Search

Biochemistry parameters of vegetation are important indicators of the photosynthetic process and provide a substantial amount of data about the status of ecosystems. Estimation of these parameters are greatly affected by the correlations of spectral bands and the sensitivity of each biochemistry parameter to inversion models. Hence, reducing the spectral dimension and inefficient computation process using an appropriate inversion strategy is significant for biochemistry parameters' estimation. In this work, we used band-selection-based artificial neural networks (ANNs) combined with feature weighting (FW) and principal component analysis (PCA) process to reduce the sensitive spectral correlations and to improve the inversion model predictability for four biochemistry parameters: chlorophyll a and b (Cab), carotenoid (Car), equivalent water thickness (EWT), and leaf mass per area (LMA). We analyzed the model performance by conducting different inversion strategies, including: (1) linking reflectance (R), transmittance (T), and R&T spectral properties in different numbers of band to four biochemistry parameters; (2) simultaneously and then separately inverting them using FW- and PCA-ANNs considering their sensitivity to the ANN model; and (3) choosing a spectral subset from R, T spectrum for EWT, and LMA inversion successively. The results show that: (i) the FW- and PCA-ANN models exhibit efficient improvements by selecting less spectral characteristics; (ii) concurrently inverting EWT and LMA can achieve a satisfactory R 2, while it is inappropriate for Cab and Car whose optimal R 2 are obtained by separately inverting all four biochemicals; (iii) the properties of R, T, and R&T spectra exhibit various performances on parameters inversion. [ABSTRACT FROM AUTHOR]

Owing to significantly improved spectral resolution, a hyperspectral imaging sensor can now uncover many unknown subtle material substances. In many cases, anomalies are usually embedded in the background. To develop a means through which these anomalies may be detected and separated from the background, we propose a spectral–spatial anomaly detection method based on a selected band subset. To be specific, we constrain an unsupervised network by making full use of the underlying physical characteristics which are beneficial to hyperspectral anomaly detection. Based on that, a selection criterion is constructed to adaptively select a subset of bands that essentially contain discriminative and informative features between the anomaly and background in an unsupervised manner. Then, the selected bands are simultaneously inputted into the spatial detector and spectral detector. To overcome the deficiencies of detecting anomalies in only one aspect, an adaptive combination of spatial result and the spectral result is introduced. Finally, a simple and powerful iterative suppression is conducted on the initial detection map to further reduce false alarm rate while ensuring detection capability. Extensive empirical researches performed on eighteen publicly available hyperspectral images (HSIs) of different sizes over different scenes demonstrate that our proposed method can achieve an average detection capability of 0.99564, and the average false alarm rate is one order of magnitude lower than the second one. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Remote Sensing is the property of Editorial Office of Journal of Remote Sensing & Science Publishing Co. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Hyperspectral images (HSIs) can provide discriminative spectral signatures regarding the physical nature of different materials. It is this unique nature that makes HSIs to be of great interest in many fields. However, HSI application faces various challenges due to high dimensionality, redundant information, noisy bands, and insufficient samples. To address these problems, we propose an unsupervised band selection method based on deep latent spectral representation learning, called DLSRL, in this article. It imposes spectral consistency on deep latent space that resolves the issue of insufficient samples and spectral information lost in HSI interpretation. It pursues the low-dimensional optimal representation of the high-dimensional HSIs. In particular, an adaptive mapping relationship is constructed between the deep latent representation and the optimal subset to preserve physical significance optimally. Furthermore, a hierarchical optimization approach is introduced to achieve target detection with the selected subset. To verify the superiority of the proposed method, experiments have been conducted on four data sets captured by different sensors over different scenes. Comparative analyses validate that the proposed method presents superior performance in terms of high detection accuracy and low false alarm rate. [ABSTRACT FROM AUTHOR]

This letter presents a correntropy-based sparse spectral clustering (CSSC) method to select proper bands of a hyperspectral image. The CSSC first constructs an affinity matrix with the correntropy measure which considers the nonlinear characteristics of hyperspectral bands and can suppress effects from noise or outliers in measuring band similarity. The CSSC imposes the sparsity and block diagonal constraint on spectral clustering, which can further improve band clustering performance. Bands are finally selected from each cluster on the connected graph. Experimental results on two widely used hyperspectral images show that the CSSC behaves better than spectral clustering and other several state-of-the-art methods in band selection. [ABSTRACT FROM AUTHOR]

During image classification, it is important to select optimal bands in order to reduce the amount of information while maintaining a considerable accuracy. However, problems exist in the artificial subjective selection of the bands, and as a result, the true accuracies of the classifications are not effectively expressed. This research was conducted using 10 bands of the Landsat-8 fusion data as the information sources. The maximum likelihood classification–recursive feature elimination (MLC-RFE) method and the support vector machine-recursive feature elimination (SVM-RFE) method were used to select the most appropriate bands, and to analyse the classification results of different methods. The results showed that the bands obtained from MLC and SVM were different, with MLC being more sensitive to the change in features compared with SVM. The highest and lowest overall accuracies of MLC were 99.1667% and 92.2312%, respectively (the corresponding Kappa coefficients were 0.9903 and 0.9094). The highest and lowest overall accuracies of SVM were 98.7231% and 86.6398%, respectively (the corresponding Kappa coefficients were 0.9851 and 0.8441). The two classifiers differed greatly as regards the classification accuracies of the optimal and worst band combinations. This indicates that the selection of the participating bands was very important for the image classification, and MLC-RFE is more suitable than SVM-RFE for Landsat-8 image classification. [ABSTRACT FROM AUTHOR]

• A novel hyperspectral band selection network is proposed for seed classification. • Band attention and sparse constraint (SC) maximizes the removal of redundant bands. • A new loss function is defined to solve the gradient update problem caused by SC. • The selected bands carry important spectrochemical information. • This method is also applicable to other hyperspectral data of food and agro-products. The development of a real-time online system for rapid and nondestructive identification of seed varieties can greatly improve production efficiency in modern agriculture. Hyperspectral imaging (HSI) is a powerful tool for seed variety identification. Nevertheless, hyperspectral data are not only high in dimensionality but also contain redundant information, which is very unfriendly to real-time online applications. Selecting a few representative bands from the entire working spectral region can significantly reduce the equipment cost and computational load of HSI. In the field of food and agr-products quality evaluation, Band selection (BS) methods based on chemometrics have been dominant for a long time. Most of these methods, however, fail to take full account of the nonlinearities and global interactions between spectral bands, which may result in the selection of some adjacent bands that still retain more redundant information. In this paper, a novel BS network is proposed, which is composed of sparse band attention module and classification net module. The former is used to generate weight of each band, and sparse constraint is applied to the weights of redundant bands, while the latter is used to achieve high-performance classification with reweighted data. Furthermore, to solve the problem of gradient updating caused by sparse constraint, a auxiliary loss function is defined to assist optimization. Finally, comparative experiments is conducted on our maize seed hyperspectral dataset. The results demonstrate that the presented method selects a subset of informative bands with less redundant information to obtain better classification performance and outperforms several other existing BS methods. [ABSTRACT FROM AUTHOR]

In this paper, a band selection method based on a scalability tree structure multilayer classification label and HSPFiGs is proposed. To better describe the separability of ground objects with a mixed Gaussian distribution, we present an adaptive method to determine the number of subclass extensions, and extend a class of ground objects with mixed a Gaussian distribution to a series of single Gaussian distributions by subclass extension. Then, according to the result of subclass extension, we construct a multilayer classification label with a scalability tree structure. The second layer of the scalability tree is a mixed classification label, and the third layer contains a series of subclass extension labels. Then, the original classification labels of HSPFiGs are replaced by the scalability tree structure multilayer classification label, and the bands of the hyperspectral images are selected in hierarchical order to obtain a mixed optimal band subset and a series of subclasses of extended optimal band subset, which together constitute an optimal band subset family. Finally, the effectiveness of the proposed method is verified by comparing it with existing band selection methods. Experimental results based on datasets from Pavia University, Salinas, KSC and Botswana show that the method selects fewer bands and has higher overall accuracy, average accuracy and kappa coefficient than those of other methods. [ABSTRACT FROM AUTHOR]

[Display omitted] • HSI can be used for identification of vegetation under natural gas leakage stress. • A band selection method was proposed to extract stressed vegetation features. • Saliency map analysis was used in the proposed band selection method. • A stress range extraction method based on selected bands was developed. When microleakage occurs in underground natural gas pipelines, the surface gas concentration may not reach detectable thresholds. Hyperspectral remote sensing can monitor indirectly through the spectral changes of surface vegetation. However, hyperspectral data often have band redundancy, and existing band selection methods lack consideration for vegetation-specific spectral response characteristics and interpretability. In this study, an interval band selection method based on class saliency map (IBS-CSA) was proposed to extract characteristic bands for identifying vegetation under natural gas microleakage stress. Firstly, a field experiment was designed to investigate the impact of natural gas stress on grass, bean, and wheat. Then, an one-dimensional convolutional neural network was constructed to obtain class saliency maps for different stress levels. Based on these maps, a band importance factor was created, and characteristic bands were extracted by applying the delineated spectral intervals. Finally, the performance of the IBS-CSA method was validated through statistical analysis and comparative modeling. The results indicate that when the proportion of selected bands reaches 10% (equivalent to 10 bands), the characteristic bands selected by the IBS-CSA method perform excellent separability, with JM distances larger than 1.8 between healthy and stressed vegetation. Furthermore, compared to other band selection methods, the IBS-CSA method performs superior accuracy and stability across all classification models, with overall accuracies of 91.40%, 96.67%, and 96.67% on the grass, bean, and wheat test datasets, respectively. This study demonstrates the potential of IBS-CSA in extracting vegetation spectral features under natural gas microleakage stress, providing unique insights into the extraction of characteristic wavelengths of stressed vegetation. [ABSTRACT FROM AUTHOR]

Prompt monitoring of maize dwarf mosaic virus (MDMV) is critical for the prevention and control of disease and to ensure high crop yield and quality. Here, we first analyzed the spectral differences between MDMV-infected red leaves and healthy leaves and constructed a sensitive index (SI) for measurements. Next, based on the characteristic bands (Rλ) associated with leaf anthocyanins (Anth), we determined vegetation indices (VIs) commonly used in plant physiological and biochemical parameter inversion and established a vegetation index (VIc) by utilizing the combination of two arbitrary bands following the construction principles of NDVI, DVI, RVI, and SAVI. Furthermore, we developed classification models based on linear discriminant analysis (LDA) and support vector machine (SVM) in order to distinguish the red leaves from healthy leaves. Finally, we performed UR, MLR, PLSR, PCR, and SVM simulations on Anth based on Rλ, VIs, VIc, and Rλ + VIs + VIc and indirectly estimated the severity of MDMV infection based on the relationship between the reflection spectra and Anth. Distinct from those of the normal leaves, the spectra of red leaves showed strong reflectance characteristics at 640 nm, and SI increased with increasing Anth. Moreover, the accuracy of the two VIc-based classification models was 100%, which is significantly higher than that of the VIs and Rλ-based models. Among the Anth regression models, the accuracy of the MLR model based on Rλ + VIs + VIc was the highest (R2c = 0.85; R2v = 0.74). The developed models could accurately identify MDMV and estimate the severity of its infection, laying the theoretical foundation for large-scale remote sensing-based monitoring of this virus in the future.

The detection of rice leaf folder (RLF) infestation usually depends on manual monitoring, and early infestations cannot be detected visually. To improve detection accuracy and reduce human error, we use push-broom hyperspectral sensors to scan rice images and use machine learning and deep neural learning methods to detect RLF-infested rice leaves. Different from traditional image processing methods, hyperspectral imaging data analysis is based on pixel-based classification and target recognition. Since the spectral information itself is a feature and can be considered a vector, deep learning neural networks do not need to use convolutional neural networks to extract features. To correctly detect the spectral image of rice leaves infested by RLF, we use the constrained energy minimization (CEM) method to suppress the background noise of the spectral image. A band selection method was utilized to reduce the computational energy consumption of using the full-band process, and six bands were selected as candidate bands. The following method is the band expansion process (BEP) method, which is utilized to expand the vector length to improve the problem of compressed spectral information for band selection. We use CEM and deep neural networks to detect defects in the spectral images of infected rice leaves and compare the performance of each in the full frequency band, frequency band selection, and frequency BEP. A total of 339 hyperspectral images were collected in this study; the results showed that six bands were sufficient for detecting early infestations of RLF, with a detection accuracy of 98% and a Dice similarity coefficient of 0.8, which provides advantages of commercialization of this field.

Hyperspectral imaging systems are becoming widely used due to their increasing accessibility and their ability to provide detailed spectral responses based on hundreds of spectral bands. However, the resulting hyperspectral images (HSIs) come at the cost of increased storage requirements, increased computational time to process, and highly redundant data. Thus, dimensionality reduction techniques are necessary to decrease the number of spectral bands while retaining the most useful information. Our contribution is two-fold: First, we propose a filter-based method called interband redundancy analysis (IBRA) based on a collinearity analysis between a band and its neighbors. This analysis helps to remove redundant bands and dramatically reduces the search space. Second, we apply a wrapper-based approach called greedy spectral selection (GSS) to the results of IBRA to select bands based on their information entropy values and train a compact convolutional neural network to evaluate the performance of the current selection. We also propose a feature extraction framework that consists of two main steps: first, it reduces the total number of bands using IBRA; then, it can use any feature extraction method to obtain the desired number of feature channels. We present classification results obtained from our methods and compare them to other dimensionality reduction methods on three hyperspectral image datasets. Additionally, we used the original hyperspectral data cube to simulate the process of using actual filters in a multispectral imager.

Band selection has imposed great impacts on hyperspectral image processing in recent years. Unfortunately, few existing methods are proposed for hyperspectral underwater target detection (HUTD). In this paper, a novel unsupervised band selection method is proposed for HUTD by embedding the bathymetric model into the band selection process. Considering the dependence between targets and background, a bathymetric latent spectral representation learning scheme is designed to investigate a physically meaningful subspace where the desired targets are the most distinguishable from the background. This calculated subspace is exploited as a reference to select out desired bands based on the spectral distance metric. Then, we propose an iteration-based band subset generation strategy for the sake of promoting the diversity of the band selection results and taking full advantage of the ample spectral information. Moreover, a representative band selection approach based on sparse representation is also conducted to eliminate the redundant information among adjacent bands. The band selection result is eventually achievable by connecting the representative bands of all the band subsets. Qualitative and quantitative evaluations demonstrate the effectiveness and efficiency of the proposed method in comparison with state-of-the-art band selection methods.

Images captured under bad weather conditions (e.g., fog, haze, mist, dust, etc.), suffer from poor contrast and visibility, and color distortions. The severity of this degradation depends on the distance, the density of the atmospheric particles and the wavelength. We analyzed eight single image dehazing algorithms representative of different strategies and originally developed for RGB images, over a database of hazy spectral images in the visible range. We carried out a brute force search to find the optimum three wavelengths according to a new combined image quality metric. The optimal triplet of monochromatic bands depends on the dehazing algorithm used and, in most cases, the different bands are quite close to each other. According to our proposed combined metric, the best method is the artificial multiple exposure image fusion (AMEF). If all wavelengths within the range 450–720 nm are used to build a sRGB renderization of the imagaes, the two best-performing methods are AMEF and the contrast limited adaptive histogram equalization (CLAHE), with very similar quality of the dehazed images. Our results show that the performance of the algorithms critically depends on the signal balance and the information present in the three channels of the input image. The capture time can be considerably shortened, and the capture device simplified by using a triplet of bands instead of the full wavelength range for dehazing purposes, although the selection of the bands must be performed specifically for a given algorithm.

Hyperspectral image (HSI) consists of hundreds of continuous narrow bands with high redundancy, resulting in the curse of dimensionality and an increased computation complexity in HSI classification. Many clustering-based band selection approaches have been proposed to deal with such a problem. However, a few of them consider the spectral and spatial relationship simultaneously. In this letter, we proposed a novel clustering-based band selection approach using deep subspace clustering (DSC). The proposed approach combines the subspace clustering task into a convolutional autoencoder by treating it as a self-expressive layer, enabling it to be trained end to end. The resulting network can fully extract the interaction of spectral bands based on using spatial information and nonlinear feature transformation. We compared the results of the proposed method with existing band selection methods for three widely used HSI data sets, showing that the proposed method is able to accurately select an informative band subset with remarkable classification accuracy. [ABSTRACT FROM AUTHOR]

• VarBWFastMI allows fast calculation of pairwise mutual information of HSI datasets. • Mutual information and entropy are used to evaluate the MIMR criterion. • A new DGSA with fewer parameters is used to generate band subsets. • Spatial-spectral fusion based neighbourhood concept for band subsets is established. Band selection plays an important role in hyperspectral data analysis as it can improve the performance of data analysis without losing information about the constitution of the underlying data. We propose a MIMR-DGSA algorithm for band selection by following the Maximum-Information-Minimum-Redundancy (MIMR) criterion that maximises the information carried by individual features of a subset and minimises redundant information between them. Subsets are generated with a modified Discrete Gravitational Search Algorithm (DGSA) where we definine a neighbourhood concept for feature subsets. A fast algorithm for pairwise mutual information calculation that incorporates variable bandwidths of hyperspectral bands called VarBWFastMI is also developed. Classification results on three hyperspectral remote sensing datasets show that the proposed MIMR-DGSA performs similar to the original MIMR with Clonal Selection Algorithm (CSA) but is computationally more efficient and easier to handle as it has fewer parameters for tuning. [ABSTRACT FROM AUTHOR]

Abundant spectral information of hyperspectral images (HSIs) has shown an obvious advantage in improving the performance of classification in the remote sensing domain. However, this is paid by the expensive consumption on the computation, transmission, as well as storage of HSIs. To address this problem, we propose to learn the discriminative compact representation for HSIs classification, which not only greatly reduces the data redundancy in the image but also preserves the discriminative information required for pixelwise classification in HSIs. To this end, we present a multi-task deep learning framework, which integrates HSIs autoencoding and classification into a two-branch deep neural network for jointly learning. In the network, we employ an encoder block to learn the compact representation of the input HSI via compression in the spectral domain. Being fed with the compact representation, the autoencoding branch then employs a decoder block to reconstruct the input HSI, while the classification branch utilizes a classifier block to predict the label for each pixel. Through end-to-end joint learning, the compact representation is not only informative enough to accurately reconstruct the original HSI but also discriminative enough to appropriately label each pixel with the trained classier. Sufficient experimental results on four HSIs classification data sets demonstrate the effectiveness of the proposed framework. [ABSTRACT FROM AUTHOR]

The heavy metal concentration of soil samples often exhibits a skewed distribution, especially for soil samples from mining areas with an extremely high concentration of heavy metals. In this study, to model soil contamination in mining areas using reflectance spectroscopy, the skewed distribution was corrected and heavy metal concentration estimated. In total, 46 soil samples from a mining area, along with corresponding field soil spectra, were collected. Laboratory spectra of the soil samples and the field spectra were used to estimate copper (Cu) concentration in the mining area. A logarithmic transformation was used to correct the skewed distribution, and based on the sorption of Cu on spectrally active soil constituents, the spectral bands associated with iron oxides were extracted from the visible and near-infrared (VNIR) region and used in the estimation. A genetic algorithm was adopted for band selection, and partial least squares regression was used to calibrate the estimation model. After transforming the distribution of Cu concentration, the accuracies (R2) of the estimation of Cu concentration using laboratory and field spectra separately were 0.94 and 0.96. The results indicate that Cu concentration in the mining area can be estimated using reflectance spectroscopy following correction of skewed distribution. Image 1 • Skewed distribution hinders the estimation of heavy metal concentration in soil. • The natural logarithm transformation corrects the highly skewed distribution. • A selected spectral subset is beneficial to the estimation of Cu concentration. • Spectroscopic method is feasible to investigate soil heavy metal concentration. Capsule : Reflectance spectroscopy of soil could be an alternative to investigate heavy metal concentration in mining areas. [ABSTRACT FROM AUTHOR]

This paper presents a new method to perform unsupervised band selection (UBS) with hyperspectral data. The method provides a probabilistic clustering approach. The band images are clustered in the image space by computing their posterior class probability. Then, for each cluster, the band exhibiting the highest probability of belonging to it is selected as cluster exemplar. More particularly, the proposed method falls into information-maximization clustering methods, where the posterior class probability is modeled and the parameters of the models are derived by maximizing the information between the data and the unknown cluster labels. In this context, we propose a new image representation for hyperspectral images, based on the first- and second-order statistics of multiple image features. We refer to this representation as multiple-feature local statistical descriptors (MLSD). The descriptors are computed with respect to regular grids, and a special pixel selection procedure reduces the number of samples within each block of the grid. A kernel-based model that embeds the MLSD is then proposed for the posterior class probability. The model is finally optimized according to an information-maximization criterion. We conduct several experiments to determine the best parameters for the proposed approach and compare the latter with other state-of-the-art UBS methods. Quantitative evaluations show that, by employing our band selection method, higher performance in terms of classification accuracy and endmember extraction can be achieved in comparison with the state of the art. [ABSTRACT FROM AUTHOR]

Spectral indexes (SI) are widely used for land cover characterization and also in several physical models for the study of land surface processes. For example, the normalized differenced vegetation index (NDVI) is used in the characterization of soil moisture along with shortwave infrared reflectance. However, for hyperspectral imagery (HSI) comprising many bands within a single spectrum, it is significant to identify the optimal bands for the development of SI. In this paper, we study the potential of band selection in specific bandwidths for the determination of SI. The proposed methodology includes two strategies for development of SI: direct SI determined by the best band within specific spectrums and fused SI determined by fusion of two best bands within specific spectrums. The experiments are conducted using three datasets, two corresponding to snow-covered areas, studied using the normalized differenced snow index (NDSI) and one comprising the agricultural area, studied using NDVI. The developed SI are evaluated through a comparison with the supervised classification maps from the corresponding HSI. A kappa coefficient of 0.693, 0.726 and 0.803 was observed between the results obtained from histogram slicing of SI with respect to the classification maps for the three datasets, respectively. [ABSTRACT FROM AUTHOR]

Hyperspectral band selection algorithms can save the computational costs during image restoration and analysis. This paper proposes a novel unsupervised band selection method, based on dynamic local cluster ratio (DLCR). The contributions of this paper can be summarized as follows. First, the similarity matrix is calculated in a novel way. Conventional approaches compute the matrix from the Euclidean distances between bands and are vulnerable to noise. Our proposed method can improve the robustness to such noise. Second, we propose an enhanced clustering strategy which clusters each band individually. Third, a dynamic ranking strategy is used to select bands iteratively. Bands that are highly correlated with each other will be prevented from being added to avoid redundancy. DLCR demonstrates improved performance on the Indian Pines and Pavia University data sets, when compared against other methods from the literature. [ABSTRACT FROM AUTHOR]

A band selection method named weighted kernel regularization (WKR) is proposed for hyperspectral imagery (HSI) classification. The WKR aims to select dissimilar and class-separable bands to better model the relationship between labeled samples. First, the WKR considers nonlinear structure of hyperspectral data and models nonlinear relations between HSI samples and their class labels using a weighted kernel ridge regression (WKRR) program with respect to sample coefficients. Second, it combines the L1 penalty term of weights on all bands with the above WKRR program into the unified framework of WKR. The L1 penalty term considers divergent contributions from different bands in describing nonlinear relations and guarantees the sparsity of band weights. Third, the WKR algorithm implements the KerNel Iterative-based Feature Extraction (KNIFE) algorithm to estimate the proper band weights. The KNIFE linearizes the nonlinear kernels to avoid high computational cost, and iteratively minimizes two convex subproblems with respect to the sample coefficients and band weights. Finally, the first k bands with larger weights and larger dissimilarity with other bands are automatically chosen to form the band subset. Experimental results show that the WKR outperforms the state-of-the-art methods in classification accuracies with a lower computational cost. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Remote Sensing is the property of Editorial Office of Journal of Remote Sensing & Science Publishing Co. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Hyperspectral images (HSIs) can describe the subtle differences in the spectral signatures of materials. However, they have low spatial resolution due to various hardware limitations. Improving it via postprocess without an auxiliary high-resolution (HR) image still remains a challenging problem. In this paper, we address this problem and propose a new HSI super-resolution (SR) method. Our approach, called deep feature matrix factorization (DFMF), blends feature matrix extracted by a deep neural network (DNN) with nonnegative matrix factorization strategy for super-resolving real-scene HSI. The estimation of the HR HSI is formulated as a combination of latent spatial feature matrix and spectral feature matrix. In the DFMF model, the input low-resolution (LR) HSI is first partitioned into several subsets according to the correlation matrix, and the key band is selected from each subset. Then, the key band group is super-resolved by a DNN model, and the HR key band group is then used as a guide to carry out deep spatial feature matrix. Specifically, the input LR HSI with prototype reflectance spectral vectors of the scene will be preserved when super-resolving in a spatial domain. Thus, the nonnegative spectral and spatial feature matrices are extracted simultaneously from alternately factorizing the pair of LR HSI and the HR key band group. Finally, the HR HSI is obtained by the integration of the spectral and spatial feature matrices. Experiments have been conducted on real-scene remote sensing HSI. Comparative analyses validate that the proposed DFMF method presents a superior super-resolving performance, as it preserves spectral information better. [ABSTRACT FROM AUTHOR]

Band selection refers to finding the most representative channels from hyperspectral images. Usually, certain objective functions are designed and combined via regularization terms. A possible drawback of these methods is that they can only generate one solution in a single run with a given band number. To overcome this problem, multiobjective (MO)-based methods, which were able to simultaneously obtain a series of subsets with different band numbers, were investigated for band selection. However, because the range of band selection problem is discrete, recently proposed weighted Tchebycheff (WT)-based MO methods may suffer weakly Pareto optimal problem. In this case, the solutions for each band number will be nonunique and no optimal solution exists. Decision makers have to manually select a unique solution for each band number. In this paper, we provide a theoretical analysis about the weakly Pareto optimal problem in band selection, and quantitatively give the boundary conditions. Moreover, we further summarize the suggestions which will help users avoid the weakly Pareto optimal problem. According to these criteria, we develop a new adaptive-penalty-based boundary intersection (APBI) framework to improve the MO algorithm in hyperspectral band selection. APBI mainly includes two advantages: 1) avoiding weakly Pareto optimum and 2) reducing the sensibility of the penalty factor. The theoretical analysis is further validated by contrast experiments. The results demonstrate that the weakly Pareto optimal solutions really exist in WT methods, while APBI can overcome this problem. [ABSTRACT FROM AUTHOR]

Abstract Hyperspectral imaging has the ability for characteristic identification because of its rich physical and chemical information. To develop online or portable devices for industrial applications, informative spectral bands relevant to the specific objects are needed to be selected. The neighborhood rough set (NRS) theory is an effective tool for selecting bands. The hyperspectral datasets gathered from practical applications often contain noise. The performance of band selection algorithm is adversely influenced by noise. In this paper, the performance of the band selection algorithm in the presence of class noise was assessed, which based on consistency measure, dependency measure and information measure of the NRS theory. The robustness and classification performance of algorithms for soybean and maize classification using hyperspectral imaging were compared systematically under different levels of noise. The results demonstrate that the robustness and classifying ability of all algorithms decreases in general when the number of mislabeled samples increases in training dataset and testing datasets. Compared with other algorithms based on the NRS theory and some classic algorithms (uninformative variable elimination and successive projections algorithm), the variable precision neighborhood rough set algorithm is proven to be superior. It is more robust and more accurate when class noise occurs in training dataset or testing datasets. This research not only highlights the strong and weak characteristics of the different approaches for different levels of noise, but also provides effective solutions in handling class noise. Highlights • Explore hyperspectral band selection algorithms in neighborhood rough set theory. • Assess performance of algorithms when noise is in training or testing dataset. • Compare robustness and classification performance for different noise levels. • Algorithms are used to solve classification task of soybean and maize. • Compared to other algorithms, the VPNRS algorithm is superior for noisy data. [ABSTRACT FROM AUTHOR]

Hyperspectral imaging, with many narrow bands of spectra, is strongly capable to detect or classify objects. It has been become one research hotspot in the field of near-ground remote sensing. However, the higher demands for computing and complex operating of instrument are still the bottleneck for hyperspectral imaging technology applied in field. Band selection is a common way to reduce the dimensionality of hyperspectral imaging cube and simplify the design of spectral imaging instrument. In this research, hyperspectral images of blueberry fruit were collected both in the laboratory and in field. A set of spectral bands were selected by analyzing the differences among blueberry fruits at different growth stages and backgrounds. Furthermore, a normalized spectral index was set up using the bands selected to identify the three growth stages of blueberry fruits, aiming to eliminate the impact of background included leaf, branch, soil, illumination variation and so on. Two classifiers of spectral angle mapping (SAM), multinomial logistic regression (MLR) and classification tree were used to verify the results of identification of blueberry fruit. The detection accuracy was 82.1% for SAM classifier using all spectral bands, 88.5% for MLR classifier using selected bands and 89.8% for decision tree using the spectral index. The results indicated that the normalization spectral index can both lower the complexity of computing and reduce the impact of noisy background in field. [ABSTRACT FROM AUTHOR]

Strong intra - band correlations along with numerous bands seriously hinder the processing and applications of hyperspectral remote sensing images in realistic applications. A separable non - negative matrix factorization (SepNMF) method is presented to explore the band selection problem on hyperspectral imagery (HSI). The method investigates the separability structure in the band set of the HSI data to improve the regular non-negative matrix factorization model, and it formulates the band selection problem into the problem of finding representative columns that represent other bands with non-negative and linear combinations in the SepNMF model. The method adopts the recursive projection method to iteratively select the representative bands to constitute the proper band subset. Three groups of experiments on two open HSI data sets are designed to carefully testify the performance of the SepNMF in band selection. Several popular methods are utilized to compare against the proposed SepNMF method. Experimental results show that the SepNMF obtains the best overall classification accuracies of all while taking shorter computational times ranking second among all the comparison methods. Therefore, the SepNMF method can be an alternative choice for selecting proper bands in hyperspectral image classification. [ABSTRACT FROM AUTHOR]

Partial least-squares (PLS) regression is a popular method for modeling chemical constituents from spectroscopic data and has been widely applied to retrieve leaf chemical components via hyperspectral remote sensing. However, one persistent challenge for applying the PLS regression is the selection of informative spectral bands among the vast array of acquired spectra. No consensus has been reached yet on how to select informative bands regardless of many techniques being proposed. In this paper, we have composited four individual data sets containing a total of 598 leaf samples from various species to evaluate four different band elimination/selection methods. Results revealed that the stepwise-PLS approach was optimal to estimate leaf chlorophyll content even under different spectral resolutions, from which informative bands were identified. Informative bands, in general, include bands inside the near-infrared (NIR), and in addition, one within the blue range and one within the red range. With such combinations, the PLS regression models meet the requirement for accurate leaf chlorophyll estimation. For most PLS regression models, their accuracies decreased with the reduction of spectral resolution, but the stepwise-PLS approach could consistently estimate the chlorophyll content at different spectral resolutions (with ${R}^{2} \ge 0.77$ for resolutions < 20 nm). The findings, hence, provide valuable insights for selecting informative spectral bands for PLS analysis and lay a strong foundation for retrieving foliar biochemical content using hyperspectral remote sensing data. [ABSTRACT FROM AUTHOR]

Hyperspectral images (HSIs) convey more useful information than RGB or gray images, which are widely used in many remote sensing tasks. In real scenarios, HSIs are inevitably corrupted by noise because of sensors’ imperfectness or atmospheric influence. Recently, many HSI denoising methods have been proposed to utilize the interband information between different spectral bands. However, these methods regard the HSI as a whole and treat the different spectral bands with the same noise level. In fact, the noise levels in different bands are different. Especially, only few certain bands are corrupted by noise, named the target noised bands. Under this circumstance, an HSI denoising method is proposed by considering the band relationship and different noise levels. The target noised bands are adaptively denoised by fusing some selected bands. Specifically, some related but quality superior bands are selected according to the target noised bands. Then, the target noised bands can be denoised by fusing the selected related bands. Experimental results show that the proposed method achieves considerable performances in comparison with several state-of-the-art hyperspectral denoising methods. [ABSTRACT FROM AUTHOR]

Spectroscopy has become one of the most used non-invasive methods to detect plant diseases before symptoms are visible. In this study it was possible to characterize the spectral variation in leaves of Solanum lycopersicum L. infected with Fusarium oxysporum during the incubation period. It was also possible to identify the relevant specific wavelengths in the range of 380-1000 nm that can be used as spectral signatures for the detection and discrimination of vascular wilt in S. lycopersicum. It was observed that inoculated tomato plants increased their reflectance in the visible range (Vis) and decreased slowly in the near infrared range (NIR) measured during incubation, showing marked differences with plants subjected to water stress in the Vis/NIR. Additionally, three ranges were found in the spectrum related to infection by F. oxysporum (510-520 nm, 650-670 nm, 700-750 nm). Linear discriminant models on spectral reflectance data were able to differentiate between tomato varieties inoculated with F. oxysporum from healthy ones with accuracies higher than 70% 9 days after inoculation. The results showed the potential of reflectance spectroscopy to discriminate plants inoculated with F. oxysporum from healthy ones as well as those subjected to water stress in the incubation period of the disease. [ABSTRACT FROM AUTHOR]

Hyperspectral band selection is a feature selection method that selects a most representative set of bands to achieve a good performance in several tasks such as classification and anomaly detection. It reduces the burden of storage, transmission, and computation. In this letter, a two-stage band selection algorithm is introduced. It selects bands and refines the result using a linear reconstruction error criterion. Then a coarse-to-fine band selection (CFBS) strategy is applied to the two-stage band selection in order to achieve a better result. CFBS selects bands group by group. Each group is selected based on bands that are not well represented by the previous groups, trying to minimize the linear reconstruction error. Experiments show that the proposed method has a significant advancement compared with other competitors. [ABSTRACT FROM AUTHOR]

The abundant spectral information of hyperspectral imagery makes it suitable for the classification of land cover types. However, the high dimensionality also brings some negative effects for the classification tasks. Dynamic classifier selection, in which the base classifiers are selected according to each new sample to be classified, can select the best classifier for each query sample. In this paper, a semi-supervised wrapper band selection method—the band selection based on dynamic classifier selection—is introduced to select the most discriminating bands. In the proposed method, band selection is conducted based on the selection of base classifier. Specifically, the support vector machine classification map is filtered to provide a high-quality reference, and K-nearest neighbors method is used to define the local region, finally, the band with the best classification performance is selected. Three widely used real hyperspectral datasets are used to illustrate the effectiveness of the proposed method, experimental results show that the proposed method obtains state-of-the-art performance. [ABSTRACT FROM AUTHOR]

Band selection is an effective approach to mitigate the “Hughes phenomenon” of hyperspectral image (HSI) classification. Recently, sparse representation (SR) theory has been successfully introduced to HSI band selection, and many SR-based methods have been developed and shown great potential and superiority. However, due to the inherent limitations of the SR scheme, i.e., individually representing each band with only a few other bands from the same subspace, the SR-based methods cannot effectively capture the global structures of the data, which limit the band selection performance. In this paper, to overcome this obstacle, the novel Laplacian-regularized low-rank subspace clustering (LLRSC) algorithm is proposed for HSI band selection. On the one hand, the low-rank subspace clustering model is introduced to capture the global structure information for the learned representation coefficient matrix and deal with the HSI band selection task in the clustering framework. On the other hand, considering the high correlation between adjacent bands, 1-D Laplacian regularization is utilized to incorporate the neighboring band information and further reduce the representation bias. Lastly, an eigenvalue analysis algorithm based on band mutation information is utilized to estimate the appropriate size of the band subset. The experimental results indicate that the proposed LLRSC algorithm outperforms the other state-of-the-art methods and achieves a very competitive band selection performance for HSIs. [ABSTRACT FROM AUTHOR]

Accurate and fast target detection is one of the key problems in hyperspectral image applications. Band selection is an essential step to improve the utilization efficiency of hyperspectral data. The current hyperspectral band selection methods don ' t consider task correlation, which affects the effectiveness of band selection results in actual target detection tasks. A new spectra equal interval extraction method was proposed based on constructing the spectra interval difference equalization calculation model. Experiments on hyperspectral remote sensing image dataset have confirmed the superiority of the new method. The results show that the proposed method can achieve better results in terms of computational time and accuracy compared with other band selection methods, and can efficiently achieve target detection of hyperspectral images. [ABSTRACT FROM AUTHOR]

Band selection for hyperspectral images helps improve the efficiency of data processing and even the accuracy of classification. It is to reduce the dimensionality of a hyperspectral image by selecting representative bands. In such a process, the quantification of band similarity is the fundamental issue, and it is usually achieved by using an information-theoretic measure, such as mutual information or relative entropy. However, these measures are incapable of quantifying similarity in terms of both composition and configuration. To solve this problem, the Boltzmann entropy (BE), which captures both configurational and compositional information, is employed in this letter. More precisely, the difference in BE between two bands is used for such quantification. The corresponding search strategy is designed for band selection. Experimental evaluation was carried out using remote sensing images for classification. The results clearly demonstrate the superiority of the proposed band selection method over traditional information-theoretic methods: an increase of up to 27% in classification accuracy was observed when using the difference in relative BE with 20 selected bands. In addition, another comparison with some state-of-the-art methods was conducted. The results show that the proposed method is still very competitive; it outperformed all the others when the number of selected bands ranges from 18 to 23. This letter, the first of its kind, reveals that the BE may form a new base for information-theoretic approaches to image processing and even for spatial information science in a broad sense. [ABSTRACT FROM AUTHOR]

Hyperspectral images (HSIs) consist of hundreds of continuous bands with high correlation, making it contain great abundant information. Band selection is an effective idea for removing redundant bands and preserving the physical significance at the same time. Popular sparse representation-based band selection commonly introduces an additional coefficient to combine error term and sparse constraint term, making it difficult to find out the optimal balance coefficient. In this letter, we propose a hybrid clustering-based band-selection approach based on using evolutionary multiobjective optimization to solve a sparse self-representation model constituted with two conflicting objectives. The proposed approach simultaneously minimizes two terms of the sparse representation model, avoiding the balance coefficient and producing a set of optimal solutions that are used to construct a similarity matrix for spectral clustering. Finally, a reduced band subset is determined by the cluster centers. We compare the results of the proposed approach with four existing band-selection methods for three real HSI data sets, showing that the proposed approach is able to effectively select representative bands with better classification accuracy. [ABSTRACT FROM AUTHOR]

Envelope analysis has been widely used to detect early stage faults of rolling element bearings. The primary initial step of envelope analysis is the proper selection of the resonance band for demodulation. Current band selection methods, such as wide band selection, "power spectral density" comparison, and selecting the accelerometer resonance band have limitations such as disturbance of the wide band, the need for a healthy signal for comparison, and the implementation of specialized sensors. In this study, an enhanced method of resonance band selection for envelope analysis was developed. The developed method implements high-pass filtering and "time synchronous averaging" to remove dominant speed-dependent (nonsynchronous and synchronous) spectral contents of a vibration signal. Wavelet packet transform and "root mean square" were then applied to determine the energy distribution of the residual signal. The band with the highest energy (resonance band) was selected for envelope analysis. An experimental study was designed for cross-validation of the developed method. The developed method in this study is more practical than current band selection methods and has no special requirement for sensors. The developed algorithm can be implemented as a processing algorithm in a commercial vibration analyzer, which enhances its ability in early-stage bearing fault detection. [ABSTRACT FROM AUTHOR]

In remote sensing image classifications, a reasonable selection of bands can help improve classification accuracy. At present, problems occur in artificial subjective selection of bands in image classifications, thereby resulting in ineffective expression of classification accuracy. In this study, 10 bands of Landsat8 fusion data were used as information sources, and recursive feature elimination based on maximum likelihood classification (MLC-RFE) was conducted to select the most important bands and analyse the classification results of the various band combinations. Results showed that green, red and blue were the three unimportant bands, which had the lowest classification accuracy (92.2312%). Coastal blue, near infrared and short-wave infrared 1 were the three important bands, which had a high classification accuracy (97.5000%). The coastal blue, near infrared, short-wave infrared 1, cirrus, short-wave infrared 2, thermal infrared 1 and thermal infrared 2 constituted the recursive optimal band set in all multi-band combinations and had the highest classification accuracy (99.1667%). The classifications of the 2-7 bands and all 10 bands had an overall accuracy of 95.3495% and 96.9624%, respectively. Additional experiments showed that the Landsat8 band elimination order and optimal band set have certain differences, but the optimal band combinations with high classification accuracies can be coupled from all of them. Our findings confirmed that various band combinations had different classification accuracies, which indicated that selecting the participating bands in a classification was crucial. Furthermore, the MLC-RFE method used in this study selected the optimal classification bands and played an important role in solving the band selection problem. [ABSTRACT FROM AUTHOR]

Soybeans and soy foods have attracted widespread attention due to their health benefits. Special varieties of soybeans are in demand from soybean processing enterprises. Because of the advantage of rapid measurement with minimal sample preparation, hyperspectral imaging technology is used for classifying soybean varieties. Based on fuzzy rough set (FRS) theory, the research of hyperspectral band selection can provide the foundation for variety classification. The performance of band selection with Gaussian membership functions and triangular membership functions under various parameters were explored. Appropriate ranges of parameters were determined by the number of bands and mutual information of subsets relative to the decision. The effectiveness of the proposed algorithms was validated through experiments on soybean hyperspectral datasets by building two classification methods, namely Extreme Learning Machine and Random Forest. Compared with ranking methods, the proposed algorithm provides a promising improvement in classification accuracy by selecting highly informative bands. To further reduce the size of the subset, a post-pruning design was used. For the Gaussian membership function, a subset containing eight bands achieved an average accuracy of 99.11% after post-pruning. As well as classification accuracy, we explored stability of band selection algorithm under small perturbations. The band selection algorithm of the Gaussian membership function was more stable than that of the triangular membership function. The results showed that the information measure (IM) based band selection algorithm is effective at obtaining satisfactory classification accuracy and providing stable results under perturbations. Highlights • Hyperspectral imaging technology was used for classifying soybean varieties. • Band selection based on information measure in fuzzy rough set theory was proposed. • The performance with the Gaussian and triangular membership functions were explored. • The effectiveness of algorithms were validated by ELM and RF classification methods. • The stability of band selection algorithms under small perturbations was explored. [ABSTRACT FROM AUTHOR]