CN1595203A - Layered lineage identification method for high spectrum mineral - Google Patents
Layered lineage identification method for high spectrum mineral Download PDFInfo
- Publication number
- CN1595203A CN1595203A CN 200410048346 CN200410048346A CN1595203A CN 1595203 A CN1595203 A CN 1595203A CN 200410048346 CN200410048346 CN 200410048346 CN 200410048346 A CN200410048346 A CN 200410048346A CN 1595203 A CN1595203 A CN 1595203A
- Authority
- CN
- China
- Prior art keywords
- mineral
- identification
- spectrum
- class
- data
- 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
Images
Landscapes
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
This invention establishes a mineral identification layer spectrum system which is mineral macro-taxonomy to mineral kind to detail mineral to mineral variation, according to the different grade of characteristic light spectrum parameters in the mineral mixed light spectrum. It concludes and valuates some common light spectrum parameters stability and the relative weigh in the mineral identification and establishes the light spectrum identification method and identification database of the more than twenty kinds of etching minerals. This invention integrates the mineral light spectrum knowledge of professional person into the identification of the mineral based on effectively solving the light spectrum change or variation and makes the general operation person can identify the minerals and realizes the intelligence, batch process and the scale utility of mineral area charting of high light spectrum remote sensor mineral identification.
Description
Technical field
The present invention relates to a kind of recognition methods of mineral layering pedigree, especially relate to a kind of recognition methods of mineral layering pedigree of high spectrum.
Background technology
High spectrum has the characteristics of collection of illustrative plates unification, and it is different from multispectral advantage and is to utilize spectral signature to realize atural object or atural object component are directly discerned.Mineral identification and mineral map plotting be high spectral technique the most successful also be the application that can bring into play its advantage.At present, the technical method of high-spectrum remote-sensing object spectrum identification mainly contains following aspect: (1) carries out carrying out rock ore deposit type identification after the enhancement process to single diagnostic absorption feature such as waveform, the symmetry etc. of end member mineral; (2) discern based on the Spectral matching of spectral signature; (3) mixed spectra decomposition model.When understanding and grasping mineral classification that the real work district may exist and known object spectrum, it is more useful to utilize these technical methods to carry out atural object identification.Be subjected to the influence of view angle and grain size to cause spectrum change or variation but obviously not enough is because actual object spectrum makes a variation, obtain data, accurately matching ratio is difficult, be difficult to simultaneously determine that mixed spectra decomposes end member, cause identification of rock ore deposit and obscuring and error analytically.On the other hand, in practical operation, need scientific and technical personnel or staff to have the knowledge background of mineralogy and spectroscopy, limited the through engineering approaches of learning on high spectrum ground and used, be difficult to satisfy the demand of high-spectrum remote-sensing extensive area mineral map plotting.
Summary of the invention
The objective of the invention is through engineering approaches, practicability, intellectuality and large-scale development in order to promote high spectrum resolution remote sensing technique, mineral ion or ionic group, Extract Mineralized Alteration type and alteration are being divided on the basis of band, the research of three level spectral signatures of altered mineral paragenetic association, analysis and summary, according to the mathematical logic association of not at the same level characteristic spectrum parameter in mineral spectrum or the mineral mixed spectra, set up the mineral identification layering pedigree of " the big class-mineral type of mineral-concrete mineral-mineral mutation "; Conclude and estimated the stability and the relative weighting in mineral identification of some spectral parameters commonly used, set up the spectrum recognition rule and the spectrum recognition rule storehouse of kind of altered mineral surplus in the of 20.Thereby effectively solving on the basis of spectrum change or variation; professional's mineral spectrum knowledge is incorporated in the mineral identification; designed and developed the recognition methods of high spectrum mineral layering pedigree; improved the reliability of mineral identifications; and make the general operation personnel also can carry out the identification of mineral, realize that the scale of intellectuality, batch processing and the charting of mineral area of high-spectrum remote-sensing mineral identification is used.
The concrete steps of high spectrum mineral layering pedigree of the present invention recognition methods are:
(1) spectral signature enhancement process: to carrying out the data of atmospheric correction and rebuilding spectrum, the processing of shelling is eliminated background influence, the characteristic absorption of enhanced spectrum, especially some secondary features;
(2) the big class identification of mineral: on the basis of (1) deal with data,, combine closely, utilize some diagnostic spectral signatures to carry out the identification of the big class of mineral, as contain Fe with spectrum identification storehouse according to mineral identification spectrum rule
2+Mineral, Fe
3+Mineral, Mn
2+With mineral, carbonate mineral, contain Al-OH key mineral, contain Mg-OH key mineral etc.;
(3) Region Segmentation is handled: respectively (1) deal with data and (2) recognition result are carried out matrix operation, be partitioned into the data block zone of (2) result's distribution;
(4) mineral species identification: to the different big class distribution of results data of the processing of (3), combine closely with spectrum identification storehouse, utilize mineral identification spectrum rule respectively, carry out mineral species identification, as carrying out the identification of alunite class, smectites, white mica class, smalite class etc. in the big class of Al-OH key mineral distributed areas.For the mineral that are easy to obscure,, need to distinguish in conjunction with global characteristics, spectral intensity and the band ratio etc. of spectrum as white mica and illite;
(5) identification of mineral mutation: utilize (1) and (4) result to carry out the computing of similar (3), be partitioned into the data block zone that mineral species distributes, and then,, carry out the identification of mineral mutation as the exact position of bands of a spectrum, symmetry etc. according to the fine-feature of bands of a spectrum at different type distribution.As in white mica class mineral distributive province, can further discern rich aluminium white mica and poor aluminium white mica;
(6) performance of recognition result: adopt soot-and-whitewash or color image to handle.
High spectrum mineral layering pedigree of the present invention recognition methods wherein is divided into mineral the big class of mineral, mineral type, concrete mineral, mineral mutation, 4 types.
High spectrum mineral layering pedigree of the present invention recognition methods, wherein the mineral of each type are according to the characteristic and the relative weighting further segmentation again of its absorption spectrum.
The advantage of high spectrum mineral layering pedigree of the present invention recognition methods is, can discern multi mineral, and or not that those skilled in the art also can carry out the identification of spectrum even make.And have discernible intellectuality, mass and a scale processing power, needs that can the adaptation zone mineral map plotting.
Other details of high spectrum mineral layering pedigree of the present invention recognition methods and characteristics can be cheer and bright by reading the embodiment hereinafter encyclopaedize in conjunction with the accompanying drawings.
Description of drawings
Fig. 1 is the AVIRIS recognition result that utilizes U.S. Cuprite area;
Fig. 2 is the recognition result that utilizes Hami east Tianshan Area AL-OH class mineral leucocratic mineral aviation Hymap data;
Fig. 3 is the recognition result that utilizes Hami east Tianshan Area Mg-OH class mineral melanocratic mineral aviation Hymap data;
Fig. 4, Fig. 5 are respectively the check analysiss that utilizes image wave spectrum (dotted portion among the figure), standard spectrum (dot-and-dash line part among the figure) and the open-air measured spectra (solid line part among the figure) of Hami east Tianshan Area aviation Hymap data identification white mica (Fig. 4) and chlorite (Fig. 5) according to the present invention;
Fig. 6 utilizes Tibet to drive imperial regional space flight Hyperion data mineral recognition result and spectral comparison analysis;
Fig. 7 is a mineral layering identification pedigree.
Embodiment
Data of the present invention are methods, are based on:
(1) foundation of mineral layering identification pedigree
Mineral ion or ionic group, Extract Mineralized Alteration type and alteration are being divided on the basis of band, the research of three level spectral signatures of altered mineral paragenetic association, analysis and summary, concluding and estimated the stability and the relative weighting in mineral identification of some spectral parameters commonly used; According to the mathematical logic association of not at the same level characteristic spectrum parameter in mineral spectrum or the mineral mixed spectra, set up the mineral layering identification pedigree of " the big class-mineral type of mineral-concrete mineral-mineral mutation ", specifically as shown in Figure 7.
Above-mentioned pedigree is not the classification on the proper mineralogy, but classifies according to the spectrum identification spectral signature of mineral, has extensibility.
(2) mineral spectrum recognition rule
1. the absorption band with spectrum is characterized as the master, and other spectral signature is auxilliary;
2. respectively based on main absorption band, bands of a spectrum assemblage characteristic, bands of a spectrum fine-feature and bands of a spectrum variation features, mineral are carried out layering identification;
3. take into full account the influence of mixed spectra during recognition rule is set up;
4. according to the effect of different spectral signature parameters in mineral identification, give its corresponding weights, and take into full account the mathematical logic association of not at the same level characteristic spectrum parameter.
(3) mineral recognition rule storehouse
The weight of the different absorption bands of given mineral (M) spectrum position is
W={ω
1,ω
2,ω
3,…,ω
j} j=1,2,……,n
Here ω 1>ω 2>ω 3 ...Utilize the IF-THEN rule can set up the logic association of mineral identification, on this basis, set up mineral spectrum recognition rule storehouse.Under classify part mineral spectrum recognition rule storehouse as.
For the big class of mineral:
if?ω
1∈[2165,2230]then?M?is?Al-OH
if?ω
1∈[2315,2330]then?M?is?Mg-OH
if?ω
1∈[2335,2386]then?M?is?CO
3 2+
if?ω
1∈[1000,1100]then?M?is?Fe
2+
if?ω
1∈[600,900]then?M?is?Fe
3+
if?ω
1∈[450,600]then?M?is?Mn
2+
Can further segment mineral species for containing the big class of ore deposit Al-OH mineral:
if(ω
1∈2165?or?2175)and?ω
2∈2440?then?M?is?Alunite
if?ω
1∈2205?and?ω
2∈2386?then?M?is?Halloysite?or?Smeckaolite
if?ω
1∈2205?and?ω
2∈2386?and?ω
3∈2315?then?M?isSmeckaolite
if(ω
1∈2205?or?2215)?and?ω
2∈2440?then?M?is?Montmorillite?orMuscovite
if(ω
1∈2205?or?2215)?and?ω
2∈2440?and?ω
3∈2355?then?M?isMuscovite
if(ω
1∈2205?or?2215)?and?ω
2∈2355?and?ω
3∈2440?then?M?isIllite
The concrete steps of high spectrum mineral layering pedigree of the present invention recognition methods are:
(1) spectral signature enhancement process: to carrying out the data of atmospheric correction and rebuilding spectrum, the processing of shelling is eliminated background influence, the characteristic absorption of enhanced spectrum, especially some secondary features;
(2) the big class identification of mineral: on the basis of (1) deal with data,, combine closely, utilize some diagnostic spectral signatures to carry out the identification of the big class of mineral, as contain Fe with spectrum identification storehouse according to mineral identification spectrum rule
2+Mineral, Fe
3+Mineral, Mn
2+With mineral, carbonate mineral, contain Al-OH key mineral, contain Mg-OH key mineral etc.;
(3) Region Segmentation is handled: respectively (1) deal with data and (2) recognition result are carried out matrix operation, be partitioned into the data block zone of (2) result's distribution;
(4) mineral species identification: to the different big class distribution of results data of the processing of (3), combine closely with spectrum identification storehouse, utilize mineral identification spectrum rule respectively, carry out mineral species identification, as carrying out the identification of alunite class, smectites, white mica class, smalite class etc. in the big class of Al-OH key mineral distributed areas;
(5) identification of mineral mutation: utilize (1) and (4) result to carry out the computing of similar (3), be partitioned into the data block zone that mineral species distributes, then in the identification of carrying out the mineral mutation at different type distribution.As in white mica class mineral distributive province, can further discern rich aluminium white mica and poor aluminium white mica;
(6) performance of recognition result: adopt soot-and-whitewash or color image to handle.
Wherein, Fig. 1 is the AVIRIS recognition result that utilizes U.S. Cuprite area, the shallow mineral distributive province of zone for discerning of contrast among the figure.
Fig. 2 is the recognition result that utilizes Hami east Tianshan Area AL-OH class mineral leucocratic mineral aviation Hymap data, and is similar to Fig. 1, the shallow mineral distributive province of zone for discerning of contrast among the figure.
Fig. 3 is the recognition result that utilizes Hami east Tianshan Area Mg-OH class mineral melanocratic mineral aviation Hymap data; Similar to Fig. 1, the zone of contrast shallow (being the higher zone of brightness) is the mineral distributive province of identification among the figure.
Fig. 4, Fig. 5 are respectively the check analysiss that utilizes image wave spectrum, standard spectrum and the open-air measured spectra of Hami east Tianshan Area aviation Hymap data identification white mica (Fig. 4) and chlorite (Fig. 5) according to the present invention; On behalf of open-air checking wave spectrum, intermediate curve, the topmost portion curve represent the image wave spectrum of chlorite, bottom curve to represent standard spectrum among the figure.
Fig. 6 utilizes Tibet to drive imperial regional space flight Hyperion data mineral recognition result and spectral comparison analysis.
Wherein last figure: the mineral of identification (canescence) distribute: middle figure: java standard library wave spectrum; Figure below: video wave spectrum
Empirical tests, recognition result is quite identical with live telecast in the open air, and the wave spectrum curve also quite mates.Therefore; the present invention has universality, is applicable to the high-spectral data of space flight and the different instruments of aviation, and the mineral species of identification has reached more than 20 kinds; and have intellectuality, mass and a scale processing power of mineral identification, needs that can the adaptation zone mineral map plotting.
Claims (3)
1. high spectrum mineral layering pedigree recognition methods comprises the steps:
(1) spectral signature enhancement process: to carrying out the data of atmospheric correction and rebuilding spectrum, the processing of shelling is eliminated background influence, the characteristic absorption of enhanced spectrum, especially some secondary features;
(2) the big class identification of mineral: on the basis of (1) deal with data,, combine closely, utilize some diagnostic spectral signatures to carry out the identification of the big class of mineral, as contain Fe with spectrum identification storehouse according to mineral identification spectrum rule
2+Mineral, Fe
3+Mineral, Mn
2+With mineral, carbonate mineral, contain Al-OH key mineral, contain Mg-OH key mineral etc.;
(3) Region Segmentation is handled: respectively (1) deal with data and (2) recognition result are carried out matrix operation, be partitioned into the data block zone of (2) result's distribution;
(4) mineral species identification: to the different big class distribution of results data of the processing of (3), combine closely with spectrum identification storehouse, utilize mineral identification spectrum rule respectively, carry out mineral species identification, as carrying out the identification of alunite class, smectites, white mica class, smalite class etc. in the big class of Al-OH key mineral distributed areas;
(5) identification of mineral mutation: utilize (1) and (4) result to carry out the computing of similar (3), be partitioned into the data block zone that mineral species distributes, then in the identification of carrying out the mineral mutation at different type distribution;
(6) performance of recognition result: adopt soot-and-whitewash or color image to handle.
2. high spectrum mineral layering pedigree according to claim 1 recognition methods wherein is divided into mineral the big class of mineral, mineral type, concrete mineral, mineral mutation, 4 types.
3. high spectrum mineral layering pedigree according to claim 2 recognition methods, wherein the mineral of each type are according to the characteristic and the relative weighting further segmentation again of its absorption spectrum.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CNB2004100483465A CN1317569C (en) | 2004-06-29 | 2004-06-29 | Layered lineage identification method for high spectrum mineral |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CNB2004100483465A CN1317569C (en) | 2004-06-29 | 2004-06-29 | Layered lineage identification method for high spectrum mineral |
Publications (2)
Publication Number | Publication Date |
---|---|
CN1595203A true CN1595203A (en) | 2005-03-16 |
CN1317569C CN1317569C (en) | 2007-05-23 |
Family
ID=34665744
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CNB2004100483465A Expired - Fee Related CN1317569C (en) | 2004-06-29 | 2004-06-29 | Layered lineage identification method for high spectrum mineral |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN1317569C (en) |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1315094C (en) * | 2005-04-14 | 2007-05-09 | 中国国土资源航空物探遥感中心 | Imaging spectrum data processing system and imaging spectrum data processing method |
CN101871884A (en) * | 2010-06-02 | 2010-10-27 | 中国国土资源航空物探遥感中心 | Atmospheric correction and regional mineral map spotting method utilizing multi-scene ASTER (Advanced Spaceborne Thermal Emission and Reflection Radiometer) remote sensing data |
CN101551471B (en) * | 2009-05-19 | 2012-01-18 | 中国国土资源航空物探遥感中心 | High-spectrum remote-sensing mineral content quantitative inversion method |
CN103903225A (en) * | 2012-12-25 | 2014-07-02 | 核工业北京地质研究院 | Hyperspectral image processing method for dolomite information extraction |
CN103984940A (en) * | 2014-06-03 | 2014-08-13 | 核工业北京地质研究院 | Method for identifying hematitization based on hyperspectral data |
CN104572580A (en) * | 2014-12-19 | 2015-04-29 | 中国国土资源航空物探遥感中心 | Construction method of function expressing mineral particle light scattering distribution feature |
CN104749653A (en) * | 2013-12-31 | 2015-07-01 | 北京大学 | Method for exploring gas enrichment area of underground coal seam based on multi-spectrum electromagnetic wave |
CN105068136A (en) * | 2015-07-27 | 2015-11-18 | 中国地质调查局武汉地质调查中心 | Potential positioning evaluation method for copper and gold mine of Indo-China peninsula demonstration zone based on multi-source information |
CN108007902A (en) * | 2016-10-27 | 2018-05-08 | 核工业北京地质研究院 | A kind of method that muscovite Al-OH absorptions position is calculated with high-spectral data |
CN109406405A (en) * | 2018-10-11 | 2019-03-01 | 核工业北京地质研究院 | A kind of high-definition remote sensing quantitative estimation method suitable for salt lake water body salinity |
CN113537235A (en) * | 2021-02-08 | 2021-10-22 | 中国石油化工股份有限公司 | Rock identification method, system, device, terminal and readable storage medium |
CN113779341A (en) * | 2021-06-11 | 2021-12-10 | 中国石油化工股份有限公司 | Database-based mineral type determination method, device, terminal and medium |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102426625B (en) * | 2011-09-21 | 2014-06-18 | 中国国土资源航空物探遥感中心 | Method for extracting porphyry copper typical altered zone mineral information based on ASTER satellite data |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE10019404A1 (en) * | 2000-04-19 | 2001-10-25 | Henkel Kgaa | Method of coloring hair includes pretreatment with aqueous formulation containing dissolved protein, protein hydrolysate or protein derivative before contact with color formulation and washing |
-
2004
- 2004-06-29 CN CNB2004100483465A patent/CN1317569C/en not_active Expired - Fee Related
Cited By (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1315094C (en) * | 2005-04-14 | 2007-05-09 | 中国国土资源航空物探遥感中心 | Imaging spectrum data processing system and imaging spectrum data processing method |
CN101551471B (en) * | 2009-05-19 | 2012-01-18 | 中国国土资源航空物探遥感中心 | High-spectrum remote-sensing mineral content quantitative inversion method |
CN101871884A (en) * | 2010-06-02 | 2010-10-27 | 中国国土资源航空物探遥感中心 | Atmospheric correction and regional mineral map spotting method utilizing multi-scene ASTER (Advanced Spaceborne Thermal Emission and Reflection Radiometer) remote sensing data |
CN103903225A (en) * | 2012-12-25 | 2014-07-02 | 核工业北京地质研究院 | Hyperspectral image processing method for dolomite information extraction |
CN103903225B (en) * | 2012-12-25 | 2016-12-28 | 核工业北京地质研究院 | A kind of Technique for Hyper-spectral Images Classification for dolomite information retrieval |
CN104749653A (en) * | 2013-12-31 | 2015-07-01 | 北京大学 | Method for exploring gas enrichment area of underground coal seam based on multi-spectrum electromagnetic wave |
CN103984940A (en) * | 2014-06-03 | 2014-08-13 | 核工业北京地质研究院 | Method for identifying hematitization based on hyperspectral data |
CN103984940B (en) * | 2014-06-03 | 2017-12-26 | 核工业北京地质研究院 | A kind of method based on high-spectral data identification hematization |
CN104572580A (en) * | 2014-12-19 | 2015-04-29 | 中国国土资源航空物探遥感中心 | Construction method of function expressing mineral particle light scattering distribution feature |
CN104572580B (en) * | 2014-12-19 | 2018-06-19 | 中国国土资源航空物探遥感中心 | The construction method of the function of one expression mineral grain light scattering spatial distribution characteristic |
CN105068136A (en) * | 2015-07-27 | 2015-11-18 | 中国地质调查局武汉地质调查中心 | Potential positioning evaluation method for copper and gold mine of Indo-China peninsula demonstration zone based on multi-source information |
CN108007902A (en) * | 2016-10-27 | 2018-05-08 | 核工业北京地质研究院 | A kind of method that muscovite Al-OH absorptions position is calculated with high-spectral data |
CN108007902B (en) * | 2016-10-27 | 2020-06-19 | 核工业北京地质研究院 | Method for calculating Al-OH absorption position of muscovite by using hyperspectral data |
CN109406405A (en) * | 2018-10-11 | 2019-03-01 | 核工业北京地质研究院 | A kind of high-definition remote sensing quantitative estimation method suitable for salt lake water body salinity |
CN113537235A (en) * | 2021-02-08 | 2021-10-22 | 中国石油化工股份有限公司 | Rock identification method, system, device, terminal and readable storage medium |
CN113779341A (en) * | 2021-06-11 | 2021-12-10 | 中国石油化工股份有限公司 | Database-based mineral type determination method, device, terminal and medium |
Also Published As
Publication number | Publication date |
---|---|
CN1317569C (en) | 2007-05-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN1317569C (en) | Layered lineage identification method for high spectrum mineral | |
CN108241871A (en) | Laser point cloud and visual fusion data classification method based on multiple features | |
Ryberg et al. | Mining metadata from unidentified ITS sequences in GenBank: a case study in Inocybe (Basidiomycota) | |
CN105139028A (en) | SAR image classification method based on hierarchical sparse filtering convolutional neural network | |
Patel et al. | Development of a machine vision system using the support vector machine regression (SVR) algorithm for the online prediction of iron ore grades | |
CN1194320C (en) | Method for lighting- and visual angle-unchanging delineation of face using first and secondary intrinsic characteristics | |
CN106503739A (en) | The target in hyperspectral remotely sensed image svm classifier method and system of combined spectral and textural characteristics | |
CN109117956A (en) | A kind of determination method of optimal feature subset | |
CN110956187A (en) | Unmanned aerial vehicle image plant canopy information extraction method based on ensemble learning | |
Askari et al. | Band ratios matrix transformation (BRMT): a sedimentary lithology mapping approach using ASTER satellite sensor | |
CN111401426B (en) | Small sample hyperspectral image classification method based on pseudo label learning | |
CN1758070A (en) | Earth surface classification method based on fully polarization synthetic aperture radar data | |
CN111428989A (en) | TOPSIS model-based mining vestige comprehensive evaluation method | |
Ritz et al. | Identification of clay minerals by infrared spectroscopy and discriminant analysis | |
CN104680180A (en) | Polarimetric SAR image classification method on basis of K-Means and sparse own coding | |
CN101299237A (en) | High spectroscopic data supervision classifying method based on information quantity dimensionality sequence | |
CN116258689A (en) | Aggregate particle identification and grading automatic analysis method based on deep learning | |
CN112115795A (en) | Hyperspectral image classification method based on Triple GAN | |
CN101067659A (en) | Remote sensing image sorting method | |
CN107563420B (en) | The Classification of Polarimetric SAR Image method encoded certainly based on scattering energy and storehouse | |
CN1315094C (en) | Imaging spectrum data processing system and imaging spectrum data processing method | |
Newell et al. | Texture-based estimation of physical characteristics of sand grains | |
CN1472634A (en) | High spectrum remote sensing image combined weighting random sorting method | |
CN111564188A (en) | Quantitative analysis method for mineral information based on variational self-coding | |
CN112330622B (en) | Hyperspectral image band selection method based on ground feature maximum discrimination |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant | ||
C19 | Lapse of patent right due to non-payment of the annual fee | ||
CF01 | Termination of patent right due to non-payment of annual fee |