CN113094651A - Hyperspectral imaging parameter optimization design method based on rough set - Google Patents
Hyperspectral imaging parameter optimization design method based on rough set Download PDFInfo
- Publication number
- CN113094651A CN113094651A CN202011366930.0A CN202011366930A CN113094651A CN 113094651 A CN113094651 A CN 113094651A CN 202011366930 A CN202011366930 A CN 202011366930A CN 113094651 A CN113094651 A CN 113094651A
- Authority
- CN
- China
- Prior art keywords
- imaging
- parameter
- data table
- influence
- parameters
- 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
- 238000000034 method Methods 0.000 title claims abstract description 92
- 238000000701 chemical imaging Methods 0.000 title claims abstract description 67
- 238000005457 optimization Methods 0.000 title claims abstract description 26
- 238000013461 design Methods 0.000 title claims abstract description 25
- 238000003384 imaging method Methods 0.000 claims abstract description 110
- 229910052500 inorganic mineral Inorganic materials 0.000 claims abstract description 63
- 239000011707 mineral Substances 0.000 claims abstract description 63
- 230000008569 process Effects 0.000 claims abstract description 45
- 238000005065 mining Methods 0.000 claims abstract description 16
- 238000013507 mapping Methods 0.000 claims abstract description 11
- 238000012417 linear regression Methods 0.000 claims abstract description 6
- 238000011156 evaluation Methods 0.000 claims description 17
- 238000004458 analytical method Methods 0.000 claims description 8
- 230000003595 spectral effect Effects 0.000 claims description 7
- 238000004422 calculation algorithm Methods 0.000 claims description 5
- 230000005540 biological transmission Effects 0.000 claims description 4
- 238000000611 regression analysis Methods 0.000 claims description 4
- 230000009471 action Effects 0.000 claims description 3
- 238000010238 partial least squares regression Methods 0.000 claims description 3
- 238000004445 quantitative analysis Methods 0.000 claims description 3
- 230000005855 radiation Effects 0.000 claims description 3
- 238000005070 sampling Methods 0.000 claims description 3
- 238000012546 transfer Methods 0.000 claims description 3
- 238000004088 simulation Methods 0.000 description 7
- 238000011160 research Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000011158 quantitative evaluation Methods 0.000 description 2
- 238000002310 reflectometry Methods 0.000 description 2
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000013210 evaluation model Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000012314 multivariate regression analysis Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000013441 quality evaluation Methods 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000005316 response function Methods 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A40/00—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production
- Y02A40/10—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production in agriculture
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Pure & Applied Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Physics (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Algebra (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Operations Research (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Probability & Statistics with Applications (AREA)
- Health & Medical Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Complex Calculations (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
A hyperspectral imaging parameter optimization design method based on a rough set comprises the following steps: (1) analyzing the hyperspectral imaging process, and determining main influence parameters in the imaging process; (2) establishing an imaging parameter data table, and dividing imaging key parameter values in the data table by using an entropy-based discretization method; (3) establishing a discretization imaging parameter data table according to the value intervals divided in the step (2), mining the imaging data table by adopting an association rule based on Boolean attribute mapping, and establishing an influence constraint relation between key influence parameters in the hyperspectral imaging process and mineral identification capacity; (4) calculating the attribute importance of the imaging key parameters to the mineral identification capability based on the discretized data table established in the step (3) and based on the rough set and the knowledge granularity; (5) establishing a multiple linear regression model based on a partial least square method, and establishing a quantitative equation between imaging parameters and mineral identification capacity; (6) and (5) according to the influence constraint relation in the step (3) and the attribute importance of each key influence parameter in the step (4) on the mineral identification capability, optimally solving the quantitative equation in the step (5) to obtain a hyperspectral imaging parameter combination with the optimal mineral identification capability.
Description
Technical Field
The invention relates to a hyperspectral imaging parameter optimization design method based on a rough set, belongs to the field of hyperspectral load optimization design and imaging performance prediction, and is suitable for hyperspectral imaging performance evaluation and parameter optimization design research oriented to mineral identification application requirements.
Background
The high spectral resolution remote sensing has the characteristics of high spectral resolution and integrated map, is widely applied to various fields, can accurately acquire detailed spectral information of different ground objects and components, and realizes the detection and analysis of complex ground objects and components. Therefore, whether the acquired hyperspectral data can meet the application requirements of a user department or not is a key problem concerned by related load development departments at present. However, the hyperspectral imaging process is complex, the data acquisition process is influenced by many factors, and in the actual imaging process, parameters such as the sensor performance of the hyperspectral imager, the response waveband of the imager, the atmospheric condition in the transmission process, the spatial resolution, the spectral response function and the like can directly influence the data quality of the hyperspectral satellite. Therefore, in practical applications, the user sector is more inclined to find the "optimal values" of these parameters to achieve the best application effect to guide the design and development of the load. However, the relationships between these influencing parameters are not completely independent, and there is a coupling and constraint relationship between them, so that all parameters cannot be simultaneously optimized. The current research is not perfect, and the load index and the application capability are directly connected, and the constraint relation among the influencing parameters is not considered. Therefore, determining the constraint influence relationship among the key influence parameters in the hyperspectral imaging process and analyzing the influence of the key influence parameters on the application capacity has important significance on the optimization design of a hyperspectral load department. In order to optimize and improve instruments to enable data to be widely applied, quantitative evaluation needs to be performed on data acquired by a remote sensing system, and the current methods for evaluating the application capability of remote sensing image data can be generally divided into: empirical analysis, imaging-based simulation model, and analytical model. The evaluation method based on the empirical analysis method is an image interpretation method based on subjectivity, which is characterized in that the influence of different imaging parameters on the data application capability is analyzed according to actually acquired data, and the influence is represented in a parameterization mode through a statistical method. The imaging simulation model researches the influence of each link on imaging quality through simulation of the whole imaging process, and is an application capability evaluation method based on imaging link simulation. The image quality evaluation method based on the analysis model is a parameterized imaging performance evaluation model, and although the method has the characteristics of accuracy, flexibility and easiness in calculation, the method lacks consideration on the mutual influence relationship and the restriction relationship among key load parameters in the remote sensing physical imaging process, and is difficult to realize the optimal design of the guidance load parameters. In summary, in order to guide the optimization design of load parameters and predict the load application capability, the research in this aspect has become a research hotspot in the field of hyperspectral remote sensing, but at present, a perfect imaging performance evaluation standard, a theoretical model and a technical system which are oriented to the application and combined with the load characteristics are not established, and the comprehensive consideration among all the influencing parameters is less and the comprehensive consideration is not combined with the data processing process.
The Rough Set (Rough Set) theory is a mathematical tool taught by Pawlak in 1982 that can quantitatively analyze and process inaccurate, inconsistent, incomplete information and knowledge. Because part of attributes in the imaging link are unknown in the hyperspectral imaging process, the problem can be regarded as an incomplete information system when the quantitative relation between the influence parameters and the data application capacity is researched. The rough set theory can process incomplete data without relying on prior information, and finds the internal relation of each attribute in an incomplete information system, so that the rough set theory is introduced to solve the uncertain relation between the imaging parameters and the application capability evaluation indexes.
Disclosure of Invention
The invention aims to provide a hyperspectral imaging parameter optimization design method based on a rough set by comprehensively considering the problems of constraint relation among parameters and imaging system information imperfection when the hyperspectral imaging parameters are optimized and designed.
The technical solution of the invention is as follows: a constraint incidence relation between imaging parameters and application capacity is established through incidence rule mining, the influence of each key parameter on mineral identification capacity is calculated based on a method of a rough set and knowledge granularity, a quantitative evaluation equation of mineral identification capacity evaluation indexes and imaging key parameters is established through multiple regression analysis, and a parameter combination of the optimal application effect is optimally solved by combining the parameter constraint relation and the attribute importance degree.
The invention relates to a hyperspectral imaging parameter optimization design method based on a rough set, which comprises the following steps:
(1) analyzing the hyperspectral imaging process, and determining main influence parameters in the imaging process;
(2) establishing an imaging parameter data table, and dividing imaging key parameter values in the data table by using an entropy-based discretization method;
(3) establishing a discretization imaging parameter data table according to the value intervals divided in the step (2), mining the imaging data table by adopting an association rule based on Boolean attribute mapping, and establishing an influence constraint relation between key influence parameters in the hyperspectral imaging process and mineral identification capacity;
(4) calculating the attribute importance of the imaging key parameters to the mineral identification capability based on the discretized data table established in the step (3) and based on the rough set and the knowledge granularity;
(5) establishing a multiple linear regression model based on a partial least square method, and establishing a quantitative equation between imaging parameters and mineral identification capability evaluation indexes;
(6) and (5) according to the influence constraint relation in the step (3) and the attribute importance of each key influence parameter in the step (4) on the mineral identification capability, optimally solving the quantitative equation in the step (5) to obtain a hyperspectral imaging parameter combination with the optimal mineral identification capability.
Analyzing the hyperspectral imaging process in the step (1), and determining main influence parameters in the imaging process: establishing a scene model, an atmospheric radiation transmission model and a detector model in the hyperspectral imaging process, analyzing the hyperspectral imaging process, and determining key influence parameters influencing imaging performance in the imaging process, wherein the key influence parameters mainly comprise a ground sampling distance, spectral resolution, a signal-to-noise ratio and a modulation transfer function.
Establishing an imaging parameter data table in the step (2), and dividing imaging key parameter values in the data table by using an entropy-based discretization method: establishing an imaging parameter data table, selecting a breakpoint which enables the overall entropy of the imaging parameter data table to be minimum as an interval division breakpoint by adopting an attribute value division method based on entropy, determining the number of discrete intervals of each parameter attribute by utilizing a minimum description length principle, and then discretizing the attribute value of the imaging key influence parameter;
the process is as follows:
firstly, every piece of imaging data d is imaged in the imaging parameter c1The values are arranged from small to large, and the obtained sequence is represented as: delta1,δ2,…,δn(ii) a Then, the imaging parameters c are recorded1Each potential boundary in the range of values of (a) is:
wherein ,LiDividing point L for the candidate interval of the imaging parameteriSample set D of each imaging parameteriThe division is into two subsets, noted:
D1i＝{d∈D|Dc1≤Li}
D2i＝{d∈D|Dc1＞Li}
when selecting LiWhen the division point is used, the sample set of the data table is divided into two subsets, and the information gain of the imaging data table is expressed as:
wherein ,DiIs a sample set, is, Ent (D)i) Information entropy of a sample set;
assume D in the sample set1iNumber of classes of m1，D2iNumber of classes of m2And then when:
the data is divided in time, wherein, Delta is log2(3m-2-[Ent(D)-m1Ent(D1i)-m2Ent(D2i)]) And obtaining the discretized data table.
Establishing a discretization imaging parameter data table according to the value intervals divided in the step (2) in the step (3), mining the imaging data table by adopting association rules based on Boolean attribute mapping, and establishing an influence constraint relation between key influence parameters in the hyperspectral imaging process and mineral identification capacity: performing Boolean attribute mapping on the discretized data table, performing association rule mining on the data table by adopting an Apriori association rule mining algorithm, and setting a set of all attribute values of the hyperspectral imaging database as I ═ I1,i2,…,imIs composed of m items, called item set, ikThe method comprises the following steps of representing a certain parameter attribute value in a hyperspectral imaging database, named as a project, recording data of all attribute values under different imaging parameter combinations as D, recording T as each component imaging parameter in D, selecting a rule meeting requirements by calculating the support degree, the promotion degree and the confidence degree of the rule and representing the mined association rule as follows:
wherein ,
x is a front item of the association rule, namely a key influence parameter, Y is a back item of the association rule, and is an evaluation index of the mineral identification capability, and an influence constraint relation between the key influence parameter and the mineral identification capability in the hyperspectral imaging process is established through the obtained association rule.
And (4) calculating the attribute importance of the imaging key parameters to the mineral identification capacity based on the rough set and the knowledge granularity based on the discretized data table established in the step (3): the hyperspectral imaging parameter data table is T ═ (U, C, D, V, f), U ═ x1,x2,…,xnThe method comprises the following steps that A is a set of objects in a data table, A is a non-empty finite set of all parameter attributes in the data table, A is C and U, C is a key influence parameter in an imaging system, D is an evaluation index of mineral identification capacity, V is a set of data table parameter values, and an information function is as follows: f, U × A → V, X, U/D, X1,X2,…,XnAnd the term is the equivalent division of the domain U under the decision attribute D, U/C is the equivalent division of the conditional feature to the domain U, and then X is U/D is X1,X2,…,XnThe knowledge feature resolution on the graph is:
KCDis(C)＝ρC(X)·Dis(C)
wherein ,ρR(X) is the accuracy of each group of data X on the equivalent relation (knowledge) R, Dis (C) is the resolution of knowledge, and in the hyperspectral imaging parameter data table, for any key influence parameter C belongs to C, the characteristic resolution is as follows:
KCDis(c)＝KCDis(C)-KCDis(C-{c})
therefore, the attribute importance of any key influence parameter on the mineral identification capacity is calculated:
and establishing an influence degree action relation of each influence parameter on the mineral identification capability based on the attribute importance.
And (5) establishing a multiple linear regression model based on a partial least square method, and establishing a quantitative equation between the imaging parameters and the evaluation indexes of the mineral identification capacity: a quantitative analysis expression of key influence parameters of mineral identification type and hyperspectral imaging performance is established by adopting a partial least squares multiple regression analysis method, and in the quantitative equation, the evaluation indexes of mineral identification capability are a random variable y and a common variable x1,x2,…,xpAs key influence parameters, y and p (p is more than or equal to 2) common variables x are established through partial least squares regression analysis1,x2,…,xpIs composed of
wherein ,
ε is a random variable for the regression coefficients of the regression equation.
And (3) in the step (6), according to the influence constraint relation in the step (3) and the attribute importance of each key influence parameter in the step (4) on the mineral identification capacity, optimally solving the quantitative equation in the step (5) to obtain a hyperspectral imaging parameter combination with the optimal mineral identification capacity: taking the quantitative speech analytic expression obtained in the step (5) as an objective function, and establishing an optimization model by combining the constraint relation of the step (3) and the step (4) as follows:
min f(x),x∈Rn
s.t.ci(x)＝0,i∈E＝{1,2,…,l},
ci(x)≤0,i∈I＝{l+1,l+2,…,l+m}.
and solving a constraint optimization problem based on optimality conditions to obtain an optimal parameter combination, thereby realizing the optimal design of the hyperspectral imaging parameters.
Compared with the prior art, the invention has the advantages that: and establishing direct relation between key indexes such as load parameters and the application capacity, and comprehensively considering the incomplete characteristics of the imaging process and the constraint relation of each parameter. According to the method, the constraint incidence relation of the imaging parameters is effectively considered by using an association rule mining algorithm and an attribute importance degree calculation method based on a rough set and knowledge granularity, the influence of different imaging parameters on the data application capacity is analyzed under an incomplete information system, the imaging parameters and the application capacity are directly linked, and the solution of the optimal combination of the hyperspectral imaging parameters is realized. It has the following advantages: (1) and (3) effectively applying an association rule mining algorithm to mine the association influence constraint relation of each imaging parameter on the mineral identification capability in the imaging process. (2) And calculating the degree of dependence of the evaluation index of the mineral identification ability on the key influence parameter by using a rough set theory, and objectively calculating the relation between the imaging parameter and the evaluation index of the mineral identification ability, so as to determine the magnitude and the influence degree of the influence of the imaging parameter on the mineral identification ability. (3) And establishing a quantitative analytical expression between the mineral identification type and the key influence parameters by utilizing multivariate regression analysis, and establishing direct relation between the application capacity and the load parameters.
Detailed Description
In order to better explain the hyperspectral imaging parameter optimization design method based on the rough set, the hyperspectral imaging parameter optimization design method is implemented by taking Hymap visible light to short wave infrared (VNIR-SWIR) hyperspectral reflectivity data as source data, changing the imaging parameters of the source data to perform data simulation, performing mineral mapping on the simulation data by adopting a method based on mixed modulation matched filtering, and taking the mineral identification type as an evaluation index of mineral identification capacity. The invention relates to a hyperspectral imaging parameter optimization design method based on a rough set theory, which comprises the following concrete implementation steps of:
(1) analyzing the hyperspectral imaging process, and determining main influence parameters in the imaging process: establishing a scene model, an atmospheric radiation transmission model and a detector model in the hyperspectral imaging process, analyzing the hyperspectral imaging process, and determining key influence parameters influencing imaging performance in the imaging process, wherein the key influence parameters mainly comprise a ground sampling distance, spectral resolution, a signal-to-noise ratio and a modulation transfer function.
(2) Establishing an imaging parameter data table, and dividing imaging key parameter values in the data table by using an entropy-based discretization method: changing imaging parameters of the hyperspectral reflectivity data from Hymap visible light to short wave infrared (VNIR-SWIR) to perform data simulation, and performing mineral mapping on the imaging parameters; establishing an imaging parameter data table, discretizing key image parameter attributes of the four hyperspectral imaging systems by adopting an entropy-based continuous attribute discretization method, and calculating an average value of the maximum value and the minimum value of two discrete intervals to obtain a discretized imaging data table when dividing an attribute value range according to a discretization result;
the process is as follows:
firstly, every piece of imaging data d is imaged in the imaging parameter c1The values are arranged from small to large, and the obtained sequence is represented as: delta1,δ2,…,δn(ii) a Then, the imaging parameters c are recorded1Each potential boundary in the range of values of (a) is:
wherein ,LiDividing point L for the candidate interval of the imaging parameteriSample set D of each imaging parameteriThe division is into two subsets, noted:
when selecting LiWhen the division point is used, the sample set of the data table is divided into two subsets, and the information gain of the imaging data table is expressed as:
wherein ,DiIs a sample set, is, Ent (D)i) Information entropy of a sample set;
assume D in the sample set1iNumber of classes of m1，D2iNumber of classes of m2And then when:
the data is divided in time, wherein, Delta is log2(3m-2-[Ent(D)-m1Ent(D1i)-m2Ent(D2i)]) And obtaining the discretized data table.
(3) Establishing a discretization imaging parameter data table according to the value intervals divided in the step (2), mining the imaging data table by adopting association rules based on Boolean attribute mapping, and establishing an influence constraint relation between key influence parameters in the hyperspectral imaging process and mineral identification capacity: performing Boolean attribute mapping on the discretized data table, performing association rule mining on the data table by adopting an Apriori association rule mining algorithm, and setting a set of all attribute values of the hyperspectral imaging database as I ═ I1,i2,…,imIs composed of m items, called item set, ikThe method comprises the following steps of representing a certain parameter attribute value in a hyperspectral imaging database, named as a project, recording data of all attribute values under different imaging parameter combinations as D, recording T as each component imaging parameter in D, calculating the support degree, the promotion degree and the confidence degree of a rule, and representing the mined association rule as follows:
wherein ,
x is a front item of the association rule, namely a key influence parameter, Y is a back item of the association rule, and is a mineral identification type, wherein the minimum support degree is 4%, the minimum confidence degree is 80%, 20 association rules are obtained by mining, and based on the rules, constraint relations between the key influence parameter and the mineral identification capacity in four hyperspectral imaging processes are established.
(4) Calculating the attribute importance of the imaging key parameters to the mineral identification capability based on the discretized data table established in the step (3) and based on the rough set and the knowledge granularity: high spectrum compositionThe image parameter data table is T ═ (U, C, D, V, f), U ═ x1,x2,…,xnThe method comprises the following steps that A is a set of objects in a data table, A is a non-empty finite set of all parameter attributes in the data table, A is C and U, C is a key influence parameter in an imaging system, D is a mineral identification type, V is a set of data table parameter values, and an information function is as follows: f, U × A → V, X, U/D, X1,X2,…,XnAnd the term is the equivalent division of the domain U under the decision attribute D, U/C is the equivalent division of the conditional feature to the domain U, and then X is U/D is X1,X2,…,XnThe knowledge feature resolution on the graph is:
KCDis(C)＝ρC(X)Dis(C)
wherein ,ρR(X) is the accuracy of each group of data X on the equivalent relation (knowledge) R, Dis (C) is the resolution of knowledge, and in the hyperspectral imaging parameter data table, for any key influence parameter C belongs to C, the characteristic resolution is as follows:
KCDis(c)＝KCDis(C)-KCDis(C-{c})
therefore, the attribute importance of any key influence parameter on the mineral identification capacity is calculated:
and establishing an influence degree action relation of each influence parameter on the mineral identification capability based on the attribute importance.
(5) Establishing a multiple linear regression model based on a partial least square method, and establishing a quantitative equation between the imaging parameters and the mineral identification types: establishing a quantitative analysis expression of key influence parameters of mineral identification types and hyperspectral imaging performance by adopting a partial least squares multiple regression analysis method; in the quantification equation, the mineral identification type is a random variable y and a common variable x1,x2,…,xpAs key influence parameters, y and p (p is more than or equal to 2) common variables x are established through partial least squares regression analysis1,x2,…,xpIs composed of
wherein ,
ε is a random variable for the regression coefficients of the regression equation.
(6) And (5) according to the influence constraint relation in the step (3) and the attribute importance of each key influence parameter in the step (4) on the mineral identification capability, optimally solving the quantitative equation in the step (5) to obtain a hyperspectral imaging parameter combination with the optimal mineral identification capability: taking the quantitative speech analytic expression obtained in the step (5) as an objective function, and establishing an optimization model by combining the constraint relation of the step (3) and the step (4) as follows:
min f(x),x∈Rn
s.t.ci(x)＝0,i∈E＝{1,2,…,l},
ci(x)≤0,i∈I＝{l+1,l+2,…,l+m}.
and solving a constraint optimization problem based on optimality conditions to obtain an optimal parameter combination, thereby realizing the optimal design of the hyperspectral imaging parameters.
Claims (7)
1. A hyperspectral imaging parameter optimization design method based on a rough set is characterized by comprising the following steps: it comprises the following steps:
(1) analyzing the hyperspectral imaging process, and determining main influence parameters in the imaging process;
(2) establishing an imaging parameter data table, and dividing imaging key parameter values in the data table by using an entropy-based discretization method;
(3) establishing a discretization imaging parameter data table according to the value intervals divided in the step (2), mining the imaging data table by adopting an association rule based on Boolean attribute mapping, and establishing an influence constraint relation between key influence parameters in the hyperspectral imaging process and mineral identification capacity;
(4) calculating the attribute importance of the imaging key parameters to the mineral identification capability based on the discretized data table established in the step (3) and based on the rough set and the knowledge granularity;
(5) establishing a multiple linear regression model based on a partial least square method, and establishing a quantitative equation between imaging parameters and mineral identification capacity;
(6) and (5) according to the influence constraint relation in the step (3) and the attribute importance of each key influence parameter in the step (4) on the mineral identification capability, optimally solving the quantitative equation in the step (5) to obtain a hyperspectral imaging parameter combination with the optimal mineral identification capability.
2. The hyperspectral imaging parameter optimization design method based on the rough set according to claim 1, wherein the hyperspectral imaging process analysis in the step (1) determines main influence parameters in the imaging process: establishing a scene model, an atmospheric radiation transmission model and a detector model in the hyperspectral imaging process, analyzing the hyperspectral imaging process, and determining key influence parameters influencing imaging performance in the imaging process, wherein the key influence parameters mainly comprise a ground sampling distance, spectral resolution, a signal-to-noise ratio and a modulation transfer function.
3. The hyperspectral imaging parameter optimization design method based on the rough set according to claim 1, wherein the imaging parameter data table is established in the step (2), and imaging key parameter values in the data table are divided by using an entropy-based discretization method: establishing an imaging parameter data table, selecting a breakpoint which enables the overall entropy of the imaging parameter data table to be minimum as an interval division breakpoint by adopting an attribute value division method based on entropy, determining the number of discrete intervals of each parameter attribute by utilizing a minimum description length principle, and then discretizing the attribute value of the imaging key influence parameter;
the process is as follows:
firstly, every piece of imaging data d is imaged in the imaging parameter c1The values are arranged from small to large, and the obtained sequence is represented as: delta1,δ2,...,δn(ii) a Then, the imaging parameters c are recorded1Each potential boundary in the range of values of (a) is:
wherein ,LiDividing point L for the candidate interval of the imaging parameteriSample set D of each imaging parameteriThe division is into two subsets, noted:
when selecting LiWhen the division point is used, the sample set of the data table is divided into two subsets, and the information gain of the imaging data table is expressed as:
wherein ,DiIs a sample set, is, Ent (D)i) Information entropy of a sample set;
assume D in the sample set1iNumber of classes of m1，D2iNumber of classes of m2And then when:
the data is divided in time, wherein, Delta is log2(3m-2-[Ent(D)-m1Ent(D1i)-m2Ent(D2i)]) And obtaining the discretized data table.
4. The rough set-based hyperspectral imaging parameter optimization design method according to claim 1, wherein the step (3)Establishing a discretization imaging parameter data table according to the value intervals divided in the step (2), mining the imaging data table by adopting association rules based on Boolean attribute mapping, and establishing an influence constraint relation between key influence parameters in the hyperspectral imaging process and mineral identification capacity: performing Boolean attribute mapping on the discretized data table, performing association rule mining on the data table by adopting an Apriori association rule mining algorithm, and setting a set of all attribute values of the hyperspectral imaging database as I ═ I1,i2,…,imIs composed of m items, called item set, ikThe method comprises the following steps of representing a certain parameter attribute value in a hyperspectral imaging database, named as a project, recording data of all attribute values under different imaging parameter combinations as D, recording T as each component imaging parameter in D, selecting a rule meeting requirements by calculating the support degree, the promotion degree and the confidence degree of the rule and representing the mined association rule as follows:
wherein ,
x is a front item of the association rule, namely a key influence parameter, Y is a back item of the association rule, and is mineral identification capacity, and an influence constraint relation between the key influence parameter and the mineral identification capacity in the hyperspectral imaging process is established through the obtained association rule.
5. The hyperspectral imaging parameter optimization design method based on the rough set according to claim 1, wherein the step (4) is based on the discretized data table established in the step (3), and the attribute importance of the imaging key parameters to the mineral identification ability is calculated based on the rough set and the knowledge granularity: the hyperspectral imaging parameter data table is T ═ (U, C, D, V, f), U ═ x1,x2,...,xnThe attribute is a non-empty finite set of all the parameter attributes in the data table, and A ═ C ^ U is a set of the objects in the data tableD, C is a key influence parameter in the imaging system, D is an evaluation index of mineral identification capacity, V is a set of data table parameter values, and an information function: f, U × A → V, X, U/D, X1,X2,...,XnAnd the term is the equivalent division of the domain U under the decision attribute D, U/C is the equivalent division of the conditional feature to the domain U, and then X is U/D is X1,X2,...,XnThe knowledge feature resolution on the graph is:
KCDis(C)＝ρC(X)·Dis(C)
wherein ,ρR(X) is the accuracy of each group of data X on the equivalence relation (knowledge) R, Dis (C) is the resolution of knowledge, and in the hyperspectral imaging parameter data table, for any key influence parameter C belongs to C, the characteristic resolution is as follows:
KCDis(c)＝KCDis(C)-KCDis(C-{c})
therefore, the attribute importance of any key influence parameter on the mineral identification capacity is calculated:
and establishing an influence degree action relation of each influence parameter on the mineral identification capability based on the attribute importance.
6. The hyperspectral imaging parameter optimization design method based on the rough set according to claim 1, wherein the step (5) is to establish a multiple linear regression model based on a partial least square method, establish a quantitative equation between the imaging parameters and the mineral identification capability: a quantitative analysis expression of mineral identification ability evaluation indexes and key influence parameters of hyperspectral imaging performance is established by adopting a partial least squares multiple regression analysis method, and in a quantitative equation, the evaluation indexes of the mineral identification ability are a random variable y and a common variable x1,x2,...,xpAs key influence parameters, y and p (p is more than or equal to 2) common variables x are established through partial least squares regression analysis1,x2,...,xpIs composed of
wherein ,
ε is a random variable for the regression coefficients of the regression equation.
7. The hyperspectral imaging parameter optimization design method based on the rough set according to claim 1, wherein the step (6) optimizes and solves the quantitative equation in the step (5) according to the influence constraint relationship in the step (3) and the attribute importance of each key influence parameter in the step (4) on the mineral identification capability to obtain the hyperspectral imaging parameter combination with the optimal mineral identification capability: taking the quantitative speech analytic expression obtained in the step (5) as an objective function, and establishing an optimization model by combining the constraint relation of the step (3) and the step (4) as follows:
min f(x),x∈Rn
s.t.ci(x)＝0,i∈E＝{1,2,…,l},
ci(x)≤0,i∈I＝{l+1,l+2,…,l+m}.
and solving a constraint optimization problem based on optimality conditions to obtain an optimal parameter combination, thereby realizing the optimal design of the hyperspectral imaging parameters.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011366930.0A CN113094651B (en) | 2020-11-27 | 2020-11-27 | Hyperspectral imaging parameter optimization design method based on rough set |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011366930.0A CN113094651B (en) | 2020-11-27 | 2020-11-27 | Hyperspectral imaging parameter optimization design method based on rough set |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113094651A true CN113094651A (en) | 2021-07-09 |
| CN113094651B CN113094651B (en) | 2023-06-09 |
Family
ID=76663706
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011366930.0A Active CN113094651B (en) | 2020-11-27 | 2020-11-27 | Hyperspectral imaging parameter optimization design method based on rough set |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113094651B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130322760A1 (en) * | 2012-06-04 | 2013-12-05 | Raytheon Company | System and method for rapid cluster analysis of hyperspectral images |
| CN103488802A (en) * | 2013-10-16 | 2014-01-01 | 国家电网公司 | EHV (Extra-High Voltage) power grid fault rule mining method based on rough set association rule |
| CN103675518A (en) * | 2013-09-29 | 2014-03-26 | 广州供电局有限公司 | Maintenance method and device for oil-immersed high-voltage equipment |
-
2020
- 2020-11-27 CN CN202011366930.0A patent/CN113094651B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130322760A1 (en) * | 2012-06-04 | 2013-12-05 | Raytheon Company | System and method for rapid cluster analysis of hyperspectral images |
| CN103675518A (en) * | 2013-09-29 | 2014-03-26 | 广州供电局有限公司 | Maintenance method and device for oil-immersed high-voltage equipment |
| CN103488802A (en) * | 2013-10-16 | 2014-01-01 | 国家电网公司 | EHV (Extra-High Voltage) power grid fault rule mining method based on rough set association rule |
Non-Patent Citations (3)
| Title |
|---|
| SWARNAJYOTI PATRA等: "A ROUGH SET BASED BAND SELECTION TECHNIQUE FOR THE ANALYSIS OF HYPERSPECTRAL IMAGES", 《2015 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM(IGARSS)》 * |
| SWARNAJYOTI PATRA等: "Hyperspectral Band Selection Based on Rough Set", 《IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING》 * |
| 詹云军等: "基于高光谱粗糙集分析的矿化信息挖掘", 《地质科技情报》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113094651B (en) | 2023-06-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Tan et al. | Random forest–based estimation of heavy metal concentration in agricultural soils with hyperspectral sensor data | |
| Rocchini et al. | Satellite remote sensing to monitor species diversity: Potential and pitfalls | |
| Lu et al. | Spatio-temporal change detection from multidimensional arrays: Detecting deforestation from MODIS time series | |
| Lobsey et al. | rs‐local data‐mines information from spectral libraries to improve local calibrations | |
| Song et al. | Geographic spatiotemporal big data correlation analysis via the Hilbert–Huang transformation | |
| Tan et al. | Mutual information-induced interval selection combined with kernel partial least squares for near-infrared spectral calibration | |
| Einig et al. | Deep learning denoising by dimension reduction: Application to the ORION-B line cubes | |
| Andrade‐Garda et al. | Partial Least‐Squares Regression | |
| Minu et al. | Prediction accuracy of soil organic carbon from ground based visible near-infrared reflectance spectroscopy | |
| Kumar et al. | Entropy-based fuzzy classification parameter optimization using uncertainty variation across spatial resolution | |
| CN113094651A (en) | Hyperspectral imaging parameter optimization design method based on rough set | |
| Zhang et al. | A New Approach for Mineral Mapping Using Drill-Core Hyperspectral Image | |
| CN110321528B (en) | Hyperspectral image soil heavy metal concentration assessment method based on semi-supervised geospatial regression analysis | |
| Tarnik et al. | Minimum variance based-Bayes Combination for prediction of soil properties on Vis-NIR reflectance spectroscopy | |
| CN100561145C (en) | A kind of high spectrum mineral map plotting method | |
| CN103853817B (en) | Based on the space singular point method of excavation of the magnanimity statistics of GIS | |
| JP2023033398A (en) | Component identification device for spectrum analysis device, method therefor and computer program | |
| CN113295674B (en) | Laser-induced breakdown spectroscopy characteristic nonlinear processing method based on S transformation | |
| Bhise et al. | Review on analysis and classification techniques of soil study in remote sensing and geographic information system | |
| Castanys et al. | Identification of Raman spectra through a case‐based reasoning system: application to artistic pigments | |
| Mikus et al. | Identification of the Probability Density Distribution of a Random Value | |
| Samadzadegan et al. | Evaluating the sensitivity of image fusion quality metrics to image degradation in satellite imagery | |
| Zhao et al. | Prediction of low Zn concentrations in soil from mountainous areas of central Yunnan Province using a combination of continuous wavelet transform and Boruta algorithm | |
| CN112666094A (en) | Common toxin recognition system and method | |
| Kang et al. | Evaluating laboratory-based classification potentials of heavy metal contaminated soils using spectro-radiometer and hyper-spectral imagery |
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 |