CN106643704B - Solar azimuth acquisition methods based on atmospheric polarization type - Google Patents
Solar azimuth acquisition methods based on atmospheric polarization type Download PDFInfo
- Publication number
- CN106643704B CN106643704B CN201710027484.2A CN201710027484A CN106643704B CN 106643704 B CN106643704 B CN 106643704B CN 201710027484 A CN201710027484 A CN 201710027484A CN 106643704 B CN106643704 B CN 106643704B
- Authority
- CN
- China
- Prior art keywords
- polarization
- solar
- degree
- polarization mode
- mode
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
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
- G01C21/02—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by astronomical means
- G01C21/025—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by astronomical means with the use of startrackers
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Astronomy & Astrophysics (AREA)
- Automation & Control Theory (AREA)
- General Physics & Mathematics (AREA)
- Photometry And Measurement Of Optical Pulse Characteristics (AREA)
Abstract
The invention belongs to bionical polarotactic navigation field, the solar azimuth acquisition methods based on atmospheric polarization type are disclosed.Firstly, the polarized light sensor using image-type measures atmospheric polarization type, including angle of polarization mode and degree of polarization mode；Secondly, realizing the optimal estimation of solar direction vector by the feature vector of solution matrix according to the optimization method of angle of polarization Model Establishment solar direction vector, being solar azimuth in the projection of horizontal plane；At the same time, gradient is sought after degree of polarization mode being carried out smoothly, sunny meridian is estimated according to the probability density distribution of gradient direction, can be obtained the orientation of the sun；Finally, the result of both methods is carried out aggregative weighted, the optimal estimation of solar azimuth is obtained.The present invention takes full advantage of the information that both angle of polarization mode and degree of polarization mode are included and estimates solar azimuth under conditions of not increasing hardware configuration, has the advantages that principle is simple, estimated accuracy is high, robustness is good.
Description
Technical field:
The present invention relates to a kind of solar azimuth acquisition methods, in particular to a kind of solar azimuth based on atmospheric polarization type
Acquisition methods belong to bionical polarotactic navigation field.
Background technique:
The navigation mode of animal is very peculiar, and navigation mechanism is understood completely and is grasped by the mankind not yet, bionic navigation
Have become the new hot spot of current field of navigation technology research.Many biology (husky ant, locust, honeybee, dorbeetle, part birds
Deng), their unique eye structures can be utilized, the polarization phenomena of light is perceived and utilize, by observing atmospheric polarization type, from
It is middle to extract sunny azimuth information, realize navigator fix.Compared with classical airmanship, bionical polarotactic navigation, which utilizes, to be had
There is strong interference immunity, error the advantages such as not accumulate, is applied widely, be relatively suitble to multiple for the sky polarization mode of natural quality
Long endurance, remote independent navigation under heterocycle border, before having extensively for the application in the fields such as vehicle, ship, aircraft
Scape.
Current polarized light sensor can be mainly divided into two major classes: point measurement formula and image measurement formula.The former once adopts
Sample can only measure the polarization information on a direction, be easy not strong by the interference of environment, robustness；The polarization of image measurement formula
Optical sensor, can measure the polarization information of the whole region in angular field of view simultaneously, and application range is wider.It is inclined using image-type
Vibration one critical issue of optical sensor bring be how to obtain solar azimuth using the regularity of distribution of sky polarization mode,
And then calculate navigation direction angle.Existing method mainly estimates solar azimuth using angle of polarization mode, and has ignored atmosphere
Another important information in polarization mode --- degree of polarization mode, this, which will lead to, not enough fills the utilization of atmosphere polarization information
Point, it there is no while obtaining using atmospheric polarization angle mould formula and degree of polarization mode the report of solar azimuth at present.Therefore, one is found
Kind estimates solar azimuth using the information that both angle of polarization mode and degree of polarization mode are included simultaneously, and then improves the sun
The method of orientation estimated accuracy and robustness has a very important significance.
Summary of the invention:
The technical problem to be solved in the present invention is that: during obtaining solar azimuth from atmospheric polarization type, how
The information for making full use of both angle of polarization mode and degree of polarization mode to be included estimates solar azimuth, and then improves and estimate
Count precision and robustness.
In order to solve the above technical problems, solution proposed by the present invention are as follows:
Solar azimuth acquisition methods based on atmospheric polarization type, method includes the following steps:
Step 1, atmospheric polarization type measurement:
Using a kind of polarized light sensor based on polyphaser, the polarization mode of a piece of sky areas of real-time measurement is obtained
Polarization mode include angle of polarization mode and degree of polarization mode；The polarized light sensor is mainly by four CCD (Charge-
Coupled Device) camera, four wide-angle lens, four polarizer groups at, polarizing film light passing axis direction according to 0 °, 45 °,
90 °, the installation of 135 ° of angle；Four cameras are sampled by isochronous controller external trigger, and the data transmission of camera acquisition is to computer
Polarization state resolving is carried out, to obtain the angle of polarization mode and degree of polarization mode of sky；
Step 2, the solar azimuth based on angle of polarization mode obtain:
According to Rayleigh scattering model, the E direction vector of light is scattered perpendicular to scattering surface, i.e. E vector and solar direction vector s
It is mutually perpendicular to, i.e.,
eTS=0 (1)
Therefore, solar direction vector can be estimated to obtain by two not conllinear E vectors；In fact, polarization state has
Effect pixel number is determined that valid pixel points are greater than 300,000, and their corresponding E vectors under normal conditions by the resolution ratio of image
Most of is incoherent；
Define E=[e1 … eN]3×N, wherein N is the number of effective pixel points, available
ETS=0N×1 (2)
In actual measurement, due to the presence of error, optimization that the optimal estimation of solar direction vector s can be expressed as
Problem,
I.e. the optimal estimation of solar direction vector is matrix (EET) minimal eigenvalue corresponding to feature vector, the sun
Direction vector is in the orientation that the projection of horizontal plane is the sun；
Step 3, the solar azimuth based on degree of polarization mode obtain:
Atmospheric polarization degree mode is axisymmetricly distributed along sun meridian, and maximum degree of polarization occurs apart from the sun
90 ° of region, and the degree of polarization towards the sun (or deviate from sun) direction is minimum is showed such as the zonal distribution in Fig. 3, brighter
Region degree of polarization it is bigger；
In order to extract sunny meridian from atmospheric polarization degree mode, the symmetry axis of the mode need to be only detected,
Using following steps:
1) degree of polarization mode is carried out smoothly, which is to ask gradient procedure to pre-process for following, and effect is suppression
The noise that system introduces when seeking gradient, can be used median filter or Wiener filter is realized；
2) gradient is asked to smoothed out degree of polarization mode, the gradient direction of all available points is counted, it is general to find out it
Rate Density Distribution (shown in Fig. 4), the Maximum-likelihood estimation of gradient direction are the meridianal estimated result of the sun, according to sun
The direction of noon line can be obtained the orientation of the sun；
The result of both methods is carried out aggregative weighted according to actual application background and priori knowledge by step 4, from
And obtain the optimal estimation of solar azimuth.
In the present invention, by above four steps, the acquisition of solar azimuth can be realized.
Compared with prior art, the invention has the following advantages that
1) polarization mode for comprehensively utilizing a piece of sky areas, is not easily susceptible to interfere, and has better environmental suitability.
2) using the information that both angle of polarization mode and degree of polarization mode are included estimate solar azimuth simultaneously, it can be with
Obtain higher estimated accuracy.
Detailed description of the invention:
Fig. 1 is the flow diagram of the method for the present invention；
Fig. 2 is single order Rayleigh scattering modular concept figure；
Fig. 3 is the atmospheric polarization degree mode (after smooth) and its gradient direction schematic diagram of actual measurement；
Fig. 4 is the probability density distribution figure of gradient direction.
Specific embodiment:
Below with reference to Figure of description and specific embodiment, invention is further described in detail.
As shown in Figure 1, the solar azimuth acquisition methods of the invention based on atmospheric polarization type, specifically include following step
It is rapid:
Step 1, atmospheric polarization type measurement:
Atmospheric polarization type is sunlight after KPT Scatter, generated polarised light on high in formed special point
Cloth mode, with the significant regularity of distribution.Utilize a kind of polarized light sensor based on polyphaser, a piece of sky of real-time measurement
The polarization mode in region, the polarization mode of acquisition include angle of polarization mode and degree of polarization mode；The polarized light sensor mainly by
Four CCD (Charge-Coupled Device) cameras, four wide-angle lens, four polarizer groups at, wherein polarizing film
Light passing axis direction is installed according to 0 °, 45 °, 90 °, 135 ° of angle；Four cameras are sampled by isochronous controller external trigger, and camera is adopted
The data transmission of collection carries out polarization state resolving to computer, obtains the angle of polarization mode and degree of polarization mode of sky.
Step 2, the solar azimuth based on angle of polarization mode obtain:
Under the conditions of bright day gas, scattering particles is mainly made of atmospheric molecule, and size is much smaller than the wavelength of light, therefore
Atmospheric scattering process under fair weather can be described with single order Rayleigh scattering model, that is, scatters the E vector (electricity in light wave of light
Vibration vector) direction is perpendicular to scattering surface, as shown in Figure 2.
In conjunction with Fig. 2, illustrate how from the angle of polarization pattern acquiring solar azimuth measured.
It is defined as follows right hand rectangular coordinate system first:
Camera coordinates system (OcXcYcZc): select No. 1 camera as reference data, XcAxis and YcAxis is respectively along ccd sensor
Horizontal and vertical, ZcAxis is the optical axis of camera.System is after leveling, ZcAxis will be directed toward zenith direction.
Incident light coordinate system (OiXiYiZi): its ZiAxis is directed toward observed direction, XiAxle position is in vertical flat where observed direction
In face (OPP '), YiAxis and XiAxis and ZiAxis constitutes right hand rectangular coordinate system (YiAxis does not mark).
The position of observer is in O, and position of the sun on celestial sphere is S, with zenith angle γSAnd azimuth angle alphaSIt describes, day
Apex angle and elevation angle complementary angle each other.
Each of image pixel (xp,yp) it is all corresponding with the aerial a certain observed direction P in day, zenith angle and
Azimuth is respectively γ and α, and for the image after correction, corresponding relationship can be indicated are as follows:
In formula, f is focal length, (cx,cy)TFor the coordinate value of the projection of optical axis in the picture.
E direction vector can indicate in camera coordinates system are as follows:
In formula, φ is the angle of polarization of the incident light, it can directly be measured by image-type polarized light sensor and be obtained,For
From coordinate system c to the direction cosine matrix of coordinate system i, it is
According to Rayleigh scattering model, the E direction vector of light is scattered perpendicular to scattering surface, i.e. E vector and solar direction vector s
It is mutually perpendicular to, it may be assumed that
eTS=0 (7)
Therefore, solar direction vector can be estimated to obtain by two not conllinear E vectors.In fact, polarization state has
Effect pixel number is determined that valid pixel points are greater than 300,000, and their corresponding E vectors under normal conditions by the resolution ratio of image
Most of is incoherent.Define E=[e1 … eN]3×N, wherein N is the number of effective pixel points, available:
ETS=0N×1 (8)
In actual measurement, due to the presence of error, optimization that the optimal estimation of solar direction vector s can be expressed as
Problem:
I.e. the optimal estimation of solar direction vector is matrix (EET) minimal eigenvalue corresponding to feature vector, the sun
Direction vector is in the orientation that the projection of horizontal plane is the sun.
Step 3, the solar azimuth based on degree of polarization mode obtain
According to Rayleigh scattering model, atmospheric polarization degree mode is axisymmetricly distributed along sun meridian, maximum polarization
Degree occurs in the region apart from 90 ° of the sun, and the degree of polarization towards the sun (or deviating from the sun) direction is minimum, shows such as Fig. 3
In zonal distribution, brighter Regional Representative's degree of polarization is bigger.
In order to extract sunny meridian from atmospheric polarization degree mode, the symmetry axis of the mode need to be only detected,
Illustrate detailed step in conjunction with Fig. 3, Fig. 4:
1) degree of polarization mode is carried out smoothly, which is to ask gradient procedure to pre-process for following, and effect is suppression
The noise that system introduces when seeking gradient, can be used median filter or Wiener filter realizes that (Fig. 3 gives smoothed out polarization
Spend model results).
2) gradient is asked to smoothed out degree of polarization mode, (the arrow in Fig. 3 is counted to the gradient direction of all available points
Head direction, that is, gradient direction, the length of arrow indicate the size of gradient), find out its probability density distribution (as shown in Figure 4).Gradient
The Maximum-likelihood estimation in direction is the meridianal estimated result of the sun, can be obtained the sun according to the meridianal direction of the sun
Orientation.
The result of both methods is carried out aggregative weighted, to obtain the sun according to actual application background by step 4
Azimuthal optimal estimation.
The above is only a preferred embodiment of the present invention, protection scope of the present invention is not limited merely to above-mentioned implementation
Example, all technical solutions belonged under thinking of the present invention all belong to the scope of protection of the present invention.It should be pointed out that for the art
Those of ordinary skill for, several improvements and modifications without departing from the principles of the present invention, these improvements and modifications
It should be regarded as protection scope of the present invention.
Claims (1)
1. the solar azimuth acquisition methods based on atmospheric polarization type, it is characterised in that the following steps are included:
Step 1, atmospheric polarization type measurement:
Using a kind of polarized light sensor based on polyphaser, the polarization mode of a piece of sky areas of real-time measurement, acquisition it is inclined
Vibration mode includes angle of polarization mode and degree of polarization mode；
Step 2, the solar azimuth based on angle of polarization mode obtain:
According to Rayleigh scattering model, the E direction vector of light is scattered perpendicular to scattering surface, i.e. E vector and solar direction vector s is mutual
Vertically, i.e.,
eTS=0 (1)
Therefore, solar direction vector is estimated to obtain by two not conllinear E vectors；In fact, the effective pixel points of polarization state
Number is determined that valid pixel points are greater than 300,000, and most of their corresponding E vectors are incoherent by the resolution ratio of image；
Define E=[e1 … eN]3×N, wherein N is the number of effective pixel points, is obtained
ETS=0N×1 (2)
In actual measurement, due to the presence of error, the optimization problem that the optimal estimation of solar direction vector s is expressed as,
I.e. the optimal estimation of solar direction vector is matrix EETMinimal eigenvalue corresponding to feature vector, solar direction vector
In the orientation that the projection of horizontal plane is the sun；
Step 3, the solar azimuth based on degree of polarization mode obtain:
In order to extract sunny meridian from atmospheric polarization degree mode, the symmetry axis of the mode need to be only detected, use
Following steps:
1) degree of polarization mode is carried out smoothly, which is to ask gradient procedure to pre-process for following, and effect is to inhibit to ask
The noise introduced when gradient, can be used median filter or Wiener filter is realized；
2) gradient is asked to smoothed out degree of polarization mode, the gradient direction of all available points is counted, it is close to find out its probability
Degree distribution；The Maximum-likelihood estimation of gradient direction is the meridianal estimated result of the sun, is according to the meridianal direction of the sun
It can get the orientation of the sun；
The result of both methods is carried out aggregative weighted according to actual application background and priori knowledge by step 4, thus
To the optimal estimation of solar azimuth.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710027484.2A CN106643704B (en) | 2017-01-16 | 2017-01-16 | Solar azimuth acquisition methods based on atmospheric polarization type |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710027484.2A CN106643704B (en) | 2017-01-16 | 2017-01-16 | Solar azimuth acquisition methods based on atmospheric polarization type |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106643704A CN106643704A (en) | 2017-05-10 |
| CN106643704B true CN106643704B (en) | 2019-07-30 |
Family
ID=58843327
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710027484.2A Active CN106643704B (en) | 2017-01-16 | 2017-01-16 | Solar azimuth acquisition methods based on atmospheric polarization type |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106643704B (en) |
Families Citing this family (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107270888B (en) * | 2017-06-20 | 2020-11-17 | 歌尔科技有限公司 | Method and device for measuring longitude and latitude and camera |
| CN107728106B (en) * | 2017-09-30 | 2019-08-20 | 中国人民解放军国防科技大学 | Orientation method of micro-array polarized light compass |
| CN108225335B (en) * | 2018-01-23 | 2020-06-19 | 中国人民解放军国防科技大学 | Course angle solving method for multi-view polarized vision |
| CN108955625B (en) * | 2018-02-05 | 2021-11-12 | 合肥工业大学 | Method and system for acquiring sun position information |
| CN108759820B (en) * | 2018-06-11 | 2021-07-02 | 北京航空航天大学 | Compound eye-imitating multichannel polarization sensor-based sun vector calculation method |
| CN108917749B (en) * | 2018-07-11 | 2021-05-11 | 大连理工大学 | Method for extracting solar meridian based on polarization imaging |
| CN111220150B (en) * | 2019-12-09 | 2021-09-14 | 北京航空航天大学 | Sun vector calculation method based on underwater polarization distribution mode |
| CN111307140B (en) * | 2020-05-11 | 2020-08-07 | 中国人民解放军国防科技大学 | Atmospheric polarized light orientation method used under cloudy weather condition |
| CN111595330B (en) * | 2020-05-29 | 2021-09-14 | 北京航空航天大学 | Night polarization course calculation method based on probability density function estimation |
| CN113280785B (en) * | 2021-07-22 | 2021-09-28 | 中国人民解放军国防科技大学 | Sky polarized light orientation method based on polarization mode consistency |
| CN115062770B (en) * | 2022-08-04 | 2022-11-08 | 中国人民解放军国防科技大学 | Navigation method based on generalized bionic polarized light navigation model and solution |
| CN115014311B (en) * | 2022-08-08 | 2022-11-01 | 中国人民解放军国防科技大学 | Atmospheric polarization information-based light compass orientation method for eliminating sky occlusion |
| CN114993295B (en) * | 2022-08-08 | 2022-10-25 | 中国人民解放军国防科技大学 | Autonomous navigation method based on polarization orientation error compensation |
| CN116222550B (en) * | 2023-05-08 | 2023-07-07 | 北京航空航天大学 | Underwater polarized sun calculation method with depth adaptability |
| CN116972857B (en) * | 2023-09-25 | 2023-12-08 | 北京航空航天大学 | Night heading determining method for sector area fitting in moonlight polarized light field |
| CN117109594B (en) * | 2023-10-23 | 2024-01-05 | 北京航空航天大学 | Autonomous orientation method based on underwater light intensity gradient |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102589544A (en) * | 2012-01-10 | 2012-07-18 | 合肥工业大学 | Three-dimensional attitude acquisition method based on space characteristics of atmospheric polarization mode |
| CN102967311A (en) * | 2012-11-30 | 2013-03-13 | 中国科学院合肥物质科学研究院 | Navigational positioning method based on sky polarization distribution model matching |
| CN104359454A (en) * | 2014-11-17 | 2015-02-18 | 中北大学 | Atmospheric polarized light-based solar space position acquisition method |
| CN105139367A (en) * | 2015-07-27 | 2015-12-09 | 中国科学院光电技术研究所 | Visible light polarization image fusion method based on non-subsampled shear wave |
-
2017
- 2017-01-16 CN CN201710027484.2A patent/CN106643704B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102589544A (en) * | 2012-01-10 | 2012-07-18 | 合肥工业大学 | Three-dimensional attitude acquisition method based on space characteristics of atmospheric polarization mode |
| CN102967311A (en) * | 2012-11-30 | 2013-03-13 | 中国科学院合肥物质科学研究院 | Navigational positioning method based on sky polarization distribution model matching |
| CN104359454A (en) * | 2014-11-17 | 2015-02-18 | 中北大学 | Atmospheric polarized light-based solar space position acquisition method |
| CN105139367A (en) * | 2015-07-27 | 2015-12-09 | 中国科学院光电技术研究所 | Visible light polarization image fusion method based on non-subsampled shear wave |
Non-Patent Citations (5)
| Title |
|---|
| A combined fuzzy pixel-based and object-based approach for classification of high-resolution multispectral data over urban areas;Aaron K.Shackelford等;《IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING》;20031031;第41卷(第10期);2354-2364 |
| 仿生偏振视觉定位定向机理与实验;王玉杰等;《光学 精密工程》;20160930;第24卷(第9期);2109-2116 |
| 利用大气偏振模式确定太阳和太阳子午线空间位置法;任建斌等;《光子学报》;20150731;第44卷(第7期);0701002-1-0701002-6 |
| 基于多偏振敏感器的太阳矢量测量方法;杨中光等;《光子学报》;20130131;第42卷(第1期);1,3-4,6-7 |
| 基于大气偏振光学的太阳跟踪方法;王晨光等;《科学技术与工程》;20161031;第16卷(第29期);20-26 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106643704A (en) | 2017-05-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106643704B (en) | Solar azimuth acquisition methods based on atmospheric polarization type | |
| CN107063170B (en) | Course angle estimation method based on atmospheric polarization angle mould formula under complex environment | |
| Garg et al. | Vision and rain | |
| CN103325112B (en) | Moving target method for quick in dynamic scene | |
| CN108759820B (en) | Compound eye-imitating multichannel polarization sensor-based sun vector calculation method | |
| CN107728106B (en) | Orientation method of micro-array polarized light compass | |
| Garg et al. | Photometric model of a rain drop | |
| CN106679676B (en) | A kind of monoscopic multifunctional optical sensor and implementation method | |
| CN110231025B (en) | Dynamic orientation method and system based on strapdown polarized light compass | |
| CN105787876B (en) | One kind being based on the matched panoramic video method for automatically split-jointing of SURF signature tracking | |
| CN107453811B (en) | A method of the unmanned plane based on photopic vision communication cooperates with SLAM | |
| CN110807815B (en) | Quick underwater calibration method based on corresponding vanishing points of two groups of mutually orthogonal parallel lines | |
| CN106971408A (en) | A kind of camera marking method based on space-time conversion thought | |
| CN114877898B (en) | Sun dynamic tracking method based on underwater polarization attitude and refraction coupling inversion | |
| CN108225335A (en) | Course angle solving method for multi-view polarized vision | |
| CN109284663A (en) | A kind of sea obstacle detection method based on normal state and uniform Mixture Distribution Model | |
| CN107402010A (en) | A kind of polarization low-light enhancing harvester and the full polarization information bionic navigation method based on Stokes vector light stream and phase | |
| Han et al. | A novel orientation method for polarized light compass under tilted conditions | |
| CN109325912A (en) | Reflective separation method and calibration split system based on polarised light light field | |
| CN114937075B (en) | Underwater polarized light field autonomous orientation method based on three-dimensional solar meridian plane fitting | |
| CN114894197B (en) | Underwater polarization autonomous course calculation method based on zenith real-time tracking | |
| CN103873773A (en) | Primary-auxiliary synergy double light path design-based omnidirectional imaging method | |
| CN114894177A (en) | Coaxial dual-view field star sensor and using method thereof | |
| Poughon et al. | A stand-alone polarimetric acquisition system for producing a long-term skylight dataset | |
| CN111539413A (en) | Bionic polarized light course resolving system and method for soft edge support vector machine |
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 |