Dynamic Linear Classifier System for Hyperspectral Image Classification for Land Cover Mapping

In recent studies, superpixel segmentation has been integrated into hyperspectral (HS) image classification methods. However, the existing superpixel-based classification methods usually suffer from two serious problems. First, the accuracy and efficiency of current superpixel segmentation approaches cannot meet the demands of practical applications for HS images; second, conventional superpixel-based classification methods generally consider each generated superpixel as a unit for the image classification, which may help to reduce the computing time but result in a significant decrease of the classification accuracy. To solve the problems, we propose a fast region growing based superpixel segmentation (FRGSS) algorithm and a novel texture-adaptive superpixel integration strategy (TASIS) for the HS image classification. Experimental results on real Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) HS images demonstrate that the proposed FRGSS outperforms the state-of-the-art superpixel algorithm. In addition, the superiority of the TASIS is verified compared to the pixel-wise and the conventional superpixel-based classification methods.

Minimum Spanning Forest (MSF) is a graph-based technique used for segmenting and classification of images. In this article, a new method based on MSF is introduced that can be used to supervised classification of hyperspectral images. For a given hyperspectral image, a pixel-based classification, such as Support Vector Machine (SVM) or Maximum Likelihood (ML) is performed. On the other hand, dimensionality reduction is carried out by Principal Components Analysis (PCA) and the first eight components are considered as the reference data. The most reliable pixels, which are obtained from the result of pixel-based classifiers, are used as markers in the construction of MSF. In the next stage, three MSF’s are created after considering three distinct criteria of similarity (dissimilarity). Ultimately, using the majority voting rule, the obtained classification maps are combined and the final classification map is formed. The simulation results presented on an AVRIS image of the vegetation area indicate that the proposed technique enhanced classification accuracy and provides an accurate classification map.

Classification of hyperspectral images always suffers from high dimensionality and very limited labeled samples. Recently, the spectral-spatial classification has attracted considerable attention and can achieve higher classification accuracy and smoother classification maps. In this paper, a novel spectral-spatial classification method for hyperspectral images by using kernel methods is investigated. For a given hyperspectral image, the principle component analysis (PCA) transform is first performed. Then, the first principle component of the input image is segmented into non-overlapping homogeneous regions by using the entropy rate superpixel (ERS) algorithm. Next, the local spectral histogram model is applied to each homogeneous region to obtain the corresponding texture features. Because this step is performed within each homogenous region, instead of within a fixed-size image window, the obtained local texture features in the image are more accurate, which can effectively benefit the improvement of classification accuracy. In the following step, a contextual spectral-texture kernel is constructed by combining spectral information in the image and the extracted texture information using the linearity property of the kernel methods. Finally, the classification map is achieved by the support vector machines (SVM) classifier using the proposed spectral-texture kernel. Experiments on two benchmark airborne hyperspectral datasets demonstrate that our method can effectively improve classification accuracies, even though only a very limited training sample is available. Specifically, our method can achieve from 8.26% to 15.1% higher in terms of overall accuracy than the traditional SVM classifier. The performance of our method was further compared to several state-of-the-art classification methods of hyperspectral images using objective quantitative measures and a visual qualitative evaluation.

Abstract. An essential step in the characterization of surface materials using hyperspectral image analysis is image classification using endmembers. Spectral unmixing is the best method for hyperspectral image classification. This method assumes that the pixel-topixel variability in scene results from varying proportions of spectral endmembers. Spectral endmembers can be derived from the imagery or measurements in the laboratory or field. The primary objective of this paper was to assess the ability of extracted endmembers against some different solutions for extraction of endmembers for hyperspectral image classification. In this paper, we compared the Pixel Purity Index (PPI) and the Sequential Maximum Angle Convex Cone (SMACC) as two popular methods of endmember extraction with library and field spectral. We used spectral information divergence for detection desirable endmembers from field spectral. For accuracy assessment of spectral mixture analysis and production of endmember abundance images for each of methods, the linear spectral unmixing algorithm is used. After a comparison between the results of these methods, it has been verified that field spectral have a better classification result in comparing with other endmember extraction methods. Also, the PPI has reliable results as an automatic endmember extraction method in comparing.

The high-dimensional data space generated by hyperspectral sensors introduces challenges for the conventional data analysis techniques. Popular dimensionality reduction techniques usually assume a Gaussian distribution, which may not be in accordance with real life. Metric learning methods, which explore the global data structure of the labeled training samples, have proved to be very efficient in hyperspectral fields. However, we can go further by utilizing locally adaptive decision constraints for the labeled training samples per class to obtain an even better performance. In this paper, we present the locally adaptive dimensionality reduction metric learning (LADRml) method for hyperspectral image classification. The aims of the presented method are: 1) first, to utilize the limited training samples to reduce the dimensionality of data without a certain distribution hypothesis; and 2) second, to better handle data with complex distributions by the use of locally adaptive decision constraints, which can assess the similarity between a pair of samples based on the distance changes before and after metric learning. The experimental results obtained with a number of challenging hyperspectral image datasets demonstrate that the proposed LADRml algorithm outperforms the state-of-the-art dimensionality reduction and metric learning methods.

Spectral features cannot effectively reflect the differences among the ground objects and distinguish their boundaries in hyperspectral image (HSI) classification. Multi-scale feature extraction can solve this problem and improve the accuracy of HSI classification. The Gaussian pyramid can effectively decompose HSI into multi-scale structures, and efficiently extract features of different scales by stepwise filtering and downsampling. Therefore, this paper proposed a Gaussian pyramid based multi-scale feature extraction (MSFE) classification method for HSI. First, the HSI is decomposed into several Gaussian pyramids to extract multi-scale features. Second, we construct probability maps in each layer of the Gaussian pyramid and employ edge-preserving filtering (EPF) algorithms to further optimize the details. Finally, the final classification map is acquired by a majority voting method. Compared with other spectral-spatial classification methods, the proposed method can not only extract the characteristics of different scales, but also can better preserve detailed structures and the edge regions of the image. Experiments performed on three real hyperspectral datasets show that the proposed method can achieve competitive classification accuracy.

In this paper, a novel method based on wavelet transformation of functional data for accurate classification of hyperspectral images is proposed. The motivation of the proposed method is that in the hyperspectral images, the spectral curve of each pixel can be viewed as a function, mathematically. And it can make the best of the abundant spectral information of the original hyperspectral images. Based on this, we have proposed an effective hyperspectral image classification method which mainly used functional principal component analysis (FPCA) before. However, FPCA method focuses on the global features analysis of hyperspectral image data and may not well extract local structural features. In this paper, in order to better reflect the local structural features of hyperspectral images, we make use of the time-frequency localization characteristics of wavelet transformation to decompose hyperspectral images. Then, the sparse wavelet decomposition coefficients are classified by using extreme learning machine (ELM). Experimental results on two popular hyperspectral images show that our method outperforms some state-of-the-art hyperspectral image classification methods.

Masked Image Modeling (MIM) has made significant advancements across various fields in recent years. Previous research in the hyperspectral (HS) domain often utilizes conventional Transformers to model spectral sequences, overlooking the impact of local details on HS image classification. Furthermore, training models using raw image features as reconstruction targets entails significant challenges. In this study, we specifically focus on the reconstruction targets and feature modeling capabilities of the Vision Transformer (ViT) to address the limitations of MIM methods in the HS domain. As a proposed solution, we introduce a novel and effective method called LFSMIM, which incorporates two key strategies: (1) filtering out high-frequency components from the reconstruction target to mitigate the network’s sensitivity to noise, and (2) enhancing the local and global modeling capabilities of the ViT to effectively capture weakened texture details and exploit global spectral features. LFSMIM demonstrated superior performance in overall accuracy compared to other methods on the Indian Pines, Pavia University, and Houston 2013 datasets, achieving accuracies of 95.522%, 98.820%, and 98.160% respectively. The code will be made available at https://github.com/yuweikong/LFSMIM.

Recently, hyperspectral image (HSI) classification methods based on deep learning have demonstrated excellent performance. However, these deep learning methods still face two major challenges. One is that they require a large number of labeled samples, and the other is that training parameters takes a lot of time. In this paper, we propose a dual-branch deep stochastic adaptive Fourier decomposition (SAFD) network (DSAFDNet) to alleviate the aforementioned two issues in HSI classification applications. SAFD is a newly developed signal processing tool with solid mathematical foundation. It can be used to find common filters (i.e. convolution kernels) of a set of random signals or multi-signals. Since the convolution kernels obtained by SAFD decomposition are complex numbers, few deep learning methods directly deal with such complex convolution kernels. To this end, we propose a dual-branch network to extract deep features from hyperspectral images using both real and imaginary parts of convolutional kernels. After deep feature extraction using DSAFDNet, we further investigate the classification performance of different classifiers on the extracted features. Experimental results show that the proposed method outperforms some HSI classification methods with similar principles. Moreover, compared with other state-of-the-art deep learning methods, the proposed method can achieve better classification performance.

We propose a new spectral-spatial method for hyperspectral image classification based on a graph cut. The classification task is formulated as an energy minimization problem on the graph of image pixels, and is solved by using the graph-cut α-expansion approach. The energy to optimize is computed as a sum of data and interaction energy terms, respectively. The data energy term is computed using the outputs of the probabilistic support vector machines classification. The second energy term, which expresses the interaction between spatially adjacent pixels, is computed by using dissimilarity measures between spectral vectors, such as vector norms, spectral angle mapper and spectral information divergence. Experimental results on hyperspectral images captured by the RO-SIS and the AVIRIS sensors reveal that the proposed method yields higher classification accuracies when compared to the recent state-of-the-art approaches.

In recent years, different from the previous hyperspectral image (HSI) classification method which only considers spectral information or spatial information, people gradually realize that information in different fields is equally important. Therefore, this paper proposes a hyperspectral image classification method called IFBF based on information fusion and bilateral filtering. The proposed IFBF method includes the following main steps. Firstly, morphological operation and super pixel segmentation are respectively used to extract the pixel-level and super pixel-level feature information of HSI. Secondly, two different levels of information are given different weights, and they are fused by decision fusion. Then, considering that multi-level information fusion will bring information redundancy, bilateral filtering method is used to filter the fused image, and finally LDM classification method is used for classification. Experimental results on the real dataset show better performance than several well-known classifications methods.

Hyperspectral image classification is a challenging problem for machine learning methods due to the small number of labelled samples and high spectral variability. In this paper, to solve this problem, a novel superpixel and multi-classifier fusion (SMCF)-based classification method for hyperspectral images is proposed. This method takes full advantage of the spectral information of superpixels and the spatial information of hyperspectral images and includes the following three steps. First, superpixels are used to increase the number of training samples and their spectral diversity. Second, label propagation (LP) is used to classify the hyperspectral images. Although LP is an efficient semi-supervised classification method, the corresponding performance is poor for certain land cover types with dispersed spatial distributions. Thus, a support vector machine (SVM) classifier is introduced to classify the hyperspectral images. Finally, the results of the SVM and LP classifiers are combined using our new class-specific weighted fusion algorithm. In the experiments, we selected three widely used and real hyperspectral data sets for evaluation. The final classification performance was evaluated based on two common metrics: the overall accuracy (OA) and the Kappa coefficient. The experimental results show that the proposed SMCF method is superior to six well-known classification methods, even when only 1% or less of the labelled samples are used.

Hyperspectral image classification is a challenging and significant domain in the field of remote sensing with numerous applications in agriculture, environmental science, mineralogy, and surveillance. In the past years, a growing number of advanced hyperspectral remote sensing image classification techniques based on manifold learning, sparse representation and deep learning have been proposed and reported a good performance in accuracy and efficiency on state-of-the-art public datasets. However, most existing methods still face challenges in dealing with large-scale hyperspectral image datasets due to their high computational complexity. In this work, we propose an improved spectral clustering method for large-scale hyperspectral image classification without any prior information. The proposed algorithm introduces two efficient approximation techniques based on Nyström extension and anchor-based graph to construct the affinity matrix. We also propose an effective solution to solve the eigenvalue decomposition problem by multiplicative update optimization. Experiments on both the synthetic datasets and the hyperspectral image datasets were conducted to demonstrate the efficiency and effectiveness of the proposed algorithm.

Recently, generative adversarial network (GAN)-based methods for hyperspectral image (HSI) classification have attracted research attention due to their ability to alleviate the challenges brought by having limited labeled samples. However, several studies have demonstrated that existing GAN-based HSI classification methods are limited in redundant spectral knowledge and cannot extract discriminative characteristics, thus affecting classification performance. In addition, GAN-based methods always suffer from the model collapse, which seriously hinders their development. In this study, we proposed a semi-supervised adaptive weighting feature fusion generative adversarial network (AWF2-GAN) to alleviate these problems. We introduced unlabeled data to address the issue of having a small number of samples. First, to build valid spectral–spatial feature engineering, the discriminator learns both the dense global spectrum and neighboring separable spatial context via well-designed extractors. Second, a lightweight adaptive feature weighting component is proposed for feature fusion; it considers four predictive fusion options, that is, adding or concatenating feature maps with similar or adaptive weights. Finally, for the mode collapse, the proposed AWF2-GAN combines supervised central loss and unsupervised mean minimization loss for optimization. Quantitative results on two HSI datasets show that our AWF2-GAN achieves superior performance over state-of-the-art GAN-based methods.

This paper introduces a novel heterogeneous domain adaptation (HDA) method for hyperspectral image (HSI) classification with a limited amount of labeled samples in both domains. The method is achieved in the way of cross-domain collaborative learning (CDCL), which is addressed via cluster canonical correlation analysis (C-CCA) and random walker (RW) algorithms. To be specific, the proposed CDCL method is an iterative process of three main components, i.e., RW-based pseudolabeling, cross-domain learning via C-CCA, and final classification based on extended RW (ERW) algorithm. First, given the initially labeled target samples as the training set (TS), the RW-based pseudolabeling is employed to update TS and extract target clusters (TCs) by fusing the segmentation results obtained by RW and ERW classifiers. Second, cross-domain learning via C-CCA is applied using labeled source samples and TCs. The unlabeled target samples are then classified with the estimated probability maps using the model trained in the projected correlation subspace. The newly estimated probability map and TS are used for updating TS again via RW-based pseudolabeling. Finally, when the iterative process converges, the result obtained by the ERW classifier using the final TS and estimated probability maps is regarded as the final classification map. Experimental results on four real HSIs demonstrate that the proposed method can achieve better performance compared with the state-of-the-art HDA and ERW methods.