Wave band selection hyperspectral classification algorithm based on heterogeneous cuckoo search

Abstract

The invention discloses a wave band selection hyperspectral classification algorithm based on heterogeneous cuckoo search so as to obtain a high-quality hyperspectral image classification result. The method comprises the steps that firstly, a heterogeneous search strategy is adopted, and the exploration and development capacity of a cuckoo search algorithm is improved; then, a wave band selection model based on a matched filter is designed to select a wave band subset with a high signal-to-noise ratio, and the model carries out dimensionality reduction on hyperspectral data, removes redundant wave bands and meanwhile provides the wave band subset capable of reserving high information content and low noise; a mapping method based on a neighborhood grouping strategy is designed to reduce the similarity between selected wavebands. And then, an automatic wave band number recommendation strategy based on sliding spectrum decomposition is put forward. Experimental results on three famous data sets show that compared with most advanced methods such as marginalized graph self-representation and neighborhood grouping normalization matched filters, the algorithm provided by the invention has the advantages of robustness, superiority and regional multi-graph fusion.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a band selection hyperspectral classification algorithm based on heterogeneous cuckoo search. Background Art

[0002] In recent years, with the advancement of spectral imaging technology, the hyperspectral images captured by sensors have rich spectral information and can easily distinguish the subtle differences between land cover materials. Therefore, hyperspectral images are applied in a variety of fields, such as medicine, agriculture, and construction. As the number of spectral channels increases, the number of frequency bands also increases accordingly, which brings a heavy burden to the research tasks of hyperspectral image classification, target detection, and change detection. In order to alleviate the high computing and storage requirements brought about by the explosive growth of hyperspectral data, it is crucial to study dimensionality reduction technology. Feature selection and feature extraction are the main research topics of dimensionality reduction technology for hyperspectral image data. The former is to select a set of suitable bands from the data set through pre-set criteria, also known as band selection; the latter is to generate new features by performing a series of transformations on the original spectral bands. Generally speaking, hyperspectral image band selection includes supervised methods and unsupervised methods.

[0003] Taking into account prior knowledge, supervised band selection methods can achieve better dimensionality reduction performance while providing more accurate features. Unsupervised band selection methods rely on assumptions about the data to complete dimensionality reduction, but the performance is usually inferior to the former. However, supervised methods often require data to be labeled for dimensionality reduction, which limits their application. Due to the high complexity and large-scale nature of hyperspectral images, performing labeling tasks is extremely time-consuming and laborious, and is also prone to errors. Therefore, unsupervised band selection methods have a wider range of applicability, and this application will focus on unsupervised band selection methods. Summary of the invention

[0004] Hyperspectral image classification refers to assigning each pixel in a hyperspectral image to a specific category or category set. In view of the above problems existing in the existing methods, this application provides an unsupervised band selection hyperspectral image classification algorithm based on heterogeneous cuckoo search, aiming to obtain more accurate hyperspectral image classification results.

[0005] In order to achieve the purpose of the present invention, the technical solution adopted by the present invention is:

[0006] A band selection hyperspectral classification algorithm based on heterogeneous cuckoo search, characterized in that the algorithm comprises the following steps:

[0007] S1. Initialize the weight parameters of the algorithm and determine the search space for the input hyperspectral image data;

[0008] S2. Using the cuckoo search algorithm in the determined search space to perform global exploration and local utilization to obtain population individuals;

[0009] S3. Perform heterogeneous search on the obtained population individuals to obtain individuals with weight labels;

[0010] S4. Filter out the bands with densely packed individuals with weight labels to obtain a band subset with a high signal-to-noise ratio;

[0011] S5. Grouping and mapping neighboring bands for the high signal-to-noise ratio band subsets to group the bands;

[0012] S6. Recommend the number of bands by using sliding spectrum decomposition for the grouped bands, and obtain the bands for the final classification task from each group through recommendation;

[0013] S7. Apply the classification algorithm to the recommended bands to obtain classification results and complete the classification.

[0014] Furthermore, the global exploration in S2 is completed by updating the population through Levy flight, which is defined as follows:

[0015]

[0016] in: is the i-th population individual in the t-th iteration, is the i-th individual in the t+1th iteration, α is the weight scale parameter, which is 0.01 (supplement), and Levy (λ) represents the Levy flight algorithm formula, which is defined as follows:

[0017]

[0018] Where: μ~N(0,σ 2 ),v~N(0,1),

[0019] Where: N represents normal distribution, μ and v represent random variables that obey normal distribution, β is the weight scale parameter of random variable v, σ 2 is the variance.

[0020] Furthermore, the local utilization in S2 is completed by performing population update through preference random walk, which is defined as follows:

[0021]

[0022] Among them: rand represents the weight scale parameter of the population individual (which needs to be distinguished from other scale parameters), which is a random real number between 0 and 1. represents the jth individual in the population at the tth iteration, represents the kth individual in the population at the tth iteration;

[0023] In order to ensure that the algorithm achieves better performance in later iterations, a quantum mechanism is introduced, which is defined as follows:

[0024]

[0025] where δ is the difference weight parameter that controls the differences between individuals in the population.

[0026] Furthermore, the definition of heterogeneous search in S3 is as follows:

[0027]

[0028] in: is the i-th individual in the t+1-th iteration, ε=δexp(η), where and ε are both difference parameters that control the differences between individuals in the population. η is a function variable, which is mainly used to correct the difference parameters and is set by prior knowledge.

[0029] ln() means taking the logarithmic function and performing logarithmic operations with e as the base, exp() means taking the exponential function and performing exponential operations with e as the base, g t represents the optimal population individual of the tth iteration, and the interval parameter sr is calculated as follows:

[0030]

[0031] Where: 2 is the variance of the entire population.

[0032] Furthermore, the grouping definition of the neighborhood bands in S5 is as follows:

[0033]

[0034] Where M is the number of bands, K is the number of groups, P k The initial cluster centers in each group.

[0035] Furthermore, the definition of the sliding spectrum decomposition in S6 is as follows:

[0036]

[0037] Where: max is the sequence, γ is the hyperparameter that balances diversity and quality, j is the variable, r is the scale parameter for measuring sequence quality (r here has a different meaning from r in the previous text and needs to be modified into two different unknowns, and the content in the manual also needs to be modified), T 1:trepresents the diversity of the j-th band sequence from the 1st to the tth iteration, v represents the singular value of the energy band, and t is the number of iterations;

[0038] The inflection point of the curve is used to determine the recommended number of bands. The definition of the inflection point of the curve is as follows:

[0039]

[0040] Where re represents the inflection point of the curve, i and K are independent variables, and w i represents the quality of the i-th band, arg max represents the parameter or index that takes the maximum value of the sequence, γ is a hyperparameter that balances diversity and quality, and T i is the sequence diversity of the ith band.

[0041] Furthermore, the classification method in S7 is a classification method combining KNN with random forest.

[0042] KNN and random forest are two common classification algorithms that can be used in combination to improve classification performance. The following are the steps of the classification method that combines KNN and random forest:

[0043] Build a random forest: First, use the training set to build a random forest model. Random forest is an ensemble learning algorithm that consists of multiple decision trees. Each decision tree is built based on a different random subset and feature subset, and classification is performed through collective decision-making.

[0044] Make predictions for the test sample: For the test sample, input it into each decision tree in the random forest model and record the prediction results of each decision tree.

[0045] KNN classification: For each test sample, according to the KNN algorithm, select K nearest neighbor training samples in the random forest (which can be the K samples with the closest feature distance to the sample), and vote based on the labels of these K neighbors.

[0046] Prediction result: According to the result of KNN voting, the final classification label of the test sample is determined.

[0047] In this method, random forest is used to provide initial classification prediction, while KNN algorithm is used to perform further voting and determine the final classification based on random forest. This combination can make full use of the ensemble learning advantages of random forest and the local neighborhood judgment ability of KNN to improve the accuracy and robustness of classification.

[0048] Compared with the prior art, the advantages of the present invention are:

[0049] 1. For high-dimensional hyperspectral data, band selection is performed to remove redundant bands while retaining high information content and low noise, reducing the amount of data required to be processed by the algorithm.

[0050] 2. Adopt heterogeneous search strategies to improve the exploration and development capabilities of the cuckoo search algorithm.

[0051] 3. Design a frequency band selection model based on matched filters to select frequency band subsets with high signal-to-noise ratio. Frequency band subsets with high signal-to-noise ratio contain the most discriminative and informative features in the image, which is very important for classification tasks and can better distinguish images of different categories, thereby improving classification accuracy. At the same time, it has good robustness to noise and image changes. It can suppress noise interference and extract more stable and reliable features.

[0052] 4. Design a mapping method based on a neighborhood grouping strategy to reduce the similarity between the selected bands and increase the richness of the selected features, ensuring that feature bands with greater differences are selected, which can better distinguish images of different categories. Bands with lower similarity can provide more unique information, thereby improving classification accuracy.

[0053] 5. Design an automatic recommendation strategy for the number of bands based on sliding spectrum decomposition. Sliding spectrum decomposition extracts the characteristic information of different bands by decomposing the spectral information of the image. In addition, sliding spectrum decomposition can decompose the spectral information of the image into different bands, each of which contains different characteristics. Automatically recommending the appropriate number of bands can eliminate redundant information and retain only the most useful features, reducing the computational complexity of the classification algorithm, avoiding unnecessary calculations and processing, reducing the computational time of the classification algorithm, improving computational efficiency, and avoiding misclassification caused by redundant information. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 It is a schematic diagram of the overall process of the algorithm framework;

[0055] Figure 2 It is a schematic diagram of the mapping method based on neighborhood band grouping;

[0056] Figure 3 It is the algorithm flow chart. DETAILED DESCRIPTION

[0057] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined purpose, the following is a detailed description of a band selection hyperspectral classification algorithm based on heterogeneous cuckoo search proposed by the present invention in combination with the accompanying drawings and preferred examples as follows:

[0058] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention. The algorithm of the present invention adopts heterogeneous search. The cuckoo algorithm consists of global exploration and local utilization. The global exploration is to achieve population update through Levy flight, which is defined as follows:

[0059]

[0060] is the i-th individual in the t-th iteration, is the i-th individual in the t+1th iteration, α=0.01. Levy(λ) represents the Levy flight algorithm formula, which is defined as follows:

[0061]

[0062] Where μ~N(0,σ 2 ),v~N(0,1), where N represents normal distribution, μ and v represent random variables that obey normal distribution, and β is the scale parameter.

[0063] Local utilization is achieved by performing population updates via a preference random walk, which is defined as follows:

[0064]

[0065] Where r represents the scale parameter, which is a random value between 0 and 1. and Respectively represent two different individuals in the population at the tth iteration. The evolution is through the two individuals and However, the search capability is not sufficient to support the algorithm to achieve better performance in later iterations.

[0066] According to quantum mechanics, L is defined as the distance between two candidate solutions and the average position of all candidate solutions

[0067]

[0068] Where δ is a parameter that controls the difference between them. In order to enhance the perturbation ability of the cuckoo search algorithm in the search space, a heterogeneous search strategy is proposed based on equation (2) and quantum mechanism, which is defined as follows:

[0069]

[0070] In the formula, is the i-th individual in the t+1-th iteration, ζ=δln(1 / n), ξ=δexp(η), ln() represents the logarithmic function with e as the base, exp() represents the exponential function with e as the base, g t represents the best individual of the tth generation, and sr is defined as follows:

[0071]

[0072] σ 2 is the variance of the entire population. In addition, a heterogeneous cuckoo search algorithm is proposed to improve the exploration and utilization of the algorithm. The detailed process of the heterogeneous cuckoo search algorithm is shown below.

[0073]

[0074]

[0075] Inspired by the method of removing bad frequency bands based on matched filter weights, a band selection model based on normalized matched filter detector is proposed to select a subset of frequency bands with higher signal-to-noise ratio. The weights calculated by the matched filter detector represent the signal-to-noise ratio and image quality of each frequency band. The larger the weight, the higher the signal-to-noise ratio. Therefore, an unsupervised band selection model is designed, which is defined as follows:

[0076]

[0077] Where minf(x) represents the minimum function, K represents the number of selected bands, and X k represents the selected band, W and H represent the width and height of the image respectively. represents the Xth k The weight of the i-th pixel in the frequency band.

[0078] In most cases, many methods only consider the amount of information and noise contained in the band, while ignoring the impact of inter-band correlation on hyperspectral image classification. However, how to minimize the similarity between selected bands is particularly important. Generally speaking, the similarity between adjacent bands is usually higher than that between non-adjacent bands. Therefore, through the design of novel mapping methods, the similarity of the selected band subsets is lower, such as Figure 2 In the neighborhood band grouping method, the hyperspectral image cube is first divided into K groups as evenly as possible, and the divided point set G is defined as follows:

[0079]

[0080] Where M is the number of bands, K is the number of groups, which is also the number of selected bands, and mod(·,·) represents the modulo operation. However, the initial division of energy bands according to formula (9) lacks a theoretical basis, resulting in unsatisfactory results. Therefore, the fine neighborhood grouping method is used to group G k Re-partition, where P k is considered as the initial cluster center in each group and is defined as follows:

[0081]

[0082] In the groups divided by the neighborhood grouping strategy, the frequency bands initially selected by the heterogeneous cuckoo search algorithm are distributed in different groups, which will result in three different situations where the frequency bands selected in the group are 0, 1, or ≥2. For the selected frequency bands in each group, different strategies are used for mapping methods to obtain subsets of the selected frequency bands, such as Figure 2 As shown in the figure. For a group with only 0 candidate frequency bands, the frequency band with the largest matched filter weight is selected in the group; when there is 1 selected frequency band in the group, this frequency band is the final selected frequency band; for a group with ≥ 2 candidate frequency bands, the frequency band selection is achieved through the roulette wheel selection strategy.

[0083] Currently, band selection methods consider the impact of different numbers of bands on classification accuracy, but less research is done to determine the number of selected bands. Therefore, we propose a recommendation strategy based on sliding decomposition to determine the number of bands. Sliding decomposition mainly provides high-quality and diverse content sequences in the content summary, which is defined as follows:

[0084]

[0085] Where max is a sequence, γ is a hyperparameter that balances diversity and quality, j is a variable, r and T 1:t Represent the sequence quality and diversity, respectively, and v represents the singular value of the energy band. In order to obtain the minimum number of selected frequency bands, the sliding decomposition measures the quality and diversity of the selected frequency bands, and the inflection point is the recommended number of selected frequency bands. This application obtains a smooth curve by fitting an exponential function to the discrete probability, and obtains the inflection point of the curve to determine the recommended number of bands, which is defined as follows:

[0086]

[0087] Where r represents the inflection point of the curve, i and K are independent variables, and w i represents the quality of the i-th frequency band, arg max represents the parameter or index that takes the maximum value of a function or sequence, γ is a hyperparameter that balances diversity and quality, and T i for sequence diversity.

[0088] Experimental results and analysis: In the experiment, public datasets such as Botswana, Kennedy Space Center and Salinas are used to verify the effectiveness and applicability of the proposed algorithm. Experimental settings In order to verify the quality of the selected frequency bands, three classifiers, random forest, support vector machine and support vector machine based on edge-preserving filtering, are applied to classify the samples. Since all classifiers are supervised, we randomly select 10% of each dataset as the training set. The same parameters are used for the two classifiers on different datasets. There are many performance indicators in hyperspectral image classification to evaluate the classification results. In this application, the overall accuracy (OA) is the percentage of correctly classified samples among all samples, the average accuracy (AA) is the average of the classification accuracy of each category, and the Kappa coefficient gives the percentage of correctly classified pixels. Three evaluation factors are adopted. The classification accuracy of the algorithm is compared with other advanced algorithms as shown in Table 1.

[0089] Table 1 Comparison of classification accuracy of the proposed classification algorithm and other state-of-the-art algorithms

[0090]

[0091]

[0092] The recommended number of bands for the three data sets are 13, 14 and 18, respectively. In order to fairly verify the performance of the algorithm used in this application, the above method was run independently 30 times, where the parameters of the matched filtering-based cuckoo search algorithm and the matched filtering-based heterogeneous cuckoo search algorithm remained consistent throughout the experiment, such as population size N = 30 and discovery probability Pa = 0.25. If the fitness of the algorithm does not change in 5 consecutive iterations, the method is automatically terminated. The number of selected bands is 30. The bold fonts in all tables represent the best classification performance of all methods. As summarized in Table 1, the classification results of the frequency band subset characterized by a wider distribution are more satisfactory. For the recommended number of selected bands for the three data sets, the proposed matched filtering-based heterogeneous cuckoo search algorithm outperforms other compared methods in terms of classification results obtained using different classifiers. For the Botswana dataset, the numerical evaluation of the classification results of different classifiers of the proposed method and other methods on the selected band subsets are shown in Tables 2, 3 and 4, respectively, including the overall accuracy (OA), average accuracy (AA) and Kappa coefficient, as well as the classification accuracy of each category.

[0093] Table 2 Random forest classification accuracy of the proposed algorithm and other state-of-the-art algorithms in Botswana

[0094]

[0095]

[0096] Table 3 Classification accuracy of support vector machine for the proposed algorithm and other state-of-the-art algorithms in Botswana

[0097]

[0098] Table 4 Classification accuracy of edge-preserving filter-based support vector machine for the proposed algorithm in Botswana and other state-of-the-art algorithms

[0099]

[0100]

[0101] As can be seen from Table 2, using random forest as the classifier, the proposed algorithm has the highest classification accuracy in 7 of the 14 categories, and all indicators of this method are the best compared with other methods. In addition to the proposed method, the adaptive subspace partitioning strategy achieved the highest classification accuracy with an overall accuracy of 84.92%, and the worst was the maximum variance principal component analysis with an overall accuracy of 81.03%. Using support vector machine as the classifier in Table 3, although the adaptive subspace partitioning strategy is still the best band selection method except for the proposed method, the number of classes that achieve the highest classification accuracy is reduced. Self-representation of marginalized graphs achieved the best classification accuracy in 1 and 14 categories, both 100%, but its overall accuracy, average accuracy, and Kappa coefficient are the worst among the compared methods. Although the classification accuracy of the cuckoo search algorithm with matched filters is not the highest in each category, its overall accuracy, average accuracy and Kappa coefficient are still higher than those of the neighborhood grouping normalized matched filter, robust dual-graph self-representation and marginalized graph self-representation, which proves the rationality and superiority of the band selection model based on matched filters. When the support vector machine based on edge-preserving filters is used as the classifier, all band selection methods except the maximum variance principal component analysis obtain a classification accuracy of more than 98%, as shown in Table 4. The proposed algorithm achieves the highest classification accuracy in 9 of the 14 categories, of which 6 categories achieve 100% classification accuracy. The classification results obtained by the adaptive subspace partitioning strategy and the fast neighborhood grouping method for hyperspectral band selection are slightly better than those of the proposed method, with overall accuracy rates of 98.84% and 98.85%, respectively. Comprehensive analysis of the above experimental results shows that the classification results of the proposed algorithm on different classifiers are better than those of other methods. Compared with the cuckoo search algorithm with matched filters, the effectiveness and superiority of the proposed heterogeneous search strategy are proved. The performance of the proposed method under multi-scale cross branches is studied. Experiments are conducted on the recommended number of selected bands, 30 selected bands, and all bands of each data set under the hyperspectral image classification method based on multi-scale cross branches. Response and second-order channel attention are used respectively. 10% of the training samples are randomly selected in the experiment. The experimental results are shown in Table 5.

[0102] Table 5 Classification results under multi-scale cross-branch response and second-order channel attention

[0103]

[0104]

[0105] To highlight the superiority of the execution time of the proposed method, all band selection methods are executed in Matlab 2020a using a PC workstation (Intel Core i9-11900K CPU processor and 32GB RAM). The execution time of all band selection methods for selecting different numbers of bands in the three datasets is shown in Table 6.

[0106] Table 6 Execution time (seconds) of different methods for selecting a certain number of bands on three datasets

[0107]

[0108] The experimental results show that the robust dual graph self-representation, region-level multi-graph fusion, and marginalized graph self-representation methods have very high execution times, while the other methods have lower processing times. For the Salinas dataset, the execution times of the robust dual graph self-representation and marginalized graph self-representation methods are both over 200 seconds, which is too time-consuming. Compared with the cuckoo search algorithm with matched filters, the execution time of the proposed method is only over about 0.05 seconds. Obviously, it is important and necessary to improve the classification performance within an acceptable time. Compared with the neighborhood grouping normalized matched filter and the fast neighborhood grouping method of hyperspectral band selection, the execution time of the proposed method is lower than that of the neighborhood grouping normalized matched filter and higher than that of the fast neighborhood grouping method of hyperspectral band selection, but the classification performance has achieved satisfactory results.

[0109] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Any technician familiar with the profession, without departing from the scope of the technical solution of the present invention, makes any simple modifications, equivalent changes and modifications to the above embodiments based on the technical essence of the present invention, which still fall within the scope of the technical solution of the present invention.

Claims

1. A band-selective hyperspectral classification algorithm based on heterogeneous cuckoo search, Features: The algorithm comprises the following steps: A band selection hyperspectral classification algorithm based on heterogeneous cuckoo search, characterized in that the algorithm comprises the following steps: S1. Initialize the weight parameters of the algorithm and determine the search space for the input hyperspectral image data; S2. Using the cuckoo search algorithm in the determined search space to perform global exploration and local utilization to obtain population individuals; S3. Perform heterogeneous search on the obtained population individuals to obtain individuals with weight labels; S4. Filter out the bands with densely packed individuals with weight labels to obtain a band subset with a high signal-to-noise ratio; S5. Grouping and mapping neighboring bands for the high signal-to-noise ratio band subsets to group the bands; S6. Recommend the number of bands by using sliding spectrum decomposition for the grouped bands, and obtain the bands for the final classification task from each group through recommendation; S7. Apply the classification algorithm to the recommended bands to obtain classification results and complete the classification.

2. A band selection hyperspectral classification algorithm based on heterogeneous cuckoo search as claimed in claim 1, Features: The global exploration in S2 is completed by updating the population through Levy flight, which is defined as follows: in: is the i-th individual in the t-th iteration, is the i-th individual in the t+1th iteration, α is the weight scale parameter, which is 0.01, and is the artificial intervention correction of the proportion of the Levy flight algorithm. Levy(λ) represents the Levy flight algorithm formula, which is defined as follows: Levy(λ)=μ / |v| 1 / β Among them: μ~N(0,σ 2 ),v~N(0,1), Where: N represents normal distribution, μ and v represent random variables that obey normal distribution, β is the weight scale parameter of random variable v, σ 2 is the variance.

3. The band selection hyperspectral classification algorithm based on heterogeneous cuckoo search according to claim 1, Features: The local utilization in S2 is completed by performing population update through preference random walk, which is defined as follows: Among them: rand represents the weight scale parameter of the population individual, which is a random real number between 0 and 1. represents the jth individual in the population at the tth iteration, represents the kth individual in the population at the tth iteration; In order to ensure that the algorithm achieves better performance in later iterations, a quantum mechanism is introduced, which is defined as follows: where δ is a variance parameter that controls the variance between individuals in the population.

4. The band selection hyperspectral classification algorithm based on heterogeneous cuckoo search according to claim 1, Features: The definition of heterogeneous search in S3 is as follows: in: is the i-th individual in the t+1-th iteration, ε=δexp(η), ln() represents the logarithmic function with e as the base, exp() represents the exponential function with e as the base, g t represents the best individual of the tth generation, sr is as follows: Where: 2 is the variance of the entire population.

5. The band selection hyperspectral classification algorithm based on heterogeneous cuckoo search according to claim 1, Features: The grouping definition of the neighborhood bands in S5 is as follows: Where M is the number of bands, K is the number of groups, P k The initial cluster centers in each group.

6. The band selection hyperspectral classification algorithm based on heterogeneous cuckoo search according to claim 1, Features: The definition of the sliding spectrum decomposition in S6 is as follows: Among them: max is the sequence, γ is the hyperparameter that balances diversity and quality, j is the variable, r represents the scale parameter for measuring the quality of the sequence, T 1:t represents the diversity of the j-th band sequence from the 1st to the tth iteration, v represents the singular value of the energy band, and t is the number of iterations; The inflection point of the curve is used to determine the recommended number of bands. The definition of the inflection point of the curve is as follows: Where re represents the inflection point of the curve, i and K are independent variables, and w i represents the quality of the i-th band, arg max represents the parameter or index that takes the maximum value of the sequence, γ is a hyperparameter that balances diversity and quality, and T i is the sequence diversity of the ith band.

7. The band selection hyperspectral classification algorithm based on heterogeneous cuckoo search according to claim 1, Features: The classification method in S7 is a classification method combining KNN and random forest. KNN and random forest are two common classification algorithms, which can be used in combination to improve classification performance; the following are the steps of the classification method combining KNN and random forest: Build a random forest: First, use the training set to build a random forest model. Random forest is an ensemble learning algorithm that consists of multiple decision trees. Each decision tree is built based on a different random subset and feature subset, and classification is performed through collective decision-making; Predict the test sample: For the test sample, input it into each decision tree in the random forest model and record the prediction results of each decision tree; KNN classification: For each test sample, according to the KNN algorithm, select K nearest neighbor training samples in the random forest (which can be the K samples with the closest feature distance to the sample), and vote based on the labels of these K neighbors; Prediction result: According to the result of KNN voting, the final classification label of the test sample is determined. In this method, random forest is used to provide initial classification prediction, while KNN algorithm is used to perform further voting and determine the final classification based on random forest. This combination can make full use of the ensemble learning advantages of random forest and the local neighborhood judgment ability of KNN to improve the accuracy and robustness of classification.

Images