CN109190647A - A kind of active passive data fusion method - Google Patents
A kind of active passive data fusion method Download PDFInfo
- Publication number
- CN109190647A CN109190647A CN201810665685.XA CN201810665685A CN109190647A CN 109190647 A CN109190647 A CN 109190647A CN 201810665685 A CN201810665685 A CN 201810665685A CN 109190647 A CN109190647 A CN 109190647A
- Authority
- CN
- China
- Prior art keywords
- data
- active
- passive
- fusion
- membership
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/251—Fusion techniques of input or preprocessed data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N7/00—Computing arrangements based on specific mathematical models
- G06N7/02—Computing arrangements based on specific mathematical models using fuzzy logic
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Software Systems (AREA)
- Automation & Control Theory (AREA)
- Biomedical Technology (AREA)
- Fuzzy Systems (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Health & Medical Sciences (AREA)
- Algebra (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The present invention provides a kind of active passive data fusion methods, pass through the method for fuzzy clustering, according to the similarity between active data and passive data on time dimension and Spatial Dimension, the data alignment on time dimension, fuzzy clustering in space dimension carries out data subset division and calculates with degree of membership is associated with.Compared with prior art, flexibility is good, compared to the selection that the quality of fusion results in existing method depends on differential seat angle threshold value thresholding, it is no longer necessary to special fusion thresholding be arranged, use more flexibleization；It is low to merge error, substantially increases fusion reliability, reduces fusion error；Adaptability is good, is applicable to all active/passive data fusion systems, also applicable for the data fusion system of multiple sensors, has good system suitability.
Description
Technical field
The present invention relates to a kind of active passive data fusion methods, are related to Radar/EW domain of data fusion.
Background technique
In recent years, with the raising of the promotion of weaponry and information-based fight capability, the integrated system of radar, electronic warfare
System becomes development trend, so that the integration technology based on active data and passive data becomes research emphasis.Data fusion technique
Essence be the information of different sensors is fused together by blending algorithm, thus obtain it is more accurate than single-sensor
Information.By Data Fusion technology, the stability of system and reliable with the space-time coverage area of expansion system, can be enhanced
Property, while enhancing the tracking ability and recognition capability to target.
But mismatched since there are sensing ranges to mismatch between active sensor and passive sensor, perceives dimension,
Acquisition of information such as loses at the reasons, cause at present there is no it is a kind of be suitable for active sensor and passive sensor data fusion row it
Effective method.In general, active sensor can provide more accurate target position information, and passive sensor can provide
Radiation source attribute information abundant, but its radiation source positions ability provided is weaker, is only capable of providing angle of arrival, and precision is poor.
Existing data fusion means are merged based on location information, by comparing active and passive angular amount measured value, according to
The differential seat angle threshold value thresholding of setting carries out fusion judgement, and fusion results are limited to differential seat angle threshold value thresholding value, and reliability is low,
Error is big, significantly limits the application range of the technology.
Summary of the invention
The technical problem to be solved in the present invention is to provide a kind of active passive data fusion methods, can overcome existing method
It is limited to the deficiency that data fusion result reliability is low, error is big caused by differential seat angle threshold value threshold settings, is reduced active
The fusion error of data and passive data, provides fusion reliability.
The technical solution adopted by the invention is as follows:
A kind of active passive data fusion method, by the method for fuzzy clustering, the root on time dimension and Spatial Dimension
According to the similarity between active data and passive data, the data alignment on time dimension, fuzzy clustering in space dimension carries out data
Subset division is calculated with degree of membership is associated with.
Specific method includes,
Fusion in Time (1) is carried out to active data and passive data, to obtaining in different observation times and in the scan period
The active data and passive data taken carries out Data Integration on time dimension, including timeslice divides and time alignment；Wherein,
The time alignment refers to, in the timeslice of selection, carries out unified sequence, shape to active data and passive data measurement moment
At the active metric data and passive metric data for measuring moment unified sequence；
It obtains membership table (3), is based on fuzzy clustering method, measure the moment according to corresponding, calculate the same measurement moment
The spatial statistics distance of corresponding active data and passive data, and fuzzy matrix is constructed, obtain degree of membership relation table；
Association fusion (4) is associated active data with passive data and merges according to degree of membership relation table.
The method also includes, completion active data (2), after Fusion in Time, according to the measurement moment of unified sequence, inquiry
The moment is with the presence or absence of the active data measured, if it is, membership table is obtained based on fuzzy clustering method, if not,
Then calculate the active data at the moment.
The specific method for calculating active data is to be mended according to fused time series by interpolation or the method for extrapolation
The corresponding all passive datas of foot measure the active data at moment.
The timeslice, which is divided, determines that target velocity is faster, and the timeslice of division is shorter with the movement properties of specific time.
Obtain membership table specific method include,
According to the corresponding all passive datas of same measurement moment a certain active data, the moment active data and its are obtained
The range ambiguity subset of corresponding all passive datas；Distance in the range ambiguity subset according to active data with it is passive
The square distance difference of the spatial position of data determines；
According to the correlation degree of distance each between active data and passive data, select at least two subordinating degree functions into
Row measurement；
It brings each distance value in range ambiguity subset into the subordinating degree function, obtains a three-dimensional fuzzy matrix；
Each degree of membership weighting value corresponding to distance value same in the three-dimensional fuzzy matrix, each degree of membership are right with it
The weight answered is added after being multiplied and obtains the membership of the distance value, to obtain the degree of membership of active data and passive data
Relation table.
The method also includes using the redundancy and complementarity between active data and passive data, after being merged
As a result data purification, and the correlation continued for some time between interior fusion results is counted, assign corresponding weight, correlation
Bigger, weight is bigger, on the contrary then reduce.
According to the correlation degree of distance each between active data and passive data, the subordinating degree function includes, in,
It can be with poor four kinds of subordinating degree functions.
In three-dimensional fuzzy matrix same distance value it is corresponding it is good, in, can and poor four kinds of degrees of membership weight, respectively 0.4,
0.3,0.2 and 0.1.
Compared with prior art, the beneficial effects of the present invention are:
Flexibility is good, compared to the selection that the quality of fusion results in existing method depends on differential seat angle threshold value thresholding, originally
Invention uses the method based on space-time dimension fuzzy clustering, is determined between active data and passive data by degree of membership relation table
Syncretic relation, it is no longer necessary to special fusion thresholding be set, more flexibleization is used.
Fusion error is low, and the present invention obtains active data using the method for fuzzy clustering and is associated with the degree of membership of passive data
Table, and be associated according to degree of membership contingency table, and assign association results certain weight, according to long-time fusion results to power
Value is updated, to substantially increase fusion reliability, reduces fusion error.
Adaptability is good, and the present invention uses the method based on space-time dimension fuzzy clustering, is applicable to all active/passive numbers
It is also applicable for the data fusion system of multiple sensors according to emerging system, there is good system suitability.
Detailed description of the invention
Fig. 1 is the active passive fusion method flow diagram of a wherein embodiment of the invention.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, with reference to the accompanying drawings and embodiments, right
The present invention is further elaborated.It should be appreciated that described herein, specific examples are only used to explain the present invention, not
For limiting the present invention.
Any feature disclosed in this specification (including abstract and attached drawing) unless specifically stated can be equivalent by other
Or the alternative features with similar purpose are replaced.That is, unless specifically stated, each feature is a series of equivalent or class
Like an example in feature.
A kind of active passive data fusion method, by the method for fuzzy clustering, the root on time dimension and Spatial Dimension
According to the similarity between active data and passive data, the data alignment on time dimension, fuzzy clustering in space dimension carries out data
Subset division is calculated with degree of membership is associated with.
The present invention program, compared with prior art method, it is no longer necessary to set special differential seat angle threshold value thresholding, fusion results
With higher reliability, merges error and substantially reduce.
Specific method includes,
As shown in Figure 1, carry out Fusion in Time (1) to active data and passive data, in different observation times and sweeping
It retouches the active data obtained in the period and passive data carries out Data Integration on time dimension, including timeslice divides and the time
Alignment；Wherein, the time alignment refers to, in the timeslice of selection, measures moment progress to active data and passive data
Unified sequence forms the active metric data and passive metric data for measuring moment unified sequence；
It obtains membership table (3), is based on fuzzy clustering method, measure the moment according to corresponding, calculate the same measurement moment
The spatial statistics distance of corresponding active data and passive data, and fuzzy matrix is constructed, obtain degree of membership relation table；
Association fusion (4) is associated active data with passive data and merges according to degree of membership relation table.
The method also includes, completion active data (2), after Fusion in Time, according to the measurement moment of unified sequence, inquiry
The moment is with the presence or absence of the active data measured, if it is, membership table is obtained based on fuzzy clustering method, if not,
Then calculate the active data at the moment.
As an implementation, the specific method for calculating active data is, according to fused time series, by interior
The method inserted or extrapolated supplies the active data that corresponding all passive datas measure the moment.
Since the data transfer rate that passive data obtains is higher than active data, subsequent fusion for convenience needs to extrapolate passive
Data measure moment corresponding all active datas.When specific operation, the measurement moment sorted according to fused unification, according to
The passive measurement moment carries out screening and completion to active data: if the corresponding passive measurement moment, there are active datas, after continuing
Continuous operation, otherwise, passive measurement moment corresponding active data according to the mode completion of interpolation or extrapolation.
When the correspondence passive measurement moment active metric data being not present, active number is carried out using interpolation or the method for extrapolation
According to completion.Using the method for curve matching building approximating function when interpolation or extrapolation, approximating function is set as y=f (t), and wherein t is
Passive data measures the moment, and y is that the passive data measures moment corresponding active data.Approximating function specific formula is as follows:
Wherein, t0、t1、t2Moment time that there is active metric data constantly, y are closed on for the passive data measurement moment0=
f(t0)、y1=f (t1)、y2=f (t2) it is respectively t0、t1、t2Corresponding active metric data, i.e. t0、t1、t2、y0、y1、y2It is
Known quantity.Utilize t0、t1、t2Moment value and its corresponding functional value y0、y1、y2It can determine the two of approximating function y=f (t)
Order polynomial coefficient substitutes into the passive measurement moment value t for needing to carry out interpolation or extrapolation, then can further extrapolate passive at this
Measure moment corresponding active data.
The timeslice, which is divided, determines that target velocity is faster, and the timeslice of division is shorter with the movement properties of specific time,
It may be selected to be minute as time of fusion piece may be selected in static/slower-velocity target, time of fusion piece, which may be selected, in high-speed target may be selected to be
Second grade.
Obtain membership table specific method include,
According to the corresponding all passive datas of same measurement moment a certain active data, the moment active data and its are obtained
The range ambiguity subset of corresponding all passive datas；Distance in the range ambiguity subset according to active data with it is passive
The square distance difference of the spatial position of data determines；
According to the correlation degree of distance each between active data and passive data, select at least two subordinating degree functions into
Row measurement；
It brings each distance value in range ambiguity subset into the subordinating degree function, obtains a three-dimensional fuzzy matrix；
Each degree of membership weighting value corresponding to distance value same in the three-dimensional fuzzy matrix, each degree of membership are right with it
The weight answered is added after being multiplied and obtains the membership of the distance value, to obtain the degree of membership of active data and passive data
Relation table.
The method also includes using the redundancy and complementarity between active data and passive data, after being merged
As a result data purification, and the correlation continued for some time between interior fusion results is counted, assign corresponding weight, correlation
Bigger, weight is bigger, on the contrary then reduce.According to long-time fusion results and weight results are provided, reduce erroneous association bring
It influences, to obtain more accurately active data and passive data fusion results.
If measuring moment corresponding active data is Pi(i=1 ..., N), corresponding passive data are Qj(j=1 ..., M),
Take a fixed active data Pi, then it constitutes one about the limited fuzzy of statistical distance r with respect to the moment all passive datas
Subset R=(ri1,ri2,…,riM).Wherein, statistical distance r is put down at a distance from the spatial position of passive data according to active data
Variance determines；I is active data PiIn some active data number；J is some passive data Q in passive datajNumber.
As a kind of specific embodiment, for the correlation degree of distance each between active data and passive data, choosing
Take, in, can, poor four kinds of subordinating degree function u1、u2、u3、u4It is measured, subordinating degree function is expressed as follows.
Wherein:
W1, w2, w3 are adjusting parameter in above formula, with specific reference to the meter of statistical distance r between active data and passive data
Range is calculated to be determined, statistics four regions [0, w1] of r for being divided by adjusting parameter w1, w2, w3, [w1, w2], [w2,
W3], [w3, ∞] respectively corresponded apart from it is associated it is good, in, can, poor four kinds of correlation degrees.
Each distance value in fuzzy subset R is substituted into subordinating degree function u1、u2、u3、u4, obtain dimension N × M × 4
Three-dimensional fuzzy matrix.
To statistical distance r same in fuzzy matrixijCorresponding 4 degrees of membership according to it is good, in, can, poor weighting value, successively take
It is 0.4,0.3,0.2,0.1, is multiplied and obtains statistical distance rijCorresponding membership cij=0.4*u1(rij)+0.3*u2(rij)+
0.2*u3(rij)+0.1*u4(rij), to obtain the degree of membership relation table C=(c of active data and passive dataij)N×M, the person in servitude
Category degree relation table is the two-dimensional matrix that dimension is N × M, and reflect active data and passive data is associated with situation.
Claims (9)
1. a kind of active passive data fusion method, by the method for fuzzy clustering, the basis on time dimension and Spatial Dimension
Similarity between active data and passive data, the data alignment on time dimension, fuzzy clustering in space dimension carry out data
Collection divides and is associated with degree of membership calculating.
2. active passive data fusion method according to claim 1, specific method include,
Fusion in Time (1) is carried out to active data and passive data, to obtaining in different observation times and in the scan period
Active data and passive data carry out Data Integration on time dimension, including timeslice divides and time alignment；Wherein, described
Time alignment refers to, in the timeslice of selection, carries out unified sequence, forming amount to active data and passive data measurement moment
Survey the active metric data and passive metric data of moment unified sequence；
It obtains membership table (3), is based on fuzzy clustering method, measure the moment according to corresponding, it is corresponding to calculate the same measurement moment
Active data and passive data spatial statistics distance, and construct fuzzy matrix, obtain degree of membership relation table；
Association fusion (4) is associated active data with passive data and merges according to degree of membership relation table.
3. active passive data fusion method according to claim 2, the method also includes, completion active data (2),
After Fusion in Time, according to the measurement moment of unified sequence, the moment is inquired with the presence or absence of the active data measured, if it is,
Membership table is obtained based on fuzzy clustering method, if it is not, then calculating the active data at the moment.
4. active passive data fusion method according to claim 3 calculates that the specific method of active data is, according to melting
Time series after conjunction supplies the active data that corresponding all passive datas measure the moment by interpolation or the method for extrapolation.
5. active passive data fusion method according to claim 2, the timeslice is divided with the movement of specific time
Attribute determines that target velocity is faster, and the timeslice of division is shorter.
6. active passive data fusion method according to claim 2, the specific method for obtaining membership table include,
According to the corresponding all passive datas of same measurement moment a certain active data, obtains the moment active data and its institute is right
The range ambiguity subset for all passive datas answered；Distance in the range ambiguity subset is according to active data and passive data
Spatial position square distance difference determine；
According to the correlation degree of distance each between active data and passive data, at least two subordinating degree function degree of progress are selected
Amount；
It brings each distance value in range ambiguity subset into the subordinating degree function, obtains a three-dimensional fuzzy matrix；
Each degree of membership weighting value corresponding to distance value same in the three-dimensional fuzzy matrix, each degree of membership are corresponding
Weight is added after being multiplied and obtains the membership of the distance value, to obtain the degree of membership relationship of active data and passive data
Table.
7. active passive data fusion method according to claim 2, the method also includes utilizing active data and nothing
Redundancy and complementarity between source data, the data purification of result after being merged, and count and continue for some time interior fusion
As a result the correlation between assigns corresponding weight, and correlation is bigger, and weight is bigger, on the contrary then reduce.
8. active passive data fusion method according to claim 6, according to each between active data and passive data
The correlation degree of distance, the subordinating degree function includes, in, can and poor four kinds of subordinating degree functions.
9. active passive data fusion method according to claim 6, same distance value is corresponding in three-dimensional fuzzy matrix
It is good, in, can and poor four kinds of degrees of membership weight, respectively 0.4,0.3,0.2 and 0.1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810665685.XA CN109190647B (en) | 2018-06-26 | 2018-06-26 | Active and passive data fusion method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810665685.XA CN109190647B (en) | 2018-06-26 | 2018-06-26 | Active and passive data fusion method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109190647A true CN109190647A (en) | 2019-01-11 |
| CN109190647B CN109190647B (en) | 2022-03-08 |
Family
ID=64948475
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810665685.XA Active CN109190647B (en) | 2018-06-26 | 2018-06-26 | Active and passive data fusion method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109190647B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110007287A (en) * | 2019-04-22 | 2019-07-12 | 电子科技大学 | A kind of fuzzy membership one-dimensional range profile multiple features fusion method |
| CN110428154A (en) * | 2019-07-20 | 2019-11-08 | 中国船舶重工集团公司第七二四研究所 | Multiband phased array devices phase mutual designation method for detecting based on radiation source database |
| CN112632463A (en) * | 2020-12-22 | 2021-04-09 | 中国航空工业集团公司沈阳飞机设计研究所 | Target data association method and device based on multiple attributes |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2007030340A1 (en) * | 2005-09-01 | 2007-03-15 | Ios Technologies, Inc. | Method and system for obtaining high resolution 3-d images of moving objects by use of sensor fusion |
| CN101216998A (en) * | 2008-01-11 | 2008-07-09 | 浙江工业大学 | An information amalgamation method of evidence theory urban traffic flow based on fuzzy rough sets |
| US20110128819A1 (en) * | 2009-12-01 | 2011-06-02 | Raytheon Company | Active sonar system and active sonar method using fuzzy logic |
| JP2012177602A (en) * | 2011-02-25 | 2012-09-13 | Toshiba Corp | Target tracking device |
| CN102780765A (en) * | 2012-06-27 | 2012-11-14 | 浙江大学 | Cloud manufacturing service resource match and combination method based on performance fusion |
| US20130080376A1 (en) * | 2009-08-19 | 2013-03-28 | Bae Systems | Fuzzy inference apparatus and methods, systems and apparatuses using such inference apparatus |
| CN104812099A (en) * | 2015-03-27 | 2015-07-29 | 湘潭大学 | Resolution adjustable data visualizing method in wireless sensor network |
| CN104931960A (en) * | 2015-05-25 | 2015-09-23 | 中国电子科技集团公司第十研究所 | Trend message and radar target state information whole-track data correlation method |
| CN108061889A (en) * | 2017-11-22 | 2018-05-22 | 西南电子技术研究所（中国电子科技集团公司第十研究所） | AIS and the correlating method of radar angular system deviation |
-
2018
- 2018-06-26 CN CN201810665685.XA patent/CN109190647B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2007030340A1 (en) * | 2005-09-01 | 2007-03-15 | Ios Technologies, Inc. | Method and system for obtaining high resolution 3-d images of moving objects by use of sensor fusion |
| CN101216998A (en) * | 2008-01-11 | 2008-07-09 | 浙江工业大学 | An information amalgamation method of evidence theory urban traffic flow based on fuzzy rough sets |
| US20130080376A1 (en) * | 2009-08-19 | 2013-03-28 | Bae Systems | Fuzzy inference apparatus and methods, systems and apparatuses using such inference apparatus |
| US20110128819A1 (en) * | 2009-12-01 | 2011-06-02 | Raytheon Company | Active sonar system and active sonar method using fuzzy logic |
| JP2012177602A (en) * | 2011-02-25 | 2012-09-13 | Toshiba Corp | Target tracking device |
| CN102780765A (en) * | 2012-06-27 | 2012-11-14 | 浙江大学 | Cloud manufacturing service resource match and combination method based on performance fusion |
| CN104812099A (en) * | 2015-03-27 | 2015-07-29 | 湘潭大学 | Resolution adjustable data visualizing method in wireless sensor network |
| CN104931960A (en) * | 2015-05-25 | 2015-09-23 | 中国电子科技集团公司第十研究所 | Trend message and radar target state information whole-track data correlation method |
| CN108061889A (en) * | 2017-11-22 | 2018-05-22 | 西南电子技术研究所（中国电子科技集团公司第十研究所） | AIS and the correlating method of radar angular system deviation |
Non-Patent Citations (4)
| Title |
|---|
| LIU HAN 等: "Clustering Methods for Multi-sensor Data Fusion", 《2012 INTERNATIONAL CONFERENCE ON INDUSTRIAL CONTROL AND ELECTRONICS ENGINEERING》 * |
| ZHU JIAN等: "Data Fusion for Magnetic Sensor Based on Fuzzy Logic Theory", 《 2011 FOURTH INTERNATIONAL CONFERENCE ON INTELLIGENT COMPUTATION TECHNOLOGY AND AUTOMATION》 * |
| 王杰贵等: "基于信息融合的机动多目标单站无源跟踪关键技术研究", 《系统仿真学报》 * |
| 马敏等: "一种无源雷达的数据关联技术", 《雷达科学与技术》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110007287A (en) * | 2019-04-22 | 2019-07-12 | 电子科技大学 | A kind of fuzzy membership one-dimensional range profile multiple features fusion method |
| CN110007287B (en) * | 2019-04-22 | 2022-08-02 | 电子科技大学 | Fuzzy membership one-dimensional range profile multi-feature fusion method |
| CN110428154A (en) * | 2019-07-20 | 2019-11-08 | 中国船舶重工集团公司第七二四研究所 | Multiband phased array devices phase mutual designation method for detecting based on radiation source database |
| CN110428154B (en) * | 2019-07-20 | 2023-04-07 | 中国船舶重工集团公司第七二四研究所 | Multi-band phased array equipment mutual guide detection method based on radiation source database |
| CN112632463A (en) * | 2020-12-22 | 2021-04-09 | 中国航空工业集团公司沈阳飞机设计研究所 | Target data association method and device based on multiple attributes |
| CN112632463B (en) * | 2020-12-22 | 2024-06-11 | 中国航空工业集团公司沈阳飞机设计研究所 | Multi-attribute-based target data association method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109190647B (en) | 2022-03-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109190647A (en) | A kind of active passive data fusion method | |
| CN105955258B (en) | Robot global grating map construction method based on the fusion of Kinect sensor information | |
| CN103487034B (en) | Method for measuring distance and height by vehicle-mounted monocular camera based on vertical type target | |
| CN104677340B (en) | Point character based monocular vision pose measurement method | |
| US8831778B2 (en) | Method of accurate mapping with mobile robots | |
| CN1940591B (en) | System and method of target tracking using sensor fusion | |
| CN108089148B (en) | A kind of passive track-corelation direction cross positioning method based on time difference information | |
| CN104807460B (en) | Unmanned plane indoor orientation method and system | |
| CN107526085B (en) | Ultrasonic array ranging modeling method and system | |
| CN109975798B (en) | Target detection method based on millimeter wave radar and camera | |
| JP2012128744A (en) | Object recognition device, object recognition method, learning device, learning method, program and information processing system | |
| CN108882149B (en) | NLOS compensation positioning method of distance correlation probability | |
| Alt et al. | Reconstruction of transparent objects in unstructured scenes with a depth camera | |
| CN109858526A (en) | Sensor-based multi-target track fusion method in a kind of target following | |
| CN102175991A (en) | Target positioning method based on maximum positioning likelihood sensor configuration | |
| CN108263389A (en) | A kind of vehicle front false target device for eliminating and method | |
| CN103714550B (en) | A kind of image registration automatic optimization method based on match curve feature evaluation | |
| CN110058222A (en) | A kind of preceding tracking of two-layered spherical particle filtering detection based on sensor selection | |
| CN109727226A (en) | A kind of position table automatic generation method based on machine learning | |
| CN104867156B (en) | Feature point identification method for pose measurement of cooperative marker | |
| CN109917372A (en) | Extension target based on target prediction measures collection division and tracking | |
| CN102541356A (en) | Touch point positioning method for optical touch panel and optical touch panel device | |
| Mo et al. | A survey on recent reflective detection methods in simultaneous localization and mapping for robot applications | |
| CN109521395A (en) | Main passive sensor object localization method based on UT-DC | |
| CN115407320A (en) | Indoor human body space positioning and posture contour recognition 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 |