Hyperspectral Image Classification Approach Research Articles

SSC-SFN: spectral-spatial non-local segment federated network for hyperspectral image classification with limited labeled samples

ABSTRACT Hyperspectral image (HSI) classification methods based on deep learning (DL) have performed well in numerous investigations. Although many modified superpixel-wise neural networks are utilized to enhance spatial information, their ability to mine spectral information in graph structures is insufficient. Moreover, single classifier approaches are unable to extract adequate spatial and spectral information simultaneously. For the classification of large-scale research areas, many works have relied on the use of a large number of labeled samples, leading to low efficiency and weak generalization. To address these issues, an effective spectral-spatial HSI classification approach based on spectral-spatial non-local segment federated network (SSC-SFN) was developed in this study. In this framework, deconvolution is employed to recover the data size, while the lost spatial information is replaced by up-pooling. The spectral dimensional features are updated through the generation of non-Euclidean graph structures and the non-local segment smoothing technique. The convolutional neural network and graph convolutional network techniques are coupled to exploit the available spectral and spatial structure information fully. Extensive experimental results obtained using four public benchmark datasets show that the classification accuracy of SSC-SFN can exceed 90% for large-scale HSIs with limited samples.

Two-Stage Hyperspectral Image Classification Using Few Labeled Samples

Hyperspectral image classification (HIC) has attracted considerable attention in the last two decades, and significant progress has been made. However, the small sample size problem of HIC is still challenging. This letter presents a two-stage HIC approach that achieves high classification accuracies with few labeled samples. For a given hyperspectral image, the spatial features are first extracted by local binary patterns (LBP). Spatial features and spectral features for each pixel are then stacked into feature vectors. These vectors are fed into SVM to finish the first classification stage. Based on the preliminary classification results, a superpixel segmentation method is introduced for selecting some superpixels which include training samples and all test pixels assigned to some class. These selected superpixels with their labels obtained by SVM are then added to training samples. According to the enlarged training sample set, Random Multi-Graph (RMG) is finally utilized to classify the remaining samples. Experimental results on three benchmark HSI datasets demonstrate that the proposed LBP and RMG-based two-stage method (LBP-RMG2) significantly outperforms several state-of-the-art algorithms with a few labeled samples.

NSCKL: Normalized Spectral Clustering With Kernel-Based Learning for Semisupervised Hyperspectral Image Classification.

Spatial-spectral classification (SSC) has become a trend for hyperspectral image (HSI) classification. However, most SSC methods mainly consider local information, so that some correlations may not be effectively discovered when they appear in regions that are not contiguous. Although many SSC methods can acquire spatial-contextual characteristics via spatial filtering, they lack the ability to consider correlations in non-Euclidean spaces. To address the aforementioned issues, we develop a new semisupervised HSI classification approach based on normalized spectral clustering with kernel-based learning (NSCKL), which can aggregate local-to-global correlations to achieve a distinguishable embedding to improve HSI classification performance. In this work, we propose a normalized spectral clustering (NSC) scheme that can learn new features under a manifold assumption. Specifically, we first design a kernel-based iterative filter (KIF) to establish vertices of the undirected graph, aiming to assign initial connections to the nodes associated with pixels. The NSC first gathers local correlations in the Euclidean space and then captures global correlations in the manifold. Even though homogeneous pixels are distributed in noncontiguous regions, our NSC can still aggregate correlations to generate new (clustered) features. Finally, the clustered features and a kernel-based extreme learning machine (KELM) are employed to achieve the semisupervised classification. The effectiveness of our NSCKL is evaluated by using several HSIs. When compared with other state-of-the-art (SOTA) classification approaches, our newly proposed NSCKL demonstrates very competitive performance. The codes will be available at https://github.com/yuanchaosu/TCYB-nsckl.

Attention-based multiscale deep learning with unsampled pixel utilization for hyperspectral image classification

In this research, a deep learning approach for hyperspectral image (HSI) classification was developed, incorporating attention mechanisms, multiscale feature learning, and utilization of unsampled pixels. The proposed model, multiscale attention-based hybrid spectral network and UNet (MSA-HybridSN-U), was evaluated on three benchmark datasets: Indian Pines, University of Pavia, and University of Houston using Overall Accuracy (OA), Average Accuracy (AA), and Kappa index (K). The proposed model MSA-HybridSN-U had high accuracy on Indian Pines (IP), Pavia University (PU), and Houston University (HU) datasets. It achieved the highest average accuracy compared with other models like 3D CNN, HybridSN, M3D-DCNN, DBDA, and ACA-HybridSN and higher than 2D CNN and SVM. For the IP dataset, the OA and AA scores are both 99.71% and 99.65% respectively, indicating a high level of accuracy in classifying the samples. The Kappa statistic, which measures inter-annotator agreement, is also high at 0.997, suggesting that the method is consistent in its predictions. For the PU dataset, the results are even higher with OA and AA scores of 99.97% and 99.89% respectively, and a Kappa statistic of 0.999, indicating even higher accuracy and consistency. Finally, for the HU dataset, the results are similarly high with OA and AA scores of 99.47% and 99.92% respectively, and a Kappa statistic of 0.994. The use of attention mechanisms, multiscale features, and unsampled pixels has improved the classification performance of the model. The combination of spectral and spatial attention modules improved the accuracy the most, with the highest accuracy of 99.97% on the PU dataset. Utilizing unsampled pixels in the classification process resulted in a noticeable improvement in accuracy, particularly on the HU dataset with an improvement of 0.29%. The results show the effectiveness of combining multiscale features and attention modules in improving the accuracy of HSI classification.

A new deep learning approach for hyperspectral image classification based on multifeature local kernel descriptors

During the last few years, many deep learning (DL) methods have been proposed for the classification of hyperspectral images (HSI), and the final results show that these models have great potential. However, most existing deep models only consider the original spectral HSI datacube, excluding other sources of information such as textural and geometrical features. In addition to their computational complexity, most DL approaches cannot effectively consider local nonlinear relationships between features. In order to address these issues, this paper develops a new DL approach called MLKD-CNN, which uses multifeature local kernel descriptors (MLKDs) and convolutional neural networks (CNN) to classify HSIs. This method produces local kernel descriptors (LKDs) of spectral, extended morphological profiles, and Gabor features in the feature generation step. A simple CNN is then used to classify MLKD generated from spatial and spectral features. The proposed MLKD considers local nonlinear relationships of both spectral and spectral features, making them capable of achieving high accuracy levels while reducing the computational burden of deep methods. The experiments on four benchmark HSIs show that the proposed MLKD-CNN outperforms some recent HSI classification methods in terms of accuracy and computation time.

Tri-CNN: A Three Branch Model for Hyperspectral Image Classification

Hyperspectral Image (HSI) classification methods that use Deep Learning (DL) have proven to be effective in recent years. In particular, Convolutional Neural Networks (CNNs) have demonstrated extremely powerful performance in such tasks. However, the lack of training samples is one of the main contributors to low classification performance. Traditional CNN-based techniques under-utilize the inter-band correlations of HSI because they primarily use 2D-CNNs for feature extraction. Contrariwise, 3D-CNNs extract both spectral and spatial information using the same operation. While this overcomes the limitation of 2D-CNNs, it may lead to insufficient extraction of features. In order to overcome this issue, we propose an HSI classification approach named Tri-CNN which is based on a multi-scale 3D-CNN and three-branch feature fusion. We first extract HSI features using 3D-CNN at various scales. The three different features are then flattened and concatenated. To obtain the classification results, the fused features then traverse a number of fully connected layers and eventually a softmax layer. Experimental results are conducted on three datasets, Pavia University (PU), Salinas scene (SA) and GulfPort (GP) datasets, respectively. Classification results indicate that our proposed methodology shows remarkable performance in terms of the Overall Accuracy (OA), Average Accuracy (AA), and Kappa metrics when compared against existing methods.

Multiattention Joint Convolution Feature Representation With Lightweight Transformer for Hyperspectral Image Classification

Hyperspectral image (HSI) classification is currently a hot topic in the field of remote sensing. The goal is to utilize the spectral and spatial information from HSI to accurately identify land covers. Convolution neural network (CNN) is a powerful approach for HSI classification. However, CNN has limited ability to capture non-local information to represent complex features. Recently, vision transformers (ViTs) have gained attention due to their ability to process non-local information. Yet, under the HSI classification scenario with ultra-small sample rates, the spectral-spatial information given to ViTs for global modeling is insufficient, resulting in limited classification capability. Therefore, in this article, Multi-Attention Joint Convolution Feature Representation with Lightweight Transformer (MAR-LWFormer) is proposed, which effectively combines the spectral and spatial features of HSI to achieve efficient classification performance at ultra-small sample rates. Specifically, we use a three-branch network architecture to extract multi-scale convolved 3D-CNN, EMAP, and LBP features of HSI, respectively, by taking full exploitation of ultra-small training samples. Second, we design a series of multi-attention modules to enhance spectral-spatial representation for the three types of features and to improve the coupling and fusion of multiple features. Third, we propose an explicit feature attention tokenizer to transform the feature information, which maximizes the effective spectral-spatial information retained in the flat tokens. Finally, the generated tokens are input to the designed lightweight transformer for encoding and classification. Experimental results on three datasets validate that MAR-LWFormer has an excellent performance in HSI classification at ultra-small sample rates when compared to several state-of-the-art classifiers.

Detection of DLBCL by pixel purity index and iterative linearly constrained minimum variance into hyperspectral imaging analysis.

It is unclear whether a hyperspectral imaging-based approach can facilitate the diagnosis of diffuse large B-cell lymphoma (DLBCL), and further investigation is required. In this study, the pixel purity index (PPI) coupled with iterative linearly constrained minimum variance (ILCMV) was used to bridge this gap. We retrospectively reviewed 22 pathological DLBCL specimens. Ten normal lymph node specimens were used as controls. PPI endmember extraction was performed to identify seed-training samples. ILCMV was then used to classify cell regions. The 3D receiver operating characteristic (ROC) showed that the spectral information divergence possessed superior ability to distinguish between normal and abnormal lymphoid cells owing to its stronger background suppression compared with the spectral angle mapper and mean square error methods. An automated cell hyperspectral image classification approach that combined the PPI and ILCMV was used to improve DLBCL diagnosis. This strategy intelligently resolved critical problems arising in unsupervised classification.

Combined Spatial-Spectral Hyperspectral Image Classification Based on Adaptive Guided Filtering

Hyperspectral image classification has a low accuracy in the face of a small training set. To solve the problem, this paper proposes a combined spatial-spectral hyperspectral image classification approach based on adaptive guided filtering. From coarse to fine classification, the local binary pattern (LBP) histogram features were improved, the spatial contrast description was enhanced, and enhanced spatial-spectral features were prepared through Gabor transform of different scales and directions, combined with super pixel blocks. Then, the pre-classification was completed by the support vector machine (SVM) classifier. To reduce noise interference, the pre-classification results were filtered again by a guided filter based on the adaptive regularization factor. To verify its effectiveness, the proposed approach was compared with the state-of-the-arts approaches through repeated experiments. The comparison shows that our approach achieved a high classification accuracy, while suppressing noise interference. This research provides a new tool for hyperspectral image classification with a small training set.

Innovative Hyperspectral Image Classification Approach Using Optimized CNN and ELM

In order to effectively extract features and improve classification accuracy for hyperspectral remote sensing images (HRSIs), the advantages of enhanced particle swarm optimization (PSO) algorithm, convolutional neural network (CNN), and extreme learning machine (ELM) are fully utilized to propose an innovative classification method of HRSIs (IPCEHRIC) in this paper. In the IPCEHRIC, an enhanced PSO algorithm (CWLPSO) is developed by improving learning factor and inertia weight to improve the global optimization performance, which is employed to optimize the parameters of the CNN in order to construct an optimized CNN model for effectively extracting the deep features of HRSIs. Then, a feature matrix is constructed and the ELM with strong generalization ability and fast learning ability is employed to realize the accurate classification of HRSIs. Pavia University data and actual HRSIs after Jiuzhaigou M7.0 earthquake are applied to test and prove the effectiveness of the IPCEHRIC. The experiment results show that the optimized CNN can effectively extract the deep features from HRSIs, and the IPCEHRIC can accurately classify the HRSIs after Jiuzhaigou M7.0 earthquake to obtain the villages, bareland, grassland, trees, water, and rocks. Therefore, the IPCEHRIC takes on stronger generalization, faster learning ability, and higher classification accuracy.

Graph-Cut-Based Collaborative Node Embeddings for Hyperspectral Images Classification

Node embedding (NE) is conducive to aggregating correlations and relieving the influence of the Hughes phenomenon when processing high-dimensional data. Although some graph neural networks can capture correlations during achieving NE, the application of NE still faces two rigorous challenges: numerous model parameters and poor generalization. In this letter, we propose a new approach for hyperspectral image (HSI) classification, called the graph-cut-based collaborative NEs (GCCNE). Specifically, we develop a graph-cut-based NE (GCNE) to achieve low-dimensional feature representation, which avoids numerous model parameters when using a graph structure. Considering that the graph-cut in a low-dimensional space does not need to set anchors to decrease the calculation amount, we adopt an ensemble framework based on random subspaces (RSs) to implement the GCNE to obtain the collaborative feature sets, enhancing the generalization of feature representation. Afterward, the collaborative feature sets are input in several kernel-based extreme learning machines (KELMs), respectively, classifying pixels. The number of RSs is the same as the number of KELMs. Finally, we acquire an ensemble result associated with each class. The effectiveness and competitiveness of the proposed method are evaluated by using real HSI datasets.

Heterogeneous Spectral-Spatial Feature Transfer With Structure Preserved Distribution Alignment for Hyperspectral Image Classification

Cross-scene knowledge transfer has been proven effective to deal with the small-sample problem in hyperspectral image (HSI) classification. Currently, most of the existing works are based on the homogeneous settings where the source and target HSIs are observed from the same feature space, while the heterogeneous situation, which is more common in real-world applications, is under insufficient exploration. In this paper, we propose a novel transfer learning approach for HSI classification, which is capable of transferring discriminative spectral-spatial feature between heterogeneous datasets. Specifically, we first extract spectral-spatial features of source and target scenes by applying the multiscale convolutional sparse decomposition (MCSD) method. By performing MCSD, the spectral information and spatial structure information at different scales can be jointly adapted to learn transferable features for classification. Then, in order to overcome the heterogeneity between the two feature sets, we build a structure preserved distribution alignment (SPDA) model to learn domain-specific projections to map the feature samples into a shared latent subspace where the discriminative knowledge can be effectively transferred. With proper reformulation, we give the analytical solution of the objective function and generate an optimization approach to solve the SPDA model efficiently. Experiments conducted on several real data pairs demonstrate that the proposed approach can explicitly narrow the disparity between heterogeneous HSIs, and yield superior classification results compared with other representative heterogeneous transfer learning methods.

An Effective Hyperspectral Image Classification Approach Based on Discrete Wavelet Transform and Dense CNN

Recently, benefiting from the rapid evolution of Deep Learning technology, hyperspectral image (HSI) classification performance is considerably improved. However, the traditional convolutional analysis resulted in too many learnable parameters of the network, and lots of training samples are required to train the network to avoid the overfitting problem. On the other hand, the 3-D discrete wavelet transform can effectively extract both spatial and spectral information, maintaining robust feature representation capabilities and reducing the computational burden of CNN simultaneously. In this letter, the 3-D discrete wavelet transform is adopted to perform preprocessing operations on HSI. Then, the 3D CNN that integrates dense connections attaches great importance to the reuse of features. Furthermore, our approach significantly reduces network parameters, relieves the training complexity of the network, alleviates the training process from overfitting, and improves classification performance with limited training samples. Three benchmark datasets were used for very rigorous HSI classification experiments to test the performance of the proposed approach. The results demonstrate the superiority of the proposed approach compared with existing state-of-the-art (SOTA) HSI classification approaches. The source code is publicly available at https://github.com/xujingran/DWTDENSE.

Open set domain adaptation based on multi-classifier adversarial network for hyperspectral image classification

Domain adaptation is a proven hyperspectral image (HSI) classification approach aimed at transferring knowledge from a label-rich domain to a label-scarce domain. Existing literature assumes a closed-set scenario in which both the source and target domains share exactly the same label space (“known classes”). However, this assumption may be too ideal in practice. Often, the target domain contains private classes unknown to the source (“unknown classes”). It requires domain adaptation methods to classify the known classes accurately while simultaneously rejecting unknown classes. Focusing on the open-set setting, this paper creatively proposes a hyperspectral open set domain adaptation model based on adversarial learning with a three-dimensional convolutional neural network as the feature extractor, which can sufficiently explore joint spatial-spectral information of HSI and improve classification performance significantly. In addition, this model introduces a dynamic weighting scheme based on multiple auxiliary classifiers for inhibiting negative transfers during adversarial training. Experiment results on three benchmark hyperspectral datasets verify the superiority of the proposed approach for the hyperspectral open set classification. Compared with state-of-the-art techniques with and without using target samples during training, the proposed method improves the mean AUC values by at least 0.157, 0.028, and 0.163 on the Pavia University, Pavia Centre, and Indian Pines datasets, respectively.

Compressive hyperspectral image classification using a 3D coded convolutional neural network.

Hyperspectral image classification (HIC) is an active research topic in remote sensing. Hyperspectral images typically generate large data cubes posing big challenges in data acquisition, storage, transmission and processing. To overcome these limitations, this paper develops a novel deep learning HIC approach based on compressive measurements of coded-aperture snapshot spectral imagers (CASSI), without reconstructing the complete hyperspectral data cube. A new kind of deep learning strategy, namely 3D coded convolutional neural network (3D-CCNN), is proposed to efficiently solve for the classification problem, where the hardware-based coded aperture is regarded as a pixel-wise connected network layer. An end-to-end training method is developed to jointly optimize the network parameters and the coded apertures with periodic structures. The accuracy of classification is effectively improved by exploiting the synergy between the deep learning network and coded apertures. The superiority of the proposed method is assessed over the state-of-the-art HIC methods on several hyperspectral datasets.

Boosting Few-Shot Hyperspectral Image Classification Using Pseudo-Label Learning

Deep neural networks have underpinned much of the recent progress in the field of hyperspectral image (HSI) classification owing to their powerful ability to learn discriminative features. However, training a deep neural network often requires the availability of a large number of labeled samples to mitigate over-fitting, and these labeled samples are not always available in practical applications. To adapt the deep neural network-based HSI classification approach to cases in which only a very limited number of labeled samples (i.e., few or even only one labeled sample) are provided, we propose a novel few-shot deep learning framework for HSI classification. In order to mitigate over-fitting, the framework borrows supervision from an auxiliary set of unlabeled samples with soft pseudo-labels to assist the training of the feature extractor on few labeled samples. By considering each labeled sample as a reference agent, the soft pseudo-label is assigned by computing the distances between the unlabeled sample and all agents. To demonstrate the effectiveness of the proposed method, we evaluate it on three benchmark HSI classification datasets. The results indicate that our method achieves better performance relative to existing competitors in few-shot and one-shot settings.

Phase-Induced Gabor-Based Multiview Active Learning for Hyperspectral Image Classification

In this letter, we propose a new phase-induced Gabor-based multiview active learning (MVAL) (PGMVAL) approach for hyperspectral image (HSI) classification. Our main contribution is to explore the potential of the phase offset term <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$P$ </tex-math></inline-formula> in hand-crafted Gabor feature extraction, which is rarely exploited in previous works. The Gabor filters with <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$P$ </tex-math></inline-formula> added, named as the phase-induced Gabor filters, are able to adjust their frequency response characteristics through <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$P$ </tex-math></inline-formula> . Specifically, we utilize the phase-induced Gabor filtering for view generation purposes under a MVAL framework. As a result, PGMVAL is capable to exploit the complementary information residing in the phase-induced Gabor features corresponding to different <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$P\text{s}$ </tex-math></inline-formula> and simultaneously avoids high memory consumption and a large number of training samples required caused by introducing a new parameter. The experimental results obtained on two benchmark HSI data sets show that the proposed PGMVAL approach using phase-induced Gabor filtering could achieve better classification results with limited training samples.

A Superpixel-Correlation-Based Multiview Approach for Hyperspectral Image Classification

Hyperspectral images provide plentiful spectral&#x2013;spatial information regarding the nature of different materials, leading to the potential of more efficient detection in diverse areas. However, the high volume of spectral bands, along with limited reference data, leads to many challenges. To alleviate these issues, we propose a superpixel-correlation-based multiview classification approach. Here, the spectral&#x2013;spatial multiple views are generated via multiscale superpixel segmentation and correlation-based spectral band clustering. A random forest classifier in conjunction with Markov random field regularization is used as the backend classifier of each view. In particular, an energy function with improved metrics of smoothness is introduced. For decision fusion, the pixelwise weight maps of the views are generated based on both classification certainty and neighboring smoothness. The proposed approach is evaluated on three widely used hyperspectral data sets, and the experimental results demonstrate that the proposed method can achieve a competitive performance compared with other existing methods.

A Hyperspectral Image Classification Approach Based on Feature Fusion and Multi-Layered Gradient Boosting Decision Trees.

At present, many Deep Neural Network (DNN) methods have been widely used for hyperspectral image classification. Promising classification results have been obtained by utilizing such models. However, due to the complexity and depth of the model, increasing the number of model parameters may lead to an overfitting of the model, especially when training data are insufficient. As the performance of the model mainly depends on sufficient data and a large network with reasonably optimized hyperparameters, using DNNs for classification requires better hardware conditions and sufficient training time. This paper proposes a feature fusion and multi-layered gradient boosting decision tree model (FF-DT) for hyperspectral image classification. First, we fuse extended morphology profiles (EMPs), linear multi-scale spatial characteristics, and nonlinear multi-scale spatial characteristics as final features to extract both special and spectral features. Furthermore, a multi-layered gradient boosting decision tree model is constructed for classification. We conduct experiments based on three datasets, which in this paper are referred to as the Pavia University, Indiana Pines, and Salinas datasets. It is shown that the proposed FF-DT achieves better performance in classification accuracy, training conditions, and time consumption than other current classical hyperspectral image classification methods.

Clustering-Based Band Selection Using Structural Similarity Index and Entropy for Hyperspectral Image Classification

Despite the unique capabilities of hyperspectral images for classification tasks, handling the high dimension of these data is challenging. Therefore, dimension reduction algorithms have been proposed to solve this challenge. In this paper, an unsupervised Feature Selection (FS) algorithm was proposed for hyperspectral image classification. First, the entropy values of hyperspectral bands were employed to identify and remove noisy bands. Afterward, the Structural Similarity (SSIM) index and the k-means clustering algorithm were combined to select a few representative bands. Subsequently, the selected bands were injected into a supervised classifier, and the obtained Overall Accuracy (OA) and Kappa Coefficient (KC) were used to evaluate the performance of the proposed method. Finally, the results were compared with the ones achieved from other well-known and state-of-the-art FS approaches. The results revealed that the proposed method outperformed other FS algorithms. Furthermore, the proposed FS algorithm obtained equal or higher OA and KC in comparison with the case of employing all hyperspectral bands. Additionally, a stability analysis step was performed to investigate the consistency of the proposed method. The results suggest the potential of the FS approach for hyperspectral image classification.