Search

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. [ABSTRACT FROM AUTHOR]

In recent years, the use of deep neural network in effective network feature extraction and the design of efficient and high-precision hyperspectral image classification algorithms has gradually become a research hotspot for scholars. However, due to the difficulty of obtaining hyperspectral images and the high cost of annotation, the training samples are very limited. In order to cope with the small sample problem, researchers often deepen the network model and use the attention mechanism to extract features; however, as the network model continues to deepen, the gradient disappears, the feature extraction ability is insufficient, and the computational cost is high. Therefore, how to make full use of the spectral and spatial information in limited samples has gradually become a difficult problem. In order to cope with such problems, this paper proposes two-branch multiscale spatial–spectral feature aggregation with a self-attention mechanism for a hyperspectral image classification model (FHDANet); the model constructs a dense two-branch pyramid structure, which can achieve the high efficiency extraction of joint spatial–spectral feature information and spectral feature information, reduce feature loss to a large extent, and strengthen the model's ability to extract contextual information. A channel–space attention module, ECBAM, is proposed, which greatly improves the extraction ability of the model for salient features, and a spatial information extraction module based on the deep feature fusion strategy HLDFF is proposed, which fully strengthens feature reusability and mitigates the feature loss problem brought about by the deepening of the model. Compared with five hyperspectral image classification algorithms, SVM, SSRN, A2S2K-ResNet, HyBridSN, SSDGL, RSSGL and LANet, this method significantly improves the classification performance on four representative datasets. Experiments have demonstrated that FHDANet can better extract and utilise the spatial and spectral information in hyperspectral images with excellent classification performance under small sample conditions. [ABSTRACT FROM AUTHOR]

Hyperspectral image classification plays a crucial role in remote sensing image analysis by classifying pixels. However, the existing methods require more spatial–global information interaction and feature extraction capabilities. To overcome these challenges, this paper proposes a novel model for hyperspectral image classification using an orthogonal self-attention ResNet and a two-step support vector machine (OSANet-TSSVM). The OSANet-TSSVM model comprises two essential components: a deep feature extraction network and an improved support vector machine (SVM) classification module. The deep feature extraction network incorporates an orthogonal self-attention module (OSM) and a channel attention module (CAM) to enhance the spatial–spectral feature extraction. The OSM focuses on computing 2D self-attention weights for the orthogonal dimensions of an image, resulting in a reduced number of parameters while capturing comprehensive global contextual information. In contrast, the CAM independently learns attention weights along the channel dimension. The CAM autonomously learns attention weights along the channel dimension, enabling the deep network to emphasise crucial channel information and enhance the spectral feature extraction capability. In addition to the feature extraction network, the OSANet-TSSVM model leverages an improved SVM classification module known as the two-step support vector machine (TSSVM) model. This module preserves the discriminative outcomes of the first-level SVM subclassifier and remaps them as new features for the TSSVM training. By integrating the results of the two classifiers, the deficiencies of the individual classifiers were effectively compensated, resulting in significantly enhanced classification accuracy. The performance of the proposed OSANet-TSSVM model was thoroughly evaluated using public datasets. The experimental results demonstrated that the model performed well in both subjective and objective evaluation metrics. The superiority of this model highlights its potential for advancing hyperspectral image classification in remote sensing applications. [ABSTRACT FROM AUTHOR]

In hyperspectral image (HSI) classification scenarios, deep learning-based methods have achieved excellent classification performance, but often rely on large-scale training datasets to ensure accuracy. However, in practical applications, the acquisition of hyperspectral labeled samples is time consuming, labor intensive and costly, which leads to a scarcity of obtained labeled samples. Suffering from insufficient training samples, few-shot sample conditions limit model training and ultimately affect HSI classification performance. To solve the above issues, an active learning (AL)-based multipath residual involution Siamese network for few-shot HSI classification (AL-MRIS) is proposed. First, an AL-based Siamese network framework is constructed. The Siamese network, which has relatively low demand for sample data, is adopted for classification, and the AL strategy is integrated to select more representative samples to improve the model's discriminative ability and reduce the costs of labeling samples in practice. Then, the multipath residual involution (MRIN) module is designed for the Siamese subnetwork to obtain the comprehensive features of the HSI. The involution operation was used to capture the fine-grained features and effectively aggregate the contextual semantic information of the HSI through dynamic weights. The MRIN module comprehensively considers the local features, dynamic features and global features through multipath residual connections, which improves the representation ability of HSIs. Moreover, a cosine distance-based contrastive loss is proposed for the Siamese network. By utilizing the directional similarity of high-dimensional HSI data, the discriminability of the Siamese classification network is improved. A large number of experimental results show that the proposed AL-MRIS method can achieve excellent classification performance with few-shot training samples, and compared with several state-of-the-art classification methods, the AL-MRIS method obtains the highest classification accuracy. [ABSTRACT FROM AUTHOR]

In recent years, with the rapid development of deep learning technology, great progress has been made in remote sensing scene image classification. Compared with natural images, remote sensing scene images are usually more complex, with high inter-class similarity and large intra-class differences, which makes it difficult for commonly used networks to effectively learn the features of remote sensing scene images. In addition, most existing methods adopt hard labels to supervise the network model, which makes the model prone to losing fine-grained information of ground objects. In order to solve these problems, a feature-augmented self-distilled convolutional neural network (FASDNet) is proposed. First, ResNet34 is adopted as the backbone network to extract multi-level features of images. Next, a feature augmentation pyramid module (FAPM) is designed to extract and fuse multi-level feature information. Then, auxiliary branches are constructed to provide additional supervision information. The self-distillation method is utilized between the feature augmentation pyramid module and the backbone network, as well as between the backbone network and auxiliary branches. Finally, the proposed model is jointly supervised using feature distillation loss, logits distillation loss, and cross-entropy loss. A lot of experiments are conducted on four widely used remote sensing scene image datasets, and the experimental results show that the proposed method is superior to some state-ot-the-art classification methods. [ABSTRACT FROM AUTHOR]

In the past, convolutional neural network (CNN) has become one of the most popular deep learning frameworks, and has been widely used in Hyperspectral image classification tasks. Convolution (Conv) in CNN uses filter weights to extract features in local receiving domain, and the weight parameters are shared globally, which more focus on the high‐frequency information of the image. Different from Conv, Transformer can obtain the long‐term dependence between long‐distance features through modelling, and adaptively focus on different regions. In addition, Transformer is considered as a low‐pass filter, which more focuses on the low‐frequency information of the image. Considering the complementary characteristics of Conv and Transformer, the two modes can be integrated for full feature extraction. In addition, the most important image features correspond to the discrimination region, while the secondary image features represent important but easily ignored regions, which are also conducive to the classification of HSIs. In this study, a complementary integrated Transformer network (CITNet) for hyperspectral image classification is proposed. Firstly, three‐dimensional convolution (Conv3D) and two‐dimensional convolution (Conv2D) are utilised to extract the shallow semantic information of the image. In order to enhance the secondary features, a channel Gaussian modulation attention module is proposed, which is embedded between Conv3D and Conv2D. This module can not only enhance secondary features, but suppress the most important and least important features. Then, considering the different and complementary characteristics of Conv and Transformer, a complementary integrated Transformer module is designed. Finally, through a large number of experiments, this study evaluates the classification performance of CITNet and several state‐of‐the‐art networks on five common datasets. The experimental results show that compared with these classification networks, CITNet can provide better classification performance. [ABSTRACT FROM AUTHOR]

With the arrival of new data acquisition platforms derived from the Internet of Things (IoT), this paper goes beyond the understanding of traditional remote sensing technologies. Deep fusion of remote sensing and computer vision has hit the industrial world and makes it possible to apply Artificial intelligence to solve problems such as automatic extraction of information and image interpretation. However, due to the complex architecture of IoT and the lack of a unified security protection mechanism, devices in remote sensing are vulnerable to privacy leaks when sharing data. It is necessary to design a security scheme suitable for computation‐limited devices in IoT, since traditional encryption methods are based on computational complexity. Visual Cryptography (VC) is a threshold scheme for images that can be decoded directly by the human visual system when superimposing encrypted images. The stacking‐to‐see feature and simple Boolean decryption operation make VC an ideal solution for privacy‐preserving recognition for large‐scale remote sensing images in IoT. In this study, the secure and efficient transmission of high‐resolution remote sensing images by meaningful VC is achieved. By diffusing the error between the encryption block and the original block to adjacent blocks, the degradation of quality in recovery images is mitigated. By fine‐tuning the pre‐trained model from large‐scale datasets, we improve the recognition performance of small encryption datasets for remote sensing images. The experimental results show that the proposed lightweight privacy‐preserving recognition framework maintains high recognition performance while enhancing security. [ABSTRACT FROM AUTHOR]

Unlike natural images, remote sensing scene images usually contain one scene label and many object labels, and many object labels are arranged dispersedly, which brings great difficulties to feature extraction of scene label. To accurately identify scene labels from remote sensing scene images with multiple object labels, it is important to fully understand the global context of the image. In order to solve the challenges of multi-label scene images and improve the classification performance, a global context feature extraction module is proposed in this paper. The module combines the semantics information of different regions through a global pooling and three different scale sub-regions pooling, which makes the module have stronger ability of global feature representation. In addition, in order to fully understand the semantic content of remote sensing images, a three branch joint feature extraction module is constructed, which consists of the global context feature module, 3 × 3 convolution branch and identity branch are fused. Finally, a lightweight convolution neural network based on joint features (LCNN-JF) is constructed using traditional convolution, depthwise separable convolution, joint feature extraction module and classifier for remote sensing scene image classification. A series of experimental results on four datasets, UCM, AID, RSSCN and NWPU, demonstrate that the proposed method has better feature representation ability and can achieve better classification of remote sensing scene images. [ABSTRACT FROM AUTHOR]

Deep learning has been demonstrated to be a powerful nonlinear modeling method with end-to-end optimization capabilities for hyperspectral Images (HSIs). However, in real classification cases, obtaining labeled samples is often time-consuming and labor-intensive, resulting in few-shot training samples. Based on this issue, a multipath and multiscale Siamese network based on spatial-spectral features for few-shot hyperspectral image classification (MMSN) is proposed. To conduct classification with few-shot training samples, a Siamese network framework with low dependence on sample information is adopted. In one subnetwork, a spatial attention module (DCAM), which combines dilated convolution and cosine similarity to comprehensively consider spatial-spectral weights, is designed first. Then, we propose a residual-dense hybrid module (RDHM), which merges three-path features, including grouped convolution-based local residual features, global residual features and global dense features. The RDHM can effectively propagate and utilize different layers of features and enhance the expression ability of these features. Finally, we construct a multikernel depth feature extraction module (MDFE) that performs multiscale convolutions with multikernel and hierarchical skip connections on the feature scales to improve the ability of the network to capture details. Extensive experimental evidence shows that the proposed MMSN method exhibits a superior performance on few-shot training samples, and its classification results are better than those of other state-of-the-art classification methods. [ABSTRACT FROM AUTHOR]

In recent years, convolution neural networks (CNNs) and graph convolution networks (GCNs) have been widely used in hyperspectral image classification (HSIC). CNNs can effectively extract the spatial spectral features of hyperspectral images (HSIs), while GCNs can quickly capture the structural features of HSIs, which makes the effective combination of the two is beneficial to improve classification performance of hyperspectral images. However, the high redundancy of feature information and the problem of small sample are still the major challenges of HSIC. In order to alleviate these problems, in this paper, a new graph and double pyramid attention network based on linear discrimination of spectral interclass slices (GDPA_LDSICS) is proposed. First, a linear discrimination of spectral inter class slices (LDSICS) module is designed. The LDSICS module can effectively eliminate a lot of redundancy in spectral dimension, which is conducive to subsequent feature extraction. Then, the spatial spectral deformation (SSD) module is constructed, which can effectively correlate the spatial spectral information closely. Finally, in order to alleviate the problem of small sample, a double branch structure of CNN and GCN is developed. On the CNN branch, a double pyramid attention (DPA) structure is designed to model context semantics to avoid information loss caused by long-distance feature extraction. On the GCN branch, an adaptive dynamic encoding (ADE) method is proposed, which can more effectively capture the topological structure of spatial spectral features. Experiments on four open datasets show that the GDPA_LDSICS can provide better classification performance and generalization performance than other most advanced methods. [ABSTRACT FROM AUTHOR]

Hyperspectral image classification (HSIC) is one of the most important research topics in the field of remote sensing. However, it is difficult to label hyperspectral data, which limits the improvement of classification performance of hyperspectral images in the case of small samples. To alleviate this problem, in this paper, a dual-branch network which combines cross-channel dense connection and multi-scale dual aggregated attention (CDC_MDAA) is proposed. On the spatial branch, a cross-channel dense connections (CDC) module is designed. The CDC can effectively combine cross-channel convolution with dense connections to extract the deep spatial features of HSIs. Then, a spatial multi-scale dual aggregated attention module (SPA_MDAA) is constructed. The SPA_MDAA adopts dual autocorrelation for attention modeling to strengthen the differences between features and enhance the ability to pay attention to important features. On the spectral branch, a spectral multi-scale dual aggregated attention module (SPE_MDAA) is designed to capture important spectral features. Finally, the spatial spectral features are fused, and the classification results are obtained. The experimental results show that the classification performance of the proposed method is superior to some state-of-the-art methods in small samples and has good generalization. [ABSTRACT FROM AUTHOR]

Gabor filter is widely used to extract spatial texture features of hyperspectral images (HSI) for HSI classification; however, a single Gabor filter cannot obtain the complete image features. In the paper, we propose an HSI classification method that combines the Gabor filter (GF) and domain-transformation standard convolution (DTNC) filter. First, we use the Gabor filter to extract spatial texture features from the first two principal components of the dimensionality-reduction HSI with PCA. Second, we use the DTNC filter to extract spatial correlation features from HSI in all bands. Finally, the Large Margin Distribution Machine (LDM) uses the linear fusion of the two kinds of spatial features to classify HSI. The experimental results show that the classification accuracy of Indian Pines, Pavia University, and Kennedy Space Center data sets is 96.64, 98.23, and 98.95% with only 4, 3, and 6% training samples, respectively; and these accuracies are 2–20% higher than the other tested methods. Compared with the hyperspectral information based on SVM, EPF, IFRF, PCA-EPFs, LDM-FL, and GFDN method, the proposed method, GFDTNCLDM, significantly improves the accuracy of HSI classification. [ABSTRACT FROM AUTHOR]

In recent years, the application of convolutional neural networks (CNNs) and graph convolutional networks (GCNs) in hyperspectral image classification (HSIC) has achieved remarkable results. However, the limited label samples are still a major challenge when using CNN and GCN to classify hyperspectral images. In order to alleviate this problem, a double branch fusion network of CNN and enhanced graph attention network (CEGAT) based on key sample selection strategy is proposed. First, a linear discrimination of spectral inter-class slices (LD_SICS) module is designed to eliminate spectral redundancy of HSIs. Then, a spatial spectral correlation attention (SSCA) module is proposed, which can extract and assign attention weight to the spatial and spectral correlation features. On the graph attention (GAT) branch, the HSI is segmented into some super pixels as input to reduce the amount of network parameters. In addition, an enhanced graph attention (EGAT) module is constructed to enhance the relationship between nodes. Finally, a key sample selection (KSS) strategy is proposed to enable the network to achieve better classification performance with few labeled samples. Compared with other state-of-the-art methods, CEGAT has better classification performance under limited label samples. [ABSTRACT FROM AUTHOR]

Convolutional neural networks (CNNs) exhibit excellent performance in hyperspectral image classification (HSIC) and have attracted significant interest. Nevertheless, the common CNN-based classification techniques still suffer from the following drawbacks. 1) Although deep CNNs can effectively extract features from hyperspectral images, a network that is too deep often leads to negative effects such as overfitting, vanishing gradients, and decreased accuracy. 2) Most of these models for HSIC do not fully consider the strong complementarity and correlation between features at different levels. To address these issues, firstly, a self-regularization parameter correction non-monotonic activation function, called Lush, was first proposed. Then, this study proposes a novel bias update method that can update network bias parameters more efficiently. On the basis of the above, a Lush multi-layer feature fusion polarization network (LMFFBNet) for hyperspectral image classification was proposed in this study. It designs a new after-melting technology to fuse deep and shallow features in multiple stages and layers, which can obtain more discriminative features, thereby improving the classification performance of hyperspectral images. Extensive experiments on five challenging datasets (Indian Pines, Pavia University, Kennedy Space Center, Salinas Valley, and Houston) have demonstrated that compared to some state-of-the-art methods, the proposed LMFFBNet method can provide better classification performance for hyperspectral images and has strong robustness. This fully proves the effectiveness of the LMFFBNet method. [ABSTRACT FROM AUTHOR]

• MS3Net is designed with a dual-stream symmetric structure for HSI classification. • Stratified-split module can promote the extraction of multiscale features. • Quadra-view attention can focus on valuable features from different dimensions. • Experimental results on four HSI datasets show the effectiveness of our method. Recently, hyperspectral image (HSI) classification has become a promising research direction in remote sensing image processing. Many HSI classification methods have been proposed based on convolutional neural networks (CNNs) and attention mechanisms (AMs). However, most current CNN-based methods only consider extracting features at a single scale in HSI, which may ignore the delicate features of some objects. Moreover, present AMs primarily focus on one feature dimension, such as spatial or channel attention, while disregarding dimension interaction. To conquer the above issues, a novel multiscale stratified-split symmetric network with quadra-view attention, namely MS3Net, is proposed for HSI classification. Generally, the proposed MS3Net has a dual-stream symmetric pipeline, which can better extract HSI's spectral signatures and spatial features. Specifically, the proposed MS3Net consists of three modules: a multiscale feature extraction module, a feature enhancement module, and a feature fusion module. Firstly, a stratified-split module is designed to extract multiscale spectral and spatial features. In addition, to reduce the complexity of the model, we designed pseudo-3-D spectral and spatial convolution to replace the traditional 3-D convolution operation. Secondly, a novel quadra-view attention module is proposed, guiding the model to focus on important features from multiple dimensions. Finally, the selective kernel feature fusion module is introduced, which can dynamically integrate spectral and spatial features. Experimental results on four benchmark HSI datasets with different scenes and resolutions confirm the visual and quantitative superiority of the proposed MS3Net over the state-of-the-art related methods in this research direction. [ABSTRACT FROM AUTHOR]