Characteristics Of Hyperspectral Data Research Articles

Estimation of the dolomite content of carbonate rock outcrops based on spectral knowledge and machine learning

Accurately estimating the dolomite content in carbonate rocks is crucial for optimizing oil and gas exploration and production strategies. Hyperspectral techniques for estimating dolomite content have advantages in terms of efficiency, cost-effectiveness, and non-destructiveness compared with traditional laboratory methods. Despite the abundance of hyperspectral data, feature selection and extraction remain challenging. In this study, hyperspectral data collected from surface outcrop in the field using the analytical spectral device (ASD) were applied to construct model for estimating dolomite content. Firstly, the data were preprocessed via outlier analysis and continuum transformation. Next, a hybrid approach integrating spectral knowledge with machine learning was proposed and applied to facilitate efficient and precise feature selection of the hyperspectral data; in this approach, preliminary screening based on spectral knowledge is followed by further hyperspectral data feature selection using a random forest algorithm. The selected features were then combined using a support vector regression algorithm to obtain the estimation model. Finally, the accuracy of the model was evaluated using the hyperspectral data from field outcrop samples. To further verify the effectiveness of this method, various combinations of eight input variables and four machine learning algorithms were compared. Among all combinations, our model achieved the highest accuracy with a test R2 value of 0.91 and a root-mean-square error of only 0.122. The proposed method is practical and efficient and provides precise quantitative data for field geologists to identify the mineral distribution in outcrops. Thus, our method provides robust support for understanding reservoir characteristics and has significant practical value in geological surveys and mineral exploration.

Discriminating Spectral-Spatial Feature Extraction for Hyperspectral Image Classification: A Review.

Hyperspectral images (HSIs) contain subtle spectral details and rich spatial contextures of land cover that benefit from developments in spectral imaging and space technology. The classification of HSIs, which aims to allocate an optimal label for each pixel, has broad prospects in the field of remote sensing. However, due to the redundancy between bands and complex spatial structures, the effectiveness of the shallow spectral-spatial features extracted by traditional machine-learning-based methods tends to be unsatisfying. Over recent decades, various methods based on deep learning in the field of computer vision have been proposed to allow for the discrimination of spectral-spatial representations for classification. In this article, the crucial factors to discriminate spectral-spatial features are systematically summarized from the perspectives of feature extraction and feature optimization. For feature extraction, techniques to ensure the discrimination of spectral features, spatial features, and spectral-spatial features are illustrated based on the characteristics of hyperspectral data and the architecture of models. For feature optimization, techniques to adjust the feature distances between classes in the classification space are introduced in detail. Finally, the characteristics and limitations of these techniques and future challenges in facilitating the discrimination of features for HSI classification are also discussed further.

Structured low-rank representation learning for hyperspectral sparse unmixing

ABSTRACT Sparse unmixing methods have been widely used to estimate the abundance of each material component from hyperspectral images. However, conventional sparse unmixing approaches only consider matrix factorization without limited explorations on the high-dimensional structures of the third-order tensors. To address this issue, we propose SUnSLRR, a novel approach to sparse unmixing of hyperspectral data based on structured low-rank tensor modelling. In contrast to traditional methods, SUnSLRR leverages the low-rank property underlying the abundance tensor to exploit structural details from multiple modes. By incorporating sparsity regularization and a low-rank constraint, SUnSLRR can effectively extract the intrinsic features of hyperspectral data. We apply the alternating direction method of multipliers framework to solve the optimization problem induced by SUnSLRR, and experiments conducted on simulated and real hyperspectral images demonstrate the superior effectiveness of our proposed method compared to traditional methods in terms of both accuracy and efficiency.

A LIBSVM quality assessment model for apple spoilage during storage based on hyperspectral data.

To assess the quality of apple samples during storage, this study proposes a spoilage benchmark based on hyperspectral data feature indicators and the Mahalanobis Distance (MD). Additionally, a quality assessment model was developed utilizing LIB Support Vector Machine (LIBSVM). Initially, a spoilage benchmark for apple samples was preliminarily established using hyperspectral data feature indicators, including the color feature, texture feature of sample hyperspectral images, and wavelet packet energy (WPE) of sample spectral information. Secondly, this study utilized the successive projection algorithm (SPA) to extract three wavelength sets sensitive to changes in the three indicators. This process resulted in the identification of 20 feature wavelengths based on the three sets. Subsequently, the spoilage benchmark for apple samples was verified using MD based on the spectral information of feature wavelengths. Ultimately, utilizing pre-processed spectral information enhanced by the sliding window algorithm and spoilage benchmark, the LIBSVM quality assessment model was developed, achieving a training set accuracy of 99.94% and a test set accuracy of 99.66%. Moreover, to assess the strength and applicability of the model, a verification experiment was conducted using a different set of apple samples. The training set accuracy was 100% and the test set accuracy was 99.83%. These findings indicate that the model can effectively indicate the level of spoilage in each sample during long-term storage. This also serves to demonstrate the robustness of the model and the effectiveness of the spoilage benchmark determination method during apple storage.

Improving chlorophyll content detection to suit maize dynamic growth effects by deep features of hyperspectral data

Improving chlorophyll content detection to suit maize dynamic growth effects by deep features of hyperspectral data

Detection and Identification of Potato-Typical Diseases Based on Multidimensional Fusion Atrous-CNN and Hyperspectral Data

As one of the world’s most crucial crops, the potato is an essential source of nutrition for human activities. However, several diseases pose a severe threat to the yield and quality of potatoes. Timely and accurate detection and identification of potato diseases are of great importance. Hyperspectral imaging has emerged as an essential tool that provides rich spectral and spatial distribution information and has been widely used in potato disease detection and identification. Nevertheless, the accuracy of prediction is often low when processing hyperspectral data using a one-dimensional convolutional neural network (1D-CNN). Additionally, conventional three-dimensional convolutional neural networks (3D-CNN) often require high hardware consumption while processing hyperspectral data. In this paper, we propose an Atrous-CNN network structure that fuses multiple dimensions to address these problems. The proposed structure combines the spectral information extracted by 1D-CNN, the spatial information extracted by 2D-CNN, and the spatial spectrum information extracted by 3D-CNN. To enhance the perceptual field of the convolution kernel and reduce the loss of hyperspectral data, null convolution is utilized in 1D-CNN and 2D-CNN to extract data features. We tested the proposed structure on three real-world potato diseases and achieved recognition accuracy of up to 0.9987. The algorithm presented in this paper effectively extracts hyperspectral data feature information using three different dimensional CNNs, leading to higher recognition accuracy and reduced hardware consumption. Therefore, it is feasible to use the 1D-CNN network and hyperspectral image technology for potato plant disease identification.

Rock alteration mapping in and around fossil shallow intrusions at Mt. Ruapehu New Zealand with laboratory and aerial hyperspectral imaging

Diagnostic absorption features in hyperspectral data can be used to identify a specific mineral or mineral associations. However, it is unknown how accurate hyperspectral mapping can be for identifying alteration mineral compositions at the resolution required to describe structures such as fossil intrusions, or whether it can accurately quantify the alteration present. This study compared petrographic observation with visible, near-infrared (VNIR), and shortwave infrared (SWIR) hyperspectral remote sensing at laboratory- (centimetre-scale) and aerial- (metre-scale) scales to characterise the abundance of surface hydrothermal rock alteration in and around a shallow fossil intrusion on Pinnacle Ridge, Mt. Ruapehu, New Zealand. We classified a high-resolution aerial hyperspectral image to develop a new surface alteration map using Spectral Angle Mapper (SAM) algorithm. The petrographic thin-section and the laboratory and aerial hyperspectral imaging revealed a spectrum of hydrous alteration phases as indicated by the presence of an absorption feature at 2207 nm. Moderate correlation exists between the depth of the absorption feature at 2207 nm and the point counting-derived alteration percent values, indicating reliability of laboratory-based hyperspectral analytical methods. In contrast, aerial hyperspectral data failed to provide any clear correlations to field-mapped alteration using a band-depth approach, and we interpret this due to ‘oversampling’ of surface (supergene) alteration, spectral mixing, and sensor limitations (e.g., bandwidth, signal-to-noise ratio). The hyperspectral image-derived alteration map, created using supervised image classification, can loosely be translated to a geotechnical map where porosity and permeability play a major role in localizing hydrothermal fluid flow and the formation of alteration mineral associations.

Hyperspectral Image Classification Model Using Squeeze and Excitation Network with Deep Learning.

In the domain of remote sensing, the classification of hyperspectral image (HSI) has become a popular topic. In general, the complicated features of hyperspectral data cause the precise classification difficult for standard machine learning approaches. Deep learning-based HSI classification has lately received a lot of interest in the field of remote sensing and has shown promising results. As opposed to conventional hand-crafted feature-based classification approaches, deep learning can automatically learn complicated features of HSIs with a greater number of hierarchical layers. Because HSI's data structure is complicated, applying deep learning to it is difficult. The primary objective of this research is to propose a deep feature extraction model for HSI classification. Deep networks can extricate features of spatial and spectral from HSI data simultaneously, which is advantageous for increasing the performances of the proposed system. The squeeze and excitation (SE) network is combined with convolutional neural networks (SE-CNN) in this work to increase its performance in extracting features and classifying HSI. The squeeze and excitation block is designed to improve the representation quality of a CNN. Three benchmark datasets are utilized in the experiment to evaluate the proposed model: Pavia Centre, Pavia University, and Salinas. The proposed model's performance is validated by a performance comparison with current deep transfer learning approaches such as VGG-16, Inception-v3, and ResNet-50. In terms of accuracy on each class of datasets and overall accuracy, the proposed SE-CNN model outperforms the compared models. The proposed model achieved an overall accuracy of 96.05% for Pavia University, 98.94% for Pavia Centre dataset, and 96.33% for Salinas dataset.

Automatic building footprint extraction and road detection from hyperspectral imagery

Hyperspectral imagery gives details of spectral information through hundreds of spectral bands also known as dimensionality. The bands with continuous spectral information model are capable of classifying various materials of interest. The enhanced dimensionality of such data allows for major changes in data relevant information, but it also presents a challenge to traditional methods for accurate hyperspectral image analysis so-called “curse of dimensionality.” The hyperspectral images are used to identify objects on the earth’s surface. Due to a large number of spectral bands, classifying objects using hyperspectral imagery has become more challenging. Feature reduction and extraction techniques are used to address these high-dimensionality issues. However, there are various challenges dealing with data classification with performance and computational time. As a result, a technique for hyperspectral image classification based on a convolutional neural network (CNN) along with geometric transformation and polygons segmentation process has been proposed. A CNN is used to convert compressed features into high-level features that were utilized to classify objects into buildings and road networks. The main objective of this paper is to design an automated building footprint extraction and road detection from hyperspectral imagery using CNN. The polygons segmentation is used for the extraction and detection of spectral features in hyperspectral data. CNN is used to classify these extracted spectral features, such as building footprints and road detection, using different kernels. When comparing the proposed techniques with other support vector machine and fully convolutional network methods, the experimental results show that CNN provides 97% classification accuracy.

A Novel Classification Framework for Hyperspectral Image Data by Improved Multilayer Perceptron Combined with Residual Network

Convolutional neural networks (CNNs) have attracted extensive attention in the field of modern remote sensing image processing and show outstanding performance in hyperspectral image (HSI) classification. Nevertheless, some hyperspectral images have fixed position priors and parameter sharing between different positions, so the common convolution layer may ignore some important fine and useful information and cannot guarantee to effectively capture the optimal image features. This paper proposes an improved multilayer perceptron (IMLP) and IMLP combined with ResNet (IMLP-ResNet) two models for HSI classification. Combined with the characteristics of hyperspectral data, we design IMLP based on three improvements. Specifically, a depthwise over-parameterized convolutional layer is introduced to increase learnable parameters of the model in IMLP, which speeds up the convergence of the model without increasing the computational complexity. Secondly, a Focal Loss function is used to suppress the useless ones in the classification task and enhance the critical spectral–spatial features, which allow the IMLP network to learn more useful hyperspectral image information. Furthermore, to enhance the convergence speed of the network, cosine annealing is introduced to further improve the training performance of IMLP. Furthermore, the IMLP module is combined with a residual network (IMLP-ResNet) to construct a symmetric structure, which extracts more advanced semantic information from hyperspectral images. The proposed IMLP and IMLP-ResNet are tested on the two public HSI datasets (i.e., Indian Pines and Pavia University) and a real hyperspectral dataset (Xuzhou). Experimental results demonstrate the superiority of the proposed IMLP-ResNet method over several state-of-the-art methods with the highest OA, which outperforms CNN by 8.19%, 6.28%, 5.59% and outperforms ResNet by 3.52%, 3.54%, 2.67% on Indian Pines, Pavia University and Xuzhou datasets, respectively, and demonstrates that the well-designed MLPs can also obtain remarkable classification performance of HSI.

TFTN: A Transformer-Based Fusion Tracking Framework of Hyperspectral and RGB

Although the RGB image has a high spatial resolution, it only depicts color intensities in red, green, and blue channels, which easily leads to the failure of the tracker based on RGB modality in some challenging scenarios, for example, when the color of the object and background is similar. The hyperspectral image with rich spectral information is more robust in these difficult situations, so it is essential to explore how to effectively apply hyperspectral features to supplement RGB information in object tracking. However, there is no fusion tracking algorithm based on hyperspectral and RGB data. Based on this, we propose a novel fusion tracking framework of hyperspectral and RGB in this article, termed as Transformer-based Fusion Tracking Network (TFTN), to enhance the performance of object tracking. Within the framework, we construct a dual-branch structure based on the Siamese Network to obtain the modality-specific representations of different modality images. Besides, the framework is generic, which is suitable for the Siamese series of tracking algorithms. In addition, we design a Siamese three-dimensional convolutional neural network as the specific branch of hyperspectral modality for synchronous extraction of the spatial and spectral features of hyperspectral data, to give full play to the role of hyperspectral data in improving network tracking performance. Particularly, inspired by the structure of Transformer, we design a Transformer-based fusion module to capture the potential interaction of intra-modality and inter-modality features of different modalities. This is the first work that combines the information of hyperspectral and RGB modalities to improve tracking performance. At the same time, it is also the first time that employs the self-attention module of Transformer to combine the information of different modalities for multi-modality fusion tracking. Experimental results on the dataset composed of hyperspectral and RGB image sequences show that the proposed TFTN tracker is superior to the state-of-the-art trackers, demonstrating the effectiveness of this method.

A modified feature fusion method for distinguishing seed strains using hyperspectral data

Abstract Precise classification of seeds is important for agriculture. Due to the slight physical and chemical difference between different types of wheat and high correlation between bands of images, it is easy to fall into the local optimum when selecting the characteristic band of using the spectral average only. In this paper, in order to solve this problem, a new variable fusion strategy was proposed based on successive projection algorithm and the variable importance in projection algorithm to obtain a comprehensive and representative variable feature for higher classification accuracy, within spectral mean and spectral standard deviation, so the 25 feature bands obtained are classified by support vector machine, and the classification accuracy rate reached 83.3%. It indicates that the new fusion strategy can mine the effective features of hyperspectral data better to improve the accuracy of the model and it can provide a theoretical basis for the hyperspectral classification of tiny kernels.

Patch Tensor-Based Multigraph Embedding Framework for Dimensionality Reduction of Hyperspectral Images

Graph-based dimensionality reduction (DR) techniques are of great interest in the field of image processing and especially on the analysis of hyperspectral images (HSIs). Considering the characteristics of hyperspectral data, many different types of graphs were designed to describe the structure of HSIs. Generally, the algorithms based on these graphs achieved promising performance. However, most of them only focus on how to improve the measurement of similarity between the data points by a single graph. Specifically, vector-based graph methods fail to capture the spatial information, while tensor-based graph methods assume that the pixels in each patch tensor belong to the same class, which is not exactly correct in practice. To overcome these shortcomings, this article proposes a patch tensor-based multigraph embedding (PTMGE) framework for the DR of HSIs, in which three different types of subgraphs are constructed to comprehensively describe the intrinsic geometrical structures of HSIs. First, a tensor subgraph is constructed to capture the spatial information and local geometrical structure. Second, for each two neighboring patch tensors in the tensor graph, a bipartite graph is designed to characterize the pixel-based relationships between the patch tensors. Then, considering that the diversity of pixels may be existed in each patch tensor, a pixel-based subgraph is built to describe the inner geometrical structures of every patch tensor. Finally, a novel graph fusion strategy is designed to calculate a final similarity matrix for projection learning. Experiments on three real hyperspectral data sets are conducted, and comparison with some state-of-the-art algorithms validated the effectiveness of our proposed PTMGE method.

Classification of hyperspectral imagery with a 3D convolutional neural network and J-M distance

A three-dimensional convolutional neural network (3D-CNN) is proposed and applied to the identification of land types from hyperspectral images. Due to the advantages of the combined use of the spectral-spatial features of hyperspectral imagery, high accuracy identification of most objects can be realized. However, too many wavelengths increase information redundancy between adjacent bands and interfere with classification accuracy to some extent, complicating achievement of better results for the identification of ground objects with relatively small differences in spectral and spatial domains. To solve such problems, in this paper, the Jeffries-Matusita (J-M) distance is introduced to select effective bands to reduce the redundancy of spectral information for identifying objects with similar features. This method is based on a 3D-CNN considering pixel spectral and spatial information. The optimal band combination algorithm based on the J-M distance is first used to extract spectral features of hyperspectral data while reducing feature dimensions. Then, the 3D-CNN is applied to mine spectral and spatial features from the hyperspectral images. Finally, a Softmax classifier is used to classify land types based on the high-level features learned by the 3D-CNN. Experiments were carried out on data from an area of north-western Indiana and a Pavia university scene. In such images, some objects have very similar spectral and spatial features. The results were compared with the current 3D-CNN land type classification and show that both methods can achieve high-precision identification of most land types, but for objects with similar features, the method proposed in this article has obvious advantages.

Hyperspectral Image Classification using Support Vector Machine with Guided Image Filter

Hyperspectral images are used to identify and detect the objects on the earth’s surface. Classifying of these hyperspectral images is becoming a difficult task, due to more number of spectral bands. These high dimensionality problems are addressed using feature reduction and extraction techniques. However, there are many challenges involved in the classification of data with accuracy and computational time. Hence in this paper, a method has been proposed for hyperspectral image classification based on support vector machine (SVM) along with guided image filter and principal component analysis (PCA). In this work, PCA is used for the extraction and reduction of spectral features in hyperspectral data. These extracted spectral features are classified using SVM like vegetation fields, building, etc., with different kernels. The experimental results show that SVM with Radial Basis Functions (RBF) kernel will give better classification accuracy compared to other kernels. Moreover, classification accuracy is further improved with a guided image filter by incorporating spatial features.

Hyperspectral Classification Based on Texture Feature Enhancement and Deep Belief Networks

With success of Deep Belief Networks (DBNs) in computer vision, DBN has attracted great attention in hyperspectral classification. Many deep learning based algorithms have been focused on deep feature extraction for classification improvement. Multi-features, such as texture feature, are widely utilized in classification process to enhance classification accuracy greatly. In this paper, a novel hyperspectral classification framework based on an optimal DBN and a novel texture feature enhancement (TFE) is proposed. Through band grouping, sample band selection and guided filtering, the texture features of hyperspectral data are improved. After TFE, the optimal DBN is employed on the hyperspectral reconstructed data for feature extraction and classification. Experimental results demonstrate that the proposed classification framework outperforms some state-of-the-art classification algorithms, and it can achieve outstanding hyperspectral classification performance. Furthermore, our proposed TFE method can play a significant role in improving classification accuracy.

Hyperspectral Data Feature Extraction Using Deep Learning Hybrid Model

The original hyperspectral data served as the initial features has the characteristics of high dimension and redundancy, which is not suitable for the subsequent analysis, so extracting feature information is needed. The deep learning model has a strong ability in feature learning, but if the model has too many layers which will lead to the original information loss in the process of layer-by-layer feature learning and reduce the subsequent classification accuracy. To solve this problem, the paper proposed a deep learning model of hybrid structure with the contractive autoencoder and restricted boltzmann machine to extract the hyperspectral data feature information. First, through pre-processing the spectral data, the 2d spectrum data is converted into a one dimensional vector. Then, a hybrid model is constructed for unsupervised training and supervised learning for the hyperspectral data, and features are extracted from bottom to top gradually according to the hybrid model. Finally, the SVM classifier is adopted to enhance the classification ability of spectral data. The paper uses the hybrid model proposed to test for extracting features with two sets of AVIRIS data and compares with PCA and GCA methods. The experiment results show that the feature extraction algorithm based on hybrid depth model can get the better features, and have strong distinguish performance, and can get better classification accuracy by the SVM algorithm.

Classification of Hyperspectral Imagery Using a New Fully Convolutional Neural Network

With success of convolutional neural networks (CNNs) in computer vision, the CNN has attracted great attention in hyperspectral classification. Many deep learning-based algorithms have been focused on deep feature extraction for classification improvement. In this letter, a novel deep learning framework for hyperspectral classification based on a fully CNN is proposed. Through convolution, deconvolution, and pooling layers, the deep features of hyperspectral data are enhanced. After feature enhancement, the optimized extreme learning machine (ELM) is utilized for classification. The proposed framework outperforms the existing CNN and other traditional classification algorithms by including deconvolution layers and an optimized ELM. Experimental results demonstrate that it can achieve outstanding hyperspectral classification performance.

Hyperspectral sensing data analysis based on quasiconformal mapping-based multiple kernels learning machine.

Hyperspectral remote sensing has a strong ability of object information expression, so it provides better support for object classification. Many methods are proposed for the hyperspectral data classification. The spectrum classification is a classical nonlinear problem, and a kernel-based machine is feasible to classify the spectrum data. In the nonlinear kernel-based space, the spectrum data are more discriminative. The kernel functions determine the data distribution in the feature space. In this paper, we propose the quasiconformal multiple kernels-based machine learning for the hyperspectral data classification. In the framework, the structure of hyperspectral data is adaptively adjusted for classification. The multiple kernels extract the multiple features of hyperspectral data for classification. Multiple features-based machine learning exhibits a great potential on the classification of hyperspectral data. Two public datasets, India Pines dataset and Pavia University dataset, are used to test the proposed algorithm. Experimental results demonstrate that the proposed quasiconformal multiple kernels-based hyperspectral data classification method can show competitive performance.

Hyperspectral Data Feature Extraction Using Rational Function Curve Fitting

Hyperspectral Data Feature Extraction Using Rational Function Curve Fitting