Pixel In Hyperspectral Image Research Articles

Dual subspace clustering for spectral-spatial hyperspectral image clustering

Subspace clustering supposes that hyperspectral image (HSI) pixels lie in a union vector spaces of multiple sample subspaces without considering their dual space, i.e., spectral space. In this article, we propose a promising dual subspace clustering (DualSC) for improving spectral-spatial HSIs clustering by relaxing subspace clustering. To this end, DualSC simultaneously optimizes row and column subspace-representations of HSI superpixels to capture the intrinsic connection between spectral and spatial information. From the new perspective, the original subspace clustering can be treated as a special case of DualSC that has larger solution space, so tends to finding better sample representation matrix for applying spectral clustering. Besides, we provide theoretical proofs that show the proposed method relaxes the subspace space clustering with dual subspace, and can recover subspace-sparse representation of HSI samples. To the best of our knowledge, this work could be one of the first dual clustering method leveraging sample and spectral subspaces simultaneously. As a result, we conduct several clustering experiments on four canonical data sets, implying that our proposed method with strong interpretability reaches comparable performance and computing efficiency with other state-of-the-art methods.

Integration of an autoencoder and background suppression for hyperspectral anomaly detection

ABSTRACT The key to hyperspectral image (HSI) anomaly detection is effectively distinguishing anomalies from the background. Various detectors, such as low-rank sparse representation and background estimation, have been proposed. However, they usually exhibit poor performance due to complex backgrounds and similar anomalies and backgrounds. Considering that most of the pixels in HSI are background, the autoencoder can emphatically and automatically extract and reconstruct background features. And background suppression can further enhance the spectral differentiation of the anomalies and backgrounds. Therefore, we propose a new anomaly detector by integrating autoencoder and background suppression. First, the anomaly coefficient of HSI data is extracted via the local characteristics. The HSI data is fed into the 2Dimensional (2D) convolution autoencoder to reconstruct the background. Since the reconstruction background contains incorrect anomalies, the anomaly coefficient isused to suppress the reconstruction image. Then, the detection map is obtained with the Mahalanobis distance. The experiment is performed in different HSI datasets. The results illustrate that the proposed method is effective and outperforms other advanced methods in terms of detection performance.

Assessing grapevine water status in a variably irrigated vineyard with NIR/SWIR hyperspectral imaging from UAV

Remote sensing is now a valued solution for more accurately budgeting water supply by identifying spectral and spatial information. A study was put in place in a Vitis vinifera L. cv. Cabernet-Sauvignon vineyard in the San Joaquin Valley, CA, USA, where a variable rate automated irrigation system was installed to irrigate vines with twelve different water regimes in four randomized replicates, totaling 48 experimental zones. The purpose of this experimental design was to create variability in grapevine water status, in order to produce a robust dataset for modeling purposes. Throughout the growing season, spectral data within these zones was gathered using a Near InfraRed (NIR) - Short Wavelength Infrared (SWIR) hyperspectral camera (900 to 1700 nm) mounted on an Unmanned Aircraft Vehicle (UAV). Given the high water-absorption in this spectral domain, this sensor was deployed to assess grapevine stem water potential, Ψstem, a standard reference for water status assessment in plants, from pure grapevine pixels in hyperspectral images. The Ψstem was acquired simultaneously in the field from bunch closure to harvest and modeled via machine-learning methods using the remotely sensed NIR-SWIR data as predictors in regression and classification modes (classes consisted of physiologically different water stress levels). Hyperspectral images were converted to bottom of atmosphere reflectance using standard panels on the ground and through the Quick Atmospheric Correction Method (QUAC) and the results were compared. The best models used data obtained with standard panels on the ground and allowed predicting Ψstem values with an R2 of 0.54 and an RMSE of 0.11 MPa as estimated in cross-validation, and the best classification reached an accuracy of 74%. This project aims to develop new methods for precisely monitoring and managing irrigation in vineyards while providing useful information about plant physiology response to deficit irrigation.

Physics-informed interactive network for hyperspectral image classification

In hyperspectral image (HSI) classification, convolutional neural networks (CNNs) have made great progress. In recent CNN-based HSI classification methods, spatial attention mechanism has been widely used to emphasize more salient features and suppress less useful ones. However, these methods tend to utilize plug-and-play attention modules which ignore the physical meaning of HSI pixels. To reflect the physical construction of HSI pixels in the attention mask, we propose a physics-informed interactive network (PI2Net) integrating a spatial guided spectral component stream (SGSC-stream) and a spectral constrained spatial attention stream (SCSA-stream). The SGSC-stream can obtain more expressive abundance features of the input HSI cubes through a component analysis block. The SCSA-stream completes the prediction of hyperspectral data in three-stage features extraction cells and a classification cell. To connect and interact between these two streams, a component-aware attention module (CAAM) and a class-wise endmember activation gate (CWEAG) are designed. The CAAM measures the similarity of abundance features to generate a component-aware attention mask, so as to learn the component-based relationships between pixels. Then, the multiscale attention masks are embedded into different stages of the SCSA-stream. The CWEAG is proposed to iteratively generate more accurate abundance features with the classification result of SCSA-stream. Experimental results based on three common hyperspectral data sets demonstrate that PI2Net outperforms several state-of-the-art methods in terms of qualitative and quantitative analysis.

Rapid pH Value Detection in Secondary Fermentation of Maize Silage Using Hyperspectral Imaging

As pH is a key factor affecting the quality of maize silage, its accurate detection is essential to ensuring product quality. Although traditional methods for testing the pH of maize silage feed are widely used, the procedures are often complex and time-consuming and may damage the sample. This study presents a non-destructive hyperspectral imaging (HSI) technology that provides a more efficient and cost-effective method of monitoring pH by capturing the spectral information of samples and analyzing their chemical and physical properties rapidly and without contact. We applied four spectral preprocessing methods, among which the multiplicative scatter correction (MSC) preprocessing method yielded the best results. To minimize model redundancy and enhance predictive performance, we utilized six feature extraction methods for characteristic wavelength extraction, integrating these with partial least squares (PLS), non-linear support vector machine regression (SVR), and extreme learning machine (ELM) algorithms to construct a quantitative pH value prediction model. The results showed that the model based on the bootstrapping soft shrinkage (BOSS) feature wavelength extraction method outperformed the other feature extraction methods, selecting 20 pH value-related feature wavelengths from 256 bands and building a stable BOSS–ELM model with prediction set determination coefficient (RP2), root-mean-square error of prediction (RMSEP), and relative percentage deviation (RPD) values of 0.9241, 0.4372, and 3.6565, respectively. To further optimize the model for precisely predicting pH at each pixel in hyperspectral images, we employed three algorithms: the genetic algorithm (GA), whale optimization algorithm (WOA), and bald eagle search (BES). These algorithms optimized and compared the BOSS–ELM model to obtain the best model for predicting maize silage pH: the BOSS–BES–ELM model. This model achieved a determination coefficient (RP2) of 0.9598, an RMSEP of 0.3216, and an RPD of 5.1448. We generated a visualized distribution map of pH value variation in maize silage using the BOSS–BES–ELM model. This study provides strong technical support and a reference for the rapid, non-destructive detection of maize silage pH from an image, an advancement of great significance to ensuring the quality of maize silage.

A new spectral simulating method based on near-infrared hyperspectral imaging for evaluation of antibiotic mycelia residues in protein feeds

Antibiotic mycelia residues (AMRs) contain antibiotic residues. If AMRs are ingested in excess by livestock, it may cause health problems. To address the current problem of unknown pixel-scale adulteration concentration in NIR-HSI, this paper innovatively proposes a new spectral simulation method for the evaluation of AMRs in protein feeds. Four common protein feeds (soybean meal (SM), distillers dried grains with solubles (DDGS), cottonseed meal (CM), and nucleotide residue (NR)) and oxytetracycline residue (OR) were selected as study materials. The first step of the method is to simulate the spectra of pixels with different adulteration concentrations using a linear mixing model (LMM). Then, a pixel-scale OR quantitative model was developed based on the simulated pixel spectra combined with local PLS based on global PLS scores (LPLS-S) (which solves the problem of nonlinear distribution of the prediction results due to the 0%-100% content of the correction set). Finally, the model was used to quantitatively predict the OR content of each pixel in hyperspectral image. The average value of each pixel was calculated as the OR content of that sample. The implementation of this method can effectively overcome the inability of PLS-DA to achieve qualitative identification of OR in 2%-20% adulterated samples. In compared to the PLS model built by averaging the spectra over the region of interest, this method utilizes the precise information of each pixel, thereby enhancing the accuracy of the detection of adulterated samples. The results demonstrate that the combination of the method of simulated spectroscopy and LPLS-S provides a novel method for the detection and analysis of illegal feed additives by NIR-HSI.

Efficient Blind Hyperspectral Unmixing Framework Based on CUR Decomposition (CUR-HU)

Hyperspectral imaging captures detailed spectral data for remote sensing. However, due to the limited spatial resolution of hyperspectral sensors, each pixel of a hyperspectral image (HSI) may contain information from multiple materials. Although the hyperspectral unmixing (HU) process involves estimating endmembers, identifying pure spectral components, and estimating pixel abundances, existing algorithms mostly focus on just one or two tasks. Blind source separation (BSS) based on nonnegative matrix factorization (NMF) algorithms identify endmembers and their abundances at each pixel of HSI simultaneously. Although they perform well, the factorization results are unstable, require high computational costs, and are difficult to interpret from the original HSI. CUR matrix decomposition selects specific columns and rows from a dataset to represent it as a product of three small submatrices, resulting in interpretable low-rank factorization. In this paper, we propose a new blind HU framework based on CUR factorization called CUR-HU that performs the entire HU process by exploiting the low-rank structure of given HSIs. CUR-HU incorporates several techniques to perform the HU process with a performance comparable to state-of-the-art methods but with higher computational efficiency. We adopt a deterministic sampling method to select the most informative pixels and spectrum components in HSIs. We use an incremental QR decomposition method to reduce computation complexity and estimate the number of endmembers. Various experiments on synthetic and real HSIs are conducted to evaluate the performance of CUR-HU. CUR-HU performs comparably to state-of-the-art methods for estimating the number of endmembers and abundance maps, but it outperforms other methods for estimating the endmembers and the computational efficiency. It has a 9.4 to 249.5 times speedup over different methods for different real HSIs.

3D-CNN and semi-supervised based network for hyperspectral unmixing

ABSTRACT Hyperspectral Unmixing (HU), which involves decomposing mixed pixels in hyperspectral images into endmembers and abundance fractions, plays a critical role in spectral analysis. Recent advancements in deep learning methods have shown successful applications in hyperspectral analysis. This paper proposes an end-to-end network structure that combines a Convolutional Neural Network (CNN) and a Multilayer Perceptron (MLP). The 3D-CNN extracts high-level features from both spatial and spectral neighbourhoods of hyperspectral image patches, while the MLP maps these abstracted features to abundance fractions. Considering the challenge of acquiring manual labels, we adopt a Semi-Supervised learning approach that leverages unlabelled data to enhance training. We divide our training data into labelled and unlabelled subsets, defining distinct loss functions for each. Additionally, we introduce a neighbourhood similarity constraint to fully exploit spatial context information. To address scenarios where no labelled data is available, we employ Generative Adversarial Networks (GANs) to generate synthetic labelled samples. Experimental evaluations conducted on both synthetic and real datasets validate the effectiveness of our proposed method, which outperforms several commonly used and state-of-the-art HU methods.

Spectral–Spatial Feature Extraction for Hyperspectral Image Classification Using Enhanced Transformer with Large-Kernel Attention

In the hyperspectral image (HSI) classification task, every HSI pixel is labeled as a specific land cover category. Although convolutional neural network (CNN)-based HSI classification methods have made significant progress in enhancing classification performance in recent years, they still have limitations in acquiring deep semantic features and face the challenges of escalating computational costs with increasing network depth. In contrast, the Transformer framework excels in expressing high-level semantic features. This study introduces a novel classification network by extracting spectral–spatial features with an enhanced Transformer with Large-Kernel Attention (ETLKA). Specifically, it utilizes distinct branches of three-dimensional and two-dimensional convolutional layers to extract more diverse shallow spectral–spatial features. Additionally, a Large-Kernel Attention mechanism is incorporated and applied before the Transformer encoder to enhance feature extraction, augment comprehension of input data, reduce the impact of redundant information, and enhance the model’s robustness. Subsequently, the obtained features are input to the Transformer encoder module for feature representation and learning. Finally, a linear layer is employed to identify the first learnable token for sample label acquisition. Empirical validation confirms the outstanding classification performance of ETLKA, surpassing several advanced techniques currently in use. This research provides a robust and academically rigorous solution for HSI classification tasks, promising significant contributions in practical applications.

Lightweight Transformer with Transposed-attention for Hyperspectral Unmixing

Hyperspectral unmixing primarily involves accurately estimating the end members and abundances from mixed pixels in hyperspectral images. In our task, we design a transposed-attention mechanism in the lightweight Transformer to capture the effective information between channels to provide better performance and faster computing speed. We compare the proposed model with those of the CyCU, FCLS, and DHTN methods. The quantitative and qualitative results indicate that our method outperforms the quality of endmember spectral and abundance maps and has a competitive advantage in calculation speed.

S2Former: Parallel Spectral–Spatial Transformer for Hyperspectral Image Classification

Due to their excellent representation talent in local features, the convolutional neural network (CNN) has achieved favourable performance in hyperspectral image (HSI) classification tasks. Nevertheless, current CNN models exhibit a marked flaw: they are hard to model the dependencies in long-range distanced positions. This flaw becomes more problematic for the HSI classification task, which targets extracting more discriminative features in local and global dimensions from limited samples. In this paper, we introduce a spatial–spectral transformer (S2Former), which explores spatial and spectral feature extraction in a dual-stream framework for HSI Classification. S2Former, which consists of a spatial transformer and a spectral transformer in parallel branches, extracts the discriminative feature in spatial and spectral dimensions. More specifically, we propose multi-head spatial self-attention to capture the long-range spatial dependency of non-adjacent HSI pixels in a spatial transformer. In the spectral transformer, we propose multi-head covariance spectral attention to mine and represent spectral signatures by computing covariance-based channel maps. Meanwhile, the local activation feed-forward network is developed to complement local details. Extensive experiments conducted on four publicly available datasets indicate that our S2Former achieves state-of-the-art performance for the HSI classification task.

Robust Dual Spatial Weighted Sparse Unmixing for Remotely Sensed Hyperspectral Imagery

Sparse unmixing plays a crucial role in the field of hyperspectral image unmixing technology, leveraging the availability of pre-existing endmember spectral libraries. In recent years, there has been a growing trend in incorporating spatial information from hyperspectral images into sparse unmixing models. There is a strong spatial correlation between pixels in hyperspectral images (that is, the spatial information is very rich), and many sparse unmixing algorithms take advantage of this to improve the sparse unmixing effect. Since hyperspectral images are susceptible to noise, the feature separability of ground objects is reduced, which makes most sparse unmixing methods and models face the risk of degradation or even failure. To address this challenge, a novel robust dual spatial weighted sparse unmixing algorithm (RDSWSU) has been proposed for hyperspectral image unmixing. This algorithm effectively utilizes the spatial information present in the hyperspectral images to mitigate the impact of noise during the unmixing process. For the proposed RDSWSU algorithm, which is based on ℓ1 sparse unmixing framework, a pre-calculated superpixel spatial weighting factor is used to smooth the noise, so as to maintain the original spatial structure of hyperspectral images. The RDSWSU algorithm, which builds upon the ℓ1 sparse unmixing framework, employs a pre-calculated spatial weighting factor at the superpixel level. This factor aids in noise smoothing and helps preserve the inherent spatial structure of hyperspectral images throughout the unmixing process. Additionally, another spatial weighting factor is utilized in the RDSWSU algorithm to capture the local smoothness of abundance maps at the sub-region level. This factor helps enhance the representation of piecewise smooth variations within different regions of the hyperspectral image. Specifically, the combination of these two spatial weighting factors in the RDSWSU algorithm results in an enhanced sparsity of the abundance matrix. The RDSWSU algorithm, which is a sparse unmixing model, offers an effective solution using the alternating direction method of multiplier (ADMM) with reduced requirements for tuning the regularization parameter. The proposed RDSWSU method outperforms other advanced sparse unmixing algorithms in terms of unmixing performance, as demonstrated by the experimental results on synthetic and real hyperspectral datasets.

An Effective Hyperspectral Image Classification Network Based on Multi-Head Self-Attention and Spectral-Coordinate Attention.

In hyperspectral image (HSI) classification, convolutional neural networks (CNNs) have been widely employed and achieved promising performance. However, CNN-based methods face difficulties in achieving both accurate and efficient HSI classification due to their limited receptive fields and deep architectures. To alleviate these limitations, we propose an effective HSI classification network based on multi-head self-attention and spectral-coordinate attention (MSSCA). Specifically, we first reduce the redundant spectral information of HSI by using a point-wise convolution network (PCN) to enhance discriminability and robustness of the network. Then, we capture long-range dependencies among HSI pixels by introducing a modified multi-head self-attention (M-MHSA) model, which applies a down-sampling operation to alleviate the computing burden caused by the dot-product operation of MHSA. Furthermore, to enhance the performance of the proposed method, we introduce a lightweight spectral-coordinate attention fusion module. This module combines spectral attention (SA) and coordinate attention (CA) to enable the network to better weight the importance of useful bands and more accurately localize target objects. Importantly, our method achieves these improvements without increasing the complexity or computational cost of the network. To demonstrate the effectiveness of our proposed method, experiments were conducted on three classic HSI datasets: Indian Pines (IP), Pavia University (PU), and Salinas. The results show that our proposed method is highly competitive in terms of both efficiency and accuracy when compared to existing methods.

Spatial-Spectral Unified Adaptive Probability Graph Convolutional Networks for Hyperspectral Image Classification.

In hyperspectral image (HSI) classification task, semisupervised graph convolutional network (GCN)-based methods have received increasing attention. However, two problems still need to be addressed. The first is that the initial graph structure in the GCN-based methods is not sufficiently flexible to encode the homogenous structure similarity of HSI pixels when facing the complex scenarios induced by the spatial variability. Another problem is that the input (graph structure) and output (output features) of the GCN-based methods are separated with a ``single pass'' procedure, which is a suboptimal problem for HSI classification because it does not flexibly optimize the graph construction with a feedback method via output features. In this article, a novel spatial-spectral unified adaptive probability GCN (SSAPGCN) method is proposed for HSI classification. First, considering the homogeneous structural similarity of the pairwise relationships of HSI pixels, this article combines the inherent spectral information and spatial coordinates to obtain the spatial-spectral adaptive probability graph (SSAPG) structure, which can capture the probabilistic connectivity between each pair of the homogeneous HSI pixels. Second, the SSAPG structure and GCN model are combined into a unified framework to a daptively learn both the graph structure and the output features simultaneously with feedback. Finally, the proposed SSAPGCN method with two layers is evaluated on four public HSI datasets to demonstrate its superiority over different classification methods in terms of two evaluation metrics, the overall accuracy (OA) and kappa coefficient (KC), especially with small training sample sizes.

Modelling Spectral Unmixing of Geological Mixtures: An Experimental Study Using Rock Samples

Spectral unmixing of geological mixtures, such as rocks, is a challenging inversion problem because of nonlinear interactions of light with the intimately mixed minerals at a microscopic scale. The fine-scale mixing of minerals in rocks limits the sensor’s ability to identify pure mineral endmembers and spectrally resolve these constituents within a given spatial resolution. In this study, we attempt to model the spectral unmixing of two rocks, namely, serpentinite and granite, by acquiring their hyperspectral images in a controlled environment, having uniform illumination, using a laboratory-based imaging spectroradiometer. The endmember spectra of each rock were identified by comparing a limited set of pure hyperspectral image pixels with the constituent minerals of the rocks based on their diagnostic spectral features. A series of spectral unmixing paradigms for explaining geological mixtures, including those ranging from simple physics-based light interaction models (linear, bilinear, and polynomial models) to classification-based models (support vector machines (SVMs) and half Siamese network (HSN)), were tested to estimate the fractional abundances of the endmembers at each pixel position of the image. The analysis of the results of the spectral unmixing algorithms using the ground truth abundance maps and actual mineralogical composition of the rock samples (estimated using X-ray diffraction (XRD) analysis) indicate a better performance of the pure pixel-guided HSN model in comparison to the linear, bilinear, polynomial, and SVM-based unmixing approaches. The HSN-based approach yielded reduced errors of abundance estimation, image reconstruction, and mineralogical composition for serpentinite and granite. With its ability to train using limited pure pixels, the half-Siamese network model has a scope for spectrally unmixing rock samples of varying mineralogical composition and grain sizes. Hence, HSN-based approaches effectively address the modelling of nonlinear mixing in geological mixtures.

A Staged Approach With Structural Sparsity for Hyperspectral Unmixing

Accurate identification of pure substance and mapping the corresponding distribution are challenging because of the existence of complex distribution mixed pixels in hyperspectral image (HSI). There are numerous different methods to decompose the HSI into pure substance spectral signatures (endmembers) and corresponding fractions (abundances). However, most of them only consider local or global representations and do not fully exploit the intrinsic feature information among and inside endmember candidate domains (preliminary abundance maps), therefrom leading them to be ineffective when similar substances appear in close proximity or under noisy occlusion. In this article, we advocate a robust staged approach with structural sparsity. The proposed approach not only thoroughly exploits the intrinsic relationships among endmember distribution regions and local spatial similarities, but also maintains the spatial fidelity structure among the local regions inside each endmember distribution region. In particular, the representations among endmembers and local similarities are learned jointly. Moreover, perturbations are tackled when searching for the best endmember signature distribution region. Furthermore, by means of imposing the structural sparsity regularization on the framework of nonnegative matrix tri-factorization (NMTF), the merits of most existing sparsity constraints are accommodated and surpassed. An extensive number of qualitative and quantitative experiments are conducted on simulated and benchmark real hyperspectral data sets. The results demonstrate that the proposed method performs better than several recent classical unmixing methods.

Anomaly Detection of Remote Sensing Images Based on the Channel Attention Mechanism and LRX

Anomaly detection of remote sensing images has gained significant attention in remote sensing image processing due to their rich spectral information. The Local RX (LRX) algorithm, derived from the Reed–Xiaoli (RX) algorithm, is a hyperspectral anomaly detection method that focuses on identifying anomalous pixels in hyperspectral images by exploiting local statistics and background modeling. However, it is still susceptible to the noises in the Hyperspectral Images (HSIs), which limits its detection performance. To address this problem, a hyperspectral anomaly detection algorithm based on channel attention mechanism and LRX is proposed in this paper. The HSI is feed into the auto-encoder network that is constrained by the channel attention module to generate a more representative reconstructed image that better captures the characteristics of different land covers and has less noises. The channel attention module in the auto-encoder network aims to explore the effective spectral bands corresponding to different land covers. Subsequently, the LRX algorithm is utilized for anomaly detection on the reconstructed image obtained from the auto-encoder network with the channel attention mechanism, which avoids the influence of noises on the anomaly detection results and improves the anomaly detection performance. The experiments are conducted on three HSIs to verify the performance of the proposed method. The proposed hyperspectral anomaly detection method achieves higher Area Under Curve (AUC) values of 0.9871, 0.9916 and 0.9642 on HYDICE urban dataset, AVIRIS aircraft dataset and Salinas Valley dataset, respectively, compared with other six methods. The experimental results demonstrate that the proposed algorithm has better anomaly detection performance than LRX and other algorithms.

Design of Vegetation Index for Identifying the Mosaic Virus in Sugarcane Plantation: A Brazilian Case Study

Phytosanitary control of crops requires the rapid mapping of diseases to enable management attention. This study aimed to evaluate the potential of vegetation indices for the detection of sugarcane mosaic disease. Spectral indices were applied to hyperspectral images collected by an unmanned aerial vehicle (UAV) to find the areas affected by the mosaic virus in sugarcane. Identifying indices capable of detecting diseased plants in agricultural crops supports data processing and the development of efficient tools. A new index was designed based on spectral regions, which presents higher differences between healthy and mosaic virus-infected leaves to enhance hyperspectral image pixels representing diseased plants. Based on the data generated, we propose the anthocyanin red edge index (AREI) for mosaic virus detection in sugarcane plantations. An index that can adequately identify sugarcane infected by the mosaic virus may incorporate wavelengths associated with variations in leaf pigment concentrations as well as changes in leaf structure. The indices that assessed to detect plants infected with the sugarcane mosaic virus were the normalised difference vegetation index (NDVI), normalised difference vegetation index red edge (NDVI705), new vegetation index (NVI), ARI2 and AREI. The results showed that AREI presented the best performance for the detection of mosaic in sugarcane from UAV images, giving an overall accuracy of 0.94, a kappa coefficient of 0.87, and omission and inclusion errors of 2.86% and 10.52%, respectively. The results show the importance of wavelengths associated with the concentration of chlorophyll and anthocyanin and the position of the red edge for the detection of diseases in sugarcane.

Reconstruction of Compressed Hyperspectral Image Using SqueezeNet Coupled Dense Attentional Net

This study addresses image denoising alongside the compression and reconstruction of hyperspectral images (HSIs) using deep learning techniques, since the research community is striving to produce effective results to utilize hyperspectral data. Here, the SqueezeNet architecture is trained with a Gaussian noise model to predict and discriminate noisy pixels of HSI to obtain a clean image as output. The denoised image is further processed by the tunable spectral filter (TSF), which is a dual-level prediction filter to produce a compressed image. Subsequently, the compressed image is analyzed through a dense attentional net (DAN) model for reconstruction by reverse dual-level prediction operation. All the proposed mechanisms are employed in Python and evaluated using a Ben-Gurion University-Interdisciplinary Computational Vision Laboratory (BGU-ICVL) dataset. The results of SqueezeNet architecture applied to the dataset produced the denoised output with a Peak Signal to Noise Ratio (PSNR) value of 45.43 dB. The TSF implemented to the denoised images provided compression with a Mean Square Error (MSE) value of 8.334. Subsequently, the DAN model executed and produced reconstructed images with a Structural Similarity Index Measure (SSIM) value of 0.9964 dB. The study proved that each stage of the proposed approach resulted in a quality output, and the developed model is more effective to further utilize the HSI. This model can be well utilized using HSI data for mineral exploration.

Flexible Hyperspectral Anomaly Detection Using Weighted Nuclear Norm

It has been demonstrated that nuclear-norm-based low-rank representation is capable of modeling cluttered backgrounds in hyperspectral images (HSIs) for robust anomaly detection. However, minimizing the nuclear norm regularizes each singular value equally during rank reduction, which restricts the capacity and flexibility of modeling the major structures of the background. To address this problem, we propose detection of anomaly pixels in HSIs using the weighted nuclear norm, which can preserve the major singular values during rank reduction. We present a down-up sampling scheme to remove plausible anomaly pixels from the image as much as possible and learn a robust principal component analysis (PCA) background dictionary. From a dictionary, we develop a weighted nuclear-norm minimization model to represent the background with a low-rank coefficients matrix that can be effectively optimized using the standard alternating direction method of multipliers (ADMM). Due to the flexible modeling capacity using the weighted nuclear norm, anomaly pixels can be distinguished from the background with the reconstruction error. The experimental results on two real HSIs datasets demonstrate the effectiveness of the proposed method for anomaly detection.