CN109489659A - A kind of localization method based on the detection of more geomagnetic elements - Google Patents
A kind of localization method based on the detection of more geomagnetic elements Download PDFInfo
- Publication number
- CN109489659A CN109489659A CN201811524507.1A CN201811524507A CN109489659A CN 109489659 A CN109489659 A CN 109489659A CN 201811524507 A CN201811524507 A CN 201811524507A CN 109489659 A CN109489659 A CN 109489659A
- Authority
- CN
- China
- Prior art keywords
- track
- artificial fish
- geomagnetic
- food concentration
- optimal
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/04—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by terrestrial means
- G01C21/08—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by terrestrial means involving use of the magnetic field of the earth
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/20—Instruments for performing navigational calculations
Abstract
The present invention provides a kind of localization methods based on the detection of more geomagnetic elements, comprising the following steps: S1, detection earth magnetism total amount, horizontal component and vertical component data；S2, several Artificial Fishs are extracted from artificial fish-swarm again corresponding track is input to horizontal component, and assessed using Hausdorff distance as evaluation criteria；S3, again from the track extract assessment it is optimal before several tracks, further reduce footprint；S4, finally will be optimal before several tracks be input in vertical component, several tracks before optimal are assessed by Hausdorff assessment algorithm, exporting an optimal track is true track, to realize location navigation.The beneficial effects of the present invention are: improving positioning accuracy and stability, the accuracy requirement of underwater navigation is met.
Description
Technical field
The present invention relates to magnetic field navigation more particularly to a kind of localization methods based on the detection of more geomagnetic elements.
Background technique
Ocean possesses the resources such as biology abundant, mineral, the energy, chemistry, and the equipment such as underwater vehicle are currently mainly used
Carry out undersea detection, the exploration of marine resources and the tasks such as exploitation, ocean rescue and salvaging.Therefore underwater vehicle becomes the world
The Hot spots for development of ocean big country.Due to being realized on submariner device under water high-precision by the idle of size, weight, power consumption etc.
Degree, prolonged navigation are very difficult.Current airmanship such as sound system, GPS, inertial navigation etc., due to hidden
The disadvantages of covering property is poor, error is higher, is not able to satisfy the requirement of duration and precision, and earth-magnetism navigation technology becomes the one kind solved the problems, such as
Approach.
Earth-magnetism navigation has passive, independently, low in energy consumption, strong antijamming capability, without accumulated error and the advantages of moderate accuracy,
Especially have broad application prospects in navigation under water.In the earth-magnetism navigation method being currently known, main use passes through magnetic field
Total amount list geomagnetic element and geomagnetic chart carry out matched method, and such method is due to magnetic field detection precision, geomagnetic chart precision and outer
The influence of portion's magnetic interference, precision be not high.Single geomagnetic element matching precision, stability are also less than more geomagnetic element matchings.
Therefore, if realizing that a kind of localization method of geomagnetic matching based on multi-characteristicquantity quantity is very urgent.
Summary of the invention
In order to solve the problems in the prior art, the present invention provides a kind of positioning sides based on the detection of more geomagnetic elements
Method.
The present invention provides a kind of localization methods based on the detection of more geomagnetic elements, comprising the following steps:
S1, detection earth magnetism total amount, horizontal component and vertical component data；First with earth magnetism aggregate data, by artificial fish-swarm
Algorithm scans on geomagnetic chart, is matched by artificial fish-swarm algorithm with geomagnetic chart, artificial fish-swarm is gathered in real trace
Near；
S2, several Artificial Fishs are extracted from artificial fish-swarm again corresponding track is input to horizontal component, and with
Hausdorff distance is assessed as evaluation criteria；
S3, again from the track extract assessment it is optimal before several tracks, further reduce footprint；
S4, finally will be optimal before several tracks be input in vertical component, by Hausdorff assessment algorithm to optimal
Preceding several tracks assessed, exporting an optimal track is true track, to realize location navigation.
As a further improvement of the present invention, step S1 includes following sub-step:
S11, acquisition inertial navigation track [xik yik]T, true track [xrk yrk]TWith magnetic survey sequence, i, r are respectively used
Lead with true track sequence number, k be sequence in ground magnetic dot, acquire magnetic survey sequence when, acquire geomagnetic total intensityIt is horizontal
IntensityWith vertical intensity magnetic valueWherein F indicates overall strength, and H is horizontal intensity, and Z is vertical intensity；
S12, first geomagnetic chart: setting artificial fish-swarm initial parameter Artificial Fish item number N, Artificial Fish moving step length Step,
Artificial Fish visual field Visual, maximum attempts Try_number, crowding δ, maximum number of iterations MAXGEN；
S13, it determines each factor range in Artificial Fish individual state J=(α, θ, △ x, △ y), initializes Artificial Fish
Group, obtains all initial tracks；
S14, For i=1 to MAXGEN；
S15, Artificial Fish current state be Ji, food concentration K is calculated using formula (1-1)i, within the vision at its
Number of partners is nf, the center state of partner is Jc, corresponding food concentration is KcIf meeting Kc/nf>δKi, execute formula
(1-1) otherwise executes the foraging behavior, (J after record is mobilenext1, Knext1)；
In formula, random number of the Rand between (0,1), | | JV- J | | it is the distance of two Artificial Fishs；
Ki=f (Ji) i-th Artificial Fish position food concentration, i.e. objective function；
S16, Artificial Fish current state be Ji, food concentration Ki, it is n in its number of partners within the visionf, partner
Optimal location state in is Jmax, corresponding food concentration is KmaxIf meeting Kmax/nf>δKmax, it executes formula (1-1),
Otherwise the foraging behavior, (J after record is mobile are executednext2, Knext2)；
S17, compare food concentration Knext1And Knext2Size, by food concentration it is biggish value and it is corresponding preceding several
A state saves as the first record, compares obtained food concentration value and the value on the first record after every Artificial Fish action
Compared with if the value is replaced state and its corresponding food concentration on the first record better than the first record by food concentration；
S18, the number of iterations i add 1, and circulation reaches setting value MAXGEN；
S19、End For。
As a further improvement of the present invention, in step S17, compare food concentration Knext1And Knext2Size, by food
The biggish value of concentration and first three corresponding ten state are stored on the first record.
As a further improvement of the present invention, food concentration is exactly the target function value of artificial fish-swarm, i.e. artificial fish-swarm
Optimization criterion, it is assumed that the earth magnetism sequence of extraction is at the track after affine transformationEarth magnetism measured data sequence is Mk, food
Concentration is set as following form:
Wherein,
Hausdorff distance does not emphasize matching double points, and relationship between points is very fuzzy, thus has very strong
Anti-interference ability and fault-tolerant ability.Improved arithmetic result value is bigger, then gathersAnd MkIt differs remoter.It is basic herein
On, Artificial Fish food concentration is changed to following formula (1-5), then it is optimal solution that food concentration is highest；
Foodconsistence is food distance in formula.
As a further improvement of the present invention, in step s 13, Artificial Fish individual state J=(α, θ, △ x, △ are determined
Y) each factor range in is as follows:
As a further improvement of the present invention, step S2 includes: second geomagnetic chart: taking out the Artificial Fish on the first record
State, then by track transformation corresponding displacement track can be obtained.
As a further improvement of the present invention, step S3 includes: to calculate every track of assessment by Hausdorff detecting and evaluating algorithms
Assessed value, several optimal tracks of assessed value are saved on the second record.
As a further improvement of the present invention, it in step S3, is calculated by Hausdorff detecting and evaluating algorithms and assesses every track
Three optimal tracks of assessed value are saved on the second record by assessed value.
As a further improvement of the present invention, step S4 includes: third geomagnetic chart: the position saved on the second record of input
Track is moved, the assessed value of every track of assessment is calculated by Hausdorff detecting and evaluating algorithms, assessed value optimal trajectory is saved in third
It records and exports, as final targetpath.
The beneficial effects of the present invention are: through the above scheme, the main characteristic using Artificial Fish aggregation in fish-swarm algorithm,
After fish-swarm algorithm stops, Artificial Fish is gathered near earth magnetism real trace, then passes through horizontal component and vertical component data
Artificial Fish is screened, obtains true track step by step, realizes a kind of determining for geomagnetic matching based on multi-characteristicquantity quantity
Position method, improves positioning accuracy and stability, meets the accuracy requirement of underwater navigation.
Specific embodiment
The invention will be further described With reference to embodiment.
A kind of localization method based on the detection of more geomagnetic elements, detection earth magnetism total amount, horizontal component and vertical component data,
It is matched by artificial fish-swarm algorithm with geomagnetic chart first with earth magnetism aggregate data, then extracts several manually from artificial fish-swarm
Corresponding track is input to horizontal component by fish, and is assessed using Hausdorff distance as evaluation criteria, again from this
It is extracted in a little tracks and assesses optimal preceding several tracks, further reduce footprint, these tracks are finally input to the
In three characteristic quantities (magnetic vertical intensity), similarly this last track is assessed by Hausdorff assessment algorithm, it is defeated
An optimal track is true track out, to realize the effect of location navigation.This is more apart from i.e. person of outstanding talent by Hausdorff
Husband's distance, the distance between proper subclass in Hausdorff distance metric space.Hausdorff distance is that another kind can answer
Used in the distance of edge matching algorithm.
Detailed process is as follows:
01, start；
02, inertial navigation track [x is acquiredik yik]T, true track [xrk yrk]TWith magnetic survey sequence, i, r are respectively inertial navigation
With true track sequence number, k is the ground magnetic dot in sequence, locality need to acquire geomagnetic total intensity when magnetic order columnHorizontal intensityWith vertical intensity magnetic valueWherein F indicates overall strength, and H is horizontal intensity, and Z is vertical intensity；
03, first geomagnetic chart: setting artificial fish-swarm initial parameter Artificial Fish item number N, Artificial Fish moving step length Step, people
Work fish visual field Visual, maximum attempts Try_number, crowding δ, maximum number of iterations MAXGEN；
04, each factor range in Artificial Fish individual state J=(α, θ, △ x, △ y) is determined, as shown in table 1, initially
Change artificial fish-swarm, obtains all initial tracks；
05, For i=1 to MAXGEN；
06, the current state of Artificial Fish is Ji, food concentration K is calculated using formula (1-1)i, in its partner within the vision
It is n with numberf, the center state of partner is Jc, corresponding food concentration is KcIf meeting Kc/nf>δKi, execute formula (1-
1) the foraging behavior, (J after record is mobile, are otherwise executednext1, Knext1)；
07, the current state of Artificial Fish is Ji, food concentration Ki, it is n in its number of partners within the visionf, partner
In optimal location state be Jmax, corresponding food concentration is KmaxIf meeting Kmax/nf>δKmax, it executes formula (1-1), it is no
Then execute the foraging behavior, (J after record is mobilenext2,Knext2)；
08, compare food concentration Knext1And Knext2Size, by food concentration it is biggish value and it is first three ten corresponding
State is stored on bulletin plate one, compares obtained food concentration value and the value on bulletin plate one after every Artificial Fish action
Compared with if the value is replaced state and its corresponding food concentration on bulletin plate one better than bulletin plate one by food concentration；
09, the number of iterations i adds 1, and circulation reaches setting value MAXGEN；
10,End For；
11, second geomagnetic chart: the state of the Artificial Fish on bulletin plate one is taken out, then correspondence can be obtained by track transformation
Displacement track；
12, the assessed value that every track of assessment is calculated by Hausdorff detecting and evaluating algorithms most avoids optimal three of assessed value
It is saved on bulletin plate two；
13, third geomagnetic chart: the displacement track saved on input bulletin plate two is calculated by Hausdorff detecting and evaluating algorithms
Assessed value optimal trajectory is saved on bulletin plate three and is exported by the assessed value for assessing every track, as final target boat
Mark；
14, terminate.
In formula, random number of the Rand between (0,1), | | JV- J | | it is the distance of two Artificial Fishs；
Ki=f (Ji) i-th Artificial Fish position food concentration, i.e. objective function；
Food concentration is exactly the target function value of artificial fish-swarm, i.e. the optimization criterion of artificial fish-swarm, it is assumed that through affine transformation
The earth magnetism sequence of extraction is at track afterwardsEarth magnetism measured data sequence is Mk, food concentration is set as following form:
Wherein,
Hausdorff distance does not emphasize matching double points, and relationship between points is very fuzzy, thus has very strong
Anti-interference ability and fault-tolerant ability.Improved arithmetic result value is bigger, then gathersAnd MkIt differs remoter.It is basic herein
On, Artificial Fish food concentration is changed to following formula (1-5), then it is optimal solution that food concentration is highest；
Foodconsistence is food distance in formula.
1 artificial fish-swarm algorithm parameter declaration of table and setting
A kind of localization method based on the detection of more geomagnetic elements provided by the invention, mainly utilizes Artificial Fish in fish-swarm algorithm
The characteristic of aggregation, after fish-swarm algorithm stopping, Artificial Fish is gathered near earth magnetism real trace, then by horizontal component and
Vertical component data screens Artificial Fish, obtains true track step by step.
A kind of localization method based on the detection of more geomagnetic elements provided by the invention, is related to magnetic field navigation, is mainly used in
The air navigation aid of underwater vehicle.
The above content is a further detailed description of the present invention in conjunction with specific preferred embodiments, and it cannot be said that
Specific implementation of the invention is only limited to these instructions.For those of ordinary skill in the art to which the present invention belongs, exist
Under the premise of not departing from present inventive concept, a number of simple deductions or replacements can also be made, all shall be regarded as belonging to of the invention
Protection scope.
Claims (9)
1. a kind of localization method based on the detection of more geomagnetic elements, which comprises the following steps:
S1, detection earth magnetism total amount, horizontal component and vertical component data；First with earth magnetism aggregate data, by artificial fish-swarm algorithm
It scans for, is matched by artificial fish-swarm algorithm with geomagnetic chart, artificial fish-swarm is gathered near real trace on geomagnetic chart；
S2, several Artificial Fishs are extracted from artificial fish-swarm again corresponding track is input to horizontal component, and with Hausdorff
Distance is assessed as evaluation criteria；
S3, again from the track extract assessment it is optimal before several tracks, further reduce footprint；
S4, finally will be optimal before several tracks be input in vertical component, by Hausdorff assessment algorithm to before optimal
Several tracks are assessed, and exporting an optimal track is true track, to realize location navigation.
2. it is according to claim 1 based on more geomagnetic elements detection localization method, it is characterised in that: step S1 include with
Lower sub-step:
S11, acquisition inertial navigation track [xik yik]T, true track [xrk yrk]TWith magnetic survey sequence, i, r are respectively inertial navigation and true
Real track sequence number, k is the ground magnetic dot in sequence, when acquiring magnetic survey sequence, acquires geomagnetic total intensityHorizontal intensityWith vertical intensity magnetic valueWherein F indicates overall strength, and H is horizontal intensity, and Z is vertical intensity；
It is S12, first geomagnetic chart: setting artificial fish-swarm initial parameter Artificial Fish item number N, Artificial Fish moving step length Step, artificial
Fish visual field Visual, maximum attempts Try_number, crowding δ, maximum number of iterations MAXGEN；
S13, it determines each factor range in Artificial Fish individual state J=(α, θ, △ x, △ y), initializes artificial fish-swarm, obtain
To all initial tracks；
S14, For i=1to MAXGEN；
S15, Artificial Fish current state be Ji, food concentration K is calculated using formula (1-1)i, in its partner within the vision
Number is nf, the center state of partner is Jc, corresponding food concentration is KcIf meeting Kc/nf>δKi, it executes formula (1-1),
Otherwise the foraging behavior, (J after record is mobile are executednext1,Knext1)；
In formula, random number of the Rand between (0,1), | | JV- J | | it is the distance of two Artificial Fishs；
Ki=f (Ji) i-th Artificial Fish position food concentration, i.e. objective function；
S16, Artificial Fish current state be Ji, food concentration Ki, it is n in its number of partners within the visionf, Huo Banzhong
Optimal location state be Jmax, corresponding food concentration is KmaxIf meeting Kmax/nf>δKmax, execute formula (1-1), otherwise
Execute the foraging behavior, (J after record is mobilenext2,Knext2)；
S17, compare food concentration Knext1And Knext2Size, by the biggish value of food concentration and several corresponding preceding states
The first record is saved as, is compared obtained food concentration value with the value on the first record after every Artificial Fish action, such as
The value is then replaced state and its corresponding food concentration on the first record better than the first record by fruit food concentration；
S18, the number of iterations i add 1, and circulation reaches setting value MAXGEN；
S19、End For。
3. the localization method according to claim 2 based on the detection of more geomagnetic elements, it is characterised in that: in step S17,
Compare food concentration Knext1And Knext2The biggish value of food concentration and first three corresponding ten state are stored in by size
On first record.
4. the localization method according to claim 2 based on the detection of more geomagnetic elements, it is characterised in that: food concentration is exactly
The target function value of artificial fish-swarm, the i.e. optimization criterion of artificial fish-swarm, it is assumed that the earth magnetism extracted at the track after affine transformation
Sequence isEarth magnetism measured data sequence is Mk, food concentration is set as following form:
Wherein,
Hausdorff distance does not emphasize matching double points, and relationship between points is very fuzzy, thus has very strong anti-
Interference performance and fault-tolerant ability.Improved arithmetic result value is bigger, then gathersAnd MkIt differs remoter.On this basis, people
Work fish food concentration is changed to following formula (1-5), then it is optimal solution that food concentration is highest；
Foodconsistence is food distance in formula.
5. the localization method according to claim 2 based on the detection of more geomagnetic elements, it is characterised in that: in step s 13,
Determine that each factor range in Artificial Fish individual state J=(α, θ, △ x, △ y) is as follows:
6. the localization method according to claim 2 based on the detection of more geomagnetic elements, it is characterised in that: step S2 includes:
Second geomagnetic chart: the state of the Artificial Fish on the first record is taken out, then corresponding displacement track can be obtained by track transformation.
7. the localization method according to claim 6 based on the detection of more geomagnetic elements, it is characterised in that: step S3 includes:
Several articles of optimal tracks of assessed value are saved in the by the assessed value that every track of assessment is calculated by Hausdorff detecting and evaluating algorithms
On two records.
8. the localization method based on the detection of more geomagnetic elements stated according to claim 7, it is characterised in that: in step S3, by
Hausdorff detecting and evaluating algorithms calculate the assessed value of every track of assessment, and three optimal tracks of assessed value are saved in the second note
In record.
9. the localization method based on the detection of more geomagnetic elements stated according to claim 8, it is characterised in that: step S4 includes: the
Three geomagnetic charts: the displacement track saved on the second record of input is calculated by Hausdorff detecting and evaluating algorithms and assesses every track
Assessed value optimal trajectory is saved in third and records and export, as final targetpath by assessed value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811524507.1A CN109489659A (en) | 2018-12-13 | 2018-12-13 | A kind of localization method based on the detection of more geomagnetic elements |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811524507.1A CN109489659A (en) | 2018-12-13 | 2018-12-13 | A kind of localization method based on the detection of more geomagnetic elements |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109489659A true CN109489659A (en) | 2019-03-19 |
Family
ID=65710251
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811524507.1A Pending CN109489659A (en) | 2018-12-13 | 2018-12-13 | A kind of localization method based on the detection of more geomagnetic elements |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109489659A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101520328A (en) * | 2009-04-01 | 2009-09-02 | 西北工业大学 | Method for autonomous navigation using geomagnetic field line map |
| US20130035890A1 (en) * | 2011-08-04 | 2013-02-07 | Wang Jeen-Shing | Moving trajectory calibration method and moving trajectory generation method |
| CN107392388A (en) * | 2017-07-31 | 2017-11-24 | 南昌航空大学 | A kind of method for planning no-manned plane three-dimensional flight path using artificial fish-swarm algorithm is improved |
-
2018
- 2018-12-13 CN CN201811524507.1A patent/CN109489659A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101520328A (en) * | 2009-04-01 | 2009-09-02 | 西北工业大学 | Method for autonomous navigation using geomagnetic field line map |
| US20130035890A1 (en) * | 2011-08-04 | 2013-02-07 | Wang Jeen-Shing | Moving trajectory calibration method and moving trajectory generation method |
| CN107392388A (en) * | 2017-07-31 | 2017-11-24 | 南昌航空大学 | A kind of method for planning no-manned plane three-dimensional flight path using artificial fish-swarm algorithm is improved |
Non-Patent Citations (4)
| Title |
|---|
| 刘飞等: ""相关地磁匹配定位技术"", 《中国惯性技术学报》 * |
| 朱占龙: ""惯性/地磁匹配组合导航相关技术研究"", 《中国优秀硕博士学位论文全文数据库（博士）信息科技辑》 * |
| 李龙鸣: ""地磁导航算法研究"", 《中国优秀硕士学位论文全文数据信息科技辑》 * |
| 郭才发: ""空间地磁应用的若干关键技术研究"", 《中国优秀硕博士学位论文全文数据库（博士）工程科技II辑》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Hong et al. | Multi-scale ship detection from SAR and optical imagery via a more accurate YOLOv3 | |
| CN106127204B (en) | A kind of multi-direction meter reading Region detection algorithms of full convolutional neural networks | |
| Yang et al. | A robust one-stage detector for multiscale ship detection with complex background in massive SAR images | |
| CN104063719B (en) | Pedestrian detection method and device based on depth convolutional network | |
| CN103630873B (en) | Merge the indoor orientation method in earth's magnetic field and WIFI signal | |
| CN105426914B (en) | A kind of image similarity detection method of facing position identification | |
| CN109271888A (en) | Personal identification method, device, electronic equipment based on gait | |
| CN109029381A (en) | A kind of detection method of tunnel slot, system and terminal device | |
| CN108765452A (en) | A kind of detection of mobile target in complex background and tracking | |
| CN107240122A (en) | Video target tracking method based on space and time continuous correlation filtering | |
| CN110472542A (en) | A kind of infrared image pedestrian detection method and detection system based on deep learning | |
| CN103324677B (en) | Hierarchical fast image global positioning system (GPS) position estimation method | |
| CN106780582B (en) | The image significance detection method merged based on textural characteristics and color characteristic | |
| CN109740662A (en) | Image object detection method based on YOLO frame | |
| CN109960742A (en) | The searching method and device of local message | |
| CN106156758B (en) | A kind of tidal saltmarsh method in SAR seashore image | |
| CN109211198A (en) | A kind of intelligent Target detection and measuring system and method based on trinocular vision | |
| CN108846333A (en) | Sign board landmark data collection generates and vehicle positioning method | |
| CN109376676A (en) | Highway engineering site operation personnel safety method for early warning based on unmanned aerial vehicle platform | |
| CN109086649A (en) | Satellite remote sensing images identifying water boy method | |
| CN110175615A (en) | The adaptive visual position recognition methods in model training method, domain and device | |
| CN106846246B (en) | A kind of object-based Super-resolution Mapping for Remote Sensing Images | |
| CN109886267A (en) | A kind of soft image conspicuousness detection method based on optimal feature selection | |
| CN107247927A (en) | A kind of remote sensing images coastline information extracting method and system based on K-T Transformation | |
| CN110207688A (en) | A kind of magnetic beacon fast orienting method and system based on characteristic vector |
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 |
Application publication date: 20190319 |
|
| RJ01 | Rejection of invention patent application after publication |