Hyperspectral Image Classification Research Articles

SF-ICNN: Spectral–Fractal Iterative Convolutional Neural Network for Classification of Hyperspectral Images

One primary concern in the field of remote-sensing image processing is the precise classification of hyperspectral images (HSIs). Lately, deep-learning models have demonstrated cutting-edge results in HSI classification. Despite this, researchers continue to study and propose simpler, more robust models. This study presents a novel deep-learning approach, the iterative convolutional neural network (ICNN), which combines spectral–fractal features and classifier probability maps iteratively, aiming to enhance the HSI classification accuracy. Experiments are conducted to prove the accuracy enhancement of the proposed method using HSI benchmark datasets of Indian pine (IP) and the University of Pavia (PU) to evaluate the performance of the proposed technique. The final results show that the proposed approach reaches overall accuracies of 99.16% and 95.5% on the IP and PU datasets, respectively, which are better than some basic methods. Additionally, the end findings demonstrate that greater accuracy levels might be achieved using a primary CNN network that employs the iteration loop than with certain current state-of-the-art spatial–spectral HSI classification techniques.

Multimodal Semantic Collaborative Classification for Hyperspectral Images and LiDAR Data

Multimodal Semantic Collaborative Classification for Hyperspectral Images and LiDAR Data

Stochastic image spectroscopy: a discriminative generative approach to hyperspectral image modelling and classification

This paper introduces a new latent variable probabilistic framework for representing spectral data of high spatial and spectral dimensionality, such as hyperspectral images. We use a generative Bayesian model to represent the image formation process and provide interpretable and efficient inference and learning methods. Surprisingly, our approach can be implemented with simple tools and does not require extensive training data, detailed pixel-by-pixel labeling, or significant computational resources. Numerous experiments with simulated data and real benchmark scenarios show encouraging image classification performance. These results validate the unique ability of our framework to discriminate complex hyperspectral images, irrespective of the presence of highly discriminative spectral signatures.

A multiscale dilated attention network for hyperspectral image classification

Hyperspectral imaging is an image obtained by combining spectral detection technology and imaging technology, which can collect electromagnetic spectra in the wavelength range of visible light to near-infrared. It is an important research content in the field of ground observation in hyperspectral remote sensing. However, hyperspectral image face significant challenges in classification task due to their high spectral dimensions, lack of labeled samples, and strong correlation between bands. In order to fully extract features from both spectral and spatial dimensions and improve classification accuracy in the case of limited training samples, a multiscale dilated attention network is proposed for hyperspectral image classification. First, a three-dimensional convolutional layer is used to extract the shallow features of the image. Then, a multiscale dilated attention module is proposed by combining dilated convolution and channel attention. Using ordinary convolution and dilated convolution to form different receptive fields. Channel attention is used to remodel the obtained multiscale features, enhancing the inter-channel correlation. After that, a multiscale spatial-spectral attention module is constructed using multiple asymmetric convolutions to obtain spatial and spectral attention features at different positions, further enhancing important feature suppression over non-important features. Finally, using softmax to classify the obtained features. Using Indian Pines, Pavia University, KSC and University of Houston as experimental datasets, the overall classification accuracy of this paper’s method achieved 98.97%, 99.14%, 99.45%, and 98.56% respectively, using only 5%, 1%, 10%, and 10% of training samples per class. Compared with seven advanced classification methods, the experimental results show that the proposed method can achieve the highest classification accuracy with limited training samples.

Gated Graph Attention-based Crossover Snake (GGA-CS) Algorithm for Hyperspectral Image Classification

Gated Graph Attention-based Crossover Snake (GGA-CS) Algorithm for Hyperspectral Image Classification

Enhancing hyperspectral image classification with graph attention neural network

Enhancing hyperspectral image classification with graph attention neural network

A local enhanced mamba network for hyperspectral image classification

Deep learning has significantly advanced hyperspectral image (HSI) classification, primarily due to its robust nonlinear feature extraction capabilities. The vision transformer has achieved notable performance but is limited by the quadratic computational burden of its self-attention mechanism. Recently, a network based on state space model named Mamba, has attracted considerable attention for its linear complexity and commendable performance. Nevertheless, Mamba was originally designed for one-dimensional causal sequence modeling, and its effectiveness in inherent non-causal HSI classification remains to be fully validated. To address this issue, we propose a novel Local Enhanced Mamba (LE-Mamba) network for hyperspectral image classification, which mainly comprises a Local Enhanced Spatial SSM (LES-S6), a Central Region Spectral SSM (CRS-S6), and a Multi-Scale Convolutional Gated Unit (MSCGU). The LES-S6 improves non-causal local feature extraction by incorporating a multi-directional local spatial scanning mechanism. Additionally, the CRS-S6 employs a bidirectional scanning mechanism in the spectral dimension to capture fine spectral details and integrate them with spatial information. The MSCGU utilizes a convolutional gating mechanism to aggregate features from diverse scanning routes and extract high-level semantic information. The overall accuracies of LE-Mamba on Indian Pines, WHU-Hi-HanChuan, WHU-Hi-LongKou, and Pavia University datasets are 99.16 %, 98.16 %, 99.57 %, and 99.63 %, respectively. Extensive experimental results on these four public datasets demonstrate that the LE-Mamba outperforms eight mainstream deep learning models in classification performance.

Pyramid Cascaded Convolutional Neural Network with Graph Convolution for Hyperspectral Image Classification

Convolutional neural networks (CNNs) and graph convolutional networks (GCNs) have made considerable advances in hyperspectral image (HSI) classification. However, most CNN-based methods learn features at a single-scale in HSI data, which may be insufficient for multi-scale feature extraction in complex data scenes. To learn the relations among samples in non-grid data, GCNs are employed and combined with CNNs to process HSIs. Nevertheless, most methods based on CNN-GCN may overlook the integration of pixel-wise spectral signatures. In this paper, we propose a pyramid cascaded convolutional neural network with graph convolution (PCCGC) for hyperspectral image classification. It mainly comprises CNN-based and GCN-based subnetworks. Specifically, in the CNN-based subnetwork, a pyramid residual cascaded module and a pyramid convolution cascaded module are employed to extract multiscale spectral and spatial features separately, which can enhance the robustness of the proposed model. Furthermore, an adaptive feature-weighted fusion strategy is utilized to adaptively fuse multiscale spectral and spatial features. In the GCN-based subnetwork, a band selection network (BSNet) is used to learn the spectral signatures in the HSI using nonlinear inter-band dependencies. Then, the spectral-enhanced GCN module is utilized to extract and enhance the important features in the spectral matrix. Subsequently, a mutual-cooperative attention mechanism is constructed to align the spectral signatures between BSNet-based matrix with the spectral-enhanced GCN-based matrix for spectral signature integration. Abundant experiments performed on four widely used real HSI datasets show that our model achieves higher classification accuracy than the fourteen other comparative methods, which shows the superior classification performance of PCCGC over the state-of-the-art methods.

Probabilistic deep metric learning for hyperspectral image classification

This paper proposes a probabilistic deep metric learning (PDML) framework for hyperspectral image classification (HSIC). The core problem for HSIC is the spectral variability between intraclass materials and the spectral similarity between interclass materials, motivating the further incorporation of spatial information to differentiate a pixel based on its surrounding patch. However, different pixels and even the same pixel in one patch might not encode the same material due to the low spatial resolution of most hyperspectral sensors, leading to an inconsistent judgment of a specific pixel. To address this issue, we propose a PDML framework to model the categorical uncertainty of the spectral distribution of an observed pixel. We propose to learn a global probabilistic distribution for each pixel in the patch and a probabilistic metric to model the distance between distributions. We treat each pixel in a patch as a training sample to exploit more information from the patch. Our framework can be readily applied to existing HSIC methods. Extensive experiments on IN, UP, KSC, and Houston 2013 datasets demonstrate that our framework improves the performance of existing methods and further achieves the state of the art.

Deep Feature Segmentation Model Driven by Hybrid Convolution Network for Hyper Spectral Image Classification

Deep Feature Segmentation Model Driven by Hybrid Convolution Network for Hyper Spectral Image Classification

Dynamic weighted residual ensemble learning for hyperspectral image classification driven by features and samples

Dynamic ensemble selection has emerged as a promising approach for hyperspectral image classification. However, selecting relevant features and informative samples remains a pressing challenge. To address this issue, we introduce two novel dynamic residual ensemble learning methods. The first proposed method is called multi-features driven dynamic weighted residuals ensemble learning (MF-DWRL). This method leverages various combinations of features to construct classifier pools that incorporate feature differences. The K-Nearest Neighbors algorithm is employed to establish the region of competence (RoC) in the dynamic ensemble selection process. By assessing the performance of the RoC, the feature sets that yield the highest classification accuracy are identified as the optimal feature combinations. Additionally, the classification accuracy is utilized as prior information to guide the residual adjustments of each classifier. The second method, known as features and samples double-driven dynamic weighted residual ensemble learning (FS-DWRL), further enhances the performance of the ensemble. This approach not only considers the selection of feature combinations but also takes into account the informative samples. By jointly optimizing the feature and sample selection processes, FS-DWRL achieves superior classification accuracy compared to existing state-of-the-art methods. To evaluate the effectiveness of the proposed methods, three hyperspectral datasets from China—WHU-Hi-HanChuan, WHU-Hi-LongKou, and WHU-Hi-HongHu—are used for classification experiments. For these datasets, the proposed methods achieve the highest classification accuracies of 90.57 %, 98.77 %, and 91.08 %, respectively. The MF-DWRL and FS-DWRL methods exhibit significant improvements in classification accuracy.

Enhanced affinity propagation clustering with a modified extreme learning machine for segmentation and classification of hyperspectral imaging

Hyperspectral Imaging (HSI) plays a crucial role in detecting, identifying, and classifying a wide range of natural resources, including minerals, geological phenomena like volcanic eruptions, and vegetation. Segmentation and classification of HSI play vital roles in extracting meaningful information and identifying different land cover or land use categories within the scene. One of the primary limitations associated with HSI is the scarcity of labeled samples. Obtaining annotated samples is a laborious and time-consuming process, posing a significant challenge in the field. This work presents an Enhanced Affinity Propagation Clustering (EAPC) and Modified Extreme Learning Machine (MELM) for segmentation and classification of HSI. Initially, the HSI images are pre-processed by the non-linear diffusion partial differential equation. Then, the segmentation process is performed by the EAPC and it is the combination of Affinity Propagation Clustering (APC) with Light Spectrum Algorithm (LSA). Finally, the classification is performed by the MELM and the experimentation is demonstrated on the Salinas dataset and achieved better accuracy and sensitivity of 97.3 % and 98.2 % respectively.

Multi-objective evolutionary multi-tasking band selection algorithm for hyperspectral image classification

Hyperspectral images (HSI) contain a great number of bands, which enable better characterization of features. However, the huge dimension and information volume brought by the abundant bands may give rise to a negative influence on the efficiency of subsequent processing on hyperspectral images. Band selection (BS) is a commonly adopted to reduce the dimension of HSIs. Different from the previous work, in this paper, hyperspectral band selection problem is formulated as a multi-objective optimization problem, where the band distribution uniformity among the selected bands and inter-class separation distance from a few labeled samples are optimized simultaneously. To fully exploit the relation between the band subsets with different sizes, we construct a multi-objective evolutionary multi-tasking algorithm for hyperspectral band selection (namely MEMT-HBS) to achieve the selected band subsets for all the selected band sizes in one run. To implement MEMT-HBS, the intra-task pairwise learning based solution generation strategy is suggested to evolve the population for each task to achieve high-quality offspring whose selected band size is restricted to a fixed scope. The inter-task band coverage based knowledge transferring strategy is utilized to choose useful individuals from adjacent tasks to further enhance the performance of current task. Compared with the state-of-the-art semi-supervised and unsupervised BS algorithms, empirical results on different standard hyperspectral datasets show that our proposed MEMT-HBS can determine the superior band subset which has a higher image classification accuracy over the comparison algorithms.

Hyperspectral image classification using a deep relation network with random replacement data augmentation

ABSTRACT Achieving high classification accuracy under a limited number of training samples remains a key challenge in hyperspectral image (HSI) classification. To address this issue, we propose a random replacement data augmentation method. The proposed method randomly selects a rectangular spatial region in HSI, and the pixels in the selected region are replaced with data from different spectral dimensions randomly to generate new sample, increasing the diversity of training samples effectively. In addition, we also propose an improved deep metric learning-based relation network, which improves model’s ability to extract deep features and fully utilizes spatial information to establish relationships between feature maps and categories effectively. Experiments have shown that the proposed method can achieve more competitive results.

Global-local manifold embedding broad graph convolutional network for hyperspectral image classification

Graph convolutional neural networks (GCNs) with domain-specific feature aggregation capabilities have unique advantages in hyperspectral image (HSI) classification. However, current GCN-based approaches frequently encounter the issue of node characteristics being over-smoothed while aggregating in higher-order domains. Furthermore, GCN linear classifiers focus solely on sample separability and ignore the potential manifold information of graph features, resulting in a failure to fully investigate extracted features. To address these problems, we propose a global-local manifold embedding broad graph convolutional network (GLMBG) for HSI classification. In GLMBG, we designed two modules from feature extraction and classification perspectives: The graph convolutional edge feature fusion extractor (GEFF) and the broad classifier of global-local manifold embedding (BGLME). GEFF is designed to learn graph node and local edge features from HSI through GCN and recursive filtering, combining them in a weighted manner to construct fused graph features. BGLME is designed to replace traditional linear classifiers with broad learning classifiers through manifold regularized embedding, fully utilizing the global and local manifold discriminant information of graph node features. The combination of GEFF and BGLME effectively reduces over-smoothing of graph node features while maximizing the utilization of manifold discriminant information, hence improving model feature discriminative ability. Experimental evaluations of three commonly used hyperspectral datasets show that our method surpasses state-of-the-art methods.

Component adaptive sparse representation for hyperspectral image classification

Component adaptive sparse representation for hyperspectral image classification

Deep hierarchical spectral-spatial feature fusion for hyperspectral image classification based on convolutional neural network

Joint spectral-spatial feature extraction has been proven to be the most effective part of hyperspectral image (HSI) classification. But, due to the mixing of informative and noisy bands in HSI, joint spectral-spatial feature extraction using convolutional neural network (CNN) may lead to information loss and high computational cost. More specifically, joint spectral-spatial feature extraction from excessive bands may cause loss of spectral information due to the involvement of convolution operation on non-informative spectral bands. Therefore, we propose a simple yet effective deep learning model, named deep hierarchical spectral-spatial feature fusion (DHSSFF), where spectral-spatial features are exploited separately to reduce the information loss and fuse the deep features to learn the semantic information. It makes use of abundant spectral bands and few informative bands of HSI for spectral and spatial feature extraction, respectively. The spectral and spatial features are extracted through 1D CNN and 3D CNN, respectively. To validate the effectiveness of our model, the experiments have been performed on five well-known HSI datasets. Experimental results demonstrate that the proposed method outperforms other state-of-the-art methods and achieved 99.17%, 98.84%, 98.70%, 99.18%, and 99.24% overall accuracy on Kennedy Space Center, Botswana, Indian Pines, University of Pavia, and Salinas datasets, respectively.

LCFE-X: Pluggable Local Channel Feature Extraction model enhancement method for hyperspectral image classification

Spectral information of hyperspectral images offers high-dimensional features for downstream tasks. Local spectral signatures in different wavelength ranges are critical for material identification and pixel classification. In line with conventional vision methods, recent studies have focused on bolstering the spatial modelling capabilities of transformers. However, the focus remains predominantly global when the channel dimension is considered. Current research on enhancing local channel feature extraction is primarily model specific and lacks generalisable methods that can be applied to various models. Therefore, this study introduces a Local Channel Feature Extraction (LCFE) module. It extracts spectral-spatial features and key features within each band group and then integrates the features to obtain local channel features. Subsequently, a pluggable LCFE-X model enhancement method is proposed. This involves performing LCFE at the front end of the model and fusing the extracted features with the original features. Three enhanced hyperspectral image classification models, namely, LCFE-ViT, LCFE-SF, and LCFE-MF, are constructed based on recently proposed models. Extensive experiments demonstrate that the LCFE module effectively extracts local spectral signatures, and the proposed method enhances the performance of the various basic models. The code is available at https://github.com/YiSu1997/LCFE-X.

A Dual-Branch Fusion of a Graph Convolutional Network and a Convolutional Neural Network for Hyperspectral Image Classification.

Semi-supervised graph convolutional networks (SSGCNs) have been proven to be effective in hyperspectral image classification (HSIC). However, limited training data and spectral uncertainty restrict the classification performance, and the computational demands of a graph convolution network (GCN) present challenges for real-time applications. To overcome these issues, a dual-branch fusion of a GCN and convolutional neural network (DFGCN) is proposed for HSIC tasks. The GCN branch uses an adaptive multi-scale superpixel segmentation method to build fusion adjacency matrices at various scales, which improves the graph convolution efficiency and node representations. Additionally, a spectral feature enhancement module (SFEM) enhances the transmission of crucial channel information between the two graph convolutions. Meanwhile, the CNN branch uses a convolutional network with an attention mechanism to focus on detailed features of local areas. By combining the multi-scale superpixel features from the GCN branch and the local pixel features from the CNN branch, this method leverages complementary features to fully learn rich spatial-spectral information. Our experimental results demonstrate that the proposed method outperforms existing advanced approaches in terms of classification efficiency and accuracy across three benchmark data sets.

Deep feature dendrite with weak mapping for small-sample hyperspectral image classification

Deep feature dendrite with weak mapping for small-sample hyperspectral image classification