Search Results (1,016)

The pH value of maize silage can accurately reflect its quality. In this study, a colorimetric sensor array (CSA) combined with hyperspectral imaging (HSI) was used to predict the pH value of maize silage during secondary fermentation. Seventeen color-sensitive dyes were used to construct the CSA, which was subsequently applied to capture the volatile odor profiles of maize silage samples. Hyperspectral images of the color-sensitive dyes on the CSA were acquired using the HSI technique. Different algorithms were used to preprocess the raw spectral data of each dye, and a partial least squares regression (PLSR) model was built for each dye separately. Subsequently, the adaptive bacterial foraging optimization (ABFO) algorithm was employed to identify three color-sensitive dyes that demonstrated heightened sensitivity to pH variations in maize silage. This study further compared the capabilities of individual dyes, as well as their combinations, in predicting the pH value of maize silage. Additionally, a novel feature wavelength extraction method based on the ABFO algorithm was proposed, which was then compared with two traditional feature extraction algorithms. These methods were combined with PLSR and backpropagation neural network (BPNN) algorithms to construct a quantitative prediction model for the pH value of maize silage. The results show that the quantitative prediction model constructed based on three dyes was more accurate than that constructed based on an individual dye. Among them, the ABFO-BPNN model constructed on the basis of combined dyes had the best prediction performance, with prediction correlation coefficient ($R_P^2$), root mean square error of the prediction set (RMSEP), and ratio of performance deviation (RPD) values of 0.9348, 0.3976, and 3.9695, respectively. The aim of this study was to develop a reliable evaluation model to achieve fast and accurate predictions of silage pH. Full article

To achieve large-scale stitching of the hyperspectral remote sensing images obtained by unmanned aerial vehicles (UAVs) equipped with an acousto-optic tunable filter spectrometer, this study proposes a method based on a feature fusion strategy and a seam-finding strategy using hyperspectral image classification. In the feature extraction stage, SuperPoint deep features from images in different spectral segments of the data cube were extracted and fused. The feature depth matcher, LightGlue, was employed for feature matching. During the data cube fusion stage, unsupervised K-means spectral classification was performed separately on the two hyperspectral data cubes. Subsequently, grayscale transformations were applied to the classified images. A dynamic programming method, based on a grayscale loss function, was then used to identify seams in the transformed images. Finally, the identified splicing seam was applied across all bands to produce a unified hyperspectral data cube. The proposed method was applied to hyperspectral data cubes acquired at specific waypoints by UAVs using an acousto-optic tunable filter spectral imager. Experimental results demonstrated that the proposed method outperformed both single-spectral-segment feature extraction methods and stitching methods that rely on seam identification from a single spectral segment. The improvement was evident in both the spatial and spectral dimensions. Full article

In recent years, convolutional neural network (CNN)-based and transformer-based approaches have made strides in improving the performance of hyperspectral image (HSI) classification tasks. However, misclassifications are unavoidable in the aforementioned methods, with a considerable number of these issues stemming from the overlapping embedding spaces among different classes. This overlap results in samples being allocated to adjacent categories, thus leading to inaccurate classifications. To mitigate these misclassification issues, we propose a novel discrete vector representation (DVR) strategy for enhancing the performance of HSI classifiers. DVR establishes a discrete vector quantification mechanism to capture and store distinct category representations in the codebook between the encoder and classification head. Specifically, DVR comprises three components: the Adaptive Module (AM), Discrete Vector Constraints Module (DVCM), and auxiliary classifier (AC). The AM aligns features derived from the backbone to the embedding space of the codebook. The DVCM employs category representations from the codebook to constrain encoded features for a rational feature distribution of distinct categories. To further enhance accuracy, the AC correlates discrete vectors with category information obtained from labels by penalizing these vectors and propagating gradients to the encoder. It is worth noting that DVR can be seamlessly integrated into HSI classifiers with diverse architectures to enhance their performance. Numerous experiments on four HSI benchmarks demonstrate that our DVR scheme improves the classifiers’ performance in terms of both quantitative metrics and visual quality of classification maps. We believe DVR can be applied to more models in the future to enhance their performance and provide inspiration for tasks such as sea ice detection and algal bloom prediction in the marine domain. Full article

Early detection of early-stage esophageal cancer (ECA) is crucial for timely intervention and improved treatment outcomes. Hyperspectral imaging (HSI) and artificial intelligence (AI) technologies offer promising avenues for enhancing diagnostic accuracy in this context. This study utilized a dataset comprising 3984 white light images (WLIs) and 3666 narrow-band images (NBIs). We employed the Yolov5 model, a state-of-the-art object detection algorithm, to predict early ECA based on the provided images. The dataset was divided into two subsets: RGB-WLIs and NBIs, and four distinct models were trained using these datasets. The experimental results revealed that the prediction performance of the training model was notably enhanced when using HSI compared to general NBI training. The HSI training model demonstrated an 8% improvement in accuracy, along with a 5–8% enhancement in precision and recall measures. Notably, the model trained with WLIs exhibited the most significant improvement. Integration of HSI with AI technologies improves the prediction performance for early ECA detection. This study underscores the potential of deep learning identification models to aid in medical detection research. Integrating these models with endoscopic diagnostic systems in healthcare settings could offer faster and more accurate results, thereby improving overall detection performance. Full article

Band selection is an effective way to reduce redundant information, while preserving the physical properties of hyperspectral images (HSI). However, most band selection methods merely consider the relevance and separability between pairs of bands and ignore those for different ground objects. To solve these issues, we propose a Unique Pixel extraction and Adaptive Neighbor Clustering (UPANC) band selection method in this theoretical study. First, in consideration of the characteristics of HSI data and tasks, unique pixels are obtained with a low-rank representation, where the importance of bands is analyzed from both spectral and spatial perspectives. Second, an adaptive neighbor clustering method is designed based on the unique pixels, which groups bands into several clusters through optimizing the graph structure under label smoothness. With support vector machines (SVM) as the classifier, the UPANC method achieved good performance, where the overall accuracy scores were 89.05%, 82.62%, and 92.07% on the Houston, IndianPines, and Pavia University datasets, respectively. The experimental results illustrated the advantages of the UPANC method, which could select optimal bands to enhance the performance in land cover observation. Full article

The fruit supply chain requires simple, non-destructive, and fast tools for quality evaluation both in the field and during the post-harvest phase. In this study, a portable visible and near-infrared (Vis/NIR) spectrophotometer and a portable Vis/NIR hyperspectral imaging (HSI) device were tested to highlight genetic differences among apricot cultivars, and to develop multi-cultivar and multi-year models for the most important marketable attributes (total soluble solids, TSS; titratable acidity, TA; dry matter, DM). To do this, the fruits of seventeen cultivars from a single experimental orchard harvested at the commercial maturity stage were considered. Spectral data emphasized genetic similarities and differences among the cultivars, capturing changes in the pigment content and macro components of the apricot samples. In recent years, machine learning techniques, such as artificial neural networks (ANNs), have been successfully applied to more efficiently extract valuable information from spectral data and to accurately predict quality traits. In this study, prediction models were developed based on a multilayer perceptron artificial neural network (ANN-MLP) combined with the Levenberg–Marquardt learning algorithm. Regarding the Vis/NIR spectrophotometer dataset, good predictive performances were achieved for TSS (R² = 0.855) and DM (R² = 0.857), while the performance for TA was unsatisfactory (R² = 0.681). In contrast, the optimal predictive ability was found for models of the HSI dataset (TSS: R² = 0.904; DM: R² = 0.918, TA: R² = 0.811), as confirmed by external validation. Moreover, the ANN allowed us to identify the most predictive input spectral regions for each model. The results showed the potential of Vis/NIR spectroscopy as an alternative to traditional destructive methods to monitor the qualitative traits of apricot fruits, reducing the time and costs of analyses. Full article

Hyperspectral imaging (HSI) technology, which offers both spatial and spectral information, holds significant potential for enhancing diagnostic performance during endoscopy and other medical procedures. However, quantitative evaluation of HSI cameras is challenging due to various influencing factors (e.g., light sources, working distance, and illumination angle) that can alter the reflectance spectra of the same target as these factors vary. Towards robust, universal test methods, we evaluated several data normalization methods aimed at minimizing the impact of these factors. Using a high-resolution HSI camera, we measured the reflectance spectra of diffuse reflectance targets illuminated by two different light sources. These spectra, along with the reference spectra from the target manufacturer, were normalized with nine different methods (e.g., area under the curve, standard normal variate, and centering power methods), followed by a uniform scaling step. We then compared the measured spectra to the reference to evaluate the capability of each normalization method in ensuring a consistent, standardized performance evaluation. Our results demonstrate that normalization can mitigate the impact of some factors during HSI camera evaluation, with performance varying across methods. Generally, noisy spectra pose challenges for normalization methods that rely on limited reflectance values, while methods based on reflectance values across the entire spectrum (such as standard normal variate) perform better. The findings also suggest that absolute reflectance spectral measurements may be less effective for clinical diagnostics, whereas normalized spectral measurements are likely more appropriate. These findings provide a foundation for standardized performance testing of HSI-based medical devices, promoting the adoption of high-quality HSI technology for critical applications such as early cancer detection. Full article

Pork adulteration detection in beef is important due to health, economic, and religious concerns. This study explored the use of a Shortwave Near Infrared–Hyperspectral Imaging (SWNIR–HSI) system which captured spectral data across 894–2504 nm to detect adulteration of pork in beef. In this study, minced pork in various concentrations ranging from 0–50% (w/w) were added to pure minced beef. Spectra obtained from the SWNIR–HSI were used to develop a partial least square regression (PLSR) model. The study compared the PLSR results between full wavelengths (variables) and selected wavelengths obtained via the variable importance in projection (VIP) method. The best results from the full-wavelength PLSR model yielded a prediction accuracy (R²P) of 0.940 and a standard error of prediction (SEP) of 4.633%, while using VIP-selected wavelengths improved performance, with R²P of 0.955 and SEP of 3.811%. The study demonstrates the potency of SWNIR–HIS, particularly with selected wavelengths, as an effective and nondestructive tool for accurately predicting pork adulteration levels in beef. Full article

Hyperspectral image (HSI) and light detection and ranging (LiDAR) data joint classification has been applied in the field of ground category recognition. However, existing methods still perform poorly in extracting high-dimensional features and elevation information, resulting in insufficient data classification accuracy. To address this challenge, we propose a novel and efficient Calibration-Enhanced Multi-Awareness Network (CEMA-Net), which exploits the joint spectral–spatial–elevation features in depth to realize the accurate identification of land cover categories. Specifically, we propose a novel multi-way feature retention (MFR) module that explores deep spectral–spatial–elevation semantic information in the data through multiple paths. In addition, we propose spectral–spatial-aware enhancement (SAE) and elevation-aware enhancement (EAE) modules, which effectively enhance the awareness of ground objects that are sensitive to spectral and elevation information. Furthermore, to address the significant representation disparities and spatial misalignments between multi-source features, we propose a spectral–spatial–elevation feature calibration fusion (SFCF) module to efficiently integrate complementary characteristics from heterogeneous features. It incorporates two key advantages: (1) efficient learning of discriminative features from multi-source data, and (2) adaptive calibration of spatial differences. Comparative experimental results on the MUUFL, Trento, and Augsburg datasets demonstrate that CEMA-Net outperforms existing state-of-the-art methods, achieving superior classification accuracy with better feature map precision and minimal noise. Full article

Detecting binary changes in co-registered bitemporal hyperspectral images (HSIs) using deep learning methods is challenging due to the high dimensionality of spectral data and significant variations between images. To address this challenge, previous approaches often used dimensionality reduction methods separately from the change detection network, leading to less accurate results. In this study, we propose an end-to-end fully connected adversarial network (EFC-AdvNet) for binary change detection, which efficiently reduces the dimensionality of bitemporal HSIs and simultaneously detects changes between them. This is accomplished by extracting critical spectral features at the pixel level through a self-spectral reconstruction (SSR) module working in conjunction with an adversarial change detection (Adv-CD) module to effectively delineate changes between bitemporal HSIs. The SSR module employs a fully connected autoencoder for hyperspectral dimensionality reduction and spectral feature extraction. By integrating the encoder segment of the SSR module with the change detection network of the Adv-CD module, we create a generator that directly produces highly accurate change maps. This joint learning approach enhances both feature extraction and change detection capabilities. The proposed network is trained using a comprehensive loss function derived from the concurrent learning of the SSR and Adv-CD modules, establishing EFC-AdvNet as a robust end-to-end network for hyperspectral binary change detection. Experimental evaluations of EFC-AdvNet on three public hyperspectral datasets demonstrate that joint learning between the SSR and Adv-CD modules improves the overall accuracy (OA) by 5.44%, 10.43%, and 7.52% for the Farmland, Hermiston, and River datasets, respectively, compared with the separate learning approach. Full article

The bioactive components of chrysanthemum tea are an essential indicator in evaluating its nutritive and commercial values. Combining hyperspectral imaging (HSI) with key wavelength selection and pattern recognition methods, this study developed a novel approach to estimating the content of bioactive components in chrysanthemums, including the total flavonoids (TFs) and chlorogenic acids (TCAs). To determine the informative wavelengths of hyperspectral images, we introduced a variable similarity regularization term into particle swarm optimization (denoted as VSPSO), which can focus on improving the combinatorial performance of key wavelengths and filtering out the features with higher collinearity simultaneously. Moreover, considering the underlying relevance of the phytochemical content and the exterior morphology characteristics, the spatial image features were also extracted. Finally, an ensemble learning model, LightGBM, was established to estimate the TF and TCA contents using the fused features. Experimental results indicated that the proposed VSPSO achieved a superior accuracy, with R² scores of 0.9280 and 0.8882 for TF and TCA prediction. Furthermore, after the involvement of spatial image information, the fused spectral–spatial features achieved the optimal model accuracy on LightGBM. The R² scores reached 0.9541 and 0.9137, increasing by 0.0308–0.1404 and 0.0181–0.1066 in comparison with classical wavelength-related methods and models. Overall, our research provides a novel method for estimating the bioactive components in chrysanthemum tea accurately and efficiently. These discoveries revealed the potential effectiveness for constructing feature fusion in HSI-based practical applications, such as nutritive value evaluation and heavy metal pollution detection, which will also facilitate the development of quality detection in the food industry. Full article

Anxi Tieguanyin belongs to the oolong tea category and is one of the top ten most famous teas in China. In this study, hyperspectral imaging (HSI) technology was combined with chemometric methods to achieve the rapid determination of free amino acid and tea polyphenol contents in Tieguanyin tea. Here, the spectral data of Tieguanyin tea samples of four quality grades were obtained via visible near-infrared hyperspectroscopy in the range of 400–1000 nm, and the free amino acid and tea polyphenol contents of the samples were detected. First derivative (1D), normalization (Nor), and Savitzky–Golay (SG) smoothing were utilized to preprocess the original spectrum. The characteristic wavelengths were extracted via principal component analysis (PCA), competitive adaptive reweighted sampling (CARS), and the successive projection algorithm (SPA). The contents of free amino acid and tea polyphenol in Tieguanyin tea were predicted by the back propagation (BP) neural network, partial least squares regression (PLSR), random forest (RF), and support vector machine (SVM). The results revealed that the free amino acid content of the clear-flavoured Tieguanyin was greater than that of the strong-flavoured type, that the tea polyphenol content of the strong-flavoured Tieguanyin was greater than that of the clear-flavoured type, and that the content of the first-grade product was greater than that of the second-grade product. The 1D preprocessing improved the resolution and sensitivity of the spectra. When using CARS, the number of wavelengths for free amino acids and tea polyphenols was reduced to 50 and 70, respectively. The combination of 1D and CARS is conducive to improving the accuracy of late modelling. The 1D-CARS-RF model had the highest accuracy in predicting the free amino acid (R_P² = 0.940, RMSEP = 0.032, and RPD = 4.446) and tea polyphenol contents (R_P² = 0.938, RMSEP = 0.334, and RPD = 4.474). The use of hyperspectral imaging combined with multiple algorithms can be used to achieve the fast and non-destructive prediction of free amino acid and tea polyphenol contents in Tieguanyin tea. Full article

Recently, there has been a surge in the adoption of deep learning (DL) techniques, especially convolutional neural networks (CNNs), to perform hyperspectral image (HSI) classification. Although deep learners have been shown to achieve impressive performance in HSI classification, they are known to be extremely sensitive to even slight perturbations to their inputs and models. When applied in safety-critical applications, it is crucial to know how robust they really are against perturbations. However, there is still limited tool support for DL testing in terms of their robustness, nor are the existing RGB testing approaches able to address the HSI-specific challenges. In this paper, we propose a mutation analysis framework specialized for DL models trained to classify HSIs, which facilitates a critical evaluation of the robustness of DL-based HSI classifiers. First, we introduce a set of mutation operators to inject faults into the inputs and models to simulate distortions of remote sensing HSI classifiers. By utilizing the mutation testing technique, we implement a novel framework which supports the multidimensional evaluation of individual DL-based classifiers. Finally, a comparative study of the robustness of seven popular CNN-based HSI classifiers (i.e., 3D-CNN, FDSSC, HybridSN, MCNN, FC3DCNN, DWTDENSE, and Tri-CNN) on six HSI datasets is provided. Results show that FDSSC and Tri-CNN achieve higher robustness in the presence of distortions, and FDSSC maintains a relatively stable level of robustness even with few training samples. These empirical findings can be partly explained by the characteristics of the classifiers’ architectures. The results substantiate the efficacy of our evaluation framework in assessing the robustness of HSI classifiers and thus confirm its contribution to the field of remote sensing image classification. Full article

Hyperspectral Imaging (HSI) excels in material identification and capturing spectral details and is widely utilized in various fields, including remote sensing and environmental monitoring. However, in real-world applications, HSI is often affected by Stray Light Interference (SLI), which severely degrades both its spatial and spectral quality, thereby reducing overall image accuracy and usability. Existing hardware solutions are often expensive and add complexity to the system, and despite these efforts, they cannot fully eliminate SLI. Traditional algorithmic methods, on the other hand, struggle to capture the intricate spatial–spectral dependencies needed for effective restoration, particularly in complex noise scenarios. Deep learning methods present a promising alternative because of their flexibility in handling complex data and strong restoration capabilities. To tackle this challenge, we propose MambaHR, a novel State Space Model (SSM) for HSI restoration under SLI. MambaHR incorporates state space modules and channel attention mechanisms, effectively capturing and integrating global and local spatial–spectral dependencies while preserving critical spectral details. Additionally, we constructed a synthetic hyperspectral dataset with SLI by simulating light spots of varying intensities and shapes across spectral channels, thereby realistically replicating the interference observed in real-world conditions. Experimental results demonstrate that MambaHR significantly outperforms existing methods across multiple benchmark HSI datasets, exhibiting superior performance in preserving spectral accuracy and enhancing spatial resolution. This method holds great potential for improving HSI processing applications in fields such as remote sensing and environmental monitoring. Full article

How to effectively extract spectral and spatial information and apply it to hyperspectral image classification (HSIC) has been a hot research topic. In recent years, the transformer-based HSIC models have attracted much interest due to their advantages in long-distance modeling of spatial and spectral features in hyperspectral images (HSIs). However, the transformer-based method suffers from high computational complexity, especially in HSIC tasks that require processing large amounts of data. In addition, the spatial variability inherent in HSIs limits the performance improvement of HSIC. To handle these challenges, a novel Spectral–Spatial Unified Mamba (SSUM) model is proposed, which introduces the State Space Model (SSM) into HSIC tasks to reduce computational complexity and improve model performance. The SSUM model is composed of two branches, i.e., the Spectral Mamba branch and the Spatial Mamba branch, designed to extract the features of HSIs from both spectral and spatial perspectives. Specifically, in the Spectral Mamba branch, a nearest-neighbor spectrum fusion (NSF) strategy is proposed to alleviate the interference caused by the spatial variability (i.e., same object having different spectra). In addition, a novel sub-spectrum scanning (SS) mechanism is proposed, which scans along the sub-spectrum dimension to enhance the model’s perception of subtle spectral details. In the Spatial Mamba branch, a Spatial Mamba (SM) module is designed by combining a 2D Selective Scan Module (SS2D) and Spatial Attention (SA) into a unified network to sufficiently extract the spatial features of HSIs. Finally, the classification results are derived by uniting the output feature of the Spectral Mamba and Spatial Mamba branch, thus improving the comprehensive performance of HSIC. The ablation studies verify the effectiveness of the proposed NSF, SS, and SM. Comparison experiments on four public HSI datasets show the superior of the proposed SSUM. Full article