogeneous destinations feature, subtract simultaneously Therefore difference between small similar target signature, it is good to differentiate that Vector Transformation-based obtains to extract the apparent feature of difference Good classification performance.
But differentiate that Vector Transformation-based is suitable only for the case where sample data is Gaussian Profile, and sample data in practice Distribution may be non-gaussian distribution, for non-gaussian distribution situation, differentiate that the recognition performance of Vector Transformation-based significantly reduces.It is existing There is the conventional recognition performance for differentiating Vector Transformation-based to have further room for improvement.
Summary of the invention
Goal of the invention of the invention is：In view of the above problems, a kind of k nearest neighbor transform characteristics extraction side is proposed Method effectively improves the classification performance to the true and false target of radar to overcome the conventional defect for differentiating Vector Transformation-based.
The technical solution that k nearest neighbor of the invention converts true and false target's feature-extraction method is specific as follows：
Step 1：The training sample set about radar target-range image is inputted, x is usedijIndicate training sample, wherein under Mark i is class discrimination symbol, subscript j is training sample specificator, and 1≤i≤g, 1≤j≤Ni, g expression categorical measure, NiIt indicates The sample number of corresponding classification；
Step 2：Calculate the estimated value of k nearest neighbor transformation matrix A
Wherein, sample matrix
The constraint coefficient matrix of similar k nearest neighbor rule
Matrix
The wherein constraint factor of similar k nearest neighbor ruleBe set as：IfOrThenOtherwiseWherein subscript k is certain class training sample specificator, σ2Indicate Gaussian parameter,Table Show the k of some vector in similar1The set of a neighbour's vector, k1To preset neighbour's number；
The constraint coefficient matrix of foreign peoples's k nearest neighbor rule
Matrix
The wherein constraint factor of foreign peoples's k nearest neighbor ruleBe set as：IfOrThenOtherwiseWherein, wherein subscript l is class discrimination symbol,Indicate different The k of some vector in class2The set of a neighbour's vector, k2To preset neighbour's number；
Step 3：Son to be extracted is inputted as the true and false target one-dimensional range profile x of the radar of featuret, according toIt obtains One-dimensional range profile xtCharacteristic vector yt。
In conclusion by adopting the above-described technical solution, the beneficial effects of the invention are as follows：
The present invention increases foreign peoples's sample by reducing the difference between similar sample characteristics based on k nearest neighbor constraint rule Difference between feature is weighted, and reduces the influence that other samples construct transformation matrix, so as to extract non-gaussian point The feature of cloth sample data overcomes the conventional defect for differentiating Vector Transformation-based, effectively improves the classification to the true and false target of radar Performance.
Specific embodiment
To make the object, technical solutions and advantages of the present invention clearer, below with reference to embodiment, to the present invention make into One step it is described in detail.
K nearest neighbor of the invention converts true and false target's feature-extraction method, by reducing similar sample based on k nearest neighbor constraint rule Difference between eigen, and the difference increased between foreign peoples's sample characteristics is weighted, and reduces other samples to transformation matrix The influence of building, so as to extract the feature of non-gaussian distribution sample data, the specific implementation process is as follows：
Use xij(n ties up column vector) indicates i-ththThe jth of the true and false target of classthA trained one-dimensional range profile, 1≤i≤g, 1≤j ≤Ni,Wherein NiIt is i-ththThe training one-dimensional range profile sample number of the true and false target of class, N are training one-dimensional range profile Total sample number.It will training one-dimensional range profile xijCarry out such as down conversion：
yij=ATxij (1)
Wherein A is transformation matrix, yijFor xijCorresponding characteristic vector, T representing matrix transposition.
Squared difference and S between similar any two sample characteristics vector are calculated in feature spaceC：
WhereinFor the constraint factor of similar k nearest neighbor rule：
Wherein Gaussian parameter σ2It is determined under conditions of meeting processing accuracy demand by experiment for empirical value, The k of some vector in indicating similar1The set of a neighbour's vector.Formula (3) shows when two samples for belonging to same target class are mutual For k1Neighbour's period of the day from 11 p.m. to 1 a.m, the difference constraint factor between similar sample are not equal to zero, and the constraint system of other similar difference between samples Number is zero.
Using the operational formula of trace of a matrix, formula (2) be can be exchanged into：
Formula (1) substitution formula (4) can be obtained：
To formula (5) abbreviation, can obtain：
SC=ATX(DC-WC)XTA (6)
Wherein
Similarly, the Weighted distance quadratic sum S between heterogeneous destinations sample characteristics is calculated in feature spaceB：
Wherein wij,lkFor the constraint factor based on foreign peoples's k nearest neighbor rule：
WhereinIndicate the k of some vector in foreign peoples2The set of a neighbour's vector.
Using the operational formula of trace of a matrix, formula (10) be can be exchanged into
Formula (1) is substituted into formula (12)
To formula (13) abbreviation, can obtain
SB=ATX(DB-WB)XTA (14)
Wherein
By solving following minimization problem, the estimated value of k nearest neighbor transformation matrix can be obtained
Local derviation is asked to A on the right of formula (17) and it is enabled to be equal to zero, the estimated value of k nearest neighbor transformation matrix can be obtainedIt is by matrix (X (DB-WB)XT)-1(X(DC-WC)XT) a maximum eigenvalue of M (< n) corresponding feature vector composition matrix.
In the estimated value for obtaining k nearest neighbor transformation matrixAfterwards, arbitrary sample x can be obtained using formula (1)tCharacteristic vector yt, i.e.,The true and false target identification processing of radar is carried out based on extracted characteristic vector again, to be effectively improved pair The classification performance of the true and false target of radar.
In order to verify the validity of proposed method, following emulation experiment is carried out.
Four kinds of point targets are set：True target, fragment, light weight decoy and weight bait.The bandwidth of radar transmitted pulse is 1000MHZ (distance resolution 0.15m, radar radial direction sampling interval are 0.075m), target is set as homogenous diffusion point target, true target Scattering point be 7, the scattering of excess-three target points are 11.Object attitude angle be 0 °~80 ° within the scope of every 1 ° one Tie up in Range Profile, to take object attitude angle be 0 °, 2 °, 4 °, 6 ° ..., 90 ° of one-dimensional range profile be trained, remaining attitude angle One-dimensional range profile is as test data, then every classification indicates 45 test samples.
To four kinds of targets (true target, fragment, light weight decoy and weight bait), within the scope of 0 °~90 ° of attitude angle, this hair is utilized Bright k nearest neighbor transform characteristics extracting method and based on differentiating that vector feature extracting method carried out identification experiment, as a result such as Shown in table one.Test neighbour's parameter k1=20, k2=10, Gaussian parameter σ2=6.25.
It can see from the result of table one, to true target, differentiate that the discrimination of vector feature extraction is 83%, and The discrimination that feature extracting method is known in k nearest neighbor transformation of the invention is 90%；To fragment, vector feature extraction is differentiated Discrimination is 78%, and the discrimination of k nearest neighbor transform characteristics extracting method of the invention is 85%；To light weight decoy, vector is differentiated The discrimination of transform characteristics extraction method is 80%, and the discrimination of k nearest neighbor transform characteristics extracting method of the invention is 86%；It is right Weight bait differentiates that the discrimination of vector feature extraction is 82%, and k nearest neighbor transform characteristics extracting method of the invention Discrimination is 83%.On average, to four class targets, the correct recognition rata of k nearest neighbor transform characteristics extracting method of the invention is high In differentiating vector feature extraction, show that k nearest neighbor transform characteristics extracting method of the invention improves multi-class targets really Recognition performance.
The recognition result of one two methods of table
The above description is merely a specific embodiment, any feature disclosed in this specification, except non-specifically Narration, can be replaced by other alternative features that are equivalent or have similar purpose；Disclosed all features or all sides Method or in the process the step of, other than mutually exclusive feature and/or step, can be combined in any way.

Claims (4)

1. a kind of k nearest neighbor converts true and false target's feature-extraction method, which is characterized in that include the following steps：
Step 1：The training sample set about radar target-range image is inputted, x is usedijIndicate training sample, wherein subscript i is Class discrimination symbol, subscript j are training sample specificator, and 1≤i≤g, 1≤j≤Ni, g expression categorical measure, NiIndicate corresponding class Other sample number；
Step 2：Calculate the estimated value of k nearest neighbor transformation matrix A
Wherein, sample matrix
The constraint coefficient matrix of similar k nearest neighbor rule
Matrix
The constraint factor of similar k nearest neighbor ruleBe set as：IfOrThenOtherwiseWherein subscript k is training sample specificator, σ2Indicate Gaussian parameter,Indicate same The k of some vector in class1The set of a neighbour's vector, k1To preset neighbour's number；
The constraint coefficient matrix of foreign peoples's k nearest neighbor rule
Matrix
The wherein constraint factor of foreign peoples's k nearest neighbor ruleBe set as：IfOrL ≠ i, ThenOtherwiseWherein, wherein subscript l is class discrimination symbol,Indicate the k of some vector in foreign peoples2It is a The set of neighbour's vector, k2To preset neighbour's number；
Step 3：Son to be extracted is inputted as the true and false target one-dimensional range profile x of the radar of featuret, according toIt obtains one-dimensional Range Profile xtCharacteristic vector yt。
2. the method as described in claim 1, which is characterized in that in step 2,
Estimated valueFor matrix (X (DB-WB)XT)-1(X(DC-WC)XT) M maximum eigenvalue corresponding feature vector composition Matrix, wherein M < n, n indicate training sample xijNumber of dimensions.
3. method according to claim 1 or 2, which is characterized in that neighbour's number k1、k2Preferred value be k1=20, k2=10.
4. method according to claim 1 or 2, which is characterized in that the preferred value of Gaussian parameter is σ2=6.25.
CN201810964240.1A 2018-08-23 2018-08-23 K-nearest neighbor transformation true and false target feature extraction method Active CN108845302B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201810964240.1A CN108845302B (en) 2018-08-23 2018-08-23 K-nearest neighbor transformation true and false target feature extraction method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810964240.1A CN108845302B (en) 2018-08-23 2018-08-23 K-nearest neighbor transformation true and false target feature extraction method

Publications (2)

Publication Number Publication Date
CN108845302A true CN108845302A (en) 2018-11-20
CN108845302B CN108845302B (en) 2022-06-03

Family

ID=64188337

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810964240.1A Active CN108845302B (en) 2018-08-23 2018-08-23 K-nearest neighbor transformation true and false target feature extraction method

Country Status (1)

Country Link
CN (1) CN108845302B (en)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110007286A (en) * 2019-04-22 2019-07-12 电子科技大学 A kind of true and false target one-dimensional range profile feature extracting method of linear discriminant study
CN110658507A (en) * 2019-10-12 2020-01-07 电子科技大学 Multi-class average maximization true and false target feature extraction method for radar target identification
CN110687514A (en) * 2019-10-16 2020-01-14 电子科技大学 Nonlinear discrimination learning true and false target one-dimensional range profile feature extraction method
CN112149061A (en) * 2020-09-25 2020-12-29 电子科技大学 Multi-class average maximization true and false target feature extraction method
CN113191447A (en) * 2021-05-17 2021-07-30 电子科技大学 Method for extracting characteristics of sample distribution structure chart in unknown target discrimination

Citations (28)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US3298021A (en) * 1963-12-24 1967-01-10 Charles E Jacobs System for the marking of radar echoes and other signals of observed objects on a radar screen
US6035057A (en) * 1997-03-10 2000-03-07 Hoffman; Efrem H. Hierarchical data matrix pattern recognition and identification system
WO2001014907A1 (en) * 1999-08-26 2001-03-01 Raytheon Company Target acquisition system and radon transform based method for target azimuth aspect estimation
US7218270B1 (en) * 2003-02-10 2007-05-15 The United States Of America As Represented By The Secretary Of The Air Force ATR trajectory tracking system (A-Track)
US20080114564A1 (en) * 2004-11-25 2008-05-15 Masayoshi Ihara Information Classifying Device, Information Classifying Method, Information Classifying Program, Information Classifying System
WO2008094172A2 (en) * 2006-06-01 2008-08-07 University Of Florida Research Foundation, Inc. Radar microsensor for detection, tracking, and classification
CN101526995A (en) * 2009-01-19 2009-09-09 西安电子科技大学 Synthetic aperture radar target identification method based on diagonal subclass judgment analysis
CN101561865A (en) * 2009-05-22 2009-10-21 西安电子科技大学 Synthetic aperture radar image target identification method based on multi-parameter spectrum feature
CN101807258A (en) * 2010-01-08 2010-08-18 西安电子科技大学 SAR (Synthetic Aperture Radar) image target recognizing method based on nuclear scale tangent dimensionality reduction
CN102902979A (en) * 2012-09-13 2013-01-30 电子科技大学 Method for automatic target recognition of synthetic aperture radar (SAR)
CN103675787A (en) * 2013-12-03 2014-03-26 电子科技大学 One-dimension range profile optimal orthogonal nolinear subspace identification method for radar targets
CN103679161A (en) * 2014-01-03 2014-03-26 苏州大学 Human-face identifying method and device
CN103679162A (en) * 2014-01-03 2014-03-26 苏州大学 Human-face identifying method and system
CN103941244A (en) * 2014-04-23 2014-07-23 电子科技大学 Radar target one-dimensional range profile local optimal sub-space recognition method
CN103942572A (en) * 2014-05-07 2014-07-23 中国标准化研究院 Method and device for extracting facial expression features based on bidirectional compressed data space dimension reduction
US20150279182A1 (en) * 2014-04-01 2015-10-01 Objectvideo, Inc. Complex event recognition in a sensor network
CN105023006A (en) * 2015-08-05 2015-11-04 西安电子科技大学 Face recognition method based on enhanced nonparametric margin maximization criteria
CN105608471A (en) * 2015-12-28 2016-05-25 苏州大学 Robust transductive label estimation and data classification method and system
CN106199544A (en) * 2016-06-24 2016-12-07 电子科技大学 The Recognition of Radar Target Using Range Profiles method of local tangent space alignment is differentiated based on core
CN106257488A (en) * 2016-07-07 2016-12-28 电子科技大学 A kind of radar target identification method based on neighborhood characteristics space discriminatory analysis
US20160379055A1 (en) * 2015-06-25 2016-12-29 Kodak Alaris Inc. Graph-based framework for video object segmentation and extraction in feature space
CN106772307A (en) * 2017-03-02 2017-05-31 电子科技大学 A kind of true and false bullet target identification method based on many radar informations
CN107037417A (en) * 2017-06-13 2017-08-11 电子科技大学 The non-linear arest neighbors subspace representation method of the one-dimensional picture of the true and false target of radar
CN107238822A (en) * 2017-06-13 2017-10-10 电子科技大学 True and false target one-dimensional range profile Nonlinear Orthogonal subspace representation method
CN107271965A (en) * 2017-06-13 2017-10-20 电子科技大学 Birds of the same feather flock together and collect the true and false target one-dimensional range profile feature extracting method of subspace
CN107678006A (en) * 2017-09-06 2018-02-09 电子科技大学 A kind of true and false target one-dimensional range profile feature extracting method of the radar of largest interval subspace
CN107678007A (en) * 2017-09-06 2018-02-09 电子科技大学 A kind of radar true and false target one-dimensional range profile feature extracting method of the close subspace of pointer field
CN107784293A (en) * 2017-11-13 2018-03-09 中国矿业大学(北京) A kind of Human bodys' response method classified based on global characteristics and rarefaction representation

Patent Citations (28)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US3298021A (en) * 1963-12-24 1967-01-10 Charles E Jacobs System for the marking of radar echoes and other signals of observed objects on a radar screen
US6035057A (en) * 1997-03-10 2000-03-07 Hoffman; Efrem H. Hierarchical data matrix pattern recognition and identification system
WO2001014907A1 (en) * 1999-08-26 2001-03-01 Raytheon Company Target acquisition system and radon transform based method for target azimuth aspect estimation
US7218270B1 (en) * 2003-02-10 2007-05-15 The United States Of America As Represented By The Secretary Of The Air Force ATR trajectory tracking system (A-Track)
US20080114564A1 (en) * 2004-11-25 2008-05-15 Masayoshi Ihara Information Classifying Device, Information Classifying Method, Information Classifying Program, Information Classifying System
WO2008094172A2 (en) * 2006-06-01 2008-08-07 University Of Florida Research Foundation, Inc. Radar microsensor for detection, tracking, and classification
CN101526995A (en) * 2009-01-19 2009-09-09 西安电子科技大学 Synthetic aperture radar target identification method based on diagonal subclass judgment analysis
CN101561865A (en) * 2009-05-22 2009-10-21 西安电子科技大学 Synthetic aperture radar image target identification method based on multi-parameter spectrum feature
CN101807258A (en) * 2010-01-08 2010-08-18 西安电子科技大学 SAR (Synthetic Aperture Radar) image target recognizing method based on nuclear scale tangent dimensionality reduction
CN102902979A (en) * 2012-09-13 2013-01-30 电子科技大学 Method for automatic target recognition of synthetic aperture radar (SAR)
CN103675787A (en) * 2013-12-03 2014-03-26 电子科技大学 One-dimension range profile optimal orthogonal nolinear subspace identification method for radar targets
CN103679161A (en) * 2014-01-03 2014-03-26 苏州大学 Human-face identifying method and device
CN103679162A (en) * 2014-01-03 2014-03-26 苏州大学 Human-face identifying method and system
US20150279182A1 (en) * 2014-04-01 2015-10-01 Objectvideo, Inc. Complex event recognition in a sensor network
CN103941244A (en) * 2014-04-23 2014-07-23 电子科技大学 Radar target one-dimensional range profile local optimal sub-space recognition method
CN103942572A (en) * 2014-05-07 2014-07-23 中国标准化研究院 Method and device for extracting facial expression features based on bidirectional compressed data space dimension reduction
US20160379055A1 (en) * 2015-06-25 2016-12-29 Kodak Alaris Inc. Graph-based framework for video object segmentation and extraction in feature space
CN105023006A (en) * 2015-08-05 2015-11-04 西安电子科技大学 Face recognition method based on enhanced nonparametric margin maximization criteria
CN105608471A (en) * 2015-12-28 2016-05-25 苏州大学 Robust transductive label estimation and data classification method and system
CN106199544A (en) * 2016-06-24 2016-12-07 电子科技大学 The Recognition of Radar Target Using Range Profiles method of local tangent space alignment is differentiated based on core
CN106257488A (en) * 2016-07-07 2016-12-28 电子科技大学 A kind of radar target identification method based on neighborhood characteristics space discriminatory analysis
CN106772307A (en) * 2017-03-02 2017-05-31 电子科技大学 A kind of true and false bullet target identification method based on many radar informations
CN107037417A (en) * 2017-06-13 2017-08-11 电子科技大学 The non-linear arest neighbors subspace representation method of the one-dimensional picture of the true and false target of radar
CN107238822A (en) * 2017-06-13 2017-10-10 电子科技大学 True and false target one-dimensional range profile Nonlinear Orthogonal subspace representation method
CN107271965A (en) * 2017-06-13 2017-10-20 电子科技大学 Birds of the same feather flock together and collect the true and false target one-dimensional range profile feature extracting method of subspace
CN107678006A (en) * 2017-09-06 2018-02-09 电子科技大学 A kind of true and false target one-dimensional range profile feature extracting method of the radar of largest interval subspace
CN107678007A (en) * 2017-09-06 2018-02-09 电子科技大学 A kind of radar true and false target one-dimensional range profile feature extracting method of the close subspace of pointer field
CN107784293A (en) * 2017-11-13 2018-03-09 中国矿业大学(北京) A kind of Human bodys' response method classified based on global characteristics and rarefaction representation

Non-Patent Citations (7)

* Cited by examiner, † Cited by third party
Title
DAIYING ZHOU;XIAOFENG SHEN;WANLIN YANG: "radar target recognition based on fussy optimal transformation using high-resolution range profile", 《PATTERN RECOGNITION LETTERS》 *
DU, C; ZHOU, S; ZHAO, J: "Feature extraction for SAR target recognition based on supervised manifold learning", 《35TH INTERNATIONAL SYMPOSIUM ON REMOTE SENSING OF ENVIRONMENT (ISRSE35)》 *
MENG, JC (MENG, JC) ; YANG, WL (YANG, WL): "Nearest neighbor classifier based on Riemannian metric in radar target recognition", 《2005 IEEE INTERNATIONAL RADAR, CONFERENCE RECORD》 *
Y. HUANG, W. JIN, B. LI, P. GE AND Y. WU: "Automatic Modulation Recognition of Radar Signals Based on Manhattan Distance-Based Features", 《IEEE 》 *
周云: "基于高分辨距离像的雷达目标识别研究", 《 中国博士学位论文全文数据库》 *
廖阔,付建胜,杨万麟: "改进的ReliefF算法用于雷达距离像目标识别", 《电子测量与仪器学报》 *
戴春杨: "雷达目标距离像的识别方法研究", 《中国优秀硕士学位论文全文数据库》 *

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110007286A (en) * 2019-04-22 2019-07-12 电子科技大学 A kind of true and false target one-dimensional range profile feature extracting method of linear discriminant study
CN110007286B (en) * 2019-04-22 2022-05-24 电子科技大学 Linear discriminant learning true and false target one-dimensional range profile feature extraction method
CN110658507A (en) * 2019-10-12 2020-01-07 电子科技大学 Multi-class average maximization true and false target feature extraction method for radar target identification
CN110658507B (en) * 2019-10-12 2022-07-29 电子科技大学 Multi-class average maximization true and false target feature extraction method for radar target identification
CN110687514A (en) * 2019-10-16 2020-01-14 电子科技大学 Nonlinear discrimination learning true and false target one-dimensional range profile feature extraction method
CN110687514B (en) * 2019-10-16 2022-03-15 电子科技大学 Nonlinear discrimination learning true and false target one-dimensional range profile feature extraction method
CN112149061A (en) * 2020-09-25 2020-12-29 电子科技大学 Multi-class average maximization true and false target feature extraction method
CN113191447A (en) * 2021-05-17 2021-07-30 电子科技大学 Method for extracting characteristics of sample distribution structure chart in unknown target discrimination
CN113191447B (en) * 2021-05-17 2022-05-24 电子科技大学 Method for extracting characteristics of sample distribution structure chart in unknown target discrimination

Also Published As

Publication number Publication date
CN108845302B (en) 2022-06-03

Similar Documents

Publication Publication Date Title
CN108845302A (en) A kind of true and false target&#39;s feature-extraction method of k nearest neighbor transformation
CN107037417B (en) The true and false target of radar is one-dimensional as non-linear arest neighbors subspace representation method
CN107238822B (en) Method for extracting orthogonal nonlinear subspace characteristics of true and false target one-dimensional range profile
CN110007286A (en) A kind of true and false target one-dimensional range profile feature extracting method of linear discriminant study
CN108761411A (en) A kind of true and false target one-dimensional range profile feature extracting method
CN107271965B (en) Method for extracting true and false target one-dimensional range profile features in cluster subspace
CN109284786B (en) SAR image terrain classification method for generating countermeasure network based on distribution and structure matching
CN102663752B (en) SAM weighted KEST hyperspectral anomaly detection algorithm
CN109242010A (en) A kind of sparse study RCS sequence characteristic extracting method
CN103217676B (en) Radar target identification method under noise background based on bispectrum de-noising
Li et al. Target discrimination for SAR ATR based on scattering center feature and K-center one-class classification
CN108845303A (en) A kind of non-linear steady true and false target&#39;s feature-extraction method in subspace
CN109901130A (en) A kind of rotor wing unmanned aerial vehicle detection and recognition methods converting and improve 2DPCA based on Radon
CN109255336A (en) Arrester recognition methods based on crusing robot
CN108594202B (en) Neighborhood distribution structure nonlinear projection target feature extraction method
Matkowski et al. Giant panda face recognition using small dataset
CN110687514B (en) Nonlinear discrimination learning true and false target one-dimensional range profile feature extraction method
CN108828574A (en) The separation enhancing true and false target&#39;s feature-extraction method in subspace between one type
CN105893945B (en) A kind of Remote Sensing Target recognition methods
CN108828533A (en) The similar structure of sample keeps non-linear projection feature extracting method in one type
Opitz et al. Evaluation of face recognition technologies for identity verification in an eGate based on operational data of an airport
CN107678007B (en) Method for extracting radar true and false target one-dimensional range profile features in exponential domain compact subspace
CN108564096B (en) A kind of neighborhood fitting RCS sequence characteristic extracting method
CN114280566B (en) One-dimensional range profile identification method based on class label association
CN110780270B (en) Target library attribute discrimination local regular learning subspace feature extraction method

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant