Hyperspectral Image Classification Method Research Articles

Hyperspectral Image Classification Based on Domain Adversarial Broad Adaptation Network

For hyperspectral image (HSI) classification tasks, obtaining sufficient labeled samples is usually difficult, time-consuming, and expensive. To address the aforementioned issue, by transferring the labeled sample information of a relevant source domain to the unlabeled target domain, an HSI classification method based on the domain adversarial broad adaptation network (DABAN) is proposed. First, the bottleneck adaptation module composed of a bottleneck layer and a domain adaptation layer is constructed and introduced to the domain adversarial neural network; thus, the domain adversarial adaptation network (DAAN) is designed. By simultaneously performing domain adversarial learning, reducing both the marginal distribution difference and second-order statistic difference between two domains, the distributions of the source and target domains are aligned. Then, the conditional distribution adaptation regularization term based on the maximum mean discrepancy is embedded into a broad learning system to obtain the conditional adaptation broad network (CABN). On the one hand, CABN can perform the class-level distribution adaptation on the domain-invariant features extracted by DAAN. On the other hand, the representation ability of the domain-invariant features expanded by CABN can be further enhanced. Experimental results on ten real hyperspectral data pairs show that, compared with the existing mainstream methods, DABAN can effectively utilize relevant source-domain information to assist in improving the classification accuracy of the target domain.

Hyperspectral Image Classification Based on Expansion Convolution Network

In recent years, convolutional neural networks (CNNs) have achieved excellent performance in hyperspectral image classification and have been widely used. However, the convolution kernel used in traditional CNN has the limitation of single scale which is not conducive to the improvement of hyperspectral classification performance. In addition, training a classification network of high-dimensional data based on limited labeled samples is still one of the challenges of hyperspectral image classification. To solve the above problems, a hyperspectral image classification method based on expansion convolution network (ECNet) is proposed. The expansion convolution injects holes into the standard convolution kernel to expand the receptive field (RF), so as to extract more context features. Because the shallow features of hyperspectral images contain more location and detail information, while the deep features contain stronger semantic information, in order to further enhance the correlation between deep and shallow information, inspired by ResNet, a similar feedback block (SFB) is introduced on the basis of ECNet, and the deep features and shallow features are fused through this feedback mechanism. Thus, an improved version of ECNet method is obtained, which is called FECNet. This study was tested on four commonly used hyperspectral data sets (i.e. Indian Pine (IP), Pavia University (UP), Kennedy Space Center (KSC), Salinas Valley (SV)) and on a higher resolution and complexly distributed land cover data set (University of Houston (HT)). The experimental results show that the proposed method has better classification performance than some state-of-the art methods, which shows that FECNet has a certain potential in hyperspectral image classification.

Dual-Triple Attention Network for Hyperspectral Image Classification Using Limited Training Samples

Hyperspectral image classification methods based on deep learning and attention mechanism have been extensively studied in recent years because of their superior performance. However, the currently applied spatial attention mechanism and channel attention mechanism are separated from each other. For this reason, we propose a new dual-triple attention network (DTAN), which realizes the high-precision classification of hyperspectral images based on capturing cross-dimensional interactive information. Specifically, DTAN is divided into two branches to extract the spectral information and spatial information of the hyperspectral image, which are called the spectral branch and spatial branch. While applying the channel attention mechanism to the spectral unit, the cross-dimensional interaction between the channel dimension and the spatial dimension is constructed. When the spatial attention mechanism is applied to the spatial branch, the correlation with the channel domain is also considered. Moreover, we introduce an efficient channel attention (ECA) module into the DenseNet, which allows the DenseNet to achieve partial cross-channel interaction. A series of experiments proved that DTAN has a significant advantage compared to other models when the training samples are minimal.

The Potential of Hyperspectral Image Classification for Oil Spill Mapping

Oil spill mapping is a very challenging problem in marine environmental monitoring. In this paper, the potential of hyperspectral image classification for mapping oil spills is comprehensively investigated. First, several representative hyperspectral image classification methods are reviewed in a general framework. Second, three oil spill mapping cases are designed to analyze the performance of different classification methods in detecting the spatial distribution, classifying the type, and estimating the thickness of oil spills. Finally, the experimental results are analyzed in detail, and some conclusions are given, which bring a comprehensive understanding to scholars who are interested in the fields of hyperspectral remote sensing and oil spill mapping.

Lightweight Self-Attention Residual Network for Hyperspectral Classification

Compared with traditional hyperspectral image classification methods, the classification model based on the deep convolutional neural network (DCNN) can achieve higher precision classification. However, the increase in classification accuracy has led to explosive growth in model complexity. In this letter, we proposed a more lightweight and efficient residual structure to alleviate this problem to replace the standard residual structure. This structure uses the “divide and conquer” idea to reduce the number of model parameters and calculations. In addition, the structure introduces a self-attention mechanism so that the input feature map and output feature map can be adaptively fused, and the feature extraction ability of the residual structure is further enhanced. The experimental results reveal that the residual structure we proposed can significantly reduce the complexity of the model and maintain a high classification accuracy, even surpassing the current mainstream classification model.

Improved Active Deep Learning for Semi-Supervised Classification of Hyperspectral Image

Hyperspectral image (HSI) data classification often faces the problem of the scarcity of labeled samples, which is considered to be one of the major challenges in the field of remote sensing. Although active deep networks have been successfully applied in semi-supervised classification tasks to address this problem, their performance inevitably meets the bottleneck due to the limitation of labeling cost. To address the aforementioned issue, this paper proposes a semi-supervised classification method for hyperspectral images that improves active deep learning. Specifically, the proposed model introduces the random multi-graph algorithm and replaces the expert mark in active learning with the anchor graph algorithm, which can label a considerable amount of unlabeled data precisely and automatically. In this way, a large number of pseudo-labeling samples would be added to the training subsets such that the model could be fine-tuned and the generalization performance could be improved without extra efforts for data manual labeling. Experiments based on three standard HSIs demonstrate that the proposed model can get better performance than other conventional methods, and they also outperform other studied algorithms in the case of a small training set.

Multi-type spectral spatial feature for hyperspectral image classification

In recent years, many methods have been proposed to capture intra-spectrum features for the hyperspectral image classification task. However, most of these methods ignore inter-spectra information. In consideration of this, we propose a novel 3-D Inter-Spectra Difference Feature (ISDF) descriptor, which models the relationship between adjacent spectra using the difference between a center pixel and each of its spectral-adjacent spatial-neighbor pixels. Moreover, to increase the completeness of ISDF, the Neighbor Spectral Difference Feature (NSDF) guided by local spatial information is proposed as a supplement to the insufficient description of intra-spectrum information. At last, the Multi-type Spectral Spatial Feature (MSSF) is constructed by fusing ISDF, NSDF, and a global spatial texture feature. Experimental results on three public hyperspectral image datasets demonstrate that our proposed MSSF is effective and can outperform eight representative hyperspectral image classification methods.

Improved Fusion of Spatial Information into Hyperspectral Classification through the Aggregation of Constrained Segment Trees: Segment Forest

Compared with traditional optical and multispectral remote sensing images, hyperspectral images have hundreds of bands that can provide the possibility of fine classification of the earth’s surface. At the same time, a hyperspectral image is an image that coexists with the spatial and spectral. It has become a hot research topic to combine the spatial spectrum information of the image to classify hyperspectral features. Based on the idea of spatial–spectral classification, this paper proposes a novel hyperspectral image classification method based on a segment forest (SF). Firstly, the first principal component of the image was extracted by the process of principal component analysis (PCA) data dimension reduction, and the data constructed the segment forest after dimension reduction to extract the non-local prior spatial information of the image. Secondly, the images’ initial classification results and probability distribution were obtained using support vector machine (SVM), and the spectral information of the images was extracted. Finally, the segment forest constructed above is used to optimize the initial classification results and obtain the final classification results. In this paper, three domestic and foreign public data sets were selected to verify the segment forest classification. SF effectively improved the classification accuracy of SVM, and the overall accuracy of Salinas was enhanced by 11.16%, WHU-Hi-HongHu by 15.89%, and XiongAn by 19.56%. Then, it was compared with six decision-level improved space spectrum classification methods, including guided filtering (GF), Markov random field (MRF), random walk (RW), minimum spanning tree (MST), MST+, and segment tree (ST). The results show that the segment forest-based hyperspectral image classification improves accuracy and efficiency compared with other algorithms, proving the algorithm’s effectiveness.

Hierarchical broad learning system for hyperspectral image classification

A new spectral-spatial hyperspectral image (HSI) classification method called hierarchical broad learning system (HBLS) has been proposed in this paper. Specifically, it combines wavelet, broad learning system (BLS) and Gabor filters into a hierarchical structure. First of all, wavelet is used to reduce the observation noise of HSIs. Then BLS is adopted to acquire a set of pixelwise probability maps from the input data, and Gabor filters are used to explore spatial information by refining these probability maps. These two operations (BLS and Gabor filtering) are alternated to form a hierarchical architecture. And the discriminative spectral-spatial features can be extracted at each layer of the hierarchical architecture. Finally, the spectral-spatial features are fed into the standard BLS for classification. Experimental results on three widely used HSIs reveal that HBLS outperforms some state-of-the-art methods in terms of classification accuracy and sample complexity.

Multiscale spectral‐spatial cross‐extraction network for hyperspectral image classification

Convolutional neural networks (CNN) are becoming increasingly popular in modern remote sensing image classification tasks and have exhibited excellent results. For the existing CNN-based hyperspectral image (HSI) classification methods, most of which extract spatial or spectral features separately by convolution. But nearly all of these methods ignore the fact that the weighted summation of convolution may lead to appear new features in another dimension. To address this issue, a novel multiscale spectral-spatial cross-extraction network (MSSCEN) is proposed for HSI classification. Specifically, the proposed MSSCEN introduces spectral-spatial features cross extraction module (SSCEM), which fed extracted features from previous layer into spatial and spectral extraction branches separately again, so that the changes that occurred in the other domain after each convolution can be fully utilized. In addition, a new independent data augmentation module based on U-Net is designed to mitigate the problem of limited labelled samples. The paper conducts experiments on three classic hyperspectral datasets and the results demonstrate that the proposed method achieves the best classification accuracy than other state-of-the-art methods.

A Novel 2D-3D CNN with Spectral-Spatial Multi-Scale Feature Fusion for Hyperspectral Image Classification

Multifarious hyperspectral image (HSI) classification methods based on convolutional neural networks (CNN) have been gradually proposed and achieve a promising classification performance. However, hyperspectral image classification still suffers from various challenges, including abundant redundant information, insufficient spectral-spatial representation, irregular class distribution, and so forth. To address these issues, we propose a novel 2D-3D CNN with spectral-spatial multi-scale feature fusion for hyperspectral image classification, which consists of two feature extraction streams, a feature fusion module as well as a classification scheme. First, we employ two diverse backbone modules for feature representation, that is, the spectral feature and the spatial feature extraction streams. The former utilizes a hierarchical feature extraction module to capture multi-scale spectral features, while the latter extracts multi-stage spatial features by introducing a multi-level fusion structure. With these network units, the category attribute information of HSI can be fully excavated. Then, to output more complete and robust information for classification, a multi-scale spectral-spatial-semantic feature fusion module is presented based on a Decomposition-Reconstruction structure. Last of all, we innovate a classification scheme to lift the classification accuracy. Experimental results on three public datasets demonstrate that the proposed method outperforms the state-of-the-art methods.

Optimal superpixel selection for hyperspectral image classification of limited training samples

ABSTRACT The hyperspectral image (HSI) classification method based on superpixel segmentation can solve the HSI classification problem of limited training samples. The proposed method improves the classification accuracy of each test sample by selecting the optimal superpixel for it and then extracting classification features. First, an HSI is segmented into superpixels with different scales. Subsequently, we propose an optimal superpixel evaluation method that selects the optimal superpixel for each sample in the HSI to extract classification feature. Lastly, the optimal superpixel is selected for each training sample to augment the training samples and improve the accuracy of the classifier. Experiments on two datasets indicate that the proposed method can effectively improve the classification accuracy of HSIs with limited training samples.

Hyperspectral Image Classification Based on Two-Branch Spectral–Spatial-Feature Attention Network

Although most of deep-learning-based hyperspectral image (HSI) classification methods achieve great performance, there still remains a challenge to utilize small-size training samples to remarkably enhance the classification accuracy. To tackle this challenge, a novel two-branch spectral–spatial-feature attention network (TSSFAN) for HSI classification is proposed in this paper. Firstly, two inputs with different spectral dimensions and spatial sizes are constructed, which can not only reduce the redundancy of the original dataset but also accurately explore the spectral and spatial features. Then, we design two parallel 3DCNN branches with attention modules, in which one focuses on extracting spectral features and adaptively learning the more discriminative spectral channels, and the other focuses on exploring spatial features and adaptively learning the more discriminative spatial structures. Next, the feature attention module is constructed to automatically adjust the weights of different features based on their contributions for classification to remarkably improve the classification performance. Finally, we design the hybrid architecture of 3D–2DCNN to acquire the final classification result, which can significantly decrease the sophistication of the network. Experimental results on three HSI datasets indicate that our presented TSSFAN method outperforms several of the most advanced classification methods.

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.

Hyperspectral image classification with deep 3D capsule network and Markov random field

To address the existing problems of capsule networks in deep feature extraction and spatial-spectral feature fusion of hyperspectral images, this paper proposes a hyperspectral image classification method that combines a deep residual 3D capsule network and Markov random field. Based on this method, the deep spatial-spectral features of hyperspectral images are extracted using the deep residual 3D convolutional structure, the vector capsules of the features are obtained by the initial capsule layer and mapped into probability capsules via the 3D dynamic routing mechanism to construct the classification probability map, and the spatial structure of the classification results is regularised by the Markov random field to further improve the classification accuracy and performance of the images. Two sets of benchmark hyperspectral images, namely Indian Pines and Pavia University data sets, were used to conduct comparative experiments and ablation study. The experimental results showed that, compared with the conventional convolutional neural network and existing capsule network models, the proposed method not only improves the classification accuracy of the images but also partly eliminates the category noise and affords a more regular classification probability map.

Multi-scale guided feature extraction and classification algorithm for hyperspectral images

To solve the problem that the traditional hyperspectral image classification method cannot effectively distinguish the boundary of objects with a single scale feature, which leads to low classification accuracy, this paper introduces the idea of guided filtering into hyperspectral image classification, and then proposes a multi-scale guided feature extraction and classification (MGFEC) algorithm for hyperspectral images. Firstly, the principal component analysis theory is used to reduce the dimension of hyperspectral image data. Then, guided filtering algorithm is used to achieve multi-scale spatial structure extraction of hyperspectral image by setting different sizes of filtering windows, so as to retain more edge details. Finally, the extracted multi-scale features are input into the support vector machine classifier for classification. Several practical hyperspectral image datasets were used to verify the experiment, and compared with other spectral feature extraction algorithms. The experimental results show that the multi-scale features extracted by the MGFEC algorithm proposed in this paper are more accurate than those extracted by only using spectral information, which leads to the improvement of the final classification accuracy. This fully shows that the proposed method is not only effective, but also suitable for processing different hyperspectral image data.

Hyperspectral Image Classification Based on Sparse Superpixel Graph

Hyperspectral image (HSI) classification is one of the major problems in the field of remote sensing. Particularly, graph-based HSI classification is a promising topic and has received increasing attention in recent years. However, graphs with pixels as nodes generate large size graphs, thus increasing the computational burden. Moreover, satisfactory classification results are often not obtained without considering spatial information in constructing graph. To address these issues, this study proposes an efficient and effective semi-supervised spectral-spatial HSI classification method based on sparse superpixel graph (SSG). In the constructed sparse superpixels graph, each vertex represents a superpixel instead of a pixel, which greatly reduces the size of graph. Meanwhile, both spectral information and spatial structure are considered by using superpixel, local spatial connection and global spectral connection. To verify the effectiveness of the proposed method, three real hyperspectral images, Indian Pines, Pavia University and Salinas, are chosen to test the performance of our proposal. Experimental results show that the proposed method has good classification completion on the three benchmarks. Compared with several competitive superpixel-based HSI classification approaches, the method has the advantages of high classification accuracy (>97.85%) and rapid implementation (<10 s). This clearly favors the application of the proposed method in practice.

Task-driven nonlocal uncertainty analysis for hyperspectral image classification using a context-based Bayesian framework

ABSTRACT Spatial contextual information could help to further improve hyperspectral image classification performance. However, most spatial-spectral hyperspectral image classification methods introduce spatial information primarily by combining pixels in a small neighbourhood. These strategies consider only limited spatial structures during classification, which reduces classification accuracy. To this end, a novel, context-based Bayesian framework with a task-driven nonlocal uncertainty analysis model is proposed to combine spectral-spatial features for hyperspectral image classification. Task-dependent measures are often needed to formulate similarity, which is used to express various relationships. Based on this observation, in this paper, we introduce a task-driven similarity measure based on nonlocal uncertainty analysis for hyperspectral classification. Nonlocal-local spatial a priori is constructed using the Dempster-Shafer theory after analysing the spatial uncertainty to a nonlocal extent, which further expands the sample capacity and spatial extent. Furthermore, an improved iterated conditional mode is proposed to acquire the energy function’s local minimum in the context-based Bayesian framework. The experimental results, using both simulated data and two popular hyperspectral data sets, indicate that the proposed methods can significantly improve classification accuracy when compared with other state-of-the-art methods.

Spatial-Aware Network for Hyperspectral Image Classification

Deep learning is now receiving widespread attention in hyperspectral image (HSI) classification. However, due to the imbalance between a huge number of weights and limited training samples, many problems and difficulties have arisen from the use of deep learning methods in HSI classification. To handle this issue, an efficient deep learning-based HSI classification method, namely, spatial-aware network (SANet) has been proposed in this paper. The main idea of SANet is to exploit discriminative spectral-spatial features by incorporating prior domain knowledge into the deep architecture, where edge-preserving side window filters are used as the convolution kernels. Thus, SANet has a small number of parameters to optimize. This makes it fit for small sample sizes. Furthermore, SANet is able not only to aware local spatial structures using side window filtering framework, but also to learn discriminative features making use of the hierarchical architecture and limited label information. The experimental results on four widely used HSI data sets demonstrate that our proposed SANet significantly outperforms many state-of-the-art approaches when only a small number of training samples are available.

A Hyperspectral Image Classification Method with CNN Based on attention-enhanced Spectral and Spatial Features

In recent years, the convolutional neural network (CNN) has had a wide application in hyperspectral image (HSI) classification. HSI has many spectral and spatial features, which is well known that different spectral bands and spatial positions in the cubes have different discriminative abilities. Therefore, this paper proposes a classification method with CNN, which uses attention-enhanced spectral and spatial features (CNN-ASS). First, we use spectral and spatial subnetworks to extract spectral and spatial features. At the same time, spectral attention and spatial attention are added to the two subnetworks, respectively. Then, we sum the weights of the classification results of the two subnetworks to get the final classification result. This paper conducts experiments on three typical hyperspectral image data sets, and the experiment results show the CNN-ASS has a competitive advantage compared with some advanced methods.