Features Of Hyperspectral Image Research Articles

Hyperspectral Image Classification Using Spatial and Edge Features Based on Deep Learning

In recent years, deep learning has been widely used in the classification of hyperspectral images and good results have been achieved. But it is easy to ignore the edge information of the image when using the spatial features of hyperspectral images to carry out the classification experiments. In order to make full use of the advantages of convolution neural network (CNN), we extract the spatial information with the method of minimum noise fraction (MNF) and the edge information by bilateral filter. The combination of the two kinds of information not only increases the useful information but also effectively removes part of the noise. The convolution neural network is used to extract features and classify for hyperspectral images on the basis of this fused information. In addition, this paper also uses another kind of edge-filtering method to amend the final classification results for a better accuracy. The proposed method was tested on three public available data sets: the University of Pavia, the Salinas, and the Indian Pines. The competitive results indicate that our approach can realize a classification of different ground targets with a very high accuracy.

Hyperspectral image classification based on convolutional neural network and random forest

ABSTRACTDeep learning-based methods, especially deep convolutional neural network (CNN), have proven their powerfulness in hyperspectral image (HSI) classification. On the other hand, ensemble learning is a useful method for classification task. In this letter, in order to further improve the classification accuracy, the combination of CNN and random forest (RF) is proposed for HSI classification. The well-designed CNN is used as individual classifier to extract the discriminant features of HSI and RF randomly selects the extracted features and training samples to formulate a multiple classifier system. Furthermore, the learned weights of CNN are adopted to initialize other individual CNN. Experimental results with two hyperspectral data sets indicate that the proposed method provides competitive classification results compared with state-of-the-art methods.

Structure Tensor and Guided Filtering-Based Algorithm for Hyperspectral Anomaly Detection

Anomaly detection is one of the most important applications of hyperspectral imaging technology. It is a challenging task due to the high dimensionality of hyperspectral images (HSIs), redundant information, noisy bands, and the limited capability of utilizing spatial information. In this paper, we address these problems and propose a novel anomaly detection method in HSIs. Our approach, called structure tensor and guided filter (STGF)-based strategy for anomaly detection, is based on the characteristics of HSIs. First, a novel band selection algorithm is proposed to reduce dimension, remove noisy bands, and select bands with effective information. Second, the selected bands are decomposed into two parts according to the characteristics of anomalies that are usually in a small area. Followed by this step, the backgrounds are removed through a simple differential operation for each selected band. Considering that not all of the bands provide the same contributions to anomaly detection, we then fuse the differential maps by a novel adaptive weighting method to obtain an initial detection map. Finally, GF is conducted to rectify the previous map under the condition that the neighboring pixels usually have quite strong correlations with each other. Experiments have been conducted on real-scene remote sensing HSI. Comparative analyses validate that the proposed STGF method presents superior performance in terms of detection accuracy and computational time.

Trilateral Smooth Filtering for Hyperspectral Image Feature Extraction

Traditional bilateral filtering (BF) cannot extract hyperspectral image (HSI) features well when the center pixel of the neighborhood pixel set is a noise point in the process of filtering the HSI. In this letter, a trilateral smooth filtering (TRSF) is presented. The proposed algorithm avoids the above-mentioned limitation problem in the BF algorithm. TRSF is successfully applied to the feature extraction of three actual HSIs. To prove the effectiveness of the proposed algorithm, support vector machines are used to classify the extracted features. Experimental results show that the proposed feature extraction method is simple and effective.

Defocus Hyperspectral Image Deblurring with Adaptive Reference Image and Scale Map

Defocus blur is one of the primary problems among hyperspectral imaging systems equipped with simple lenses. Most of the previous deblurring methods focus on how to utilize structure information of a single channel, while ignoring the characteristics of hyperspectral images. In this work, we analyze the correlations and differences among spectral channels, and propose a deblurring framework for defocus hyperspectral images. First, we divide the hyperspectral image channels into two sets, and the set with less blur is treated as a group of spectral bases. Then, according to the inherent correlations of spectral channels, a reference image can be derived from the spectral bases to guide the restoration of blurry channels. Finally, considering the disagreement between the reference image and the ground truth, a scale map based on gradient similarity is introduced as a prior in the deblurring framework. The experimental results on public dataset demonstrate that the proposed method outperforms several image deblurring methods in both visual effect and quality metrics.

Self-Supervised Feature Learning With CRF Embedding for Hyperspectral Image Classification

The challenges in hyperspectral image (HSI) classification lie in the existence of noisy spectral information and lack of contextual information among pixels. Considering the three different levels in HSIs, i.e., subpixel, pixel, and superpixel, offer complementary information, we develop a novel HSI feature learning network (HSINet) to learn consistent features by self-supervision for HSI classification. HSINet contains a three-layer deep neural network and a multifeature convolutional neural network. It automatically extracts the features such as spatial, spectral, color, and boundary as well as context information. To boost the performance of self-supervised feature learning with the likelihood maximization, the conditional random field (CRF) framework is embedded into HSINet. The potential terms of unary, pairwise, and higher order in CRF are constructed by the corresponding subpixel, pixel, and superpixel. Furthermore, the feedback information derived from these terms are also fused into the different-level feature learning process, which makes the HSINet-CRF be a trainable end-to-end deep learning model with the back-propagation algorithm. Comprehensive evaluations are performed on three widely used HSI data sets and our method outperforms the state-of-the-art methods.

Hyperspectral classification using an adaptive spectral-spatial kernel-based low-rank approximation

ABSTRACTThis paper presents a novel adaptive spectral-spatial kernel-based low-rank approximation method for spectral-spatial hyperspectral image (HSI) classification. In the first of three steps of the proposed method, superpixel and image patch are used together to calculate the weights in the homogeneous region. Second, an adaptive spectral-spatial kernel is defined to capture the spectral and spatial feature of HSIs. In the final step, an adaptive spectral-spatial kernel and low-rank approximation are integrated into a decision model to perform HSI classification. Extensive experimental results on Indian Pines and Pavia University demonstrate the superiority of the proposed classifier when compared with other competing classifiers.

Capsule Networks for Hyperspectral Image Classification

Convolutional neural networks (CNNs) have recently exhibited an excellent performance in hyperspectral image classification tasks. However, the straightforward CNN-based network architecture still finds obstacles when effectively exploiting the relationships between hyperspectral imaging (HSI) features in the spectral–spatial domain, which is a key factor to deal with the high level of complexity present in remotely sensed HSI data. Despite the fact that deeper architectures try to mitigate these limitations, they also find challenges with the convergence of the network parameters, which eventually limit the classification performance under highly demanding scenarios. In this paper, we propose a new CNN architecture based on spectral–spatial capsule networks in order to achieve a highly accurate classification of HSIs while significantly reducing the network design complexity. Specifically, based on Hinton’s capsule networks, we develop a CNN model extension that redefines the concept of capsule units to become spectral–spatial units specialized in classifying remotely sensed HSI data. The proposed model is composed by several building blocks, called spectral–spatial capsules, which are able to learn HSI spectral–spatial features considering their corresponding spatial positions in the scene, their associated spectral signatures, and also their possible transformations. Our experiments, conducted using five well-known HSI data sets and several state-of-the-art classification methods, reveal that our HSI classification approach based on spectral–spatial capsules is able to provide competitive advantages in terms of both classification accuracy and computational time.

A nonlinear and explicit framework of supervised manifold-feature extraction for hyperspectral image classification

Hyperspectral remote sensing has drawn great research interests in earth observation, since massive and contiguous spectrum can provide rich information of ground objects. However, such numerous bands also pose great challenges to efficient processing of hyperspectral images (HSI). Manifold learning has been widely used in feature extraction of HSI data to find intrinsic and compact representations of original spectrum. Nevertheless, lack of explicit and nonlinear mapping is still a critical limitation. In this paper, we propose a supervised learning framework for manifold-learning based HSI feature extraction and classification, which provides a nonlinear and explicit mapping for fast and efficient feature learning. We also introduce two concrete learning methods that are induced from this framework, which can extract different intrinsic topology of HSI data to achieve nonlinear dimensionality reduction. Experiments conducted on benchmark data sets demonstrate that high classification accuracy can be obtained with the proposed framework, which consistently outperforms linear mappings for manifold learning methods.

Graph embedded discriminant analysis for the extraction of features in hyperspectral images

Graph embedded discriminant analysis for the extraction of features in hyperspectral images

SuperBF: Superpixel-Based Bilateral Filtering Algorithm and Its Application in Feature Extraction of Hyperspectral Images

Bilateral filtering (BF), which is an edge-preserving filtering (EPF) method, has been widely recognized as a simple and efficient approach for hyperspectral image (HSI) feature extraction. However, due to the limitation of spatial resolution and the influence of the complexity of land feature distribution in HSIs, updating the target pixel through weighted averaging of neighbouring pixels is prone to generating mixed pixels, i.e., the updated target pixel is mixed with the feature of other land objects in addition to that of the target object, decreasing the quality of the image feature extraction. To address this problem, in this study, we propose a superpixel-based BF algorithm, SuperBF. This algorithm divides a HSI into many homogeneous regions via superpixel segmentation and then separately filters each homogenous region via BF; this approach ensures that the pixel structure in the template after BF is similar to that in the filtering process, reduces the probability of generating mixed pixels, and thus improves the quality of the image feature extraction. To verify the effectiveness of this proposed method, a support vector machine (SVM) classifier is used to classify the extracted SuperBF features. Experiments on three commonly employed HSI datasets demonstrated that SuperBF is significantly superior to the traditional BF-based hyperspectral feature extraction method and some new feature extraction methods.

Laplacian Regularized Spatial-Aware Collaborative Graph for Discriminant Analysis of Hyperspectral Imagery

Dimensionality Reduction (DR) models are of significance to extract low-dimensional features for Hyperspectral Images (HSIs) data analysis where there exist lots of noisy and redundant spectral features. Among many DR techniques, the Graph-Embedding Discriminant Analysis framework has demonstrated its effectiveness for HSI feature reduction. Based on this framework, many representation based models are developed to learn the similarity graphs, but most of these methods ignore the spatial information, resulting in unsatisfactory performance of DR models. In this paper, we firstly propose a novel supervised DR algorithm termed Spatial-aware Collaborative Graph for Discriminant Analysis (SaCGDA) by introducing a simple but efficient spatial constraint into Collaborative Graph-based Discriminate Analysis (CGDA) which is inspired by recently developed Spatial-aware Collaborative Representation (SaCR). In order to make the representation of samples on the data manifold smoother, i.e., similar pixels share similar representations, we further add the spectral Laplacian regularization and propose the Laplacian regularized SaCGDA (LapSaCGDA), where the two spectral and spatial constraints can exploit the intrinsic geometric structures embedded in HSIs efficiently. Experiments on three HSIs data sets verify that the proposed SaCGDA and LapSaCGDA outperform other state-of-the-art methods.

Leukocyte classification based on spatial and spectral features of microscopic hyperspectral images

Observing and identifying blood cells is a direct way for early diagnosis of blood diseases. Traditional blood cell recognition methods are usually time-consuming and laborious tasks for medical staff. This paper proposed an efficient leukocyte recognition method based on microscopic hyperspectral imaging technology. In order to achieve better segmentation performance and further improve the representativeness of features, the sequential maximum angle convex cone algorithm and iterative self-organizing data analysis technique algorithm are combined to segment the leukocytes from microscopic hyperspectral images. In addition, the uniform and rotation invariant local binary pattern is adopted as a textural measurement of the leukocytes. Combined the texture features with shape and spectral features, support vector machine is used to classify the leukocytes into different types. Experimental results show that the proposed method provides higher segmentation and recognition accuracy compared with the existing method. Moreover, the addition of spectral features improves the recognition performance shows the potential diagnosis capacity of microscopic hyperspectral imaging technology.

Robust multi‐view representation for spatial–spectral domain in application of hyperspectral image classification

Spatial-spectral representation plays an important role in hyperspectral images (HSIs) classification. However, many of the existing local feature algorithms for HSIs are based on the two-dimensional image and do not take full advantage of the information hidden in HSI, such as spatial-spectral locality correlation information, thereby reducing the robustness of these algorithms. In response to these problems, this study presents a robust multi-view spatial-spectral representation method with the characteristics of HSIs. There are two key techniques in this representation method, called spatial-spectral locality constrained linear coding (SSLLC) and spatial-spectral pyramid matching model (SSPM). Firstly, SSLLC applies the locality information of the feature points and visual words and uses the discriminant information provided by the nearest-neighbouring spatial-spectral feature points in HSIs. Secondly, SSPM works by partitioning the image into increasingly fine sub-cubes and uses the cubes to match the local features of the HSIs. The multi-view representation is tolerant to illumination change, image rotation, affine distortion etc. To assess the validity of authors' algorithm, the authors compared their results with several existing approaches, including a deep learning method. The experimental results show that this representation method can effectively improve the accuracy of HSIs 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.

Tridiagonal Folmat Enhanced Multivariance Products Representation Based Hyperspectral Data Compression

Hyperspectral imaging features an important issue in remote sens ing and applications. Requirement to collect high volumes of hyper spectral data in remote sensing algorithms poses a compression prob lem. To this end, many techniques or algorithms have been develop ed and continues to be improved in scientific literature. In this paper, we propose a recently developed lossy compression method whi ch is called tridiagonal folded matrix enhanced multivariance prod ucts representation (TFEMPR). This is a specific multidimensional array decomposition method using a new mathematical concept called “folded matrix” and provides binary decomposi tion for multidimensional arrays. Beside the method a comparati ve analysis of compression algorithms is presented in this paper by means of compression performances. Compression performance of TFEMPR is compared with the state-art-methods such as compressive -projection principal component analysis, matching pursu it and block compressed sensing algorithms, etc., via average peak signal-to-noise ratio. Experiments with AVIRIS data set indicate a superior reconstructed image quality for the propo sed technique in comparison to state-of-the-art hyperspectral data compression methods.

Spectral-Spatial Feature Extraction of Hyperspectral Images Based on Propagation Filter.

Recently, image-filtering based hyperspectral image (HSI) feature extraction has been widely studied. However, due to limited spatial resolution and feature distribution complexity, the problems of cross-region mixing after filtering and spectral discriminative reduction still remain. To address these issues, this paper proposes a spectral-spatial propagation filter (PF) based HSI feature extraction method that can effectively address the above problems. The dimensionality/band of an HSI is typically high; therefore, principal component analysis (PCA) is first used to reduce the HSI dimensionality. Then, the principal components of the HSI are filtered with the PF. When cross-region mixture occurs in the image, the filter template reduces the weight assignments of the cross-region mixed pixels to handle the issue of cross-region mixed pixels simply and effectively. To validate the effectiveness of the proposed method, experiments are carried out on three common HSIs using support vector machine (SVM) classifiers with features learned by the PF. The experimental results demonstrate that the proposed method effectively extracts the spectral-spatial features of HSIs and significantly improves the accuracy of HSI classification.

Convolutional neural network extreme learning machine for effective classification of hyperspectral images

Due to its excellent performance in terms of fast implementation, strong generalization capability and straightforward solution, extreme learning machine (ELM) has attracted increasingly attentions in pattern recognition such as face recognition and hyperspectral image (HSI) classification. However, the performance of ELM for HSI classification remains a challenging problem especially in effective extraction of the featured information from the massive volume of data. To this end, we propose in this paper a new method to combine Convolutional neural network (CNN) with ELM (CNN-ELM) for HSI classification. As CNN has been successfully applied for feature extraction in different applications, the combined CNN-ELM approach aims to take advantages of these two techniques for improved classification of HSI. By preserving the spatial features whilst reconstructing the spectral features of HSI, the proposed CNN-ELM method can significantly improve the accuracy of HSI classification without increasing the computational complexity. Comprehensive experiments using three publicly available HSI data sets, Pavia University, Pavia center, and Salinas have fully validated the improved performance of the proposed method when benchmarking with several state-of-the-art approaches.

Hyperspectral Image Compression and Reconstruction Based on Block-Sparse Dictionary Learning

A large amount of hyperspectral image (HSI) data poses a significant challenge for transmission and storage. A new signal processing mechanism—compressed sensing (CS)—is appropriate for processing signals with a massive amount of data and can achieve high reconstruction accuracy. According to the structural properties of HSI, the same ground features show the same spectral properties. In this paper, an approach is proposed to compress and reconstruct HSI based on CS and block-sparse dictionary learning. Primarily, a dictionary of a given set of signal is trained and prior knowledge is not required on the association of the training dataset into groups. Then, a measurement matrix is used to compress an HSI cube to reduce the data volume of the signal. Finally, we use the trained block-sparse dictionary to reconstruct the image, along with the HSI feature classification information. Our experimental results showed that, for block-sparse HSI data, the proposed approach significantly improved the performance compared with other related state of the art methods.

Spectral–Spatial Weighted Sparse Regression for Hyperspectral Image Unmixing

Spectral unmixing aims at estimating the fractional abundances of a set of pure spectral materials (endmembers) in each pixel of a hyperspectral image. The wide availability of large spectral libraries has fostered the role of sparse regression techniques in the task of characterizing mixed pixels in remotely sensed hyperspectral images. A general solution for sparse unmixing methods consists of using the $\ell _{1}$ regularizer to control the sparsity, resulting in a very promising performance but also suffering from sensitivity to large and small sparse coefficients. A recent trend to address this issue is to introduce weighting factors to penalize the nonzero coefficients in the unmixing solution. While most methods for this purpose focus on analyzing the hyperspectral data by considering the pixels as independent entities, it is known that there exists a strong spatial correlation among features in hyperspectral images. This information can be naturally exploited in order to improve the representation of pixels in the scene. In order to take advantage of the spatial information for hyperspectral unmixing, in this paper, we develop a new spectral–spatial weighted sparse unmixing (S2WSU) framework, which uses both spectral and spatial weighting factors, further imposing sparsity on the solution. Our experimental results, conducted using both simulated and real hyperspectral data sets, illustrate the good potential of the proposed S2WSU, which can greatly improve the abundance estimation results when compared with other advanced spectral unmixing methods.