Hyperspectral Image Analysis Research Articles

Efficient band reduction for hyperspectral imaging with dependency-based segmented principal component analysis

ABSTRACT In the context of hyperspectral image (HSI) analysis, a widely used feature extraction method, Principal Components Analysis (PCA) suffers from limitations such as wavelength bias and a lack of consideration for local spectral information. While various segmentation based PCA methods attempt to address these issues by incorporating local relationships, they still overlook band similarity beyond immediate neighbours. To address these challenges, this paper introduces a novel approach called dependency based segmented PCA (dPCA). This method employs hierarchical clustering-driven mutual information-based segmentation, facilitating more comprehensive feature extraction from HSI data. By utilizing this dependency-based segmentation, both global and local structures are effectively captured, providing enhanced details for classification tasks. The proposed dPCA is evaluated on four prominent HSI datasets in remote sensing for land use classification, and the experimental results underscore its superiority over conventional PCA, and other segmentation based PCA methods in terms of classification performance.

Identifying Crop Distress and Stress-Induced Plant Diseases Using Hyper Spectral Image Analysis

The purpose of this study is to determine whether hyper spectral images can be used to identify plant diseases and crop pressure from aerial photographs. With extensive research on the prevalent methods used closer to the problem, this study offers a potent strategy for identifying crop distress and illnesses using this efficient imaging technique. To identify the spectral fingerprints of common indications and symptoms of plant diseases and crop strains, this study evaluates the available hyper spectral photo datasets. After that, the data are examined using two learning algorithms—the highly randomized trees and the Random Woodland set of rules—to create predictions that are entirely dependent on the results that are discovered. In the end, a benchmarked set of test statistics is used to assess the prediction accuracy. The results of this study show that hyper spectral photo evaluation has a strong and promising utility for crop stress and disease identification. Hyper spectral light evaluation is a method for identifying plant diseases caused by strain on crops. By gathering and evaluating high-dimensional spectral reflection data from satellite or aircraft structures, details regarding the physiological homes of flowers can be identified. The health of plants, illnesses brought on by stress, and agricultural productivity predictions can all be made using these facts. Hyper spectral recordings can also be used to create actions that reduce agricultural losses and enhance the health of plants that are prone to disease.

Assessing water quality environmental grades using hyperspectral images and a deep learning model: A case study in Jiangsu, China

Water quality assessment is essential for effective environmental management, yet traditional methods such as chemical sampling are often labor-intensive and inefficient for large-scale, continual monitoring. This study addresses these limitations by leveraging hyperspectral images (HSIs) analysis and introducing a capsule network (CapsNet) model enhanced with a multidimensional integration attention (MDIA) mechanism. The model is specifically designed to integrate both channel and spatial information, enabling precise water quality grade assessment by detecting subtle features within HSIs data. To validate the performance of the model, spectral data from 5 water quality regions are collected and processed via a UAV-carried spectrometer, with 4503 water quality data samples. Rigorous classification experiments demonstrated that the model achieves 98.73 % accuracy, with an average improvement of 4.89 % compared with the other models. This approach significantly improves decision support systems for water resource management, facilitating the sustainable use of water resources.

Application of Supervised Learning Methods and Information Gain Methods in the Determination of Asbestos–Cement Roofs’ Deterioration State

This study introduces an innovative approach to evaluate the condition of asbestos–cement (AC) roofs by integrating field data with five distinct supervised learning models: decision trees, KNN, logistic regression, support vector machine, and random forest. A novel methodology for assessing the importance of 380 reflectance bands was employed, offering fresh insights into the key indicators of AC roof deterioration. The research systematically organized and prioritized reflectance bands based on their information gain, optimizing both the selection of relevant bands and the performance of the models in differentiating between low and high intervention priority (LIP and HIP) roofs. The decision tree model, when applied to the top 10 most relevant bands, achieved the highest cross-validation accuracy of 76.047%, making it the most effective tool for identifying AC roof conditions. Additionally, the random forest model demonstrated strong performance across various band groups, further validating its utility. Utilizing the open-source software Weka (version 3.8.6), this study adeptly executed relevance evaluation and model implementation, providing a practical and scalable solution for material characterization, especially in regions where resources for spectral and hyperspectral image analysis are limited. The findings of this study offer valuable tools for government and environmental authorities, particularly in developing countries, where efficient and cost-effective AC roof assessment is crucial for public health and safety. The methodology is adaptable to different urban environments and climatic conditions, supporting global efforts in asbestos management, especially in countries where asbestos regulations are newly implemented. Organized within the CRISP-DM framework, this paper details the methodological phases, presents compelling results on reflectance band relevance, evaluates machine learning models, and concludes with prospects for future research aimed at enhancing asbestos detection and removal strategies.

Hierarchical homogeneity-based superpixel segmentation: application to hyperspectral image analysis

ABSTRACT Hyperspectral image (HI) analysis approaches have recently become increasingly complex and sophisticated. Recently, the combination of spectral-spatial information and superpixel techniques have addressed some hyperspectral data issues, such as the higher spatial variability of spectral signatures and dimensionality of the data. However, most existing superpixel approaches do not account for specific HI characteristics resulting from its high spectral dimension. In this work, we propose a multiscale superpixel method that is computationally efficient for processing hyperspectral data. The Simple Linear Iterative Clustering (SLIC) oversegmentation algorithm, on which the technique is based, has been extended hierarchically. Using a novel robust homogeneity testing, the proposed hierarchical approach leads to superpixels of variable sizes but with higher spectral homogeneity when compared to the classical SLIC segmentation. For validation, the proposed homogeneity-based hierarchical method was applied as a preprocessing step in the spectral unmixing and classification tasks carried out using, respectively, the Multiscale sparse Unmixing Algorithm (MUA) and the CNN-Enhanced Graph Convolutional Network (CEGCN) methods. Simulation results with both synthetic and real data show that the technique is competitive with state-of-the-art solutions.

Evaluation technologies for assessing drought tolerance of Kimchi cabbage seedlings using hyperspectral imaging and principal component analysis

Conventionally, methods for evaluating the tolerance of kimchi cabbage have primarily relied on visual inspection. The development of evaluation criteria based on hyperspectral imaging may help address the problem of decision-making errors arising from visual inspection. However, to evaluate the tolerance of kimchi cabbage using hyperspectral imaging, not only are hyperspectral big data processing and sophisticated exponential model development required, but also real-time evaluation technology with high field usability. This study presents an evaluation method for extracting vegetation information from hyperspectral data, logically analyzing the extracted data, validating the developed model, and ensuring field utility. The red-edge band between 680 and 700 nm is for evaluating the drought tolerance of Kimchi cabbage. The proposed method allows for assessing the drought tolerance of Kimchi cabbage seedlings within a range of 1 to 30, using a robust index with a variance of approximately 2.25 and a sensitivity index with a variance of around 8.4. Since the proposed nonlinear drought tolerance evaluation method must strongly correlate with the chlorophyll index, its performance was verified using the newly proposed cross-point analyzer. While nonlinear drought evaluation technology can serve as a robust analysis method based on extensive data, it has the disadvantage of requiring a long evaluation time. However, the additionally developed cross-point analyzer can improve the real-time capability of testing. Proper utilization of these two analytical technologies enhances the performance of robust and rapid drought tolerance evaluation for Kimchi cabbage seedlings. Therefore, this study introduces two techniques for non-destructively and quantitatively explaining plant water stress.

Combination model for freshness prediction of pork using VIS/NIR hyperspectral imaging with chemometrics.

This study aimed to develop an enhanced model for predicting pork freshness by integrating hyperspectral imaging and chemometric analysis. A total of 30 Longissimus thoracis samples from three sows were stored under vacuum conditions at 4 ± 2℃ for 27 days to acquire data. The freshness prediction model for pork loin employed partial least squares regression (PLSR) with Monte Carlo data augmentation. Total bacterial count (TBC) and volatile basic nitrogen (VBN), which exhibited increases correlating with metabolite changes during storage, were designated as freshness indicators. Metabolic contents of the sample were quantified using NMR. A total of 64 metabolites were identified, with 34 and 35 showing high correlations with TBC and VBN, respectively. Lysine and malate for TBC (R2 = 0.886) and methionine and niacinamide for VBN (R2 = 0.909) were identified as the main metabolites in each indicator by Model 1. Model 2 predicted main metabolites using HSI spectral data. Model 3, which predicted freshness indicators with HSI spectral data, demonstrated high prediction coefficients; TBC R2p = 0.7220 and VBN R2p = 0.8392. Furthermore, the combination model (Model 4), utilizing HSI spectral data and predicted metabolites from Model 2 to predict freshness indicators, improved the prediction coefficients compared to Model 3; TBC R2p = 0.7583 and VBN R2p = 0.8441. Combining HSI spectral data with metabolites correlated to the meat freshness may elucidate why certain HSI spectra indicate meat freshness and prove to be more effective in predicting the freshness state of pork loin compared to using only HSI spectral data.

Elastic reweighted sparsity regularized sparse unmixing for hyperspectral image analysis

Sparse unmixing is a crucial component in the analysis of hyperspectral images because of its ability to sparsely estimate abundances with a spectral library of considerable scale. The existing sparse unmixing techniques tend to employ the sparsity from a single perspective, i.e., ℓ1 or ℓ2,1. In this paper, we accurately estimate abundances from element-wise and channel-wise sparsity perspectives, which forms a new elastic reweighted sparse regularized sparse unmixing method, termed ElSpaSU. The proposed ElSpaSU method leverages the abundance matrix simultaneously using ℓ1 and ℓ2,1 sparsity regularizations. To further promote sparsity in the abundances, the proposed ElSpaSU incorporates two types of iterative reweighting weights. We utilize the alternating direction method of multipliers (ADMM) framework to ensure guaranteed convergence in solving the optimization problem. Experimental outcomes from simulated and real hyperspectral images highlight the remarkable efficacy of the suggested ElSpaSU in contrast to competing approaches.

Evolving multispectral sensor configurations using genetic programming for estuary health monitoring

ABSTRACT Assessing ecosystem health on a large scale is crucial for a wide range of management and regulatory decisions. Technologies such as hyperspectral imaging allow noninvasive and rapid estimation of key attributes based on observed reflectance. However, these images are high-dimensional and real-world applications require models based on fewer wavelengths. This paper proposes a new wavelength selection and feature extraction method for hyperspectral image analysis based on genetic programming to automatically select key wavelength regions and informative image features. A dataset of hyperspectral images of sediment in the field was collected and paired with ground-truth measurements of the sediment porosity and organic matter content. Two new program structures were proposed to construct feature extraction trees from either the mean reflectance spectra (spectra-based) or full hyperspectral images (image-based). SVR models were constructed to predict attributes based on the extracted features. Various regression models were used to predict the porosity and organic matter content. Full-wavelength models were constructed to reliably predict the organic matter content. The proposed spectra-based genetic programming solutions show competitive results compared to common wavelength selection methods, such as SPA, CARS, and RC. Finally, the best-evolved solution was applied to predict sediment organic matter content across all collected images.

Carbon Nanotube Sensor Platforms for the Detection of Cellular Nitric Oxide Efflux Gradients

Cell communication is the ability to receive, process, and transmit signals from the environment and within cells to ensure functional coordination during physiological events. Cells communicate between themselves using waves of chemical concentration that change in both direction and time. Nitric oxide (NO) is a gaseous, ubiquitous, intra - and inter-cellular signaling molecule. NO’s small size and lipophilic nature allows it to diffuse through cell membranes and reach intracellular compartments of nearby cells. However, NO detection in biological systems represents a challenge due to NO’s short half-life (in the range of seconds) before breaking down into different subproducts. The lack of spatial NO detection, not an upstream or downstream indicator of NO, has hindered understanding of the extracellular NO dynamic signaling during both physiological and pathological events. However, single wall carbon nanotube (SWNT)-based fluorescent sensors allow for the detection of NO, and when immobilized onto a glass substrate, they can be used to quantify extracellular NO in a spatial-temporal manner. We detected changes in extracellular NO efflux from different macrophage cell lines known for their NO production under inflammatory responses, specifically human THP-1 monocytes and murine macrophage RAW 264.7. The cells were seeded on the SWNT platform and treated with Liposaccharides (LPS) 24 h to increase their NO release. The SWNT platform’s sensing response to NO was detected by changes in fluorescence intensity. Fluorescence data was collected on a custom-built hyperspectral microscope to give us near infrared (nIR) signal quantification with spatial resolution. Images were collected before and after the respective NO induction method. To analyze the extracellular NO mappings, bright field images of the cells were used to extract the cell coordinates and translate them to fluorescent images. Hyperspectral image analysis was performed with MATLAB to determine SWNT fluorescence below each cell and its surrounding area. To validate that the change in the fluorescence response was attributed to NO and not from cellular interaction with the SWNT sensor, we added 2-Phenyl-4,4,5,5-tetramethylimidazoline-1-oxyl 3-oxide (PTIO), a NO scavenger, after visualizing the SWNT quenching to recover the initial fluorescence signal, showing that the cells didn’t affect SWNT functionality. Through fluorescence intensity changes with pixel specificity on the image acquisition, we were able to spatially quantify NO released by cells with dynamic diffusion gradients. The newly developed platform provides the means to quantify extracellular NO. In this study, only two cell lines were studied, but the platforms will allow for the quantification of NO for other cell types as well. By comparing extracellular NO concentrations for different types of cells, we will be able to better understand physiological and pathological patterns of NO release, leading to a better understanding of cellular signaling.

Collaborative representation based unsupervised CNN for hyperspectral anomaly detection

The convolutional neural networks (CNNs) have shown high success in supervised analysis of hyperspectral images. But, the use of a supervised CNN is not possible for an unsupervised task such as hyperspectral anomaly detection. So, an unsupervised CNN with pre-determined convolutional kernels without requirement to labeled samples or training process is proposed in this work. The proposed method uses the collaborative representation (CR) for background estimate and introduces the global preserving projection (GPP) for dimensionality reduction of it. Then, the convolutional kernels are randomly selected from the reduced CR data. Moreover, two distances in inner and guard windows are defined, which difference of them results in the anomaly score. The CR based unsupervised CNN (CUCNN) method achieves high detection accuracy compared to its counterparts and is more than 9 times faster than other presented unsupervised CNN detectors.

Identification and classification of buckwheat grain by microfocus radiography and hyperspectral imaging methods

Classification of buckwheat grains is important because the absence of defective grains is a guarantee of yield and quality. Buckwheat grains were randomly selected from a batch whose grains varied in quality. The identification and classification of buckwheat grains according to the degree of fulfillment was carried out by a combination of microfocus X-ray and hyperspectral image analysis and multivariate analysis techniques. Using microfocus radiography, buckwheat grains were categorized into groups according to the degree of fulfillment. Hyperspectral image of buckwheat grains in the range of 935-1720 nm was acquired using a Specim FX17 camera. Using the polygon selection function, the averaged spectra were obtained and a data matrix of grain samples was generated. The bands of the spectrum contributing most to the grading of the grain samples by degree of fulfillment were identified using the principal component analysis. The classification model of grading buckwheat grain into groups by degree of fulfillment was constructed by partial least squares discriminant analysis method. The results showed that hyperspectral image is a potential tool for rapid and accurate identification of buckwheat grains, which can be used in large-scale grain classification and grain quality determination.

Hyperspectral Image Analysis and Machine Learning Techniques for Crop Disease Detection and Identification: A Review

Originally, the use of hyperspectral images was for military applications, but their use has been extended to precision agriculture. In particular, they are used for activities related to crop classification or disease detection, combining these hyperspectral images with machine learning techniques and algorithms. The study of hyperspectral images has a wide range of wavelengths for observation. These wavelengths allow for monitoring agricultural crops such as cereals, oilseeds, vegetables, and fruits, and other applications. In the ranges of these wavelengths, crop conditions such as maturity index and nutrient status, or the early detection of some diseases that cause losses in crops, can be studied and diagnosed. Therefore, this article proposes a technical review of the main applications of hyperspectral images in agricultural crops and perspectives and challenges that combine artificial intelligence algorithms such as machine learning and deep learning in the classification and detection of diseases of crops such as cereals, oilseeds, fruits, and vegetables. A systematic review of the scientific literature was carried out using a 10-year observation window to determine the evolution of the integration of these technological tools that support sustainable agriculture; among the findings, information on the most documented crops is highlighted, among which are some cereals and citrus fruits due to their high demand and large cultivation areas, as well as information on the main fruits and vegetables that are integrating these technologies. Also, the main artificial intelligence algorithms that are being worked on are summarized and classified, as well as the wavelength ranges for the prediction, disease detection, and analysis of other tasks of physiological characteristics used for sustainable production. This review can be useful as a reference for future research, based mainly on detection, classification, and other tasks in agricultural crops and decision making, to implement the most appropriate artificial intelligence algorithms.

Coarse to superfine: can hyperspectral soil organic carbon models predict higher-resolution information?

Introduction: Modeling and mapping of soil organic carbon concentration and distribution at the pedon scale is a current knowledge gap that can be addressed by laboratory-based hyperspectral imaging and chemometric analysis of soil cores. Despite the advancements in soil organic carbon models based on hyperspectral images, it is not clear how these models will perform upon input with images at higher resolutions than those of their training sets. This study aims to measure the generalizability of a soil organic carbon model based on a test set with higher resolution hyperspectral images than that of its training set.Methods: Organic carbon contents were measured at 10 cm intervals on eight soil cores for use as the training set and at 1 cm intervals on a single core for use as the test set. Three regression models, namely, multilayer perceptron, partial least-squares, and support vector regressions, were trained and tested with the median of each hyperspectral image for each of these intervals as the training and test predictors. Permutation importance analysis was performed to explain the models.Results: The results show that although all three models had the same validation R2 of 0.92 for cross-validation on the 10 cm data, multilayer perceptron regression allowed the best generalization with a test R2 of 0.96 compared to the partial least-squares regression (0.81) and support vector regression (0.86). It was demonstrated that the multilayer perceptron model is more robust to soil surface anomalies and that it predicts soil organic carbon on the test set by learning the spectral features related to soil organic matter chromophore activity in the 950–1,150 nm region along with clay mineralogy derived from peaks at 1,400, 1,900, 2,200, 2,250, and 2,350 nm.Conclusions: This study shows that while the regression models based on hyperspectral images perform well at the 10-cm-resolution cross validation, multilayer perceptron regression shows superior generalization and robustness for a higher 1-cm-resolution test set without much loss of prediction power.

Systematic analysis of hyperspectral imaging and intelligent sensor systems in multiscale agriculture

This article delves into the systematic analysis of Hyperspectral Imaging Technology (HSI) and Intelligent Sensor Systems in the context of multiscale agriculture, showcasing their critical role in enhancing efficiency and sustainability in agricultural production amid the challenges posed by global population growth. It highlights the pressing need to optimize agricultural processes through advanced technologies to tackle issues such as resource scarcity and environmental pollution. By presenting case studies, the article illustrates the effective integration of HSI and intelligent sensors in key agricultural processessoil analysis, crop monitoring, and pest detectionunderscoring their significance in advancing precision agriculture. The discussion extends to the potentials of data fusion and decision support systems in elevating crop yield and quality. Concluding, the paper emphasizes that despite facing hurdles like technical barriers and maintenance costs, the application of these technologies not only boosts production efficiency and precision but also contributes to agricultural sustainability, underlining the importance of continued research and innovation for a more sustainable and efficient agricultural future.

A pipeline for processing hyperspectral images, with a case of melanin-containing barley grains as an example.

Analysis of hyperspectral images is of great interest in plant studies. Nowadays, this analysis is used more and more widely, so the development of hyperspectral image processing methods is an urgent task. This paper presents a hyperspectral image processing pipeline that includes: preprocessing, basic statistical analysis, visualization of a multichannel hyperspectral image, and solving classification and clustering problems using machine learning methods. The current version of the package implements the following methods: construction of a confidence interval of an arbitrary level for the difference of sample averages; verification of the similarity of intensity distributions of spectral lines for two sets of hyperspectral images on the basis of the Mann-Whitney U-criterion and Pearson's criterion of agreement; visualization in two-dimensional space using dimensionality reduction methods PCA, ISOMAP and UMAP; classification using linear or ridge regression, random forest and catboost; clustering of samples using the EM-algorithm. The software pipeline is implemented in Python using the Pandas, NumPy, OpenCV, SciPy, Sklearn, Umap, CatBoost and Plotly libraries. The source code is available at: https://github.com/igor2704/Hyperspectral_images. The pipeline was applied to identify melanin pigment in the shell of barley grains based on hyperspectral data. Visualization based on PCA, UMAP and ISOMAP methods, as well as the use of clustering algorithms, showed that a linear separation of grain samples with and without pigmentation could be performed with high accuracy based on hyperspectral data. The analysis revealed statistically significant differences in the distribution of median intensities for samples of images of grains with and without pigmentation. Thus, it was demonstrated that hyperspectral images can be used to determine the presence or absence of melanin in barley grains with great accuracy. The flexible and convenient tool created in this work will significantly increase the efficiency of hyperspectral image analysis.

Biomass Estimation of Milk Vetch Using UAV Hyperspectral Imagery and Machine Learning

Milk vetch (Astragalus sinicus L.) is a winter-growing plant that can enhance soil fertility and provide essential nutrients for subsequent season crops. The fertilizing capacity of milk vetch is closely related to its above-ground biomass. Compared to the manual measurement methods of milk vetch biomass, remote sensing-based estimation methods have the advantages of rapid, noninvasive, and large-scale measurement. However, few studies have been conducted on remote sensing-based estimation of milk vetch biomass. To address this shortcoming, this study proposes combining unmanned aerial vehicle (UAV)-based hyperspectral imagery and machine learning algorithms for accurate estimation of milk vetch biomass. Through the analysis of hyperspectral images and feature selection based on the Pearson correlation and principal component analysis, vegetation indices (VIs), including near-infrared reflectance (NIR), red-edge spectral transform index (RE), and difference vegetation index (DVI), are selected as estimation metrics of the model development process. Four machine learning methods, including random forest (RF), multiple linear regression (MLR), deep neural network (DNN), and support vector machine (SVM), are used to construct the biomass models. The results show that the RF estimation model exhibits the highest coefficient of determination (R2) of 0.950 and the lowest relative root-mean-squared error (RRMSE) of 14.86% among all the models. Notably, the DNN model demonstrates promising performance on the test set, with the R2 and RRMSE values slightly superior and inferior to those of the RF, respectively. The proposed method based on UAV imagery and machine learning can provide an accurate and reliable large-scale estimation of milk vetch biomass.

Is Endmember Extraction a Critical Step in the Analysis of Hyperspectral Images in Mining Environments?

Is Endmember Extraction a Critical Step in the Analysis of Hyperspectral Images in Mining Environments?

Non-destructive monitoring of qualitative properties of salted cabbage using hyperspectral image analysis

The feasibility of using VIS-NIR and SWIR hyperspectral imaging (HSI) to determine the salinity, soluble solids, and water content in salted kimchi cabbages during the salting process was assessed. Hyperspectral images of kimchi cabbages acquired at different salt concentrations and periods of the salting process were developed as prediction and discriminant models for the qualitative properties. Principal component analysis showed that the distribution according to the spectral characteristics of kimchi cabbages could be grouped, and data reduction for optimal model developing was attempted based on the key wavelengths selected in the loading plot. The optimal partial least squares regression models for the prediction of salinity and soluble solids had best performance by achieving R2p values of over 0.86 and 0.90 in the VIS-NIR and SWIR regions, respectively. The accuracy and specificity of the optimal PLS-DA model for salinity level have improved efficiency to over 0.93. Visualization of the spectrum information in each pixel of the hyperspectral image using the PCA model displayed the salinity level in kimchi cabbages under different salting conditions. The prediction models were sufficiently accurate to consider HSI as a useful tool for controlling and optimizing the salting process.

Advancing hyperspectral image classification with dual branch networks and informative feature extraction

ABSTRACT Hyperspectral imaging is increasingly important in academia and various professions, facing challenges like redundant features, inter-class correlations, and the curse of dimensionality. Principal Component Analysis and its variants, such as Sparse-PCA and Segmented-PCA, reduce the dimensionality of hyperspectral data but interpreting PCA results is complex. Our SPCA-mRMR technique integrates Sparse-PCA with a greedy feature selection method, mRMR. This, combined with a Dual Branch CNN model, improves hyperspectral image analysis, especially with noisy or limited data. Optimization reduces computational costs and enhances classification accuracy. Evaluations show our method’s efficiency, using fewer variables without compromising accuracy, crucial for advancing HSI applications.