Spectral data fusion method and system based on dictionary learning

Abstract

The invention belongs to the technical field of data processing, and particularly discloses a spectral data fusion method and system based on dictionary learning, and the method comprises the following steps: S1, carrying out the adaptive pixel clustering of hyperspectral data and multispectral data, and obtaining an ideal cluster number; s2, calculating a spectral dictionary of each cluster of hyperspectral data by using an online dictionary learning algorithm; s3, calculating a sparse coefficient of each cluster of multi-spectral data after clustering in combination with the spectral dictionary; s4, calculating fusion data corresponding to each cluster according to the spectrum dictionary and the sparse coefficient, and integrating the fusion data of each cluster to obtain a fusion image; according to the method, a more accurate and more stable clustering result can be obtained when a complex data set is processed; and meanwhile, a non-negative constraint condition is applied to the coefficient matrix, so that the robustness of the result is enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a spectral data fusion method and system based on dictionary learning. Background Art

[0002] Optical remote sensing systems are limited by imaging indicators such as the optical diffraction limit, modulation transfer function, and signal-to-noise ratio. It is difficult to obtain remote sensing images with both high spatial resolution and high spectral resolution. Therefore, a large number of studies are devoted to combining the advantages of different optical data in spatial resolution and spectral resolution to obtain data with high spatial resolution and spectral resolution. This process is also called data fusion.

[0003] Dictionary learning is widely used in multispectral and hyperspectral data fusion. The core idea is to obtain the coefficient matrix of multispectral data and the spectral basis (dictionary) matrix of hyperspectral data by solving the optimization problem, and then multiply the two to get the final fusion result.

[0004] At present, most dictionary learning methods use hyperspectral data to learn a universal spectral dictionary, and then solve the coefficient matrix based on the dictionary and multispectral data to obtain the fusion result. Learning a single dictionary for the entire hyperspectral data ignores the spatial self-similarity of the hyperspectral data, and cannot achieve accurate fusion of each region in the image. Moreover, large-scale dictionary sparse coding of the entire hyperspectral data will bring serious computational burden. In addition, the dictionary learning data fusion method assumes that the spectral information exists in a low-dimensional subspace (dictionary). However, when the number of atoms in the dictionary of the entire hyperspectral data is much larger than the number of multispectral data bands, the accuracy of the sparse representation method will deteriorate due to the serious ill-posedness of the optimization problem. The coefficient matrix of multispectral data is usually solved using the greedy algorithm synchronous orthogonal matching pursuit (SOMP). Each iteration updates a single dictionary atom, which takes a long time to optimize and is inefficient. In addition, the solution process uses the standard least squares approximation, which does not take into account the non-negativity of the solution. The result is easily affected by the noise in the data and has poor robustness.

[0005] In summary, a spectral data fusion method and system based on dictionary learning is needed to solve the above problems in the prior art. Summary of the invention

[0006] The present invention provides a spectral data fusion method and system based on dictionary learning, which solves the problem that most dictionary learning data fusion methods cannot accurately fuse each area in the image, and the reduction of the amount of data in each category after clustering avoids the serious computational burden brought by large-scale dictionary sparse coding and the problem of accuracy degradation caused by the number of atoms in the dictionary of hyperspectral data being greater than the number of multispectral data bands.

[0007] In order to achieve the purpose of solving the above technical problems, the present invention adopts the following technical solutions: A spectral data fusion method based on dictionary learning includes the following steps: Step S1, performing adaptive pixel clustering on hyperspectral data and multispectral data to obtain an ideal number of clusters; Step S2, using an online dictionary learning algorithm to calculate the spectral dictionary of each cluster of hyperspectral data; Step S3, calculating the sparse coefficient of each cluster of multispectral data after clustering in combination with the spectral dictionary; Step S4, calculating the fusion data corresponding to each cluster according to the spectral dictionary and the sparse coefficient, and integrating the fusion data of each cluster to obtain a fusion image; The adaptive pixel clustering in step S1 specifically includes: Determine the ideal cluster center through iterative calculation; The Calinski-Harabasz index was calculated based on the intra-cluster data; The number of clusters is preset, and the above steps are repeated within the range to obtain multiple Calinski-Harabasz indices. When the Calinski-Harabasz index is the largest, the corresponding number of clusters is selected as the ideal number of clusters.

[0008] In some embodiments of the present invention, determining the ideal cluster center by iterative calculation includes: Determine the initial cluster center based on the local density of hyperspectral data and multispectral data; Using the initial cluster centers, calculate the mean of the data points in each cluster and update the cluster centers; Repeat the above steps until the number of iterations is reached and determine the ideal cluster center.

[0009] In some embodiments of the present invention, the update formula of the cluster center is: ; Where k is the cluster number, C k is the center of the kth cluster, S k is the set of data points belonging to the kth cluster, d k is the number of data points in the kth cluster, x i Represents the value of a data point.

[0010] In some embodiments of the present invention, the process of determining the initial cluster center includes the following steps: Data preprocessing to eliminate dimensional differences between different features; The local density is calculated using the following formula: , where ρ iis the local density of data point i, d ij is the distance between data points i and j, σ is the width parameter of the Gaussian kernel; The point with the highest local density is selected as the initial cluster center.

[0011] In some embodiments of the present invention, the calculation process of the spectral dictionary in step S2 includes the following steps: Each cluster of hyperspectral data clustered in step S1 is recorded as: ; Where k is the cluster number, R is used to represent the real number set; L is the number of hyperspectral data bands; d k is the number of data points in the kth cluster; The spectral dictionary is calculated by solving the constraint problem shown below ; ; in, Represents the objective function The smallest D k , B k Value; B k is the sparse coefficient of the kth cluster of hyperspectral data; Represents the matrix B k The L1 norm of ; express The square of the L2 norm of ; st means restricted by ; ε is a number infinitely close to 0; h k is the spectral dictionary D k The number of end members.

[0012] In some embodiments of the present invention, the calculation of the sparse coefficient in step S3 includes the following steps: Each cluster of multispectral data clustered in step S1 is recorded as: ; Where k is the cluster number, R is used to represent the real number set; l is the number of bands of multispectral data; d k is the number of data points in the kth cluster of hyperspectral data; c is the spatial resolution multiple of multispectral data compared to hyperspectral data; Divide the multispectral data into multiple non-overlapping blocks P of size (n*n) km , denoted as ; Using the generalized non-negative synchronous orthogonal matching pursuit algorithm to solve the following inequality, we can get each small block P km The corresponding sparse coefficient A km : ; Represents the objective function The smallest A km Value, is the conversion matrix from hyperspectral to multispectral, L is the number of bands of hyperspectral data, l is the number of bands of multispectral data, is the spectral dictionary after conversion, m k Indicates the total number of small blocks in the kth cluster; Represents the coefficient matrix A km The row sparsity constraint of express The square of the L2 norm of ; st means restricted by ; ε is a number infinitely close to 0; The sparse coefficient A of each small block in each cluster km The sparse coefficient A of the multispectral data of the current cluster can be obtained by summing k .

[0013] In some embodiments of the present invention, step S4 specifically includes the following steps: The fused image of each cluster is calculated using the following formula based on the spectral dictionary and sparse coefficient of each cluster: ; Then each cluster fused image X k Corresponding to the corresponding area, a fused image is obtained.

[0014] In some embodiments of the present invention, a spectral data fusion system based on dictionary learning is provided, comprising: An adaptive clustering module, which is used to perform adaptive pixel clustering using the Kmeans algorithm according to the density of hyperspectral data and multispectral data; A calculation module, which is used to calculate the spectral dictionary through an online dictionary learning algorithm; and is also used to calculate the sparse coefficients through a generalized non-negative synchronous orthogonal matching pursuit algorithm; A fusion module, which is used to perform image fusion according to the sparse coefficients of each cluster and the spectral dictionary; The communication module is used to communicate with external devices.

[0015] In some embodiments of the present invention, there is provided an electronic device, comprising: A processor, and a memory and a transceiver communicatively connected to the processor; The memory stores computer-executable instructions; the transceiver is used to send and receive data; The processor executes the computer-executable instructions stored in the memory to implement the above-mentioned spectral data fusion method.

[0016] In some embodiments of the present invention, a computer-readable storage medium is provided, characterized in that: The computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, they are used to implement the above-mentioned spectral data fusion method.

[0017] The technical solution of the present invention has the following technical effects compared with the prior art: The present invention uses a density-based adaptive Kmeans algorithm to cluster multispectral and hyperspectral data, taking advantage of the non-local self-similarity of remote sensing data, and improving the fusion accuracy compared to global dictionary learning. Compared with the traditional Kmeans algorithm, it has significant advantages in the selection of initial cluster centers, robustness to outliers, selection of adaptive cluster numbers, and adaptability to complex shape clustering. These advantages enable the algorithm to obtain more accurate and stable clustering results when processing complex data sets.

[0018] At the same time, the present invention uses a generalized non-negative synchronous orthogonal matching pursuit (GSOMP+) algorithm to calculate sparse coefficients, which improves the computational efficiency compared to the synchronous orthogonal matching pursuit (SOMP) algorithm used in most data fusion algorithms, imposes non-negative constraints on the coefficient matrix, and enhances the robustness of the results. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0020] Figure 1 The present invention discloses a flow chart of a spectral data fusion method based on dictionary learning.

[0021] Figure 2 The present invention is a fusion process diagram of a spectral data fusion method based on dictionary learning.

[0022] Figure 3 It is a schematic diagram for comparing the fusion result obtained by the data fusion method of the present invention with the true value.

[0023] Figure 4 This is a schematic diagram comparing the fusion result obtained using the ordinary Kmeans algorithm and the true value.

[0024] Figure 5 Schematic diagram of the comparison between the fusion result and the true value obtained by data fusion using the detail injection method GLP.

[0025] Figure 6 Schematic diagram of the comparison between the fusion result obtained by data fusion using the detail injection method SFIM and the true value.

[0026] Figure 7 Schematic diagram of the comparison between the fusion result and the true value obtained by data fusion using the matrix decomposition algorithm CNMF.

[0027] Figure 8 It is a structural schematic diagram of the spectral data fusion system.

[0028] Fig. 9 It is a structural schematic diagram of the electronic device.

[0029] Reference numerals: 100, spectral data fusion system; 110, adaptive clustering module; 120, computing module; 130, fusion module; 140, communication module; 200, electronic device; 210, processor; 220, memory; 230, transceiver. DETAILED DESCRIPTION

[0030] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0031] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected" and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0032] Example 1: Reference Figure 1 and Figure 2 As shown, this embodiment provides a spectral data fusion method based on dictionary learning, comprising the following steps: Step S1, performing adaptive pixel clustering on hyperspectral data and multispectral data to obtain an ideal number of clusters; S11. Data preprocessing: such as standardization or normalization to eliminate dimensional differences between different features.

[0033] S12. Calculate local density: The local density can be determined by calculating the distance between each data point and its neighboring points.

[0034] Density calculation formula: , where ρ iis the local density of data point i, d ij is the distance between data points i and j, and σ is the width parameter of the Gaussian kernel.

[0035] S13. Select initial cluster center: select the point with the highest local density as the initial cluster center.

[0036] S14. Execute the clustering algorithm: use the initial cluster center selected in step S13, assign the data points to the nearest cluster center according to the distance metric, calculate the mean of all data points in each cluster as the new cluster center, and repeat the steps of assigning clusters and updating cluster centers until the cluster center no longer changes significantly or the predetermined number of iterations is reached.

[0037] Cluster center update formula: ; Where k is the cluster number, C k is the center of the kth cluster, S k is the set of data points belonging to the kth cluster, d k is the number of data points in the kth cluster, x i Represents the value of a data point.

[0038] S15. Calculate the Calinski-Harabasz index: For each cluster, calculate the sum of the squares of the distances from the data points within the cluster to the cluster center, then average them to get the intra-cluster variance, calculate the square of the average distance between all cluster centers to get the inter-cluster variance, and calculate the Calinski-Harabasz index based on the intra-cluster variance and the inter-cluster variance.

[0039] Within-cluster variance ; Total variance within cluster ; Where K is the number of clusters; Between-cluster variance ; Where C is the global center of all data points; The Calinski-Harabasz index is specifically Calinski-Harabasz= ; Where N is the total number of data points.

[0040] S16, select the optimal number of clusters: preset the number of clusters, and within the preset range of the number of clusters, for example, the range can be selected as 3-6, repeat steps S14 and S15, and select the number of clusters that maximizes the Calinski-Harabasz index as the optimal number of clusters, i.e., the ideal number of clusters K.

[0041] The present invention uses a density-based adaptive Kmeans algorithm to cluster multispectral and hyperspectral data, taking advantage of the non-local self-similarity of remote sensing data, and improving the fusion accuracy compared to global dictionary learning. The density-based adaptive Kmeans algorithm has significant advantages over the traditional Kmeans algorithm in terms of initial cluster center selection, robustness to outliers, selection of adaptive cluster number, and adaptability to complex shape clustering. These advantages enable the algorithm to obtain more accurate and stable clustering results when processing complex data sets.

[0042] In step S1, the non-local self-similarity of remote sensing data is taken into account. The spectra of adjacent data points have high similarity, while the spectra of data points far away have low similarity. The hyperspectral data are divided into K clusters according to the density-based adaptive Kmeans clustering algorithm to obtain The data points in each cluster have extremely high similarity. After clustering, each cluster of hyperspectral data can be expressed as , represents the reflectance spectrum of a typical object in the imaging area, where d k is the number of data points in the kth cluster, and L is the number of hyperspectral data bands.

[0043] Dictionary learning and coefficient estimation for each cluster of pixels can accurately fuse the data in each area, making full use of the advantages of non-local self-similarity of remote sensing data, while avoiding the problem of reduced accuracy caused by the larger number of atoms in the dictionary of hyperspectral data than the number of bands in multispectral data. Specifically, the following steps are adopted: Step S2, using an online dictionary learning algorithm to calculate the spectral dictionary of each cluster of hyperspectral data; Online dictionary learning is a machine learning algorithm that aims to dynamically learn a dictionary (or base dictionary, codebook) from data streams or real-time data, which can efficiently represent the signals or features in the data set. This learning method is different from traditional batch dictionary learning (such as the K-singular value decomposition algorithm), which usually assumes that all data is available before training and learns the entire dictionary at one time. Online dictionary learning is more suitable for processing large-scale data streams or real-time data because it can gradually update the dictionary as new data arrives without recalculating the entire data set.

[0044] In step S2, the spectral dictionary is calculated by solving the constraint problem shown below: ; ; in, Represents the objective function The smallest D k , B k Value; B k is the sparse coefficient of the kth cluster of hyperspectral data; Represents the matrix B k The L1 norm of ; express The square of the L2 norm of ; st means restricted by ; ε is a number infinitely close to 0; h k is the spectral dictionary D k The number of end members.

[0045] Step S3, calculating the sparse coefficient of each cluster of multispectral data after clustering in combination with the spectral dictionary; The sparse coefficients of each cluster of multispectral data are calculated using the generalized non-negative simultaneous orthogonal matching pursuit algorithm (GSOMP+).

[0046] Get the spectral dictionary D of each cluster k After that, we need to calculate each cluster of high-resolution multispectral data The corresponding sparse coefficient , where c is the spatial resolution multiple of multispectral data compared to hyperspectral data.

[0047] Since adjacent pixels in high spatial resolution images represent the same type of objects in the scene and can be represented by a group of the same atoms, the high-resolution multispectral data can be divided into multiple non-overlapping blocks of size (n*n), so each block It can be approximated by the spectral dictionary obtained above, (k and m represent the mth small block of the kth cluster respectively) and the sparse coefficient A corresponding to each small block is obtained by solving the following problem: km .

[0048] ; Represents the objective function The smallest A km Value, is the conversion matrix from hyperspectral to multispectral, L is the number of bands of hyperspectral data, l is the number of bands of multispectral data, is the spectral dictionary after conversion, m k Indicates the total number of small blocks in the kth cluster; Represents the coefficient matrix A km The row sparsity constraint of express The square of the L2 norm of ; st means restricted by ; ε is a number infinitely close to 0; The sparse coefficient A of each small block in each cluster km The sparse coefficient A of the multispectral data of the current cluster can be obtained by summing k .

[0049] The problem is solved by using an improved version of the greedy algorithm Orthogonal Matching Pursuit (OMP), generalized non-negative synchronous orthogonal matching pursuit (GSOMP+). Compared with the original orthogonal matching pursuit algorithm, it adds the constraints of non-negative solution space and allows updating multiple dictionary atoms in each iteration, which improves the computational efficiency and enhances the robustness of the results.

[0050] Step S4, calculating the fusion data corresponding to each cluster according to the spectral dictionary and the sparse coefficient, and integrating the fusion data of each cluster to obtain a fusion image; Specifically, the fused image is calculated based on the sparse coefficients of each cluster and the spectral dictionary. ; After obtaining the spectral dictionary and sparse coefficient of each cluster, the fused data corresponding to each cluster is calculated according to the above formula, and the data of each cluster is mapped to the corresponding area to obtain the final result after fusion.

[0051] Reference Figure 3 As shown, it is a schematic diagram of the comparison between the fusion result obtained by the data fusion method of the present invention and the true value, as well as the peak signal-to-noise ratio (PSNR) and the universal image quality index (UIQI). It can be clearly seen that the fusion result obtained by the fusion method of the present invention is highly consistent with the true value, proving that the fusion effect of the present invention is good.

[0052] Reference Figure 4 As shown, it is a comparison chart of the fusion result and the true value obtained after clustering using the ordinary Kmeans algorithm and then data fusion, as well as the peak signal-to-noise ratio (PSNR) and the universal image quality index (UIQI); the overlap effect is poor, and it can be concluded that the fusion effect obtained by fusion after the density-based adaptive Kmeans algorithm used in step S1 of the present invention is better.

[0053] in addition, Figure 5 Schematic diagram of the comparison between the fusion result and the true value obtained by data fusion for the detail injection method GLP, as well as the peak signal-to-noise ratio (PSNR) and the universal image quality index (UIQI). Figure 6 Schematic diagram of the comparison between the fusion result and the true value obtained by data fusion for the detail injection method SFIM, as well as the peak signal-to-noise ratio (PSNR) and the universal image quality index (UIQI). Figure 7 The figure shows the comparison between the fusion results and the true value obtained by using the CNMF algorithm for data fusion, as well as the peak signal-to-noise ratio (PSNR) and the universal image quality index (UIQI). The above three fusion results are all significantly different from the true value.

[0054] The present invention uses a generalized non-negative simultaneous orthogonal matching pursuit (GSOMP+) algorithm to calculate sparse coefficients. Compared with the simultaneous orthogonal matching pursuit (SOMP) algorithm used in most data fusion algorithms, the present invention improves the computational efficiency, imposes non-negative constraints on the coefficient matrix, and enhances the robustness of the results.

[0055] Example 2: This example will be based on Figure 8 and Fig. 9 A spectral data fusion system 100 and an electronic device 200 based on dictionary learning are described.

[0056] Among them, refer to Figure 8 As shown, a spectral data fusion system 100 based on dictionary learning is provided, comprising: An adaptive clustering module 110, which is used to perform adaptive pixel clustering using a Kmeans algorithm according to the density of the hyperspectral data and the multispectral data; A calculation module 120, which is used to calculate a spectral dictionary by an online dictionary learning algorithm; and is also used to calculate sparse coefficients by a generalized non-negative synchronous orthogonal matching pursuit algorithm; A fusion module 130, which is used to perform image fusion according to the sparse coefficient of each cluster and the spectral dictionary; The communication module 140 is used to communicate with external devices.

[0057] It should be understood that the spectral data fusion system 100 here is embodied in the form of a functional module. The term "module" here may refer to an application specific integrated circuit (ASIC), an electronic circuit, a processor (such as a shared processor, a dedicated processor or a group processor, etc.) and a memory for executing one or more software or firmware programs, a merging logic circuit and / or other suitable components that support the described functions. In an optional example, those skilled in the art may understand that the spectral data fusion system 100 may be specifically the electronic device 200 in the above embodiment, or the function of the electronic device 200 in the above embodiment may be integrated in the spectral data fusion system 100, and the spectral data fusion system 100 may be used to execute the various processes and / or steps corresponding to the electronic device 200 in the above method embodiment, and to avoid repetition, it will not be repeated here.

[0058] The spectral data fusion system 100 has the functions of implementing the corresponding steps performed by the electronic device 200 of the spectral data fusion method in Example 1; the above functions can be implemented by hardware, or by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the above functions. For example, the above acquisition module can be a communication interface, such as a transceiver interface.

[0059] Reference Fig. 9 As shown, in this embodiment, an electronic device 200 is provided, including: A processor 210, and a memory 220 and a transceiver 230 communicatively connected to the processor; The memory 220 stores computer-executable instructions; the transceiver 230 is used to send and receive data; The processor 210 executes the computer-executable instructions stored in the memory 220 to implement the spectral data fusion method in Example 1.

[0060] It should be understood that the electronic device 200 can be used to execute the corresponding steps and / or processes in the above method embodiments. Optionally, the memory 220 may include a read-only memory and a random access memory, and provide instructions and data to the processor. A portion of the memory 220 may also include a non-volatile random access memory. For example, the memory 220 may also store information about the device type. The processor 210 may be used to execute the instructions stored in the memory 220, and when the processor 210 executes the instructions, the processor 210 may execute the corresponding steps and / or processes in the above method embodiments.

[0061] It should be understood that in the embodiment of the present application, the processor 210 may be a central processing unit (CPU), and the processor 210 may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0062] In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in the processor 210 or an instruction in the form of software. The steps of the method disclosed in conjunction with the embodiment of the present application can be directly embodied as a hardware processor for execution, or a combination of hardware and software modules in the processor 210 for execution. The software module can be located in a mature storage medium in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in a memory, and the processor executes the instructions in the memory, and completes the steps of the above method in conjunction with its hardware. To avoid repetition, it is not described in detail here.

[0063] Embodiment 3: In this embodiment, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, they are used to implement the spectral data fusion method in Embodiment 1.

[0064] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0065] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0066] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0067] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.

[0068] In the description of the above embodiments, specific features, structures, materials or characteristics may be combined in a suitable manner in any one or more embodiments or examples.

[0069] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed by the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A spectral data fusion method based on dictionary learning, characterized in that: The following steps are involved: Step S1, performing adaptive pixel clustering on hyperspectral data and multispectral data to obtain an ideal number of clusters; Step S2, using an online dictionary learning algorithm to calculate the spectral dictionary of each cluster of hyperspectral data; Step S3, calculating the sparse coefficient of each cluster of multispectral data after clustering in combination with the spectral dictionary; Step S4, calculating the fusion data corresponding to each cluster according to the spectral dictionary and the sparse coefficient, and integrating the fusion data of each cluster to obtain a fusion image; The adaptive pixel clustering in step S1 specifically includes: Determine the ideal cluster center through iterative calculation; The Calinski-Harabasz index was calculated based on the intra-cluster data; The number of clusters is preset, and the above steps are repeated within the range to obtain multiple Calinski-Harabasz indices. When the Calinski-Harabasz index is the largest, the corresponding number of clusters is selected as the ideal number of clusters.

2. The spectral data fusion method based on dictionary learning according to claim 1, characterized in that: Determining the ideal cluster center by iterative calculation includes: Determine the initial cluster center based on the local density of hyperspectral data and multispectral data; Using the initial cluster centers, calculate the mean of the data points in each cluster and update the cluster centers; Repeat the above steps until the number of iterations is reached and determine the ideal cluster center.

3. The spectral data fusion method based on dictionary learning according to claim 2 is characterized in that: The update formula of the cluster center is: ； Where k is the cluster number, C k is the center of the kth cluster, S k is the set of data points belonging to the kth cluster, d k is the number of data points in the kth cluster, x i Represents the value of a data point.

4. The spectral data fusion method based on dictionary learning according to claim 2, characterized in that: The process of determining the initial cluster center includes the following steps: Data preprocessing to eliminate dimensional differences between different features; The local density is calculated using the following formula: ， where ρ i is the local density of data point i, d ij is the distance between data points i and j, σ is the width parameter of the Gaussian kernel; The point with the highest local density is selected as the initial cluster center.

5. The spectral data fusion method based on dictionary learning according to claim 1, characterized in that: The calculation process of the spectral dictionary in step S2 includes the following steps: Each cluster of hyperspectral data clustered in step S1 is recorded as: ； Where k is the cluster number, R is used to represent the real number set; L is the number of hyperspectral data bands; d k is the number of data points in the kth cluster; The spectral dictionary is calculated by solving the constraint problem shown below ; ； in, Represents the objective function The smallest D k , B k Value; B k is the sparse coefficient of the kth cluster of hyperspectral data; Represents the matrix B k The L1 norm of express The square of the L2 norm of ; st means restricted by ; ε is a number infinitely close to 0; h k is the spectral dictionary D k The number of end members.

6. The spectral data fusion method based on dictionary learning according to claim 1, characterized in that: The calculation of the sparse coefficient in step S3 includes the following steps: Each cluster of multispectral data clustered in step S1 is recorded as: ； Where k is the cluster number, R is used to represent the real number set; l is the number of bands of multispectral data; d k is the number of hyperspectral data points in the kth cluster; c is the spatial resolution multiple of multispectral data compared to hyperspectral data; Divide the multispectral data into multiple non-overlapping blocks P of size (n*n) km , denoted as; Using the generalized non-negative synchronous orthogonal matching pursuit algorithm to solve the following inequality, we can get each small block P km The corresponding sparse coefficient A km : ； Represents the objective function The smallest A km Value, is the conversion matrix from hyperspectral to multispectral, L is the number of bands of hyperspectral data, l is the number of bands of multispectral data, is the spectral dictionary after conversion, m k Indicates the total number of small blocks in the kth cluster; Represents the coefficient matrix A km The row sparsity constraint of express The square of the L2 norm of ; st means restricted by ; ε is a number infinitely close to 0; The sparse coefficient A of each small block in each cluster km The sparse coefficient A of the multispectral data of the current cluster can be obtained by summing k .

7. The spectral data fusion method based on dictionary learning according to claim 6, characterized in that: The step S4 specifically comprises the following steps: The fused image of each cluster is calculated using the following formula based on the spectral dictionary and sparse coefficient of each cluster: ； Then each cluster fused image X k Corresponding to the corresponding area, a fused image is obtained.

8. A spectral data fusion system based on dictionary learning, characterized in that: To implement the method according to any one of claims 1 to 7, comprising: An adaptive clustering module, which is used to perform adaptive pixel clustering using the Kmeans algorithm according to the density of hyperspectral data and multispectral data; A calculation module, which is used to calculate the spectral dictionary through an online dictionary learning algorithm; and is also used to calculate the sparse coefficients through a generalized non-negative synchronous orthogonal matching pursuit algorithm; A fusion module, which is used to perform image fusion according to the sparse coefficients of each cluster and the spectral dictionary; The communication module is used to communicate with external devices.

9. An electronic device, characterized in that: include: A processor, and a memory and a transceiver communicatively connected to the processor; The memory stores computer-executable instructions; the transceiver is used to send and receive data; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 7 when executed by a processor.

Images