CN116778339A - Method and system for selecting hyperspectral wave bands by aid of local view auxiliary discrimination - Google Patents
Method and system for selecting hyperspectral wave bands by aid of local view auxiliary discrimination Download PDFInfo
- Publication number
- CN116778339A CN116778339A CN202310887160.1A CN202310887160A CN116778339A CN 116778339 A CN116778339 A CN 116778339A CN 202310887160 A CN202310887160 A CN 202310887160A CN 116778339 A CN116778339 A CN 116778339A
- Authority
- CN
- China
- Prior art keywords
- band
- hyperspectral
- super
- matrix
- pixel
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 60
- 239000011159 matrix material Substances 0.000 claims abstract description 48
- 238000001228 spectrum Methods 0.000 claims abstract description 26
- 230000011218 segmentation Effects 0.000 claims abstract description 19
- 238000009826 distribution Methods 0.000 claims abstract description 17
- 238000010187 selection method Methods 0.000 claims abstract description 16
- 238000005516 engineering process Methods 0.000 claims abstract description 9
- 238000005457 optimization Methods 0.000 claims abstract description 9
- 230000006870 function Effects 0.000 claims description 17
- 239000013598 vector Substances 0.000 claims description 16
- 230000008569 process Effects 0.000 claims description 12
- 238000003860 storage Methods 0.000 claims description 9
- 238000010276 construction Methods 0.000 claims description 7
- 230000003595 spectral effect Effects 0.000 claims description 5
- 230000003044 adaptive effect Effects 0.000 claims description 3
- 238000004422 calculation algorithm Methods 0.000 claims description 2
- 238000004364 calculation method Methods 0.000 claims description 2
- 238000003709 image segmentation Methods 0.000 claims description 2
- 238000005295 random walk Methods 0.000 claims description 2
- 238000002474 experimental method Methods 0.000 description 7
- 238000000605 extraction Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 230000009467 reduction Effects 0.000 description 3
- 238000012850 discrimination method Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 238000003971 tillage Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- 244000068988 Glycine max Species 0.000 description 1
- 235000010469 Glycine max Nutrition 0.000 description 1
- 240000008042 Zea mays Species 0.000 description 1
- 235000005824 Zea mays ssp. parviglumis Nutrition 0.000 description 1
- 235000002017 Zea mays subsp mays Nutrition 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 235000005822 corn Nutrition 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000003331 infrared imaging Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000704 physical effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000012847 principal component analysis method Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses a hyperspectral wave band selection method and a hyperspectral wave band selection system for auxiliary discrimination of a local view. Firstly, a hyperspectral image is segmented by using a super-pixel segmentation technology ERS to form a series of super-pixel blocks to capture spectrum characteristic differences of different ground object distributions; secondly, regarding each super pixel block, regarding the wave band as a super graph vertex, constructing a corresponding super graph to express a multi-element adjacent relation among the wave bands, rationalizing the wave band adjacent structure as far as possible to guide the optimization of the sparse self-expression model, and reducing the redundancy of a wave band subset; the consensus matrix fuses the coefficient matrix of each super pixel block through iterative updating; finally, calculating the importance of the reconstructed original data of each wave band according to the consensus matrix, and selecting a wave band subset to realize the purpose of representing the hyperspectral image by using the unified wave band subset; the method fully captures the spectrum characteristic difference of the heterogeneous region, can practically enhance the pixel space local constraint of the model, and improves the quality of the wave band subset, thereby improving the accuracy of the subsequent classification.
Description
Technical Field
The invention belongs to the technical field of hyperspectral image dimension reduction, and particularly relates to a hyperspectral wave band selection method and a hyperspectral wave band selection system for auxiliary discrimination of a local view.
Background
The hyperspectral remote sensing image has hundreds of adjacent and long spectrum channels, can provide higher spectrum resolution than the RGB image, has rich spectrum and space information, and is more beneficial to the accurate identification of ground features. However, the nano-scale spectrum resolution of the hyperspectral image also causes problems for data processing, such as high computational complexity and information redundancy, which results in waste of storage space.
In order to solve these problems, it is necessary to perform a dimension-reduction preprocessing on the hyperspectral image. Typical dimension reduction methods have feature extraction and band selection. The feature extraction projects the original high-dimensional data into a low-dimensional space, and changes the physical properties of the original data, so that some key information is destroyed. The band selection is to select the band subset with the most discrimination from the original data, and compared with the feature extraction, the band selection can better keep the information of the original hyperspectral data without changing the physical characteristics of the band, so that the data after the dimension reduction has higher interpretability and usability.
Band selection techniques can be broadly divided into two categories, supervised and unsupervised. The supervision band selection requires a certain priori information, such as training samples and corresponding labels, and the difficulty and the cost of obtaining the labels of the labels prevent the development of the supervision band selection to a certain extent. In contrast, the unsupervised band selection method does not need explicit labels, only uses unlabeled data to develop a learning model, provides a feasible solution for a plurality of band selection methods plagued by labels, and is more convenient to apply.
In recent years, application of the sparse representation theory to the hyperspectral field is proved to be reasonable, the interpretability of the model is improved based on sparse hyperspectral band selection, the redundancy phenomenon of data is greatly reduced, meanwhile, the storage efficiency is improved, and unnecessary resource waste is avoided. However, some existing researches only expand functions of the sparse self-expression model to a certain extent, influence of pixel space information on key feature extraction is ignored in the process of band selection, and a real multi-element adjacent structure cannot be accurately expressed when a band relation is described, so that the quality of a final selected band subset is low.
Disclosure of Invention
Aiming at the problem that the traditional sparse self-representation band selection method has insufficient local constraint on pixel space in the band selection process, the invention provides a local view assisted discrimination hyperspectral band selection method so as to fully capture spectrum characteristic differences of heterogeneous areas, enhance the local constraint on pixel space of a model, improve the quality of a band subset and further improve the accuracy of subsequent classification.
In order to achieve the above purpose, the invention adopts the following technical scheme:
the hyperspectral band selection method for auxiliary discrimination of the local view comprises the following steps:
step 1, according to the distribution characteristics of ground objects, a hyperspectral image is segmented by utilizing a super-pixel segmentation technology ERS, so as to form a pixel-level super-pixel block for capturing the spectrum characteristic differences of different ground object distributions;
step 2, constructing a local spectrum-space hypergraph of each super pixel block by combining the spatial adjacency and the band spectrum correlation so as to express a multi-element adjacency relationship among the bands and rationalize a band adjacency structure;
step 3, combining the local spectrum-space hypergraph of the super pixel block constructed in the step 2 and the sparse self-representation model to construct a local view auxiliary discrimination hyperspectral band selection model RwSSR;
and 4, carrying out optimization solution on the hyperspectral band selection model RwSSR for auxiliary discrimination of the local view by adopting an iterative updating method to obtain a consensus matrix, calculating the band priority and selecting a band subset.
In addition, on the basis of the hyperspectral band selecting method for auxiliary discrimination of the partial view, the invention also provides a hyperspectral band selecting system for auxiliary discrimination of the partial view, which adopts the following technical scheme:
a partial view assisted discrimination hyperspectral band selection system comprising:
the super-pixel block segmentation module is used for segmenting the hyperspectral image by utilizing a super-pixel segmentation technology ERS according to the distribution characteristics of the ground objects to form pixel-level super-pixel blocks for capturing the spectrum characteristic differences of different ground object distributions;
the local spectrum-space hypergraph construction module is used for constructing a local spectrum-space hypergraph of each super pixel block by combining the spatial proximity and the band spectrum correlation so as to express the multi-element adjacent relation among the bands and rationalize the band adjacent structure;
the hyperspectral wave band selection model construction module is used for combining the local spectrum-space hypergraph of the constructed hyperspectral pixel block and the sparse self-expression model to construct a local view auxiliary discrimination hyperspectral wave band selection model RwSSR;
and the wave band subset selection module is used for carrying out optimization solution on the local view auxiliary discrimination hyperspectral wave band selection model RwSSR by adopting an iterative updating method to obtain a consensus matrix, calculating the wave band priority and selecting the wave band subset.
In addition, on the basis of the above-mentioned method for selecting hyperspectral wave bands by using the auxiliary discrimination of the partial view, the invention also provides a computer device which comprises a memory and one or more processors.
The memory stores executable codes, and the processor is used for realizing the steps of the above-mentioned method for selecting the hyperspectral wave bands by using the auxiliary discrimination of the local view when executing the executable codes.
In addition, on the basis of the above-mentioned method for selecting hyperspectral wave bands by using the auxiliary discrimination of the partial view, the invention also provides a computer readable storage medium on which a program is stored. The program, when executed by a processor, is adapted to carry out the steps of the above-mentioned method for locally view assisted discrimination of hyperspectral band selection.
The invention has the following advantages:
as described above, the invention provides a method and a system for selecting hyperspectral wavebands by using a local view for assisting discrimination. Firstly, a hyperspectral image is segmented by using a super-pixel segmentation technology ERS to form a series of super-pixel blocks to capture spectrum characteristic differences of different ground object distributions; secondly, regarding each super pixel block, regarding the wave band as a super graph vertex, constructing a corresponding super graph to express a multi-element adjacent relation among the wave bands, rationalizing the wave band adjacent structure as far as possible to guide the optimization of the sparse self-expression model, and reducing the redundancy of a wave band subset; the consensus matrix fuses coefficient matrixes of the super pixel blocks through an iterative updating method; finally, calculating the importance of the reconstructed original data of each wave band according to the consensus matrix, and selecting a wave band subset, thereby realizing the purpose of representing the hyperspectral image by using the unified wave band subset; the method fully captures the spectrum characteristic difference of the heterogeneous region, can practically enhance the pixel space local constraint of the model, and improves the quality of the wave band subset, thereby improving the accuracy of the subsequent classification.
Drawings
Fig. 1 is a flowchart of a method for selecting hyperspectral bands with assistance of a partial view in an embodiment of the present invention.
Fig. 2 is a schematic diagram of a process for segmenting hyperspectral images using the super-pixel segmentation technique ERS.
FIG. 3 is a graph showing average accuracy versus the Indian pins dataset for each band selection method in an embodiment of the invention.
FIG. 4 is a graph of overall accuracy versus the Indian pins dataset for each band selection method in an embodiment of the invention.
Detailed Description
The invention is described in further detail below with reference to the attached drawings and detailed description:
example 1
The embodiment 1 describes a method for selecting hyperspectral wave bands by using a local view auxiliary discrimination method, so as to solve the problem that the conventional sparse self-expression wave band selection method has insufficient local constraint on pixel space in the wave band selection process.
As shown in fig. 1, the method for selecting hyperspectral bands by using the partial view assisted discrimination method comprises the following steps:
and step 1, according to the distribution characteristics of the ground objects, the hyperspectral image is segmented by utilizing a super-pixel segmentation technology ERS, so as to form a pixel-level super-pixel block for capturing the spectrum characteristic differences of different ground object distributions.
The hyperspectral image is divided into a series of hyperspectral blocks X with similar spectral characteristics and non-overlapping each other by using a hyperspectral image segmentation technique ERS s And selecting a corresponding sensitive wave band set for different ground objects to represent different ground object coverage, wherein S is defined to represent the number of super pixel blocks, and S is more than or equal to 1 and less than or equal to S.
ERS maps the first principal component of the hyperspectral image to a graph G (V, E); wherein the vertex set V comprises all pixel points, E is an edge set connecting the pixel points, and the weight w (E ij ) Representing the similarity between adjacent pixels, the formula is as follows:
wherein ,vi 、v j All represent pixel points, v i 、v j ∈V；e ij Representing pixel point v i and vj One edge e ij ∈E；G s Expressed as the S-th super pixel block, S is more than or equal to 1 and less than or equal to S, namely
Similarity between pixel points in the same super pixel block is expressed by exp (- |v) i -v j ||/2δ 2 ) And calculating the similarity between pixel points of different super pixel blocks to be 0, wherein delta represents a kernel parameter.
Defining hyperspectral image X, x= [ b ] 1 ,b 2 ,...,b L ]，b l Represents the first band, l.e. [1, L ]]L represents the band number, each band b l Comprising N pixels, i.e. b l ＝(x 1 ,x 2 ,...,x N ) T ，x n Represents the nth pixel, n E [1, N]。
The objective function definition of ERS is shown in equation (2), which finds a subset from edge set EA, make the graphAll Y connected subgraphs are contained, and finally, the purpose of dividing the image is achieved by removing certain edges in the original edge set E.
Wherein the figureA graph obtained by performing ERS segmentation on the first principal component of the hyperspectral image is shown.
H (A) is a graphThe entropy rate of the upper random walk model ensures the compactness and homogeneity of the vertexes on each cluster; b (A) is a balance item describing cluster distribution, and the scale similarity of each cluster is ensured.
μ is a variable weight factor for coordinating the proportional relationship between H (a) and B (a). N (N) A Representation of the drawingsThe number of connected sub-graphs, Y represents the number of preset connected sub-graphs, V, A represents the graph +.>And a subset of edges.
The process of segmenting the hyperspectral image using the superpixel segmentation technique ERS is shown in fig. 2.
The connectivity of the edges between clusters can be eliminated through the objective function of ERS, so that S super-pixel blocks are generated by segmentation, and the corresponding hyperspectral image X is re-expressed as X= [ X ] 1 ,X 2 ,...X s ,...X S ]，1≤s≤S，X s Representing a super pixel block.
And 2, constructing a local spectrum-space hypergraph of each super pixel block by combining the spatial adjacency and the band spectrum correlation so as to express the multi-element adjacency relationship among the bands and rationalize the band adjacency structure.
Combining spatial proximity and band spectral correlation, for each superpixel block X s Constructing a corresponding local spectrum-space hypergraphTo form a graphic complete hypergraphic structure +.>
Each super pixel block X s Is a partial spectral-spatial hypergraph of (2)Denoted as-> wherein ,/>Representing local spectrum-space hypergraph->Vertex set of>Representing local spectrum-space hypergraph->Is a hyperedge set of (1).
Setting a band vectorVertex set->Is composed of L wave band vectors, e i representing band vector b i A super edge composed of K-nearest neighbors e i ∈E s 。
Superb e i Weights w (e) i ) From the superside e i The connection relation among all the vertices in the interior is determined, and the calculation formula is as follows:
wherein θ represents a balance parameter, and the expression thereof is as follows:
wherein the band vector b j ∈V s For the vertex, K represents the superside e i Is a neighbor number of (c). f (b) i )、f(b j ) Respectively represent the vertexes b in the hypergraph i 、b j Is a function of the integral of (a).
From b i B i For the central forming of superb e i The remaining vertices in (a) are determined, i.e
Due to the rest of vertexes in the hyperedge and b i According to the degree of affinity of the vertex b i And vertex b j The affinity between the two is set as follows:
wherein the band vector b k ∈V s Is a vertex.
f ij Is taken as a value and simultaneously measures the correlation of the wave band spectrumSex characteristicsSpatial proximity +.>I.e.
and />As shown in equations (4) and (5), respectively:
wherein Is a balance parameter.
and />Respectively represent the band vectors b i Sum band vector b j Is included.
Construction of each local hypergraphIs the correlation matrix H of (1) s Weight matrix W s Degree matrix of vertices->Degree matrix of superside->
W s ＝diag(w s (e 1 ),w s (e 2 )…w s (e L )) (7)
wherein ,ws (e i ) Representing superedge e i I.e. [1, L)]。
w s (e j ) Representing superedge e j Weights of (h), h s (b i ,e j ) Representing band vector b i Diag (·) represents the diagonal matrix.
So far, the local spectrum-space hypergraph is obtainedCorresponding Laplace matrix L s The following are provided:
wherein I is an identity matrix; l (L) s The space similarity between the band sequences is utilized to reflect the local spectrum-space hypergraph more trulyActual adjacency between bands.
And 3, combining the local spectrum-space hypergraph of the super pixel block constructed in the step 2 and the sparse self-representation model to construct a local view auxiliary discrimination hyperspectral band selection model RwSSR.
The local view assisted discrimination hyperspectral band selection model RwSSR is obtained as follows:
let x= [ b ] 1 ,b 2 ,...,b L ]Representing a hyperspectral image, consisting of L bands, each band containing N pixels b l ＝(x 1 ,x 2 ,...,x N ) T And taking the band redundancy of the hyperspectral image into account, add l 2,1 Regularization sparsely populated coefficient matrices approximating the data set X with as few bands as possible, i.e., dictionary columns, the sparse self-representation model can be represented as:
wherein A is expressed as a sparse coefficient matrix, |·||i F Representing the F-norm, the formula for F-norm of the sparse coefficient matrix is expressed asAlpha is denoted as a regularization parameter, I.I 2,1 Representation l 2,1 A is equal to or greater than 0, which is used to ensure the non-negative characteristics of A, diag (A) is not represented by itself.
Corresponding to any super-pixel block X after super-pixel segmentation s The objective function is defined as:
wherein ,As Is each super pixel block X s Is a local coefficient matrix of (A) s Representing hyperspectral band versus superpixel block X s Is of importance for reconstruction. In order to mine the band reconstruction information of the whole hyperspectral image, the invention uses all local coefficient matrixes A s And integrating a consensus matrix A of the whole hyperspectral image, so that the consensus matrix A integrally constrains the hyperspectral image to integrally reflect the local characteristics of the hyperspectral image, the band selection is more accurate, and the objective function is further expressed as:
wherein ,λ1 Representing regularization parameters.
w s Is an adaptive balance parameter for ensuringOverall minimization. Specifically, if->Very large, w in order to minimize this term s Should be reduced; and vice versa.
For simplicity, the parameter w will be the same in this embodiment s Set to 1/2A s -A. By passing throughTerm, coefficient matrix A of each super pixel block s And fusing the information into a consensus matrix A, so that the consensus matrix A contains the key band information of the super pixel block.
Because of spectral similarity between bands and spatial similarity between adjacent sequence bands, these correlations cannot be represented in equation (13). To this end, according to the definition of the spectrum-space hypergraph, optimize (13) as:
wherein ,λ2 Is a regularization parameter, L s Is each super pixel block X s Laplacian matrix, A s Is each super pixel block X s Is represented by a coefficient matrix, tr (·) representing a trace operator, avoiding that each band is represented by itself, I A I 2,1 L representing consensus matrix A 2,1 Norms.
So far, the model is based on the spatial information of the reserved pixel level by introducing a band local constraint term L of a spectrum level s The method and the device enable the pixel space and the spectrum space to be comprehensively considered in the optimization process, and improve the follow-up sparse representation model solution.
And 4, carrying out optimization solution on the hyperspectral band selection model RwSSR for auxiliary discrimination of the local view by adopting an iterative updating method to obtain a consensus matrix, calculating the band priority and selecting a band subset.
Solving an objective function by adopting an iterative updating algorithm to obtain A s 、A、w s The process of (2) is as follows:
step 4.1. First fix A and w s Update A s The fixed target function is converted into:
pair A s Deriving to obtain A s The updated equation of (2) is:
wherein n represents the current iteration number; a is that s (n+1) Represents the n+1th iteration A s Is of the value of A (n) Representing the value representing the nth iteration a,represents the nth iteration w s Is a value of (a).
Step 4.2. Second fix A s and ws Updating A, and converting the fixed target function into:
setting u=diag (U) 1 ,u 2 ,…,u L ) Is an L x L diagonal matrix,
wherein ,ai Represents the ith row, ||a in the consensus matrix A i || 2 Representation a i L of (2) 2 Norms, ζ is u i Avoiding the occurrence of zero denominator numbers; accordingly, equation (17) is rewritten as:
derive A and letThe updated equation for A is obtained as:
wherein ,A(n+1) Representing the value of iteration a at the n+1th time.
Step 4.3. Refastening A s And A, update w s Obtaining w s The updated equation of (2) is:
wherein ,represents the n+1st iteration w s Is a value of (a).
When the iteration is updated to the prescribed iteration number, or A (n+1) -A (n) Stopping when the I is smaller than the set threshold, wherein each row a in the obtained consensus matrix A i Representing the contribution of the ith band to reconstructed original data X.
wherein ,ri ＝||a i2 The larger the value of i indicates the more important the band.
Thus, for r i Sorting in descending order, selecting the first n BS The individual bands serve subsequent classifications as final band subsets.
In addition, in order to verify the effectiveness of the method proposed by the present invention, the following experiments were also performed:
1. sample data: indian pins hyperspectral data, originating from the Indian laboratory in the united states, were taken by an onboard visible infrared imaging spectrometer (aviis), the dataset having 220 bands, the spectrum ranges from 0.4 μm to 2.5 μm, the size is 145×145×220, and 16 kinds of target objects are contained, including no-tillage corn, split-tillage soybean, tree forest and the like. The dataset contained 21025 pixels, with a total number of target pels of 10249 and the background contained 10776 pixels.
2. Experiment setting:
the comparison method comprises the following steps: the reliability and accuracy of the method are verified by adopting a Support Vector Machine (SVM) as a classifier, and seven different comparison methods, namely a maximum variance principal component analysis Method (MVPCA), an enhanced rapid density peak clustering method (E-FDPC), an optimal class frame aggregation method (OCF), an Adaptive Subspace Partitioning Strategy (ASPS), an extensible single-pass self-learning method (SOP-SRL), a graph regularization spatio-spectral subspace clustering method (GRSC) and a Full band (Full bands), are adopted for classifying.
Evaluation index: the experiment adopts two indexes to evaluate the quality of the wave band subset, namely average precision (AA) and total precision (OA), and the larger the value of the evaluation index is, the better the classification effect is, and the selected wave band subset is more accurate. 10% of the samples were randomly selected as training set in the experiment, the remainder being used for testing. All experiments were repeated five times and the average was calculated.
3. Parameter analysis:
five parameters in total need to be adjusted in experiments, namely S, K and lambda respectively 1 、λ 2 Alpha. Wherein K is the number of neighbors of each superside, the set parameter range is {3,5,7,9}, and the parameter lambda 1 、λ 2 Alpha has a value range of {1e } -3 ,1e -2 ,1e -1 ,1,1e 1 ,1e 2 ,1e 3 The range of the super pixel division block number S is {10,50,100}. The experiment uses voting to determine the optimal parameters. Firstly, selecting an optimal parameter set under different wave bands, then selecting a group of parameters with the largest occurrence number in a voting mode, and recording the results obtained under the group of parameters as final results. For the Indian pins dataset, the final values of the five parameters are shown in table 1.
TABLE 1
| Parameters (parameters) | S | K | λ 1 | λ 2 | α |
| Optimum value | 100 | 3 | 1e -1 | 1e -3 | 1e -3 |
4. Experimental results:
fig. 3 and 4 show the overall and average accuracy of the comparison at different band numbers on the Indian pins dataset, respectively. As can be seen from FIGS. 3 and 4, E-FDPC, MVPCA, OCF performs poorly downstream. SOP-SRL and ASPS effects are unstable. GRSC is stable in effect but does not appear to be prominent. The RwSSR method provided by the invention gradually overtakes other comparison methods when the band number is smaller than 15 by taking the band number of 15 as a demarcation point, and the RwSSR method is far ahead of the other comparison methods and gradually tends to be stable when the band number is larger than 15. This suggests that RwSSR exhibits good performance and enables selection of a subset of bands that contribute to hyperspectral image classification. In conclusion, the method has excellent performance and stable performance in the wave band selection process.
According to the hyperspectral band selection method, firstly, a hyperspectral image is segmented by using a hyperspectral pixel segmentation technology ERS to form a series of hyperspectral blocks to capture spectrum characteristic differences of different ground object distributions, secondly, a local spectrum-space hyperspectral image of each hyperspectral pixel block is constructed to express a multi-element adjacent relation among bands, the band adjacent structure is rationalized as much as possible, and finally band information of the hyperspectral pixel blocks is integrated through a consensus matrix, so that the aim of representing the whole hyperspectral image by using a unified band subset is fulfilled, local constraint of pixel space is practically enhanced, the quality of the band subset is improved, and therefore the problem that the key characteristic extraction of pixel space information is ignored in the band selection process by a traditional sparse self-representation model is effectively solved.
Example 2
This embodiment 2 describes a partial view assisted discrimination hyperspectral band selecting system based on the same inventive concept as the partial view assisted discrimination hyperspectral band selecting method in embodiment 1 described above.
Specifically, the hyperspectral band selection system for auxiliary discrimination of the local view comprises:
the super-pixel block segmentation module is used for segmenting the hyperspectral image by utilizing a super-pixel segmentation technology ERS according to the distribution characteristics of the ground objects to form pixel-level super-pixel blocks for capturing the spectrum characteristic differences of different ground object distributions;
the local spectrum-space hypergraph construction module is used for constructing a local spectrum-space hypergraph of each super pixel block by combining the spatial proximity and the band spectrum correlation so as to express the multi-element adjacent relation among the bands and rationalize the band adjacent structure;
the hyperspectral wave band selection model construction module is used for combining the local spectrum-space hypergraph of the constructed hyperspectral pixel block and the sparse self-expression model to construct a local view auxiliary discrimination hyperspectral wave band selection model RwSSR;
and the wave band subset selection module is used for carrying out optimization solution on the local view auxiliary discrimination hyperspectral wave band selection model RwSSR by adopting an iterative updating method to obtain a consensus matrix, calculating the wave band priority and selecting the wave band subset.
It should be noted that, in the hyperspectral band selection system with auxiliary discrimination of the partial view, the implementation process of the functions and roles of each functional module is specifically shown in the implementation process of the corresponding steps in the method in the above embodiment 1, and will not be described herein.
Example 3
Embodiment 3 describes a computer apparatus for implementing the steps of the partial view assisted discrimination hyperspectral band selection method described in embodiment 1 above.
The computer device includes a memory and one or more processors. Executable code is stored in the memory for implementing the steps of the partial view assisted discrimination hyperspectral band selection method when the executable code is executed by the processor.
In this embodiment, the computer device is any device or apparatus having data processing capability, which is not described herein.
Example 4
Embodiment 4 describes a computer-readable storage medium for implementing the steps of the partial view assisted discrimination hyperspectral band selection method described in embodiment 1 above.
The computer-readable storage medium of embodiment 4 has stored thereon a program which, when executed by a processor, is adapted to implement the steps of a method for localized view assisted discrimination of hyperspectral band selection.
The computer readable storage medium may be an internal storage unit of any device or apparatus having data processing capability, such as a hard disk or a memory, or may be an external storage device of any device having data processing capability, such as a plug-in hard disk, a Smart Media Card (SMC), an SD Card, a Flash memory Card (Flash Card), or the like, which are provided on the device.
The foregoing description is, of course, merely illustrative of preferred embodiments of the present invention, and it should be understood that the present invention is not limited to the above-described embodiments, but is intended to cover all modifications, equivalents and alternatives falling within the spirit and scope of the present invention as defined by the appended claims.
Claims (8)
1. The hyperspectral band selection method for auxiliary discrimination of the partial view is characterized by comprising the following steps of:
step 1, according to the distribution characteristics of ground objects, a hyperspectral image is segmented by utilizing a super-pixel segmentation technology ERS, so as to form a pixel-level super-pixel block for capturing the spectrum characteristic differences of different ground object distributions;
step 2, constructing a local spectrum-space hypergraph of each super pixel block by combining the spatial adjacency and the band spectrum correlation so as to express a multi-element adjacency relationship among the bands and rationalize a band adjacency structure;
step 3, combining the local spectrum-space hypergraph of the super pixel block constructed in the step 2 and the sparse self-representation model to construct a local view auxiliary discrimination hyperspectral band selection model RwSSR;
and 4, carrying out optimization solution on the hyperspectral band selection model RwSSR for auxiliary discrimination of the local view by adopting an iterative updating method to obtain a consensus matrix, calculating the band priority and selecting a band subset.
2. The method for selecting a hyperspectral band by partial view assisted discrimination as claimed in claim 1 wherein,
the step 1 specifically comprises the following steps:
the hyperspectral image is divided by using a hyperspectral image segmentation technique ERS, and is divided into a series of hyperspectral regions X with similar spectral characteristics and non-overlapping each other s Selecting a corresponding sensitive wave band set for different ground objects to represent different ground object coverage, wherein S is defined to represent the number of super pixel blocks, and S is more than or equal to 1 and less than or equal to S;
ERS maps the first principal component of the hyperspectral image to a graph G (V, E); wherein the vertex set V comprises all pixel points, E is an edge set connecting the pixel points, and the weight w (E ij ) Representing the similarity between adjacent pixels, the formula is as follows:
wherein ,vi 、v j All represent pixel points, v i 、v j ∈V；e ij Representing pixel point v i and vj One edge e ij ∈E；G s Expressed as the S-th super pixel block, S is more than or equal to 1 and less than or equal to S, namely
Similarity between pixel points in the same super pixel block is expressed by exp (- |v) i -v j ||/2δ 2 ) Calculating the similarity between pixel points of different super pixel blocks to be 0; wherein δ represents a core parameter;
defining hyperspectral image X, x= [ b ] 1 ,b 2 ,...,b L ]，b l Represents the first band, l.e. [1, L ]]L represents the number of bands, each band b l Comprising N pixels, i.e. b l ＝(x 1 ,x 2 ,...,x N ) T ，x n Represents the nth pixel, n E [1, N]；
The objective function definition of ERS is shown in equation (2), which finds a subset a from the edge set E, so that the graphAll Y connected subgraphs are contained, and the image is segmented by removing certain edges in the original edge set E;
wherein the figureA graph showing the hyperspectral image after ERS segmentation of the first principal component;
h (A) is a graphThe entropy rate of the upper random walk model ensures the compactness and homogeneity of the vertexes on each cluster; b (A) is a balance item describing cluster distribution, and the scale similarity of each cluster is ensured;
μ is a variable weight factor for coordinating the proportional relationship between H (a) and B (a); n (N) A Representation of the drawingsThe number of the connected subgraphs, Y represents the number of the preset connected subgraphs, V, A represents the graph +.>A subset of vertices and edges of (a);
the connectivity of the edges between clusters can be eliminated through the objective function of ERS, so that S super-pixel blocks are generated by segmentation, and the corresponding hyperspectral image X is re-expressed as X= [ X ] 1 ,X 2 ,...X s ,...X S ]，1≤s≤S，X s Representing a super pixel block.
3. The method for selecting a hyperspectral band by partial view assisted discrimination as claimed in claim 2 wherein,
the step 2 specifically comprises the following steps:
combining spatial proximity and band spectral correlation, for each superpixel block X s Constructing a corresponding local spectrum-space hypergraphTo form a graphic complete hypergraphic structure +.>
Each super pixel block X s Is a partial spectral-spatial hypergraph of (2)Denoted as-> wherein ,/>Representing local spectrum-space hypergraph->Vertex set of>Representing local spectrum-space hypergraph->Is a hyperedge set of (1);
setting a band vector b i ∈V s Vertex set V s Is composed of L band vectors, V s ＝{b 1 ,b 2 ,...b L }，i∈[1，L]，e i Representing band vector b i A super edge composed of K-nearest neighbors e i ∈E s ；
Superb e i Weights w (e) i ) From the superside e i The connection relation among all the vertices in the interior is determined, and the calculation formula is as follows:
wherein θ represents a balance parameter, and the expression thereof is as follows:
wherein the band vector b j ∈V s For the vertex, K represents the superside e i Is the number of neighbors of (a); f (b) i )、f(b j ) Respectively represent the vertexes b in the hypergraph i 、b j Is a function of the integral of (a);
from b i B i For the central forming of superb e i The remaining vertices in (a) are determined, i.e
Due to the rest of vertexes in the hyperedge and b i According to the degree of affinity of the vertex b i And vertex b j The affinity between the two is set as follows:
wherein the band vector b k ∈V s Is a vertex;
f ij is taken as a value and simultaneously measures the correlation of the wave band spectrumSpatial proximity +.>I.e. < ->
and />As shown in equations (4) and (5), respectively:
wherein ,is a balance parameter;
and />Respectively represent the band vectors b i Sum band vector b j Is a spatial index value of (1); constructing each partial spectrum-space hypergraph +.>Is the correlation matrix H of (1) s Weight matrix W s Vertex pointDegree matrix->Degree matrix of superside->
W s ＝diag(w s (e 1 ),w s (e 2 )...w s (e L )) (7)
wherein ,ws (e i ) Representing superedge e i Weight, i.e. [1, L]；
w s (e j ) Representing superedge e j Weights of (h), h s (b i ,e j ) Representing band vector b i Diag (·) represents a diagonal matrix;
so far, the local spectrum-space hypergraph is obtainedCorresponding Laplace matrix L s The following are provided:
wherein I is an identity matrix.
4. The method for selecting a hyperspectral band as claimed in claim 3 wherein the partial view assists in discrimination,
the step 3 specifically comprises the following steps:
combining the local spectrum-space hypergraph of the super pixel block and a sparse self-expression model, constructing a hyperspectral band selection model RwSSR based on local view auxiliary discrimination, and defining an objective function as follows:
wherein ,λ1 and λ2 Is a regularization parameter, L s Is each super pixel block X s Laplacian matrix, A s Is each super pixel block X s The coefficient matrix of (2), tr (·) represents the trace operator, avoiding each band to be represented by itself;
w s is an adaptive balance parameter for ensuringOverall minimization; alpha represents a regularization parameter and, I A I 2,1 Sparse is carried out on the consensus matrix A; I.I F Represents F norm by ∈>Term, coefficient matrix A of each super pixel block s And fusing the two adjacent blocks into a consensus matrix A, so that the consensus matrix A contains the key band information of all the super pixel blocks.
5. The method of partial view assisted decision hyperspectral band selection as claimed in claim 4 wherein,
the step 4 specifically comprises the following steps:
solving an objective function by adopting an iterative updating algorithm to obtain A s 、A、w s The process of (2) is as follows:
step 4.1. First fix A and w s Update A s The fixed target function is converted into:
pair A s Deriving to obtain A s The updated equation of (2) is:
wherein n represents the current iteration number; a is that s (n+1) Represents the n+1th iteration A s Is of the value of A (n) Representing the value of the nth iteration a,represents the nth iteration w s Is a value of (2);
step 4.2. Second fix A s and ws Updating A, and converting the fixed target function into:
setting u=diag (U) 1 ,u 2 ,...,u L ) Is an L x L diagonal matrix;
wherein ,ai Represents the ith row, ||a in the consensus matrix A i || 2 Representation a i L of (2) 2 The norm of the sample is calculated,is u i Avoiding the occurrence of zero denominator numbers; accordingly, equation (14) is rewritten as:
derive A and letThe updated equation for A is obtained as:
wherein ,A(n+1) Representing the value of iteration a at n +1,
step 4.3. Refastening A s And A, update w s Obtaining w s The updated equation of (2) is:
wherein ,represents the n+1st iteration w s Is a value of (2);
when the iteration is updated to the prescribed iteration number, or A (n+1) -A (n) Stopping when the I is smaller than the set threshold, wherein each row a in the obtained consensus matrix A i Representing the contribution of the ith band to reconstructed raw data X;
wherein ,ri ＝||a i || 2 The larger the value of (c) indicates the more important the band;
thus, for r i Sorting in descending order, selecting the first n BS The individual bands are taken as final band subsets.
6. The hyperspectral band selection system is assisted in local view discrimination, which is characterized by comprising:
the super-pixel block segmentation module is used for segmenting the hyperspectral image by utilizing a super-pixel segmentation technology ERS according to the distribution characteristics of the ground objects to form pixel-level super-pixel blocks for capturing the spectrum characteristic differences of different ground object distributions;
the local spectrum-space hypergraph construction module is used for constructing a local spectrum-space hypergraph of each super pixel block by combining the spatial proximity and the band spectrum correlation so as to express the multi-element adjacent relation among the bands and rationalize the band adjacent structure;
the hyperspectral wave band selection model construction module is used for combining the local spectrum-space hypergraph of the constructed hyperspectral pixel block and the sparse self-expression model to construct a local view auxiliary discrimination hyperspectral wave band selection model RwSSR;
and the wave band subset selection module is used for carrying out optimization solution on the local view auxiliary discrimination hyperspectral wave band selection model RwSSR by adopting an iterative updating method to obtain a consensus matrix, calculating the wave band priority and selecting the wave band subset.
7. A computer device comprising a memory and one or more processors, the memory having executable code stored therein, wherein the processor, when executing the executable code, performs the steps of the method for localized view assisted discrimination hyperspectral band selection as claimed in any one of claims 1 to 5.
8. A computer-readable storage medium having a program stored thereon, which when executed by a processor, implements the steps of the partial view assisted discrimination hyperspectral band selection method as claimed in any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310887160.1A CN116778339A (en) | 2023-07-19 | 2023-07-19 | Method and system for selecting hyperspectral wave bands by aid of local view auxiliary discrimination |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310887160.1A CN116778339A (en) | 2023-07-19 | 2023-07-19 | Method and system for selecting hyperspectral wave bands by aid of local view auxiliary discrimination |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116778339A true CN116778339A (en) | 2023-09-19 |
Family
ID=87989621
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310887160.1A Pending CN116778339A (en) | 2023-07-19 | 2023-07-19 | Method and system for selecting hyperspectral wave bands by aid of local view auxiliary discrimination |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116778339A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118072180A (en) * | 2024-04-17 | 2024-05-24 | 昆明理工大学 | Hyperspectral image classification method based on keyson hypergraph enhancement |
-
2023
- 2023-07-19 CN CN202310887160.1A patent/CN116778339A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118072180A (en) * | 2024-04-17 | 2024-05-24 | 昆明理工大学 | Hyperspectral image classification method based on keyson hypergraph enhancement |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111860612B (en) | Unsupervised hyperspectral image hidden low-rank projection learning feature extraction method | |
| CN110399909B (en) | Hyperspectral image classification method based on label constraint elastic network graph model | |
| Wang et al. | Fast spectral clustering with anchor graph for large hyperspectral images | |
| US10846566B2 (en) | Method and system for multi-scale cell image segmentation using multiple parallel convolutional neural networks | |
| US10102443B1 (en) | Hierarchical conditional random field model for labeling and segmenting images | |
| Fang et al. | Spectral–spatial classification of hyperspectral images with a superpixel-based discriminative sparse model | |
| Jia et al. | Spectral–spatial Gabor surface feature fusion approach for hyperspectral imagery classification | |
| Li et al. | Semisupervised hyperspectral image segmentation using multinomial logistic regression with active learning | |
| CN110717354A (en) | Superpixel classification method based on semi-supervised K-SVD and multi-scale sparse representation | |
| CN107563442B (en) | Hyperspectral image classification method based on sparse low-rank regular graph tensor embedding | |
| CN109671070B (en) | Target detection method based on feature weighting and feature correlation fusion | |
| Shahdoosti et al. | Spectral–spatial feature extraction using orthogonal linear discriminant analysis for classification of hyperspectral data | |
| US9449395B2 (en) | Methods and systems for image matting and foreground estimation based on hierarchical graphs | |
| CN110458192B (en) | Hyperspectral remote sensing image classification method and system based on visual saliency | |
| CN109409438B (en) | Remote sensing image classification method based on IFCM clustering and variational inference | |
| CN113269201A (en) | Hyperspectral image band selection method and system based on potential feature fusion | |
| CN111652041A (en) | Hyperspectral band selection method, device and apparatus based on depth subspace clustering | |
| Zhang et al. | Polygon structure-guided hyperspectral image classification with single sample for strong geometric characteristics scenes | |
| CN113723492A (en) | Hyperspectral image semi-supervised classification method and device for improving active deep learning | |
| Wang et al. | A novel sparse boosting method for crater detection in the high resolution planetary image | |
| CN116778339A (en) | Method and system for selecting hyperspectral wave bands by aid of local view auxiliary discrimination | |
| CN113298009A (en) | Self-adaptive neighbor face image clustering method based on entropy regularization | |
| CN112163114A (en) | Image retrieval method based on feature fusion | |
| CN110852304B (en) | Hyperspectral data processing method based on deep learning method | |
| CN115496933A (en) | Hyperspectral classification method and system based on space-spectrum prototype feature learning |
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 |