Hyperspectral Image Classification Method Research Articles

High Efficient Deep Feature Extraction and Classification of Spectral-Spatial Hyperspectral Image Using Cross Domain Convolutional Neural Networks

Recently, numerous remote sensing applications highly depend on the hyperspectral image (HSI). HSI classification, as a fundamental issue, has attracted increasing attention and become a hot topic in the remote sensing community. We implemented a regularized convolutional neural network (CNN), which adopted dropout and regularization strategies to address the overfitting problem of limited training samples. Although many kinds of the literature have confirmed that it is an effective way for HSI classification to integrate spectrum with spatial context, the scaling issue is not fully exploited. In this paper, we propose a high efficient deep feature extraction and the classification method for the spectral-spatial HSI, which can make full use of multiscale spatial feature obtained by guided filter. The proposed approach is the first attempt to lean a CNN for spectral and multiscale spatial features. Compared to its counterparts, experimental results show that the proposed method can achieve 3% improvement in accuracy, according to various datasets such as Indian Pines, Pavia University, and Salinas.

Robust Regression-Based Markov Random Field for Hyperspectral Image Classification

Recently, regression-based classifiers, such as the sparse representation classifier and collaborative representation classifier, have been proposed for hyperspectral image (HSI) classification. However, HSIs are typically corrupted by noise, occlusion, or data loss. Obtaining a good performance for most regression-based methods is difficult. To address this challenge, we present a novel robust regression-based nearest regularized subspace (R <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> NRS) for HSI classification. In our method, each band of a pixel is assigned with a regularized regression coefficient in the NRS model to reduce the influence of those bands corrupted during classification. The reconstruction error, Markov random field, and high-confidence index next jointly generate a comprehensive spatial-spectral model to perform the HSI classification. The experimental results on two HSI data sets demonstrate the superior performance of our proposed method for HSI classification for the case when some bands of the image are corrupted by noise or data loss.

Hyper-Spectral Characteristics in Support of Object Classification and Verification

It is known that a typical hyper-spectral image consists of a sequence of wavelength bands and each wavelength band illustrates a two-dimensional image. This paper presents a HSI classification method including two approaches. The first approach is a probabilistic algorithm for object classification based on the image illustrated by single hyper-spectral wavelength bands, respectively, which generate a sequence of registered object images. Since hyper-spectral images (HSIs) obtained by air-borne or satellite-borne remote sensors has limited size, which may affect the classification accuracy, especially for small objects due to lack of pixels. The second approach investigates the hyper-spectral characteristics for a specific object in terms of uniformed hyper-spectrum energy function in wavelength domain. The hyper-spectral characteristics are applied to object verification, especially for objects which are difficult to distinguish from each other using classic classification methods, so that the accuracy is improved. The classification accuracy for the proposed object-oriented characterization method is evaluated in terms of producer accuracy (PA) and Kappa coefficient based on hyper-spectral images obtained from air-borne or satellite-borne remote sensors, respectively. The numerical results demonstrate that the proposed method can effectively identify and verify objects in hyper-spectral image, especially for those objects that are difficult to be distinguished from each other by classic methods. Furthermore, the proposed object classification method based on hyper-spectral characteristics is compared to conventional methods, including spectral information divergence (SID) method and multiple spectral angle mapper-Markov random fields (MSAM-MRF) method. It can be seen that the accuracy of object classification achieved by the proposed method can be up to 20% higher than that of classic methods.

Semi-Supervised hyperspectral image classification using local low-rank representation

ABSTRACTIn the area of hyperspectral image (HSI) classification, graph-based semi-supervised learning (SSL) has been proved to be highly effective. Constructing a proper graph is critical for graph-based SSL tasks. In HSI, spectral distance is widely used to calculate the weight of graph edge, though it can be influenced by noise and outliers. Meanwhile, links among all the data points are incorporated in the graph, including those from different subspaces. Thus the constructed graph might contain incorrect information. In this letter, a novel semi-supervised HSI classification method using local low-rank representation (SL2R) is proposed. Edge weight calculation will not be affected by noise or outliers thanks to the robustness of low-rank representation (LRR). Since each graph is constructed at local level, where pixels are basically embedded in the same subspace, links among uncorrelated pixels can be removed. Moreover, spatial context is naturally characterized by low-rank constraint on adjacent pixels. Experimental results on two data sets (Indian Pines and Botswana) confirm the effectiveness of the proposed method.

Spectral-Spatial Methods for Hyperspectral Image Classification. Review

Various methods of spectral-spatial classification of hyperspectral data are reviewed. Papers devoted to the most popular ways of using spatial information for increasing the accuracy of classification maps are considered. It is shown that the best results are obtained by using preprocessing of “raw” data before the procedures of pixel-wise spectral classification. Disadvantages, limits, and possible directions for developing existing methods are investigated and analyzed.

Hyperspectral Image Classification via Superpixel Correlation Coefficient Representation

Superpixel segmentation is a powerful tool that can effectively utilize spectral and spatial information for hyperspectral image (HSI) classification. In this paper, we propose a new HSI classification method via superpixel and correlation coefficient (CC) representation (SCCR), where CC is a powerful metric to assess similarity among pixels. Considering the correlation among pixels within each superpixel, the superpixel region is viewed as the neighborhood of a test sample that can better exploit the spatial structure information of HSI. In the proposed method, recursive filtering is first used to extract features for hyperspectral data analysis. Then, based on the $k$ -nearest neighbors theory, the CC between each test sample and each class of training samples can be jointly calculated by the $k$ most relevant pixels in the neighborhood, which effectively reduces the effect of the mixed samples from different classes on the classification accuracy. Finally, the class label of each test sample is determined by which class presents the maximum CC. The experimental results demonstrate that the proposed SCCR improves classification performance compared to other well-known classification methods.

Active-Learning-Incorporated Deep Transfer Learning for Hyperspectral Image Classification

A hyperspectral image (HSI) includes a vast quantity of samples, a large number of bands, and randomly occurring redundancy. Classifying such complex data is challenging, and its classification performance can be affected significantly by the amount of labeled training samples, as well as the quality, position, and others factors of these samples. Collecting such labeled training samples is labor and time consuming, motivating the idea of taking advantage of labeled samples from other pre-existing related images. Therefore, transfer learning, which can mitigate the semantic gap between existing and new HSIs, has drawn increasing research attention. However, existing transfer learning methods for HSIs (which mainly concentrate on how to overcome the divergence among images) may fail to carefully consider the contents to be transferred and thus limit their performances. In this paper, we present two novel ideas: 1) we, for the first time, introduce an active learning process to initialize the salient samples on the HSI data, which would be transferred later; and 2) we propose constructing and connecting higher level features for the source and target HSI data to further overcome the cross-domain disparity. Different from existing methods, the proposed framework requires no a priori knowledge on the target domain, and it works for both homogeneous and heterogeneous HSI data. Experimental results on three real-world HSIs support the effectiveness of the proposed method for HSI classification.

Spectral–Spatial Feature Extraction for HSI Classification Based on Supervised Hypergraph and Sample Expanded CNN

Hyperspectral image (HSI) classification remains a challenging problem due to unique characteristics of HSI data (such as numerous bands and strong correlations in the spectral and spatial domains) and small sample size. To address such concerns, we propose a novel spectral–spatial feature extraction method for HSI classification by employing graph embedding and deep learning (DL) models. Since the conventional graph cannot capture the complex manifold relationship of HSI data, and there exist the observations of within-class variation as well as the similarity between different classes in the spectral domain, we construct the supervised within-class/between-class hypergraph (SWBH) to extract the spectral features of HSI. Since it is difficult for DL models to learn representative features for HSI data when the labeled training samples are limited, we propose the random zero settings to newly generate a large amount of labeled HSI samples for the training of convolutional neural network (CNN). The designed sample expanded CNN (SECNN) is used to extract the HSI spatial features. Thus, the spectral–spatial features of HSI can be learned by integrating the features extracted from SWBH and SECNN, respectively. Experiments on three real HSI datasets demonstrate higher classification accuracy of the proposed SWBH–SECNN method.

Exploring Hierarchical Convolutional Features for Hyperspectral Image Classification

Hyperspectral image (HSI) classification is an active and important research task driven by many practical applications. To leverage deep learning models especially convolutional neural networks (CNNs) for HSI classification, this paper proposes a simple yet effective method to extract hierarchical deep spatial feature for HSI classification by exploring the power of off-the-shelf CNN models, without any additional retraining or fine-tuning on the target data set. To obtain better classification accuracy, we further propose a unified metric learning-based framework to alternately learn discriminative spectral–spatial features, which have better representation capability and train support vector machine (SVM) classifiers. To this end, we design a new objective function that explicitly embeds a metric learning regularization term into SVM training. The metric learning regularization term is used to learn a powerful spectral–spatial feature representation by fusing spectral feature and deep spatial feature, which has small intraclass scatter but big between class separation. By transforming HSI data into new spectral–spatial feature space through CNN and metric learning, we can pull the pixels from the same class closer, while pushing the different class pixels farther away. In the experiments, we comprehensively evaluate the proposed method on three commonly used HSI benchmark data sets. State-of-the-art results are achieved when compared with the existing HSI classification methods.

Hyperspectral Image Classification Based on Improved Rotation Forest Algorithm.

Hyperspectral image classification is a hot issue in the field of remote sensing. It is possible to achieve high accuracy and strong generalization through a good classification method that is used to process image data. In this paper, an efficient hyperspectral image classification method based on improved Rotation Forest (ROF) is proposed. It is named ROF-KELM. Firstly, Non-negative matrix factorization( NMF) is used to do feature segmentation in order to get more effective data. Secondly, kernel extreme learning machine (KELM) is chosen as base classifier to improve the classification efficiency. The proposed method inherits the advantages of KELM and has an analytic solution to directly implement the multiclass classification. Then, Q-statistic is used to select base classifiers. Finally, the results are obtained by using the voting method. Three simulation examples, classification of AVIRIS image, ROSIS image and the UCI public data sets respectively, are conducted to demonstrate the effectiveness of the proposed method.

Joint spatial-spectral hyperspectral image classification based on convolutional neural network

Hyperspectral image (HSI) classification technology has been widely used in many earth observation tasks, such as detection, recognition, and surveillance. The traditional hyperspectral image classification methods mainly utilize hand-crafted features, such as edge and texture descriptors, which are not robust for different input data. By contrast, deep learning based methods exploit high-level features for hyperspectral image classification, but they usually degenerate the spatial-spectral structure, depend on a large number of training samples, and ignore a large amount of implicitly useful information. To address these problems, a new joint spatial-spectral hyperspectral image classification method based on different-scale two-stream convolutional network and spatial enhancement strategy is proposed in this paper. First, the pixel blocks at different scales around the center pixel are selected as the basic units to be processed. Then, a spatial enhancement strategy is designed to obtain various spatial location information under the limited training samples by the spatial rotation and row-column transformation. Finally, the spatial-spectral feature is learned by a different-scale two-stream convolutional network, and the classification result of the center pixel is obtained by a softmax layer. Experimental results on two datasets demonstrate that the proposed method outperforms other state-of-the-art methods qualitatively and quantitatively.

Adaptive total variation-based spectral-spatial feature extraction of hyperspectral image

In this paper, a simple yet quite useful hyperspectral images (HSI) classification method based on adaptive total variation filtering (ATVF) is proposed. The proposed method consists of the following steps: First, the spectral dimension of the HSI is reduced with principal component analysis (PCA). Then, ATVF is employed to extract image features which not only reduces the noise in the image, but also effectively exploits spatial–spectral information. Therefore, it can provide an improved representation. Finally, the efficient extreme learning machine (ELM) with a very simple structure is used for classification. This paper analyzes the influence of different parameters of the ATVF and ELM algorithm on the classification performance in detail. Experiments are performed on three hyperspectral urban data sets. By comparing with other HSI classification methods and other different feature extraction methods, the proposed method based on the ATVF algorithm shows outstanding performance in terms of classification accuracy and computational efficiency when compared with other hyperspectral classification methods.

Classification of hyperspectral images via weighted spatial correlation representation

Superpixel segmentation has been widely applied in hyperspectral image (HSI) classification. In this letter, a weighted spatial correlation representation (WSCR) method for HSI classification is proposed where an effective metric spatial correlation representation (SCR) that measures the correlation coefficient (CC) among different pixels in the superpixels is described, which fully utilizes the spatial information and structural features of superpixels. In addition, considering that the contribution of each SCR is different, the Gaussian weighted is considered. The proposed method includes the following steps: First, a superpixels image is obtained from HSI based on the entropy rate superpixel (ERS) algorithm. Second, the WSCRs for the training and test samples are calculated. Then, a joint sparse representation (JSR) classification is used to obtain the representation residuals of different pixels. Finally, the class label of each pixel is determined by the defined decision function that combines the WSCR and JSR. Experimental results obtained on two real HSI datasets demonstrate the superiority of the proposed methods compared to other widely used methods in terms of classification accuracy.

Hyperspectral image classification using multi-feature fusion

Traditional hyperspectral image (HSI) classification methods typically use the spectral features and do not make full use of the spatial or other features of the HSI. To address this problem, this paper proposes a novel HSI classification method based on a multi-feature fusion strategy. The spectral-spatial features are first extracted by spectral-spatial feature learning (SSFL), which is a deep hierarchical architecture. Additionally, the texture features of the local binary pattern (LBP) image are applied and fused with the spectral-spatial features. Then, the kernel extreme learning machine (KELM) is used to classify the hyperspectral images. The results of a number of experiments show that the proposed method effectively improves the classification accuracy of hyperspectral images.

Hyperspectral image classification using spectral-spatial LSTMs

Abstract In this paper, we propose a hyperspectral image (HSI) classification method using spectral-spatial long short term memory (LSTM) networks. Specifically, for each pixel, we feed its spectral values in different channels into Spectral LSTM one by one to learn the spectral feature. Meanwhile, we firstly use principle component analysis (PCA) to extract the first principle component from a HSI, and then select local image patches centered at each pixel from it. After that, we feed the row vectors of each image patch into Spatial LSTM one by one to learn the spatial feature for the center pixel. In the classification stage, the spectral and spatial features of each pixel are fed into softmax classifiers respectively to derive two different results, and a decision fusion strategy is further used to obtain a joint spectral-spatial results. Experimental results on three widely used HSIs (i.e., Indian Pines, Pavia University, and Kennedy Space Center) show that our method can improve the classification accuracy by at least 2.69%, 1.53% and 1.08% compared to other state-of-the-art methods.

Deformable Convolutional Neural Networks for Hyperspectral Image Classification

Convolutional neural networks (CNNs) have recently been demonstrated to be a powerful tool for hyperspectral image (HSI) classification, since they adopt deep convolutional layers whose kernels can effectively extract high-level spatial–spectral features. However, sampling locations of traditional convolutional kernels are fixed and cannot be changed according to complex spatial structures in HSIs. In addition, the typical pooling layers (e.g., average or maximum operations) in CNNs are also fixed and cannot be learned for feature downsampling in an adaptive manner. In this letter, a novel deformable CNN-based HSI classification method is proposed, which is called deformable HSI classification networks (DHCNet). The proposed network, DHCNet, introduces the deformable convolutional sampling locations, whose size and shape can be adaptively adjusted according to HSIs’ complex spatial contexts. Specifically, to create the deformable sampling locations, 2-D offsets are first calculated for each pixel of input images. The sampling locations of each pixel with calculated offsets can cover the locations of other neighboring pixels with similar characteristics. With the deformable sampling locations, deformable feature images are then created by compressing neighboring similar structural information of each pixel into fixed grids. Therefore, applying the regular convolutions on the deformable feature images can reflect complex structures more effectively. Moreover, instead of adopting the pooling layers, the strided convolution is further introduced on the feature images, which can be learned for feature downsampling according to spatial contexts. Experimental results on two real HSI data sets demonstrate that DHCNet can obtain better classification performance than can several well-known classification methods.

Semi-Supervised Classification for Hyperspectral Images Based on Multiple Classifiers and Relaxation Strategy

Hyperspectral image (HSI) classification is a fundamental and challenging problem in remote sensing and its various applications. However, it is difficult to perfectly classify remotely sensed hyperspectral data by directly using classification techniques developed in pattern recognition. This is partially owing to a multitude of noise points and the limited training samples. Based on multinomial logistic regression (MLR), the local mean-based pseudo nearest neighbor (LMPNN) rule, and the discontinuity preserving relaxation (DPR) method, in this paper, a semi-supervised method for HSI classification is proposed. In pre-processing and post-processing, the DPR strategy is adopted to denoise the original hyperspectral data and improve the classification accuracy, respectively. The application of two classifiers, MLR and LMPNN, can automatically acquire more labeled samples in terms of a few labeled instances per class. This is termed the pre-classification procedure. The final classification result of the HSI is obtained by employing the MLRsub approach. The effectiveness of the proposal is experimentally evaluated by two real hyperspectral datasets, which are widely used to test the performance of the HSI classification algorithm. The comparison results using several competing methods confirm that the proposed method is effective, even for limited training samples.

3D-Gabor Inspired Multiview Active Learning for Spectral-Spatial Hyperspectral Image Classification

Active learning (AL) has been shown to be very effective in hyperspectral image (HSI) classification. It significantly improves the performance by selecting a small quantity of the most informative training samples to reduce the complexity of classification. Multiview AL (MVAL) can make the comprehensive analysis of both object characterization and sampling selection in AL by using various features of multiple views. However, the original MVAL cannot effectively exploit the spectral-spatial information by respecting the three-dimensional (3D) nature of the HSI and the query selection strategy in the MVAL is only based on the disagreement of multiple views. In this paper, we propose a 3D-Gabor inspired MVAL method for spectral-spatial HSI classification, which consists of two main steps. First, in the view generation step, we adopt a 3D-Gabor filter to generate multiple cubes with limited bands and utilize the feature assessment strategies to select cubes for constructing views. Second, in the sampling selection step, a novel method is proposed by using both internal and external uncertainty estimation (IEUE) of views. Specifically, we use the distributions of posterior probability to learn the “internal uncertainty” of each independent view, and adopt the inconsistencies between views to estimate the “external uncertainty”. Classification accuracies of the proposed method for the four benchmark HSI datasets can be as high as 99.57%, 99.93%, 99.02%, 98.82%, respectively, demonstrating the improved performance as compared with other state-of-the-art methods.

An Algorithm of Improved Optimum Index Factor Band Selection from Hyperspectral Remote Sensing Image

Hyperspectral remote sensing sensors can capture hundreds of narrow contiguous bands and provide plenty of valuable information. Due to the high-dimension characteristics of hyperspectral data, band selection plays an important role in the field of Hyperspectral Image (HSI) classification. In this paper, a HSI classification method based on Improved Optimum Index Factor (IOIF) band selection is proposed. First, we review the standard OIF and its shortcoming for processing huge bands. Then we introduce the proposed feature selection method based on IOIF. Experiments are conducted on the Indian Pines dataset. The evaluation results show that the proposed approach can select those bands with more discriminative information rapidly and improve the classification accuracy effectively.

Superpixel-Based Extended Random Walker for Hyperspectral Image Classification

In this paper, a novel SuperPixel-based Extended Random Walker (SPERW) classification method for hyperspectral images is proposed that consists of three main steps. First, a multiscale segmentation algorithm is adopted to generate many superpixels, each of which represents a homogeneous region of adaptive shape and size. Then, a new weighted graph is constructed based on the superpixels in which the nodes correspond to the superpixels and the edges correspond to the links connecting two adjacent superpixels. Each edge has a weight that defines the similarity between the two superpixels. Second, a widely used pixelwise classifier, i.e., the support vector machine, is adopted to obtain classification probability maps for a hyperspectral image, which are then used to approximate the prior probabilities of the superpixels. Finally, the obtained prior probability maps of the superpixels are optimized by using the Extended Random Walker (ERW) algorithm, which encodes the spatial information both among and within the superpixels of the hyperspectral image in a weighted graph. Compared with the spectrum of a single pixel, the spectrum of a superpixel is more stable and less affected by noise; therefore, superpixels are more appropriate for adoption as the basic elements in the hyperspectral image classification. Because the spectral correlation between pixels within the same superpixel and the spatial correlation among adjacent superpixels are both well considered in the ERW-based global optimization framework, the proposed method shows high classification accuracy on four widely used real hyperspectral data sets even when the number of training samples is relatively small.