Sparse Graph Regularization for Hyperspectral Remote Sensing Image Classification

A spatial-spectral metric learning (SSML) framework for hyperspectral image (HSI) classification is proposed. SSML learns a metric by considering both the spectral characteristics and spatial features represented as the mean of neighboring pixels. It first performs the local pixel neighborhood preserving embedding (LPNPE) to reduce the dimensionality of HSI and meanwhile to preserve the spatial local similarity structure. Then, it learns a spectral and spatial distance metric, separately. Finally, the combination of the spectral and spatial metrics yields a joint spatial-spectral metric. It is followed by a nearest neighbor (NN) classifier for HSI classification. SSML shows good performance over the spectral and spatial NN and SVM on the benchmark hyperspectral data set of Indian Pines.

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.

<strong class="journal-contentHeaderColor">Abstract.</strong> Hyperspectral images contain abundant spectral and spatial information about the earth's surface, labeling data processing and analysis more difficult, as well as the problem of sample labeling. In this paper, local binary pattern (LBP), sparse representation and mixed logistic regression model are introduced, and a sample labeling method based on neighborhood information and priority classifier discrimination is presented. Then, a hyperspectral remote sensing image classification method based on texture features and semi-supervised learning is implemented. The LBP is employed to extract features of spatial texture information from remote sensing images and enrich the feature information of samples. Then the multivariate logistic regression model is used to select the unlabeled samples with the largest amount of information, and the unlabeled samples with neighborhood information and priority classifier tags are selected to obtain the pseudo-labeled samples after learning. By making full use of the advantages of sparse representation and mixed logistic regression model, a new hyperspectral remote sensing image classification model based on semi-supervised learning is constructed to effectively achieve accurate classification of hyperspectral images. The data of Indian Pines, Salinas scene and Pavia University are selected to verify the validity of the proposed method. The experiment results show that the proposed classification method can obtain higher classification accuracy and show stronger timeliness and generalization ability.

Hyperspectral Image (HSI) classification plays a key role remote sensing field. Recently, deep learning has demonstrated its effectiveness in HSI Classification field. This paper presents a spectral-spatial HSI classification technique established on the deep learning based deep belief network (DBN) for deep and abstract feature extraction and adaptive boundary adjustment based segmentation. Proposed approach focuses on integrating the deep learning based spectral features and segmentation based spatial features into a framework for improved performance. Specifically, first the deep DBN model is exploited as a spectral feature extraction based classifier to extract the deep spectral features. Second, spatial contextual features are obtained by utilizing effective adaptive boundary adjustment based segmentation technique. Finally, maximum voting based criteria is operated to integrate the results of extracted spectral and spatial information for improved HSI classification. In general, exploiting spectral features from DBN process and spatial features from segmentation and integration of spectral and spatial information by maximum voting based criteria, has a substantial effect on the performance of HSI classification. Experimental performance on real and widely used hyperspectral data sets with different contexts and resolutions demonstrates the accuracy of the proposed technique and performance is comparable to several recently proposed HSI classification techniques.

Dimensionality reduction based on random projection (RP) includes two problems, namely, the dimensionality is limited by the data size and the class separability of the dimensionality reduction results is unstable due to the randomly generated projection matrix. These problems make the RP algorithm unsuitable for large-size hyperspectral image (HSI) classification. To solve these problems, this paper presents a new partitioned RP (PRP) algorithm and proves its rationality in theory. First, a large-size HSI is evenly divided into multiple small-size sub-HSIs. Afterwards, the projection matrix that maximizes the class separability is selected from multiple samplings in which the class dissimilarity measurement is defined as large inter-class distance and small intra-class variance. By using the same projection matrix, each small-size sub-HSI is projected to generate a low dimensional sub-HSI, thereby generating a low dimensional HSI. Next, the minimum distance (MD) classifier is utilized to classify the low dimensional HSI obtained by the PRP algorithm. Finally, four real HSIs are used for experiments, and three of the most popular classification algorithms based on RP are selected as comparison algorithms to validate the effectiveness of the proposed algorithm. The classification performance is evaluated with the kappa coefficient, overall accuracy (OA), average accuracy (AA), average precision rate (APR), and running time. Experimental results indicate that the proposed algorithm can obtain reliable classification results in a very short time.

Spectral-spatial classification of hyperspectral image based on discriminant sparsity preserving embedding

Hyperspectral remote sensing image classification based on residual generative Adversarial Neural Networks

Sparsity preserving projections (SPP) has drawn more and more attention recently. However, the SPP only focuses on the sparse structure but ignores the discriminant information of labeled samples. We proposed a new sparse manifold learning method, called sparse discriminant embedding (SDE), for hyperspectral image (HSI) classification. The SDE utilizes the merits of both sparsity property and manifold structure. It not only preserves the sparse reconstructive relations but also explicitly boosts the discriminant manifold structure of the data, and the discriminating power of the SDE is further improved than the SPP. Experiments on the Flightline C1, Washington DC Mall, and Botswana HSI datasets are performed to demonstrate the effectiveness of the proposed SDE method.

In this paper, a compact-dictionary-based sparse representation (CDSR) method is proposed for hyperspectral image (HSI) classification. The proposed dictionary in CDSR is dynamically generated according to the spatial and spectral context of each pixel. It can effectively shrink the decision range for classification, and reduce the computational burden since the compact dictionary is composed of the classes correlated with the target pixel in terms of spatial location and spectral information. In order to obtain better spatial context information, a spatial location expanding strategy is designed for spreading local explicit label information to a wider region. Experimental results demonstrate the effectiveness and superiority of the proposed method when compared with some widely used HSI classification approaches.

Hyperspectral Remote Sensing Image Classification Based on Multiple Feature Fusion

ABSTRACTIn this article, we present a desktop application for the analysis, reference data generation, registration, and supervised spatial-spectral classification of hyperspectral remote-sensing images through a simple and intuitive interface. Regarding the classification ability, the different classification schemes are implemented by using a chain structure as a base. It consists of five configurable stages that must be executed in a fixed order: preprocessing, spatial processing, pixel-wise classification, combination, and post-processing. The modular implementation makes its extension easy by adding new algorithms for each stage or new classification chains. The tool has been designed as a platform that is open to the incorporation of algorithms by the users interested in comparing classification schemes. As an example of use, a classification scheme based on the Quick Shift (QS) algorithm for segmentation and on Extreme Learning Machines (ELMs) or Support Vector Machines (SVMs) for classification is also proposed. The application is license-free, runs on the Linux operating system, and was developed in C language using the GTK library, as well as other free libraries to build the graphical user interfaces (GUIs).

By means of a sparse collaborative representation mechanism, sparse-representation-based classifiers show a superior performance in hyperspectral image (HSI) classification. Exploiting the similarity and distinctiveness of HSI neighboring pixels, we propose a new nearest regularized joint sparse representation (NRJSR) classification method in this letter. In the classification process of the central test pixel, the weights of different neighboring pixels and the sparse representation coefficients of different training samples are optimized simultaneously within a regularized sparsity model, which can obtain adaptive weights with good joint sparse representation ability. An alternative iteration strategy is used to solve the regularized joint sparsity model. The proposed NRJSR algorithm is tested on two benchmark HSI data sets. Experimental results demonstrate that the proposed algorithm performs better than other sparsity-based algorithms and spectral and spectral–spatial support vector machine classifiers.

Most hyperspectral image (HSI) classification methods assume that all classes in the test set are present during training. However, in real-world applications, acquiring labeled training samples is challenging. As a result, it is difficult for the training dataset to cover all possible land cover types, leading to the generalized zero-shot learning (GZSL) problem. Recently, vision-language models (VLMs) have provided rich semantic priors for land cover classes, offering promising potential for GZSL. However, two fundamental gaps hinder their application to HSI classification: the task paradigm gap, arising from the difference between image-level VLMs and the pixel-level HSI classification task; and the knowledge gap, due to the inconsistency between VLM features and HSI spectral–spatial representations. To bridge both gaps, a novel framework leveraging VLM semantic priors for GZSL in HSI classification is proposed, primarily using pseudo-labeling technique to provide knowledge for unseen classes. Specifically, a pseudo-label generation and enhancement module enables a paradigm transition from image-level understanding to pixel-level classification by incorporating HSI’s spatial information. A pseudo-label correction module then refines noisy labels using spectral cues to address the knowledge gap. Finally, a global learning strategy integrates pseudo-label distillation, supervised learning, and feature regularization to classify seen classes while enabling generalization to unseen ones. Experiments on benchmark HSI datasets demonstrate the proposed method’s superiority in generalized zero-shot classification. This work highlights the potential of VLMs in advancing HSI classification in practical applications.

Recently, collaborative representation has received much attention in the hyperspectral image (HSI) classification due to its simplicity and effectiveness. However, the existing collaborative representation-based HSI classification methods ignore the correlation among different classes. To overcome this problem, we propose a discriminative kernel collaborative representation and Tikhonov regularization method (DKCRT) for HSI classification, which can make the kernel collaborative representation of different classes to be more discriminative. Specifically, the kernel trick is adopted to map the original HSI into a high space to improve the class separability. Besides, distance-weighted kernel Tikhonov regularization is adopted to enforce these training samples to have large representation coefficients, which are similar to the test sample in the high-dimensional feature space. Moreover, we add a discriminative regularization term to further enhance the separability of different classes, which can take the correlation among different classes into consideration. Furthermore, to take the spatial information of HSI into consideration, we extend the DKCRT to a joint version named JDKCRT. Experiments on real HSIs demonstrate the efficiency of the proposed DKCRT and JDKCRT.

With the development of remote sensing technology and machine learning, the research on hyperspectral remote sensing image classification has also progressed rapidly. In this paper, based on the random forest model, a new classification model of hyperspectral remote sensing images is proposed, which can effectively classify the spectral information and texture information of hyperspectral images. First, the texture features are extracted from the hyperspectral remote sensing image data and superimposed on the original spectral domain data, thus forming a new spectral-space domain data. Then, the model forms an optimal combination of parameters by selecting parameters such as the number of decision trees, maximum depth and minimum number of leaves, and this model has a higher classification accuracy for the dataset than the original random forest model. Experimental results on Indian, KSC and Salinas hyperspectral images show that the method proposed in this paper can solve the problems of hyperspectral data nonlinearity and information redundancy due to the expansion of data and the selection of parameter combinations, thus improving the classification effect of the original random forest and the average accuracy of the classification.