Hyperspectral Data Sets Research Articles

A No-Reference Quality Assessment Method for Hyperspectral Sharpened Images via Benford’s Law

In recent years, hyperspectral (HS) sharpening technology has received high attention and HS sharpened images have been widely applied. However, the quality assessment of HS sharpened images has not been well addressed and is still limited to the use of full-reference quality evaluation. In this paper, a novel no-reference quality assessment method based on Benford’s law for HS sharpened images is proposed. Without a reference image, the proposed method detects fusion distortion by performing first digit distribution on three quality perception features in HS sharpened images, using the standard Benford’s law as a benchmark. The experiment evaluates 10 HS fusion methods on three HS datasets and selects four full-reference metrics and four no-reference metrics to compare with the proposed method. The experimental results demonstrate the superior performance of the proposed method.

A Study on Dimensionality Reduction and Parameters for Hyperspectral Imagery Based on Manifold Learning.

With the rapid advancement of remote-sensing technology, the spectral information obtained from hyperspectral remote-sensing imagery has become increasingly rich, facilitating detailed spectral analysis of Earth's surface objects. However, the abundance of spectral information presents certain challenges for data processing, such as the "curse of dimensionality" leading to the "Hughes phenomenon", "strong correlation" due to high resolution, and "nonlinear characteristics" caused by varying surface reflectances. Consequently, dimensionality reduction of hyperspectral data emerges as a critical task. This paper begins by elucidating the principles and processes of hyperspectral image dimensionality reduction based on manifold theory and learning methods, in light of the nonlinear structures and features present in hyperspectral remote-sensing data, and formulates a dimensionality reduction process based on manifold learning. Subsequently, this study explores the capabilities of feature extraction and low-dimensional embedding for hyperspectral imagery using manifold learning approaches, including principal components analysis (PCA), multidimensional scaling (MDS), and linear discriminant analysis (LDA) for linear methods; and isometric mapping (Isomap), locally linear embedding (LLE), Laplacian eigenmaps (LE), Hessian locally linear embedding (HLLE), local tangent space alignment (LTSA), and maximum variance unfolding (MVU) for nonlinear methods, based on the Indian Pines hyperspectral dataset and Pavia University dataset. Furthermore, the paper investigates the optimal neighborhood computation time and overall algorithm runtime for feature extraction in hyperspectral imagery, varying by the choice of neighborhood k and intrinsic dimensionality d values across different manifold learning methods. Based on the outcomes of feature extraction, the study examines the classification experiments of various manifold learning methods, comparing and analyzing the variations in classification accuracy and Kappa coefficient with different selections of neighborhood k and intrinsic dimensionality d values. Building on this, the impact of selecting different bandwidths t for the Gaussian kernel in the LE method and different Lagrange multipliers λ for the MVU method on classification accuracy, given varying choices of neighborhood k and intrinsic dimensionality d, is explored. Through these experiments, the paper investigates the capability and effectiveness of different manifold learning methods in feature extraction and dimensionality reduction within hyperspectral imagery, as influenced by the selection of neighborhood k and intrinsic dimensionality d values, identifying the optimal neighborhood k and intrinsic dimensionality d value for each method. A comparison of classification accuracies reveals that the LTSA method yields superior classification results compared to other manifold learning approaches. The study demonstrates the advantages of manifold learning methods in processing hyperspectral image data, providing an experimental reference for subsequent research on hyperspectral image dimensionality reduction using manifold learning methods.

Solving Spectrum Unmixing as a Multi-Task Bayesian Inverse Problem with Latent Factors for Endmember Variability

With the increasing customization of spectrometers, spectral unmixing has become a widely used technique in fields such as remote sensing, textiles, and environmental protection. However, endmember variability is a common issue for unmixing, where changes in lighting, atmospheric, temporal conditions, or the intrinsic spectral characteristics of materials, can all result in variations in the measured spectrum. Recent studies have employed deep neural networks to tackle endmember variability. However, these approaches rely on generic networks to implicitly resolve the issue, which struggles with the ill-posed nature and lack of effective convergence constraints for endmember variability. This paper proposes a streamlined multi-task learning model to rectify this problem, incorporating abundance regression and multi-label classification with Unmixing as a Bayesian Inverse Problem, denoted as BIPU. To address the issue of the ill-posed nature, the uncertainty of unmixing is quantified and minimized through the Laplace approximation in a Bayesian inverse solver. In addition, to improve convergence under the influence of endmember variability, the paper introduces two types of constraints. The first separates background factors of variants from the initial factors for each endmember, while the second identifies and eliminates the influence of non-existent endmembers via multi-label classification during convergence. The effectiveness of this model is demonstrated not only on a self-collected near-infrared spectral textile dataset (FENIR), but also on three commonly used remote sensing hyperspectral image datasets, where it achieves state-of-the-art unmixing performance and exhibits strong generalization capabilities.

Enhancing Hyperspectral Images via Diffusion Model and Group-Autoencoder Super-resolution Network

Existing hyperspectral image (HSI) super-resolution (SR) methods struggle to effectively capture the complex spectral-spatial relationships and low-level details, while diffusion models represent a promising generative model known for their exceptional performance in modeling complex relations and learning high and low-level visual features. The direct application of diffusion models to HSI SR is hampered by challenges such as difficulties in model convergence and protracted inference time. In this work, we introduce a novel Group-Autoencoder (GAE) framework that synergistically combines with the diffusion model to construct a highly effective HSI SR model (DMGASR). Our proposed GAE framework encodes high-dimensional HSI data into low-dimensional latent space where the diffusion model works, thereby alleviating the difficulty of training the diffusion model while maintaining band correlation and considerably reducing inference time. Experimental results on both natural and remote sensing hyperspectral datasets demonstrate that the proposed method is superior to other state-of-the-art methods both visually and metrically.

Testing the suitability of automated machine learning, hyperspectral imaging and CIELAB color space for proximal in situ fertilization level classification

Automated machine learning (AutoML) is considered the next advancement in artificial intelligence due to its commitment to delivering high-performance end-to-end machine learning pipelines with minimal user input. Although AutoML has demonstrated significant potential in computer vision tasks, as far as current knowledge extends, there is currently no study that has applied AutoML specifically to hyperspectral imaging for fertilization level classification. To address this information gap, the use of AutoML for classifying fertilization levels using a hyperspectral and CIELAB color space dataset was investigated. A comparative analysis was conducted between the performance of an open-source AutoML framework, PyCaret, and traditional machine learning using the PLS-DA algorithm. PyCaret achieved the highest accuracy (1.00) in classifying different fertilization levels using the hyperspectral dataset, while PLS-DA attained an accuracy of 0.91. However, the CIELAB dataset was not as effective for this classification task, achieving an accuracy of only 0.72. It is worth noting that the hyperspectral dataset outperformed the CIELAB dataset in both AutoML and PLS-DA analyses. Finally, the findings suggest that AutoML holds substantial potential to enhance the use of hyperspectral imaging in agriculture, particularly for fertilization tasks.

A multiscale enhanced pavement crack segmentation network coupling spectral and spatial information of UAV hyperspectral imagery

Road pavement cracks are a critical factor affecting the health conditions of road pavements. Accurate crack detection contributes to providing data support for road maintenance measures. Compared to conventional crack detection algorithms, deep learning based crack segmentation methods have practical significance for road maintenance and traffic safety management due to their high precision and automation. However, existing deep learning methods often suffer from segmentation accuracy loss due to the varying crack sizes and the presence of stains on the pavement with spatial characteristics similar to cracks, leading to the misclassification of cracks. Therefore, this study proposed a multiscale enhanced road pavement crack segmentation network (MS-CrackSeg) by coupling spectral and spatial information to detect pavement cracks from unmanned aerial vehicle (UAV) hyperspectral imagery. MS-CrackSeg can simultaneously learn the spatial and rich spectral features of cracks in the hyperspectral imagery, improving the discrimination of those targets with similar spatial features to cracks compared to previous approaches. Moreover, the Multiscale Self-Attention-like Feature Extraction Module (MSSA) is introduced to extract and fuse multiscale crack features to enhance the crack detection. Experiments on a dataset consisting of 1031 hyperspectral images demonstrated the superior crack segmentation of the proposed method compared to the comparative methods. In particular, the proposed method achieved the highest F1-score of 0.74 and mean Intersection over Union of 0.79, indicating an exceptional performance. The developed approach offers improved data support for road maintenance measures and has validated the advantages of UAV hyperspectral imagery in road crack segmentation. The annotated hyperspectral dataset and the code for MS-CrackSeg network are available at https://github.com/williamchen-x/MS-CrackSeg.

Rapid non-destructive evaluation of texture properties changes in crispy tilapia during crispiness using hyperspectral imaging and data fusion

In this study, two distinct hyperspectral imaging systems, the Visible and Near-Infrared Spectroscopy (VNIR) and the Short-Wave Infrared Spectroscopy (SWIR), were employed in combine with chemometric techniques to examine the alterations in the texture properties (hardness, resilience, chewiness, and cohesiveness) of tilapia during the crispy process. Partial least squares regression (PLSR) was used to establish a linear relationship between the spectral reflectance values and the different texture parameters of tilapia, and various preprocessing, variable selection, and data fusion (Low-Level Fusion (LLF) and Mid-Level Fusion (MLF)) methods were considered to optimize the calibration model. For hardness, with RP, RMSEP, %RMSEP and RPD values of 0.63, 5.84, 21.65% and 1.26 respectively. For resilience, the LLF presented superior performance, with RP, RMSEP, %RMSEP and RPD values of 0.92, 0.03, 6.8% and 2.52 respectively. For chewiness, the MLF presented superior performance, with RP, RMSEP, %RMSEP and RPD values of 0.68, 4.03, 23.05% and 1.36. For cohesiveness, the MLF exhibited the best performance, with RP, RMSEP, %RMSEP and RPD values of 0.82, 0.03, 4.85% and 1.65 respectively. It was demonstrated that the fusion of both hyperspectral datasets provides a promising method for non-destructive texture measurement of tilapia at different stages of crispiness.

A fast hyperspectral change detection algorithm for agricultural crops based on low-rank matrix and morphological feature extraction

Crop change detection study is the foundation of agricultural sustainability. The inherent high spectral resolution of hyperspectral images, combined with multi-temporal datasets, facilitates the detection of subtle changes. To enhance the accuracy and applicability of hyperspectral change detection in agricultural scenes, this paper introduces a fast hyperspectral change detection approach for agricultural crops based on low-rank matrix and morphological feature extraction (FLRaMF). The goal is to improve detection precision and computational efficiency of the change detection process. The method initially employs rapid low-rank matrix extraction to separate changing and non-changing pixels in the spectral domain. Subsequently, spatial information is introduced using attribute profiles, restricting spectral anomalies through hyperspectral morphology, which ultimately improves the detection results. This study utilized four hyperspectral change detection datasets in agricultural crop scenarios, optimizing and analyzing parameters. Experimental results and analysis indicate that the FLRaMF method can achieve higher detection accuracy with reduced computation cost in unsupervised, default parameter scenarios when performing agricultural crop change detection tasks.

Hyperspectral image classification method based on narrowing semantic gap convolutional neural network

ABSTRACT In recent years, numerous hyperspectral image classification methods based on convolutional neural network (CNN) have been proposed in recent years. However, the majority of CNN-based classification models fail to take into account the semantic gap between shallow and deep features, and instead, just sum up or splice these two types of features, which leads to subpar feature fusion. To address the above problems, the paper proposes a hyperspectral image classification method based on Narrowing Semantic Gap Convolutional Neural Network (NSGCNN). We developed the feature fusion sub-network, which consists of Feature Semantic Enhancement Module (FSEM), Spatial Detail Supplement Module (SDCM), and Cross-layer Feature Fusion Module (CFFM). FSEM extracts rich global semantic information based on multi-scale dilated convolution. Reverse attention mechanism is introduced in the SDCM to complement deep-layer features with fine spatial features like edges and textures. The fusing of hierarchical features is then achieved using CFFM. Additionally, we can regulate the model’s parameter count by regulating the number of output feature maps. Experimental results on three benchmark hyperspectral datasets demonstrate that NSGCNN outperforms other state-of-the-art methods in terms of classification performance and significantly outperforms them in terms of model complexity.

Robust hyperspectral image classification using generative adversarial networks

This paper introduces Sill-Rgan, a novel Generative Adversarial Network (GAN) designed to improve hyperspectral image (HSI) classification under varying lighting conditions. Sill-Rgan uniquely maps different light condition domains, enhancing sample classification robustness and generating new virtual samples. Addressing challenges like high spectral dimensionality and noise in HSI classification, our approach utilizes a deep proxy-based learning framework. It integrates and improves advanced GAN models and multitask networks for optimal training stability and loss function optimization. The model's mapping network is adept at generating domain-specific latent codes, enabling the transformation of original hyperspectral data into enhanced versions. Extensive experiments conducted on hyperspectral datasets of agricultural products under diverse indoor and outdoor lighting conditions confirm the effectiveness of Sill-Rgan. The results highlight the model's adaptability in both supervised and semi-supervised learning scenarios, yielding exceptional classification accuracy and enhanced data quality. The versatile potential of Sill-Rgan extends its applicability to a broad range of spectral data classifications, underlining its significant contribution to hyperspectral imaging. This advancement opens new avenues in machine vision systems, particularly in scenarios with dynamic lighting challenges.

Determination of asbestos cement rooftop surface composition using regression analysis and hyper-spectral reflectance data in the visible and near-infrared ranges

The effects of asbestos on human health have spurred numerous studies examining its risks in urban environments. Recent works have shifted towards less-invasive techniques for remote detection and classification of asbestos-cement. In this context, this study combines visible (VIS) and near-infrared (NIR) reflectance data collected in-situ with reference signals from the USGS spectral library, utilizing optimized regression analysis to determine the surface composition of corrugated asbestos-cement rooftops. An outlier filter was successfully implemented to enhance the accuracy of regression calculations, achieving a high level of agreement with actual field observations. The regression analysis revealed varying proportions of weathered cement, hazardous asbestos fibers (specifically chrysotile and cummingtonite), and biological growth (such as lichens and moss). These results are consistent with previous research on the composition of asbestos-cement rooftops, including a comparable field study and XRD analysis conducted in 2019. This underscores the importance of using regression analysis, preceded by an outlier filtering step, on VIS and NIR reflectance data to ascertain the surface composition of asbestos-cement rooftops. This methodology holds potential for application to larger hyperspectral datasets across more extensive sample surfaces and areas.

Mayfly algorithm-based semi-supervised band selection with enhanced bitonic filter for spectral-spatial hyperspectral image classification

ABSTRACT Hyperspectral imaging effectively distinguishes land cover classes with discriminative spectral-spatial characteristics. However, hyperspectral image (HSI) classification encounters three significant challenges: the curse of dimensionality, the scarcity of training samples, and the necessity to incorporate spatial information within the classification process. The large number of redundant and irrelevant spectral bands in HSI can negatively impact the classification performance. Furthermore, the annotation process for training samples is expensive and time-consuming. To address these challenges, this work presents a novel semi-supervised approach for hyperspectral image dimensionality reduction using the Mayfly Algorithm (MA). The proposed method aims to preserve the most informative spectral bands while leveraging both labelled and unlabelled samples in the process. The MA algorithm effectively balances exploration and exploitation strategies, enhancing population diversity and mitigating challenges such as premature convergence and local optima. Additionally, the inclusion of structural variation and thresholding (SVT) in the Bitonic filter enables the incorporation of spatial features during the classification phase. This improves the separability of pixels belonging to different objects and leads to significant improvements in classification performance. Finally, two machine learning classifiers, namely Random Forest (RF) and Support Vector Machine (SVM), are applied at the pixel level for hyperspectral image classification. Extensive experimental results on three real hyperspectral datasets demonstrate the superiority of the proposed approach compared to state-of-the-art algorithms like Harmony Search (HS), Genetic Algorithm (GA), Particle Swarm Optimization (PSO), and more with an average improvement of 3.2%.

Background covariance discriminative dictionary learning for hyperspectral target detection

Hyperspectral target detection (HTD) aims to identifying targets within a hyperspectral image (HSI) based on provided target spectra. In the current HTD field, representation-based detectors have attracted much attention. However, there are two prominent challenges that are particularly noteworthy. First, the background class encompasses diverse land covers, making its accurate representation challenging. Second, the detection ability can be significantly influenced by the abnormalities and noise in HSI. To tackle these concerns, we propose a novel background covariance discriminative dictionary learning (BCDDL) model for HTD. To enhance the background representation ability and overcome the sparse noise, we combine the dictionary learning with spectral covariance descriptors and undertake background reconstruction in regional scale. Specifically, the input HSI is pre-processed into superpixels, the spectral covariance of each superpixel is used to provide a compact and flexible description of local regional statistical properties. Further, a novel spatial clustering-based dictionary learning method is proposed to learn the background discriminative covariances dictionary. The collaborative representation model within symmetric positive definite (SPD) manifold is utilized to reconstruct background region and get the residual. By merging the background residual with pixel-wise target reconstruction residual, we derive final detection output. Comprehensive experiments on two public hyperspectral datasets and two novel GaoFen-5 datasets demonstrate the superiority of our BCDDL approach over 10 state-of-the-art methods, especially in terms of suppressing background.

SFFNet: Staged Feature Fusion Network of Connecting Convolutional Neural Networks and Graph Convolutional Neural Networks for Hyperspectral Image Classification

The immense representation power of deep learning frameworks has kept them in the spotlight in hyperspectral image (HSI) classification. Graph Convolutional Neural Networks (GCNs) can be used to compensate for the lack of spatial information in Convolutional Neural Networks (CNNs). However, most GCNs construct graph data structures based on pixel points, which requires the construction of neighborhood matrices on all data. Meanwhile, the setting of GCNs to construct similarity relations based on spatial structure is not fully applicable to HSIs. To make the network more compatible with HSIs, we propose a staged feature fusion model called SFFNet, a neural network framework connecting CNN and GCN models. The CNN performs the first stage of feature extraction, assisted by adding neighboring features and overcoming the defects of local convolution; then, the GCN performs the second stage for classification, and the graph data structure is constructed based on spectral similarity, optimizing the original connectivity relationships. In addition, the framework enables the batch training of the GCN by using the extracted spectral features as nodes, which greatly reduces the hardware requirements. The experimental results on three publicly available benchmark hyperspectral datasets show that our proposed framework outperforms other relevant deep learning models, with an overall classification accuracy of over 97%.

A novel framework combining band selection algorithm and improved 3D prototypical network for tree species classification using airborne hyperspectral images

Fine-grained identification of forest types and tree species represents a critical aspect of forest resource inventory and monitoring. The use of airborne hyperspectral remote sensing imagery stands out for its ability to finely differentiate among tree species, leveraging its exceptional spatial resolution and rich spectral details. However, this approach is limited by several challenges (e.g., high spectral correlation and information redundancy). In accordance, the adoption of a lightweight deep learning approach in the form of a few-shot learning model can effectively resolve the challenges of multi-forest tree species classification. Therefore, integrating a data dimensionality reduction algorithm with a few-shot classification model presents a promising avenue for resolving the fine-grained classification of forest tree species. In this study, we propose the innovative classification framework FAST 3D-CNN P-Net. This framework utilizes CNN for band selection, enhances the fine-grained identification process in hyperspectral data, and integrates an optimized FAST 3D-CNN into the P-Net classifier (a few-shot classifier). First, a CNN-based band selection method is employed to learn the nonlinear dependencies between spectral bands, assign weights to rank the bands, and reconstruct the global spectral information using the most informative bands. It then constructs a novel classification model, designated FAST 3D-CNN P-Net, through the integration of an optimal 3D-CNN with a prototypical network. To enhance classification performance, the FAST 3D-CNN P-Net utilizes reconstructed hyperspectral images derived from the band selection results as input. The effectiveness of the proposed framework was assessed with the airborne GFF dataset and the widely accessible medium-resolution hyperspectral datasets, Indian Pines (IP) and Kennedy Space Center (KSC). The overall classification accuracy reached 98.33 % for the GFF dataset and 97.21 % and 99.43 % for the IP and KSC, respectively, exhibiting performance superiority compared to the standalone 3D-CNN classification network. This classification framework demonstrates efficiency in selecting a subset of hyperspectral bands with minimal redundancy, empowering the rapid and accurate classification and mapping of tree species in complicated, multi-species forest stands, even with a limited quantity of labeled samples.

Spectral-Spatial Feature Fusion for Hyperspectral Anomaly Detection.

Hyperspectral anomaly detection is used to recognize unusual patterns or anomalies in hyperspectral data. Currently, many spectral-spatial detection methods have been proposed with a cascaded manner; however, they often neglect the complementary characteristics between the spectral and spatial dimensions, which easily leads to yield high false alarm rate. To alleviate this issue, a spectral-spatial information fusion (SSIF) method is designed for hyperspectral anomaly detection. First, an isolation forest is exploited to obtain spectral anomaly map, in which the object-level feature is constructed with an entropy rate segmentation algorithm. Then, a local spatial saliency detection scheme is proposed to produce the spatial anomaly result. Finally, the spectral and spatial anomaly scores are integrated together followed by a domain transform recursive filtering to generate the final detection result. Experiments on five hyperspectral datasets covering ocean and airport scenes prove that the proposed SSIF produces superior detection results over other state-of-the-art detection techniques.

Spatial Resolution Enhancement of Vegetation Indexes via Fusion of Hyperspectral and Multispectral Satellite Data

The definition and calculation of a spectral index suitable for characterizing vegetated landscapes depend on the number and widths of the bands of the imaging instrument. Here, we point out the advantages of performing the fusion of hyperspectral (HS) satellite data with the multispectral (MS) bands of Sentinel-2 to calculate such vegetation indexes as the normalized area over reflectance curve (NAOC) and the red-edge inflection point (REIP), which benefit from the availability of quasi-continuous pixel spectra. Unfortunately, MS data may be acquired from satellite platforms with very high spatial resolution; HS data may not. Despite their excellent spectral resolution, satellite imaging spectrometers currently resolve areas not greater than 30 × 30 m2, where different thematic classes of landscape may be mixed together to form a unique pixel spectrum. A way to resolve mixed pixels is to perform the fusion of the HS dataset with the same dataset produced by an MS scanner that images the same scene with a finer spatial resolution. The HS dataset is sharpened from 30 m to 10 m by means of the Sentinel-2 bands that have all been previously brought to 10 m. To do so, the hyper-sharpening protocol, that is, m:n fusion, is exploited in two nested steps: the first one to bring the 20 m bands of Sentinel-2 all to 10 m, the second one to sharpen all the 30 m HS bands to 10 m by using the Sentinel-2 bands previously hyper-sharpened to 10 m. Results are presented on an agricultural test site in The Netherlands imaged by Sentinel-2 and by the satellite imaging spectrometer recently launched as a part of the environmental mapping and analysis program (EnMAP). Firstly, the excellent match of statistical consistency of the fused HS data to the original MS and HS data is evaluated by means of analysis tools, existing and developed ad hoc for this specific case. Then, the spatial and radiometric accuracy of REIP and NAOC calculated from fused HS data are analyzed on the classes of pure and mixed pixels. On pure pixels, the values of REIP and NAOC calculated from fused data are consistent with those calculated from the original HS data. Conversely, mixed pixels are spectrally unmixed by the fusion process to resolve the 10 m scale of the MS data. How the proposed method can be used to check the temporal evolution of vegetation indexes when a unique HS image and many MS images are available is the object of a final discussion.

Hyperspectral Image Classification Using Multi-Scale Lightweight Transformer

The distinctive feature of hyperspectral images (HSIs) is their large number of spectral bands, which allows us to identify categories of ground objects by capturing discrepancies in spectral information. Convolutional neural networks (CNN) with attention modules effectively improve the classification accuracy of HSI. However, CNNs are not successful in capturing long-range spectral–spatial dependence. In recent years, Vision Transformer (VIT) has received widespread attention due to its excellent performance in acquiring long-range features. However, it requires calculating the pairwise correlation between token embeddings and has the complexity of the square of the number of tokens, which leads to an increase in the computational complexity of the network. In order to cope with this issue, this paper proposes a multi-scale spectral–spatial attention network with frequency-domain lightweight Transformer (MSA-LWFormer) for HSI classification. This method synergistically integrates CNN, attention mechanisms, and Transformer into the spectral–spatial feature extraction module and frequency-domain fused classification module. Specifically, the spectral–spatial feature extraction module employs a multi-scale 2D-CNN with multi-scale spectral attention (MS-SA) to extract the shallow spectral–spatial features and capture the long-range spectral dependence. In addition, The frequency-domain fused classification module designs a frequency-domain lightweight Transformer that employs the Fast Fourier Transform (FFT) to convert features from the spatial domain to the frequency domain, effectively extracting global information and significantly reducing the time complexity of the network. Experiments on three classic hyperspectral datasets show that MSA-LWFormer has excellent performance.

A Hyperspectral Change Detection (HCD-Net) Framework Based on Double Stream Convolutional Neural Networks and an Attention Module

Human activities and natural phenomena continually transform the Earth’s surface, presenting ongoing challenges to the environment. Therefore, the accurate and timely monitoring and prediction of these alterations are essential for devising effective solutions and mitigating environmental impacts in advance. This study introduces a novel framework, called HCD-Net, for detecting changes using bi-temporal hyperspectral images. HCD-Net is built upon a dual-stream deep feature extraction process, complemented by an attention mechanism. The first stream employs 3D convolution layers and 3D Squeeze-and-Excitation (SE) blocks to extract deep features, while the second stream utilizes 2D convolution and 2D SE blocks for the same purpose. The deep features from both streams are then concatenated and processed through dense layers for decision-making. The performance of HCD-Net is evaluated against existing state-of-the-art change detection methods. For this purpose, the bi-temporal Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) hyperspectral dataset was utilized to assess the change detection performance. The findings indicate that HCD-Net achieves superior accuracy and the lowest false alarm rate among the compared methods, with an overall classification accuracy exceeding 96%, and a kappa coefficient greater than 0.9.

Spatial–Spectral Total Variation-Regularized Low-Rank Tensor Representation for Hyperspectral Anomaly Detection

Hyperspectral anomaly detection is a vital aspect of remote sensing as it focuses on identifying pixels with distinct spectral–spatial properties in comparison to their background representations. However, existing methods for anomaly detection in HSIs often overlook the spatial correlation between pixels by converting the three-dimensional tensor data into its folded form of independent signatures, which may lead to insufficient detection performance. To address this limitation, we develop an anomaly detection algorithm from a tensor representation perspective, which begins by separating the observed hyperspectral image into background and anomaly cubes. We leverage the tensor nuclear norm (TNN) to capture the inherent low-rank structure of background cube globally. This allows us to effectively model and represent the background information. To further improve the detection performance, we introduce spatial–spectral total variation (SSTV) for effectively promoting piecewise smoothness of the background tensor, aiding in the identification of anomalies. Additionally, we incorporate RX-derived attention weights-guided [Formula: see text] norm. This encourages group sparsity of anomalous pixels, improving the precision of anomaly detection. To solve our proposed method, we employ the alternating direction method of multipliers (ADMM), ensuring guaranteed convergence and efficient computation. Through experiments on different kinds of hyperspectral real datasets, we have demonstrated that our method surpasses several state-of-the-art detectors.