Search

The goal of hyperspectral image fusion (HIF) is to reconstruct high spatial resolution hyperspectral images (HR-HSI) via fusing low spatial resolution hyperspectral images (LR-HSI) and high spatial resolution multispectral images (HR-MSI) without loss of spatial and spectral information. Most existing HIF methods are designed based on the assumption that the observation models are known, which is unrealistic in many scenarios. To address this blind HIF problem, we propose a deep learning-based method that optimizes the observation model and fusion processes iteratively and alternatively during the reconstruction to enforce bidirectional data consistency, which leads to better spatial and spectral accuracy. However, general deep neural network inherently suffers from information loss, preventing us to achieve this bidirectional data consistency. To settle this problem, we enhance the blind HIF algorithm by making part of the deep neural network invertible via applying a slightly modified spectral normalization to the weights of the network. Furthermore, in order to reduce spatial distortion and feature redundancy, we introduce a Content-Aware ReAssembly of FEatures module and an SE-ResBlock model to our network. The former module helps to boost the fusion performance, while the latter make our model more compact. Experiments demonstrate that our model performs favorably against compared methods in terms of both nonblind HIF fusion and semiblind HIF fusion.

Today there is a rapid development taking place in phenotyping of plants using non-destructive image based machine vision techniques. Machine vision based plant phenotyping ranges from single plant trait estimation to broad assessment of crop canopy for thousands of plants in the field. Plant phenotyping systems either use single imaging method or integrative approach signifying simultaneous use of some of the imaging techniques like visible red, green and blue (RGB) imaging, thermal imaging, chlorophyll fluorescence imaging (CFIM), hyperspectral imaging, 3-dimensional (3-D) imaging or high resolution volumetric imaging. This paper provides an overview of imaging techniques and their applications in the field of plant phenotyping. This paper presents a comprehensive survey on recent machine vision methods for plant trait estimation and classification. In this paper, information about publicly available datasets is provided for uniform comparison among the state-of-the-art phenotyping methods. This paper also presents future research directions related to the use of deep learning based machine vision algorithms for structural (2-D and 3-D), physiological and temporal trait estimation, and classification studies in plants.

A largely ignored fact in spectral super-resolution (SSR) is that the subsistent mapping methods neglect the auxiliary prior of camera spectral sensitivity (CSS) and only pay attention to wider or deeper network framework design while ignoring to excavate the spatial and spectral dependencies among intermediate layers, hence constraining representational capability of convolutional neural networks (CNNs). To conquer these drawbacks, we propose a novel deep hybrid 2-D-3-D CNN based on dual second-order attention with CSS prior (HSACS), which can excavate sufficient spatial-spectral context information. Specifically, dual second-order attention embedded in the residual block for more powerful spatial-spectral feature representation and relation learning is composed of a brand new trainable 2-D second-order channel attention (SCA) or 3-D second-order band attention (SBA) and a structure tensor attention (STA). Concretely, the band and channel attention modules are developed to adaptively recalibrate the band-wise and interchannel features via employing second-order band or channel feature statistics for more discriminative representations. Besides, the STA is promoted to rebuild the significant high-frequency spatial details for enough spatial feature extraction. Moreover, the CSS is first employed as a superior prior to avoid its effect of SSR quality, on the strength of which the resolved RGB can be calculated naturally through the super-reconstructed hyperspectral image (HSI); then, the final loss consists of the discrepancies of RGB and the HSI as a finer constraint. Experimental results demonstrate the superiority and progressiveness of the presented approach in terms of quantitative metrics and visual effect over SOTA SSR methods.

Due to the unavoidable influence of sparse and Gaussian noise during the process of data acquisition, the quality of hyperspectral images (HSIs) is degraded and their applications are greatly limited. It is therefore necessary to restore clean HSIs. In the traditional methods, low-rank and sparse matrix decomposition methods are usually applied to restore the pure data matrix from the observed data matrix. However, due to the fact that the optimization of the l0-norm for the sparse modeling is a non-convex and NP-hard problem, convex relaxation and regularization parameters are usually introduced. However, convex relaxation often leads to inaccurate sparse modeling results, and the sensitive regularization parameters can lead to unstable results. Thus, in this paper, to address these issues, an accurate multi-objective low-rank and sparse denoising framework is proposed for HSIs to achieve accurate modeling. The l0-norm is directly modeled as the sparse noise and is optimized by an evolutionary algorithm, and the denoising problem is converted into a multi-objective optimization problem through simultaneously optimizing the low-rank term, the sparse term, and the data fidelity term, without sensitive regularization parameters. However, since the low-rank clean image and sparse noise of the HSI are encoded into a solution, the length of the solution is too long to be optimized. In this paper, a subfitness strategy is constructed to achieve effective optimization through comparing the objective function values corresponding to each band for each solution. The experiments undertaken with simulated images in 11 noise cases and four real noisy images confirm the effectiveness of the proposed method.

The goal of hyperspectral image analysis is often to determine which materials, out of a given set of possibilities, are present in each pixel. As hyperspectral data are being gathered in rapidly increasing amounts, automatic image analysis is becoming progressively more important. Automatic identification of materials from a mixed pixel is possible with 1) Bayesian unmixing algorithms and 2) multiobjective sparse unmixing algorithms when a method such as elbow estimation is used to select the best solution from the set of Pareto-optimal solutions. We develop a new elbow estimation method called termination condition adaptive elbow (TCAE) for selecting the best solution from the set of Pareto-optimal solutions to a biobjective unmixing problem. Specifically, the two objectives are assumed to be the sparsity level of the fractional abundance vector and the reconstruction error. We conduct experiments with real-world unmixing applications in mind, and TCAE performs significantly better than a state-of-the-art elbow estimation method when they are both used to select the best solution from the sequence of fractional abundance vectors generated by iterative spectral mixture analysis (ISMA). Furthermore, the combination of ISMA and TCAE is able to identify endmembers from mixed pixels several times faster and with higher F1-score than the two Bayesian unmixing algorithms used as a reference. We conclude that the combination of ISMA and TCAE facilitates automatic, reliable, and rapid identification of endmembers from mixed pixels.

Soil standing may be studied indirectly using remote sensing through an assessment of state of the plants growing on it. The ability to evaluate the physiological state of plants using the hyperspectral survey data also provides a tool to characterize vegetation cover and individual samples of woody plants. In the present work the hyperspectral imaging was applied to identify the species of the woody plants evaluating the differences in their physiological state. Samples of Quercus macrocarpa Michx., Q. robur L. and Q. rubra L. were studied using Cubert UHD-185 hyperspectral camera over five periods with an interval of 7-10 days. In total, 80 vegetation indices (VIs) were calculated. Sample sets of values of VIs were analyzed using analysis of variance (ANOVA), principal component analysis (PCA), decision tree (DT), random forest (RF) methods. It was shown using the ANOVA, that the following VIs are the most dependent on the species affiliation of the samples: Carter2, Carter3, Carter4, CI, CI2, CRI4, Datt, Datt2, GMI2, Maccioni, mSR2, MTCI, NDVI2, OSAVI2, PRI, REP_Li, SR1, SR2, SR6, Vogelmann, Vogelmann2, Vogelmann4. VIs that are effective for the separation of oak species, were also revealed using the DT method – these are Boochs, Boochs2, CARI, CRI1, CRI3, D1, D2, Datt, Datt3; Datt4, Datt5, DD, DDn, EGFN, Gitelson, MCARI2, MTCI, MTVI, NDVI3, PRI, PSND, PSRI, RDVI, REP_Li, SPVI, SR4, Vogelmann, Vogelmann2, Vogelmann3. PCA and RF methods reliably differentiated Q. rubra from Q. robur and Q. macrocarpa. Q. rubra, unlike other species, was under stress from the impact of soil pH against the background of drought. This was manifested in leaf chlorosis. Influence of the environmental stress factors on the reliability and efficiency of species identification was demonstrated. Q. robur and Q. macrocarpawere were poorly separated by PCA and RF methods all over the five periods of the experiment.

International audience; Hyperspectral images (HSIs) are of crucial importance in order to better understand features from a large number of spectral channels. Restricted by its inner imaging mechanism, the spatial resolution is often limited for HSIs. To alleviate this issue, in this work, we propose a simple and efficient architecture of deep convolutional neural networks to fuse a low-resolution HSI (LR-HSI) and a high-resolution multispectral image (HR-MSI), yielding a high-resolution HSI (HR-HSI). The network is designed to preserve both spatial and spectral information thanks to a new architecture based on: 1) the use of the LR-HSI at the HR-MSI’s scale to get an output with satisfied spectral preservation and 2) the application of the attention and pixelShuffle modules to extract information, aiming to output high-quality spatial details. Finally, a plain mean squared error loss function is used to measure the performance during the training. Extensive experiments demonstrate that the proposed network architecture achieves the best performance (both qualitatively and quantitatively) compared with recent state-of-the-art HSI super-resolution approaches. Moreover, other significant advantages can be pointed out by the use of the proposed approach, such as a better network generalization ability, a limited computational burden, and the robustness with respect to the number of training samples. Please find the source code and pretrained models from https://liangjiandeng.github.io/Projects_Res/HSRnet_2021tnnls.html .

Rising oceanic temperatures create more frequent coral bleaching events worldwide and as such there exists a need for rapid, non-destructive survey techniques to gather greater and higher definition information than that offered by traditional spectral based monitoring systems. Here, we examine thermally induced laboratory bleaching of Montipora capricornis and Montipora confusa samples, utilising hyperspectral data to gain an understanding of coral bleaching from a spectral standpoint. The data revealed several characteristic spectral peaks that can be used to make health determinations. The fluorescence peaks are attributed to fluorescent proteins (FPs) and Chlorophyll-a fluorescence. The reflectance peaks can be attributed to Chlorophyll absorption and accessory pigments such as Peridinin and Diadinoxanthin. Each characteristic spectral peak or ‘marker’ allows for observation of each aspect of coral health and hence, simultaneous monitoring of these markers using hyperspectral imaging techniques provides an opportunity to better understand the processes occurring during bleaching and the rates at which they occur relative to one another.

Anomaly detection (AD) using hyperspectral images (HSIs) is of great interest for deep space exploration and Earth observations. This article proposes a weakly supervised discriminative learning with a spectral constrained generative adversarial network (GAN) for hyperspectral anomaly detection (HAD), called weaklyAD. It can enhance the discrimination between anomaly and background with background homogenization and anomaly saliency in cases where anomalous samples are limited and sensitive to the background. A novel probability-based category thresholding is first proposed to label coarse samples in preparation for weakly supervised learning. Subsequently, a discriminative reconstruction model is learned by the proposed network in a weakly supervised fashion. The proposed network has an end-to-end architecture, which not only includes an encoder, a decoder, a latent layer discriminator, and a spectral discriminator competitively but also contains a novel Kullback-Leibler (KL) divergence-based orthogonal projection divergence (OPD) spectral constraint. Finally, the well-learned network is used to reconstruct HSIs captured by the same sensor. Our work paves a new weakly supervised way for HAD, which intends to match the performance of supervised methods without the prerequisite of manually labeled data. Assessments and generalization experiments over real HSIs demonstrate the unique promise of such a proposed approach.

By training different models and averaging their predictions, the performance of the machine-learning algorithm can be improved. The performance optimization of multiple models is supposed to generalize further data well. This requires the knowledge transfer of generalization information between models. In this article, a multiple kernel mutual learning method based on transfer learning of combined mid-level features is proposed for hyperspectral classification. Three-layer homogenous superpixels are computed on the image formed by PCA, which is used for computing mid-level features. The three mid-level features include: 1) the sparse reconstructed feature; 2) combined mean feature; and 3) uniqueness. The sparse reconstruction feature is obtained by a joint sparse representation model under the constraint of three-scale superpixels' boundaries and regions. The combined mean features are computed with average values of spectra in multilayer superpixels, and the uniqueness is obtained by the superposed manifold ranking values of multilayer superpixels. Next, three kernels of samples in different feature spaces are computed for mutual learning by minimizing the divergence. Then, a combined kernel is constructed to optimize the sample distance measurement and applied by employing SVM training to build classifiers. Experiments are performed on real hyperspectral datasets, and the corresponding results demonstrated that the proposed method can perform significantly better than several state-of-the-art competitive algorithms based on MKL and deep learning.

Over the last two decades, research in hyperspectral imaging has been increasing and its use in horticulture is expected to be spreading in the coming years. The emerging tech-niques are currently gaining interest of the research community. However, there are still challenges to the applicability. In this review we demonstrate that hyperspectral imaging can be used as an effective tool for fruit, vegetables and mushrooms in assessing quality parameters related to well defined variables that can be analysed in the laboratory, as well as complex properties such as maturity, ripeness, detection of biotic defects, physiological disorders, mechanical damages, and sensory quality. Therefore, this paper starts by giving an overview of the quality concept of produce, measuring principles, theory and analysis of hyperspectral imaging systems. Then, emerging techniques to monitor and assess quality parameters, both pre-and postharvest, are described, as well as applications of these are reviewed and discussed. Afterwards, this review proceeds by illustrating the current and potential use of artificial intelligence and its subdomains, machine learning and deep learning, for hyperspectral imaging analysis in horticulture. Lastly, some challenges and considerations for future research are highlighted, including improvement of data avail-ability, possible solutions for an improved integration of artificial intelligence and the transfer of knowledge from research parameters to parameters relevant for industrial stakeholders.

Traditional target detection methods assume that the background spectrum is subject to the Gaussian distribution, which may only perform well under certain conditions. In addition, traditional target detection methods suffer from the problem of the unbalanced number of target and background samples. To solve these problems, this study presents a novel target detection method based on asymmetric weighted logistic metric learning (AWLML). We first construct a logistic metric-learning approach as an objective function with a positive semidefinite constraint to learn the metric matrix from a set of labeled samples. Then, an asymmetric weighted strategy is provided to emphasize the unbalance between the number of target and background samples. Finally, an accelerated proximal gradient method is applied to identify the global minimum value. Extensive experiments on three challenging hyperspectral datasets demonstrate that the proposed AWLML algorithm improves the state-of-the-art target detection performance.

It has been proved that the determination of independent components (ICs) in the independent component analysis (ICA) can be attributed to calculating the eigenpairs of high-order statistical tensors of the data. However, previous works can only obtain approximate solutions, which may affect the accuracy of the ICs. In addition, the number of ICs would need to be set manually. Recently, an algorithm based on semidefinite programming (SDP) has been proposed, which utilizes the first-order gradient information of the Lagrangian function and can obtain all the accurate real eigenpairs. In this article, for the first time, we introduce this into the ICA field, which tends to further improve the accuracy of the ICs. Note that the number of eigenpairs of symmetric tensors is usually larger than the number of ICs, indicating that the results directly obtained by SDP are redundant. Thus, in practice, it is necessary to introduce second-order derivative information to identify local extremum solutions. Therefore, originating from the SDP method, we present a new modified version, called modified SDP (MSDP), which incorporates the concept of the projected Hessian matrix into SDP and, thus, can intellectually exclude redundant ICs and select true ICs. Some cases that have been tested in the experiments demonstrate its effectiveness. Experiments on the image/sound blind separation and real multi/hyperspectral image also show its superiority in improving the accuracy of ICs and automatically determining the number of ICs. In addition, the results on hyperspectral simulation and real data also demonstrate that MSDP is also capable of dealing with cases, where the number of features is less than the number of ICs.

Hyperspectral images (HSIs) are inevitably contaminated by the mixed noise (such as Gaussian noise, impulse noise, deadlines, and stripes), which could influence the subsequent processing accuracy. Generally, HSI restoration can be transformed into the low-rank matrix recovery (LRMR). In the LRMR, the nuclear norm is widely used to substitute the matrix rank, but its effectiveness is still worth improving. Besides, the l0-norm cannot capture the sparse noise's structured sparsity property. To handle these issues, the adaptive rank and structured sparsity corrections (ARSSC) are presented for HSI restoration. The ARSSC introduces two convex regularizers, that is: 1) the rank correction (RC) and 2) the structured sparsity correction (SSC), to, respectively, approximate the matrix rank and the l2,0-norm. The RC and the SSC can adaptively offset the penalization of large entries from the nuclear norm and the l2,1-norm, respectively, where the larger the entry, the greater its offset. Therefore, the proposed ARSSC achieves a tighter approximation of the noise-free HSI low-rank structure and promotes the structured sparsity of sparse noise. An efficient alternative direction method of multipliers (ADMM) algorithm is applied to solve the resulting convex optimization problem. The superiority of the ARSSC in terms of the mixed noise removal and spatial-spectral structure information preserving, is demonstrated by several experimental results both on simulated and real datasets, compared with other state-of-the-art HSI restoration approaches.

Intraoperative identification of cancerous tissue is fundamental during oncological surgical or endoscopic procedures. This relies on visual assessment supported by histopathological evaluation, implying a longer operative time. Hyperspectral imaging (HSI), a contrast-free and contactless imaging technology, provides spatially resolved spectroscopic analysis, with the potential to differentiate tissue at a cellular level. However, HSI produces "big data", which is impossible to directly interpret by clinicians. We hypothesize that advanced machine learning algorithms (convolutional neural networks-CNNs) can accurately detect colorectal cancer in HSI data.In 34 patients undergoing colorectal resections for cancer, immediately after extraction, the specimen was opened, the tumor-bearing section was exposed and imaged using HSI. Cancer and normal mucosa were categorized from histopathology. A state-of-the-art CNN was developed to automatically detect regions of colorectal cancer in a hyperspectral image. Accuracy was validated with three levels of cross-validation (twofold, fivefold, and 15-fold).32 patients had colorectal adenocarcinomas confirmed by histopathology (9 left, 11 right, 4 transverse colon, and 9 rectum). 6 patients had a local initial stage (T1-2) and 26 had a local advanced stage (T3-4). The cancer detection performance of the CNN using 15-fold cross-validation showed high sensitivity and specificity (87% and 90%, respectively) and a ROC-AUC score of 0.95 (considered outstanding). In the T1-2 group, the sensitivity and specificity were 89% and 90%, respectively, and in the T3-4 group, the sensitivity and specificity were 81% and 93%, respectively.Automatic colorectal cancer detection on fresh specimens using HSI, using a properly trained CNN is feasible and accurate, even with small datasets, regardless of the local tumor extension. In the near future, this approach may become a useful intraoperative tool during oncological endoscopic and surgical procedures, and may result in precise and non-destructive optical biopsies to support objective and consistent tumor-free resection margins.

Trace inspection is a key technology for collecting crime scenes in the criminal investigation department. A lot of information can be obtained by restoring and analyzing the remaining traces on the scene. However, with the development of digital technology, digital trace inspection has become more and more popular. So, the main research of this article is the design and realization of the trace inspection system based on hyperspectral imaging technology. This article proposes nondestructive testing technology in hyperspectral imaging technology. Combining basic principles of spectroscopy and the image of residual traces such as car tires, shoe soles, and blood stains, it can identify the key traces. Then, based on the image denoising and least squares support vector machine method, this study improves the accuracy and restoration of the image. Therefore, this study designs a test for the trace inspection system for testing hyperspectral imaging technology. The test items include the performance of the trace inspection system, the noise reduction of the trace inspection system, and the ability of the trace inspection system to inspect blood stains. The final collected data are improved to get the trace inspection system based on hyperspectral imaging technology proposed in this study. Compared with the traditional trace inspection system, the experimental results show that the trace inspection system based on hyperspectral imaging technology can improve the accuracy by 5%–28%, compared with the traditional trace inspection system. The image restoration degree of the hyperspectral imaging technology trace inspection system can be improved by 1%–19%, compared with the traditional trace inspection system.

To analyze the blood oxygen concentrations (StO 2 ) of different stages of pressure injury (PI) tissue using hyperspectral images to serve as a guideline for the treatment and care of PIs.This study used a prospective design. A total of 30 patients with sacral PIs were recruited from the rehabilitation ward of a teaching hospital. The authors used a hyperspectral detector to collect wound images and the Beer-Lambert law to estimate changes in tissue StO 2 in different stages of PI.The tissue StO 2 of healthy skin and that of stage 1 PI skin were similar, whereas the tissue StO 2 of the wound in stage 2 PIs was significantly higher than that of healthy skin and scabbed tissue (medians, 82.5%, 74.4%, and 68.3%; P.05). In stage 3 PIs, StO 2 was highest in subcutaneous tissue and adipose tissue (82.5%) and lowest in peripheral scabs (68.35%). The tissue StO 2 was highest in subcutaneous tissue in stage 4 PIs, and this tissue was red in the hyperspectral spectrum. The scab-covered area of unstageable PIs had the lowest StO 2 of all PI tissue types (median, 44.3%).Hyperspectral imaging provides physiologic information on wound microcirculation, which can enable better evaluation of healing status. Assessing tissue StO 2 data can provide a clinical index of wound healing.

Near-infrared spectroscopy (NIRS) allows for the rapid estimation of a wide range of wood properties. Typically, NIRS studies on wood have utilized benchtop spectrometers, but efforts to utilize NIR hyperspectral imaging to examine wood and wood products have increased. Compared to benchtop NIR systems, hyperspectral imaging has several advantages (speed, visualization of spatial variability), but the data typically have a lower signal-to-noise ratio as well as fewer wavelengths saved; thus, hyperspectral imaging systems have a larger spectral sampling interval (SSI). Furthermore, the SSI and wavelength range varies considerably among different HSI cameras. NIR-HSI systems based on indium gallium arsenide (InGaAs) detectors have a wavelength range typically from 900 to 1700 nm, while short-wave infrared hyperspectral imaging (SWIR-HSI) systems based on mercury cadmium telluride (MCT) detectors have the ‘full’ NIR wavelength range from 1000 to 2500 nm. These factors may influence the performance of wood property calibrations. We compared one NIR-HSI (900–1700 nm) and three SWIR-HSI (1000–2500 nm) commercially available cameras with an NIRS benchtop spectrometer (1100–2500 nm). The performance of specific gravity (SG) and stiffness (MOE) calibration models was compared with one-hundred Douglas-fir (Pseudotsuga menziesii) samples. The limited wavelength range of an NIR-HSI camera provided the best models for MOE, whereas the NIR-HSI and two SWIR-HSI cameras provided similar SG results. SWIR-HSI models heavily favored wavelengths greater than 1900 nm.

This paper focuses on automatic Cholangiocarcinoma (CC) diagnosis from microscopic hyperspectral (HSI) pathological dataset with deep learning method. The first benchmark based on the microscopic hyperspectral pathological images is set up. Particularly, 880 scenes of multidimensional hyperspectral Cholangiocarcinoma images are collected and manually labeled each pixel as either tumor or non-tumor for supervised learning. Moreover, each scene from the slide is given a binary label indicating whether it is from a patient or a normal person. Different from traditional RGB images, the HSI acquires pixels in multiple spectral intervals, which is added as an extension on the channel dimension of 3-channel RGB image. This work aims at fully exploiting the spatial-spectral HSI data through a deep Convolution Neural Network (CNN). The whole scene is first divided into several patches. Then they are fed into CNN for the tumor/non-tumor binary prediction and the tumor area regression. The further diagnosis on the scene is made by random forest based on the features from patch prediction. Experiments show that HSI provides a more accurate result than RGB image. Moreover, a spectral interval convolution and normalization scheme are proposed for further mining the spectral information in HSI, which demonstrates the effectiveness of the spatial-spectral data for CC diagnosis.

Over the last decade, hyperspectral imaging has become a popular technique for the non-invasive identification and mapping of painting materials in many typologies of artworks, thanks to the possibility of obtaining spectral information over the spatial region. A few attempts have also been made on stained-glass windows to identify the chromophore elements responsible for glass color. Hyperspectral imaging of stained glass can be complex; in most cases, stained-glass windows are an integral part of buildings, and sunlight represents the natural light source for illuminating these artifacts. While it may be considered an advantage, sunlight is not homogeneous throughout the day, and different weather conditions can affect the quality of the hyperspectral images. In addition, the presence of buildings and vegetation in the background could also modify the colors of the stained-glass windows and consequently alter the characteristic peaks of the chromophores in the spectra. This work aims to solve some of these issues and proposes different strategies to improve the results obtainable in situ. The methodology was tested on stained-glass panels displayed in the windows of the Swiss National Museum. Stained-glass panels located in windows of an internal wall were also analyzed, developing a lighting setup to account for the lack of natural light. Hyperspectral images of the selected stained glass were acquired multiple times, choosing different transmittance references for the preprocessing and exposure time to evaluate differences in the collected spectral images. The use of a diffuser sheet to mitigate the effect of external factors was also tested on some panels exposed to sunlight. Results from representative case studies will be presented to discuss the feasibility and limitations of in-situ hyperspectral imaging applications on stained glass and provide some general recommendations to consider during the acquisitions.

In boreal forests, European aspen (Populus tremula L.) is a keystone species that hosts a variety of accompanying species including epiphytic lichens. Forest management actions have led to a decrease in aspen abundance and subsequent loss of suitable habitats of epiphytic lichens. In this study, we evaluate the environmental responses of epiphytic lichen species richness and community composition on aspen, focusing on the potential of remote sensing by combined hyperspectral imaging and airborne laser scanning to identify suitable habitats for epiphytic lichens. We measured different substrate and habitat parameters in the field (e.g., aspen diameter and bark pH) and by remote sensing (e.g., mean canopy height and tree species composition of the surrounding forest) in the study area in Southern Finland that includes protected and non-protected forest. We used linear regression and the Hierarchical Model of Species Communities (HMSC) to compare how the different parameters explain and predict lichen species richness and community composition, respectively. We show that coarse predictions of epiphytic lichen community composition can be made using parameters extracted from remote sensing data. Estimated mean canopy height, tree density, dominant tree species and tree species diversity of the stand predicted the species community on aspens slightly better than field parameters. Remote sensing variables calculated over a larger area (30 m radius) always outperformed the same variables calculated over a smaller area (10 m radius) in predicting community composition, highlighting the cost-efficiency of remote sensing compared to covering a similar area with on-ground measurements. These results are encouraging for the prospects of using remote sensing data to direct field inventories and to map potential high-biodiversity habitats. Aspen bark pH was the only parameter affecting species richness regardless of whether the forest was protected or not, whereas, interestingly, the effects of tree diameter, height and furrow depth were only significant in protected areas. Our results also underline the importance of protected areas, since they hosted a higher tree-specific number of epiphytic lichen species, and red listed species, than non-protected areas.

Monitoring insects of different species to understand the factors affecting their diversity and decline is a major challenge. Laser remote sensing and spectroscopy offer promising novel solutions to this. Coherent scattering from thin wing membranes also known as wing interference patterns (WIPs) have recently been demonstrated to be species specific. The colors of WIPs arise due to unique fringy spectra, which can be retrieved over long distances. To demonstrate this, a new concept of infrared (950–1650 nm) hyperspectral lidar with 64 spectral bands based on a supercontinuum light source using ray-tracing and 3D printing is developed. A lidar with an unprecedented number of spectral channels, high signal-to-noise ratio, and spatio-temporal resolution enabling detection of free-flying insects and their wingbeats. As proof of principle, coherent scatter from a damselfly wing at 87 m distance without averaging (4 ms recording) is retrieved. The fringed signal properties are used to determine an effective wing membrane thickness of 1412 nm with ±4 nm precision matching laboratory recordings of the same wing. Similar signals from free flying insects (2 ms recording) are later recorded. The accuracy and the method's potential are discussed to discriminate species by capturing coherent features from free-flying insects.

Colon cancer is a disease characterized by the unusual and uncontrolled development of cells that are found in the large intestine. If the tumour extends to the lower part of the colon (rectum), the cancer may be colorectal. Medical imaging is the denomination of methods used to create visual representations of the human body for clinical analysis, such as diagnosing, monitoring, and treating medical conditions. In this research, a computational proposal is presented to aid the diagnosis of colon cancer, which consists of using hyperspectral images obtained from slides with biopsy samples of colon tissue in paraffin, characterizing pixels so that, afterwards, imaging techniques can be applied. Using computer graphics augmenting conventional histological deep learning architecture, it can classify pixels in hyperspectral images as cancerous, inflammatory, or healthy. It is possible to find connections between histochemical characteristics and the absorbance of tissue under various conditions using infrared photons at various frequencies in hyperspectral imaging (HSI). Deep learning techniques were used to construct and implement a predictor to detect anomalies, as well as to develop a computer interface to assist pathologists in the diagnosis of colon cancer. An infrared absorbance spectrum of each of the pixels used in the developed classifier resulted in an accuracy level of 94% for these three classes.

Abnormal target detection in hyperspectral remote sensing image is one of the hotspots in image research. The image noise generated in the detection process will lead to the decline of the quality of hyperspectral remote sensing image. In view of this, this paper proposes an abnormal target detection method of hyperspectral remote sensing image based on the convolution neural network. Firstly, the deep residual learning network model has been used to remove the noise in hyperspectral remote sensing image. Secondly, the spatial and spectral features of hyperspectral remote sensing images were used to optimize the clustering dictionary, and then the image segmentation containing target information is completed. Finally, the image was input into the deep convolution neural network with a dual classifier, and the network detects the abnormal target in the image. The test results of this algorithm show that the structural similarity of the denoised image is higher than 0.86, which shows that this method has good noise reduction performance, image details will not damage, segmentation effect is good, and it can obtain high-definition target image information and accurately detect abnormal targets in the image.

Solar photovoltaic power plants are in rapid expansion throughout the world, with the total area occupied by panels being linked to the total electrical power produced. This paper considers this case as an instance of the generic problem of estimating the total area occupied by a class of interest in spaceborne hyperspectral images. As the spatial resolution characterizing these sensors is too coarse, spectral unmixing techniques identify the contribution of a specific material to the spectrum related to a single image element. Final results are obtained by summing all contributions in an area of interest, and favourably compared to pixel-based detection, also using higher resolution Sentinel-2 data. The data used in this paper are acquired by the currently operative DESIS sensor, mounted on the International Space Station, encouraging the use of spaceborne imaging spectrometers for such applications.

The most common burn wound assessment continues to be the clinical inspection and the tactile examination, which are subjective and remain challenging even for experienced burn surgeons. Recently, hyperspectral imaging camera systems have been increasingly used to support the evaluation of burn wounds. The aim of our study was to determine if hyperspectral imaging analysis differentiates and objectifies the assessment of burn wounds in burns of the upper extremities. We included 97 superficial partial, deep partial dermal burns, and full thickness burns. Hyperspectral imaging analysis was performed for all burns using proprietary software. The software recorded parameters for tissue oxygenation (StO2), tissue hemoglobin index, and near-infrared perfusion. These values were compared with the recordings for healthy, non-burned skin. We found that hyperspectral imaging analysis effectively differentiates burn wounds and shows the ability to distinguish even superficial partial burns from deep partial burns in the near-infrared perfusion analysis feature. Although, it was not possible to differentiate burn wounds in all features. Currently, it is important to optimize the respective reference values of the individual burn degrees for an objectified assessment.

The purpose of this research is to seek a better inversion algorithm. And on this basis, it explores the feasibility of using hyperspectral monitoring technology instead of laboratory physical and chemical index test and evaluates the prediction effect of inversion model on water quality change. So as to be more convenient, more economical and extensive monitoring methods for water quality monitoring of urban internal river are provided. This paper takes the water samples collected in Fuyang River in downtown Handan as the research object and obtains original spectral data of the samples by the ASD FieldSpec 4 field hyperspectral spectrometer. After the smoothing filter pretreatment by the Savitzky-Golay (SG) method and specified mathematical transformations, the modeling spectral indicators of various water quality parameters are selected and determined by calculating the maximum mean of absolute values for correlation coefficients of various spectral indicators and measured values in the wavelength range from 400 to 950 nm. By introducing partial least squares (PLS), random forest (RF), and Lasso (least absolute shrinkage and selection operator), six water quality parameter fitting models were constructed including turbidity (Turb), suspended substance (SS), chemical oxygen demand (COD), NH4-N, total nitrogen (TN), and total phosphorus (TP), which are also testified and evaluated through hyperspectral data. The results show that different spectral transformation methods highlight different information inversion effects. The first derivative of reciprocal logarithm of spectral data after SG smoothing has a good modeling effect on four water quality parameters including Turb, COD, NH

This paper explores the problem of recovering the discriminative representation of a hyperspectral remote sensing image (HRSI), which suffers from spectral variations, to boost its classification accuracy. To tackle this challenge, we propose a new method, namely local-global balanced low-rank approximation (GLB-LRA), which can increase the similarity between pixels belonging to an identical category while promoting the discriminability between pixels of different categories. Specifically, by taking advantage of the particular structural spatial information of HRSIs, we exploit the low-rankness of an HRSI robustly in both spatial and spectral domains from the perspective of local and global balance. We mathematically formulate GLB-LRA as an explicit optimization problem and propose an iterative algorithm to solve it efficiently. Experimental results over three commonly-used benchmark datasets demonstrate the significant superiority of our method over state-of-the-art methods.

Spectral super-resolution is a very important technique to obtain hyperspectral images from only multispectral images, which can effectively solve the high acquisition cost and low spatial resolution of hyperspectral images. However, in practice, multispectral channels or images captured by the same sensor are often with different spatial resolutions, which brings a severe challenge to spectral super-resolution. This paper proposed a universal spectral super-resolution network based on physical optimization unfolding for arbitrary multispectral images, including single-resolution and cross-scale multispectral images. Furthermore, two new strategies are proposed to make full use of the spectral information, namely, cross-dimensional channel attention and cross-depth feature fusion. Experimental results on five data sets show superiority and stability of PoNet addressing any spectral super-resolution situations.

The proposed study was carried out to develop a fast and efficient strategy for plastic waste sensor-based sorting in recycling plants, based on hyperspectral imaging (HSI), combined with variable selection methods, to produce a high-quality recycled polyethylene terephthalate (PET) flakes stream. Variable selection techniques were applied in order to identify a limited number of spectral bands useful to recognize the presence of other plastic materials, considered as contaminant, inside a stream of recycled PET flakes, reducing processing time as requested by sorting online applications. Post-consumer plastic samples were acquired by HSI device working in the short-wave infrared (SWIR) range (1000 - 2500 nm). As a first step, the hypercubes were processed applying chemometric logics to build a partial least squares discriminant analysis (PLSDA) classification model using the full investigated spectral range, able to identify PET and contaminant classes. As a second step, two different variable selection methods were then applied, i.e., interval PLSDA (I-PLSDA) and variable importance in projection (VIP) scores, in order to identify a limited number of spectral bands useful to recognize the two classes and to evaluate the best method, showing efficiency values close to those obtained by the full spectrum model. The best result was achieved by the VIP score method with an average efficiency value of 0.98. The obtained results suggested that the variables selection method can represent a powerful approach for the sensor-based sorting-online, decreasing the amount of data to be processed and thus enabling faster recognition compared to the full spectrum model.

Lattice self-assemblies (LSAs), which mimic protein assemblies, were studied using a new nonlinear vibrational imaging technique called vibrational sum-frequency generation (VSFG) microscopy. This technique successfully mapped out the mesoscopic morphology, microscopic geometry, symmetry, and ultrafast dynamics of an LSA formed by β-cyclodextrin (β-CD) and sodium dodecyl sulfate (SDS). The spatial imaging also revealed correlations between these different physical properties. Such knowledge shed light on the functions and mechanical properties of LSAs. In this Feature Article, we briefly introduce the fundamental principles of the VSFG microscope and then discuss the in-depth molecular physics of the LSAs revealed by this imaging technique. The application of the VSFG microscope to the artificial LSAs also paved the way for an alternative approach to studying the structure-dynamic-function relationships of protein assemblies, which were essential for life and difficult to study because of their various and complicated interactions. We expect that the hyperspectral VSFG microscope could be broadly applied to many noncentrosymmetric soft materials.

Estimating endmembers and corresponding abundances from mixed pixels are essential steps for hyperspectral unmixing. In hyperspectral unmixing, obtaining accurate unmixing results is difficult since less prior knowledge is available. Besides, the unmixing results are influenced by noise and highly correlated endmembers, so that the obtained abundance maps exist small values which are not present in the image. In this paper, we separate each abundance map into a feature layer and a sparse layer to protect the obtained abundance maps from the above-mentioned factors. The feature layer represents the main information of the abundance map. And the sparse layer contains outliers dominated by the above-mentioned factors. In particular, we design a feature extraction regularization to describe the feature layer and use a weighted l 1 norm to describe the sparse layer. Then, under the framework of non-negative tensor factorization (NTF), we propose a novel unmixing algorithm named spatial feature extraction NTF (SFE-NTF) for hyperspectral unmixing. The proposed SFE-NTF is based on an augmented multiplicative algorithm. Experimental results on both synthetic and real hyperspectral data demonstrate that the proposed algorithm outperforms other state-of-the-art algorithms.

Band selection is one of the most effective methods to reduce the band redundancy of hyperspectral images (HSIs). Most existing band selection methods tend to regard each band as a whole, and then explore the band redundancy with the pixel-wise features directly. However, since the regions of HSIs corresponding to different objects have diverse spectral properties and spatial structure, such above scheme limits the performance of hyperspectral band selection due to the lack of spatial information. To address above issues, a novel band selection method via region-aware latent features fusion based clustering (RLFFC) is proposed. Specifically, we employ the superpixel segmentation to segment HSIs into multiple regions so that the spatial information of HSIs can be fully preserved. In order to capture the priori information, we construct its corresponding Laplacian matrix from which a group of low dimensional latent features are generated to further enhance the separability among different bands. Then, a shared latent feature representation of HSIs is obtained by fusing region-aware latent features to effectively capture the band redundancy of HSIs. Finally, the k -means clustering algorithm is utilized to obtain the index of the selected bands from the shared latent feature representation. As a result, the spectral and spatial properties are well exploited in the proposed method. Extensive experiments on four public hyperspectral datasets show that the proposed method achieves superior performance when compared with other state-of-the-art ones.

Our ability to interrogate and manipulate the genome far exceeds our capacity to measure the effects of genetic changes on plant traits. Much effort has been made recently by the plant science research community to address this imbalance. The responses of plants to environmental conditions can now be defined using a variety of imaging approaches. Hyperspectral imaging (HSI) has emerged as a promising approach to measure traits using a wide range of wavebands simultaneously in 3D to capture information in lab, glasshouse, or field settings. HSI has been applied to define abiotic, biotic, and quality traits for optimisation of crop management.

The key to hyperspectral anomaly detection is to effectively distinguish anomalies from the background, especially in the case that background is complex and anomalies are weak. Hyperspectral imagery (HSI) as an image-spectrum merging cube data can be intrinsically represented as a third-order tensor that integrates spectral information and spatial information. In this article, a prior-based tensor approximation (PTA) is proposed for hyperspectral anomaly detection, in which HSI is decomposed into a background tensor and an anomaly tensor. In the background tensor, a low-rank prior is incorporated into spectral dimension by truncated nuclear norm regularization, and a piecewise-smooth prior on spatial dimension can be embedded by a linear total variation-norm regularization. For anomaly tensor, it is unfolded along spectral dimension coupled with spatial group sparse prior that can be represented by the l2,1-norm regularization. In the designed method, all the priors are integrated into a unified convex framework, and the anomalies can be finally determined by the anomaly tensor. Experimental results validated on several real hyperspectral data sets demonstrate that the proposed algorithm outperforms some state-of-the-art anomaly detection methods.

Metasurfaces, which are ultrathin planar artificial materials flexibly controlling the phase, amplitude, and polarization of the light, have facilitated the high integration and miniaturization of hyperspectral imaging systems. However, the pushbroom hyperspectral imaging systems based on metasurfaces usually face the large smile and keystone, which reduces the spectral uniformity and the fidelity of the spectral information. Moreover, the employment of many metasurfaces would cause manufacturing difficulties. In this paper, a planar hyperspectral imager only using two metasurfaces is proposed to achieve a spectral resolution of 3.5 nm in 850-1000 nm band with the near diffraction-limited focusing capability, and its maximum of smile and keystone reach to 124.4 μm and 33.6 μm for the image plane size of 4.75 mm × 1.35 mm and pixel size of 26 μm × 26 μm, respectively. This imager can provide a promising avenue for portable environmental monitoring systems and wearable electronic consumer products.

This study aimed to understand the spectral changes induced by Podosphaera xanthii, the causal agent of powdery mildew, in cucumber leaves from the moment of inoculation until visible symptoms are apparent. A principal component analysis (PCA) was applied to the spectra to assess the spectral separability between healthy and infected leaves. A spectral ratio between infected and healthy leaf spectra was used to determine the best wavelengths for detecting the disease. Additionally, the spectra were used to compute two spectral variables [i.e., the red-well point (RWP) and the red-edge inflexion point (REP)]. A linear support vector machine (SVM) classifier was applied to certain spectral features to assess how well these features can separate the infected leaves from the healthy ones. The PCA showed that a good separability could be achieved from 4 days post-inoculation (DPI). The best model to fit the RWP and REP wavelengths corresponded to a linear model. The linear model had a higher adjusted R2 for the infected leaves than for the healthy leaves. The SVM trained with five first principal components scores achieved an overall accuracy of 95% at 4 DPI (i.e., two days before the visible symptoms). With the RWP and REP parameters, the SVM accuracy increased as a function of the day of inoculation, reaching 89% and 86%, respectively, when symptoms were visible at 6 DPI. Further research must consider a higher number of samples and more temporal repetitions of the experiment.

Multiple and heterogenous Earth observation (EO) platforms are broadly used for a wide array of applications, and the integration of these diverse modalities facilitates better extraction of information than using them individually. The detection capability of the multispectral unmanned aerial vehicle (UAV) and satellite imagery can be significantly improved by fusing with ground hyperspectral data. However, variability in spatial and spectral resolution can affect the efficiency of such dataset's fusion. In this study, to address the modality bias, the input data was projected to a shared latent space using cross-modal generative approaches or guided unsupervised transformation. The proposed adversarial networks and variational encoder-based strategies used bi-directional transformations to model the cross-domain correlation without using cross-domain correspondence. It may be noted that an interpolation-based convolution was adopted instead of the normal convolution for learning the features of the point spectral data (ground spectra). The proposed generative adversarial network-based approach employed dynamic time wrapping based layers along with a cyclic consistency constraint to use the minimal number of unlabeled samples, having cross-domain correlation, to compute a cross-modal generative latent space. The proposed variational encoder-based transformation also addressed the cross-modal resolution differences and limited availability of cross-domain samples by using a mixture of expert-based strategy, cross-domain constraints, and adversarial learning. In addition, the latent space was modelled to be composed of modality independent and modality dependent spaces, thereby further reducing the requirement of training samples and addressing the cross-modality biases. An unsupervised covariance guided transformation was also proposed to transform the labelled samples without using cross-domain correlation prior. The proposed latent space transformation approaches resolved the requirement of cross-domain samples which has been a critical issue with the fusion of multi-modal Earth observation data. This study also proposed a latent graph generation and graph convolutional approach to predict the labels resolving the domain discrepancy and cross-modality biases. Based on the experiments over different standard benchmark airborne datasets and real-world UAV datasets, the developed approaches outperformed the prominent hyperspectral panchromatic sharpening, image fusion, and domain adaptation approaches. By using specific constraints and regularizations, the network developed was less sensitive to network parameters, unlike in similar implementations. The proposed approach illustrated improved generalizability in comparison with the prominent existing approaches. In addition to the fusion-based classification of the multispectral and hyperspectral datasets, the proposed approach was extended to the classification of hyperspectral airborne datasets where the latent graph generation and convolution were employed to resolve the domain bias with a small number of training samples. Overall, the developed transformations and architectures will be useful for the semantic interpretation and analysis of multimodal data and are applicable to signal processing, manifold learning, video analysis, data mining, and time series analysis, to name a few., This research was partly supported by the Hebrew University of Jerusalem Intramural Research Found Career Development, Association of Field Crop Farmers in Israel and the Chief Scientist of the Israeli Ministry of Agriculture and Rural Development (projects 20-02-0087 and 12-01-0041).

Hyperspectral infrared satellite observations from geostationary platforms allow for the retrieval of temperature and water vapor measurements with higher temporal and vertical resolution than was previously available. The Chinese satellite Fengyun-4A (FY-4A) includes the Geostationary Interferometric Infrared Sounder (GIIRS), which has the ability to measure vertical profiles of temperature and water vapor from space at times when ground-based upper-air soundings are not available and can fill an important need in short-range weather prediction. In this study, convective available potential energy (CAPE) and lifted index (LI), which are used for forecasting atmospheric instability, were computed using the SHARPpy algorithm used by the NWS Storm Prediction Center. However, remote infrared and microwave sensing is lacking detailed information in the boundary layer, so the addition of the NOAA Meteorological Assimilation and Data Ingest System (MADIS) surface data may be necessary in order to get accurate temperature and moisture measurement near the surface. This study uses 10–16 May 2019 in the coastal region near Hong Kong for evaluating the use of hourly surface observations combined with satellite soundings from FY-4A GIIRS at 2-h intervals. The GIIRS plus MADIS surface-based CAPE and LI estimates are compared to estimates derived from low-Earth-orbiting (LEO) SNPP and NOAA-20 from NOAA, MetOp from EUMETSAT, NWP reanalysis, and local radiosondes. In the case study, the 2-h sampling interval of the GIIRS geostationary sounder was able to capture the rapid transition (16 h) from a stable to an unstable atmosphere in both CAPE and LI. The use of surface observations with satellite soundings gave mixed results, possibly due to the complex terrain near Hong Kong.

Modelling of material appearance from reflectance measurements has become increasingly prevalent due to the development of novel methodologies in Computer Graphics. In the last few years, some advances have been made in measuring the light-material interactions, by employing goniometers/reflectometers under specific laboratory’s constraints. A wide range of applications benefit from data-driven appearance modelling techniques and material databases to create photorealistic scenarios and physically based simulations. However, important limitations arise from the current material scanning process, mostly related to the high diversity of existing materials in the real-world, the tedious process for material scanning and the spectral characterisation behaviour. Consequently, new approaches are required both for the automatic material acquisition process and for the generation of measured material databases. In this study, a novel approach for material appearance acquisition using hyperspectral data is proposed. A dense 3D point cloud filled with spectral data was generated from the images obtained by an unmanned aerial vehicle (UAV) equipped with an RGB camera and a hyperspectral sensor. The observed hyperspectral signatures were used to recognise natural and artificial materials in the 3D point cloud according to spectral similarity. Then, a parametrisation of Bidirectional Reflectance Distribution Function (BRDF) was carried out by sampling the BRDF space for each material. Consequently, each material is characterised by multiple samples with different incoming and outgoing angles. Finally, an analysis of BRDF sample completeness is performed considering four sunlight positions and 16x16 resolution for each material. The results demonstrated the capability of the used technology and the effectiveness of our method to be used in applications such as spectral rendering and real-word material acquisition and classification.

The problem of effectively exploiting the information multiple data sources has become a relevant but challenging research topic in remote sensing. In this paper, we propose a new approach to exploit the complementarity of two data sources: hyperspectral images (HSIs) and light detection and ranging (LiDAR) data. Specifically, we develop a new dual-channel spatial, spectral and multiscale attention convolutional long short-term memory neural network (called dual-channel A3CLNN) for feature extraction and classification of multisource remote sensing data. Spatial, spectral and multiscale attention mechanisms are first designed for HSI and LiDAR data in order to learn spectral- and spatial-enhanced feature representations, and to represent multiscale information for different classes. In the designed fusion network, a novel composite attention learning mechanism (combined with a three-level fusion strategy) is used to fully integrate the features in these two data sources. Finally, inspired by the idea of transfer learning, a novel stepwise training strategy is designed to yield a final classification result. Our experimental results, conducted on several multisource remote sensing data sets, demonstrate that the newly proposed dual-channel A3CLNN exhibits better feature representation ability (leading to more competitive classification performance) than other state-of-the-art methods., Comment: 16 pages, 10 figures

Hyperspectral unmixing plays an important role in hyperspectral imagery (HSI) processing. Numerous unmixing algorithms have been proposed over the last decades. In this letter, we focus on the blind source separation model, which has drawn much attention in the hyperspectral community. However, the nonconvexity of the blind unmixing method often suffers from undesired solution. Thus, additional assumptions and regularizations are required to advance the unmixing performance. In this work, we proposed a new weighted total variation regularized blind unmixing (wtvBU) for HSI. The nonconvex sparsity-inducing function log-exp was exploited to build the weight matrix, which promotes the smooth transitions in the abundance map while preserving the spatial contextual information of the image scene. The proposed algorithm was efficiently solved via the alternating direction method of multipliers. Experimental results on two benchmark HSIs demonstrated that wtvBU achieved competitive performance when compared with other state-of-the-art unmixing algorithms.

The use of deep learning methods in hyperspectral image (HSI) classification has been a promising approach due to its powerful ability to automatically extract features in recent years. This article proposes a novel deep framework for HSI classification problems, referred to as feature-grouped network based on spectral-spatial connected attention mechanism (FG-SSCA). Different from the existing deep learning methods, the proposed framework integrates the spectral attention module and spatial attention module continuously from the raw HSI input, which is embedded into convolutional neural networks and could enhance the distinguishing ability of spectral bands and learn the spatial relevance between the neighboring pixels together. Meanwhile, the generating feature maps are sliced into a series of small groups in sequence along the direction of spectral bands and each group sequentially extracts spatial-spectral features through multiple spectral and spatial residual blocks. This feature-grouped strategy could fully utilize the redundancy and difference of bands and obtain more available and valuable information. The proposed FG-SSCA method could greatly improve generalization performance and make tremendous successes in HSI classification. Experimental results on several HSI benchmark data sets verify the effectiveness and superiority of the proposed method in comparison with the state-of-the-art approaches for HSI classification.

The bilateral filter (BF) is a nonlinear filtering method, which can remove noise and retain better edge information. It has been widely used in the field of hyperspectral images (HSIs) filtering. In this letter, we propose a novel spectral-spatial information integration method based on the BF with multispatial domain (MBF). The proposed method includes three steps. First, principal component analysis (PCA) is used for the original HSI to obtain multiple components containing almost all information; second, multiple principal components are used as both spatial domain and range domain information for BF; finally, the extreme learning machine (ELM) is used for classification. To verify the effectiveness of the proposed approach, we evaluate performance on three benchmark data sets. Our method will improve the existing filtering methods by constructing multiple spatial domains for filtering, which will make more effective use of spatial features and solve the problem of lack of spatial information in HSIs. This method is compared with other filtering algorithms. Comparative experiments show that our proposed method can improve the classification accuracy. And the MBF information is more effective than the BF with single spatial domain information and other filtering methods.

Hyperspectral anomaly detection is a popular topic in remote sensing image intelligent interpretation. To detect anomaly, many methods for background representation have been proposed. However, the prior information of background and anomaly is not fully explored in these methods. To tackle this issue, we combine low-rank dictionary learning (LRDL) with total variation (TV) constraint for hyperspectral anomaly detection. To be specific, the LRDL is introduced for background representation to explore the low-rank priori of background. Considering the smooth structural characteristic of background in spatial, we introduce the TV constraint on coefficients matrix for better background representation learning. Then the residual part is used to discriminate anomaly. The experiments on three real data sets demonstrate the effectiveness of the proposed method compared with state-of-the-art algorithms in hyperspectral anomaly detection.