Investigation on Physiological Status of Regional Vegetation Using Pushbroom Hyperspectral Imager Data

To extract vegetation pigment concentration and physiological status has been studied in two test areas covered with swamp and flourish vegetation using pushbroom hyperspectral imager (PHI) data which flied in September of 2000 at Daxing'anling district of Heilongjiang Province, China. The ratio analysis of reflectance spectra (RARS) indices, which were put forward by Chappelle et al (1992), are chosen in this paper owing to their effect and simpleness against both comparison with various methods and techniques for exploration of pigment concentration and characteristics of PHI data. The correlation coefficients between RARS indices and pigment concentration of vegetation were up to 0.8. The new RARS indices modes are established in the two test areas using both PHI data and spectra of different vegetations measured in the field. The indices' parameter images of chlorophyll a (Chl a), chlorophyll b (Chl b) and carotenoids (Cars) of the test areas covered with swamp and flourish vegetation are acquired by the new RARS indices modes. Furthermore, the regional concentration of Chl a and Chl b are extracted and quantified using regression equations between RARS indices and pigment concentrations, which were built by Blackburn (1998). The results showed the physiological status and variety clearly, and are in good agreement with the distribution of vegetation in the field.

Early detection of pine wilt disease in Pinus tabuliformis in North China using a field portable spectrometer and UAV-based hyperspectral imagery

Background:Pine wilt disease(PWD)is a major ecological concern in China that has caused severe damage to millions of Chinese pines(Pinus tabulaeformis).To control the spread of PWD,it is necessary to develop an effective approach to detect its presence in the early stage of infection.One potential solution is the use of Unmanned Airborne Vehicle(UAV)based hyperspectral images(HIs).UAV-based HIs have high spatial and spectral resolution and can gather data rapidly,potentially enabling the effective monitoring of large forests.Despite this,few studies examine the feasibility of HI data use in assessing the stage and severity of PWD infection in Chinese pine.Method:To fill this gap,we used a Random Forest(RF)algorithm to estimate the stage of PWD infection of trees sampled using UAV-based HI data and ground-based data(data directly collected from trees in the field).We compared relative accuracy of each of these data collection methods.We built our RF model using vegetation indices(VIs),red edge parameters(REPs),moisture indices(MIs),and their combination.Results:We report several key results.For ground data,the model that combined all parameters(OA:80.17%,Kappa:0.73)performed better than VIs(OA:75.21%,Kappa:0.66),REPs(OA:79.34%,Kappa:0.67),and MIs(OA:74.38%,Kappa:0.65)in predicting the PWD stage of individual pine tree infection.REPs had the highest accuracy(OA:80.33%,Kappa:0.58)in distinguishing trees at the early stage of PWD from healthy trees.UAV-based HI data yielded similar results:the model combined VIs,REPs and MIs(OA:74.38%,Kappa:0.66)exhibited the highest accuracy in estimating the PWD stage of sampled trees,and REPs performed best in distinguishing healthy trees from trees at early stage of PWD(OA:71.67%,Kappa:0.40).Conclusion:Overall,our results confirm the validity of using HI data to identify pine trees infected with PWD in its early stage,although its accuracy must be improved before widespread use is practical.We also show UAV-based data PWD classifications are less accurate but comparable to those of ground-based data.We believe that these results can be used to improve preventative measures in the control of PWD.

Graph-Based Dimensionality Reduction for Hyperspectral Imagery: A Review

Hyperspectral image(HSI)contains a wealth of spectral information,which makes fine classification of ground objects possible.In the meanwhile,overly redundant information in HSI brings many challenges.Specifically,the lack of training samples and the high computational cost are the inevitable obstacles in the design of classifier.In order to solve these problems,dimensionality reduction is usually adopted.Recently,graph-based dimensionality reduction has become a hot topic.In this paper,the graph-based methods for HSI dimensionality reduction are summarized from the following aspects.1)The traditional graph-based methods employ Euclidean distance to explore the local information of samples in spectral feature space.2)The dimensionality-reduction methods based on sparse or collaborative representation regard the sparse or collaborative coefficients as graph weights to effectively reduce reconstruction errors and represent most important information of HSI in the dictionary.3)Improved methods based on sparse or collaborative graph have made great progress by considering global low-rank information,local intra-class information and spatial information.In order to compare typical techniques,three real HSI datasets were used to carry out relevant experiments,and then the experimental results were analysed and discussed.Finally,the future development of this research field is prospected.

An airborne pushbroom hyperspectral imager with wide field of view

An airborne pushbroom hyperspectrai imager （APHI） with wide field （42° field of view） is presented. It is composed of two 22° field of view （FOV） imagers and can provide 1304 pixels in spatial dimension, 124 bands in spectral dimension in one frame. APHI has a bandwidth ranging from 400 to 900 nm. The spectral resolution is 5 nm and the spatial resolution is 0.6 m at 1000-m height. The implementation of this system is helpful to overcome the restriction of FOV in pushbroom hyperspectral imaging in a more feasible way. The electronic and optical designs axe also introduced in detail.

Optimized extreme learning machine for urban land cover classification using hyperspectral imagery

This work presents a new urban land cover classification framework using the firefly algorithm （FA） optimized extreme learning machine （ELM）. FA is adopted to optimize the regularization coefficient C and Ganssian kernel σ for kernel ELM. Additionally, effectiveness of spectral features derived from an FA-based band selection algorithm is studied for the proposed classification task. Three sets of hyperspectral databases were recorded using different sensors, namely HYDICE, HyMap, and AVIRIS. Our study shows that the proposed method outperforms traditional classification algorithms such as SVM and reduces computational cost significantly.

Hyperspectral Imagery Denoising Using a Spatial-Spectral Domain Mixing Prior

By introducing a novel spatial-spectral domain mixing prior, this paper establishes a Maximum a posteriori （MAP） framework for hyperspectral images （HSIs） denoising. The proposed mixing prior takes advantage of different properties of HSI in the spatial and spectral domain. Furthermore, we propose a spatially adaptive weighted prior combining smoothing prior and discontinuity-preserving prior in the spectral domain. The weights can be defined as a function of the spectral discontinuity measure （DM）. For minimizing the objective function, a half-quadratic optimization algorithm is used. The experimental results illustrate that our proposed model can get a higher signal-to-noise ratio （SNR） than using only smoothing prior or discontinuity-preserving prior.

Method for evaluation of geological strength index of carbonate cliff rocks:Coupled hyperspectral-digital borehole image technique

The deterioration of unstable rock mass raised interest in evaluating rock mass quality.However,the traditional evaluation method for the geological strength index(GSI)primarily emphasizes the rock structure and characteristics of discontinuities.It ignores the influence of mineral composition and shows a deficiency in assessing the integrity coefficient.In this context,hyperspectral imaging and digital panoramic borehole camera technologies are applied to analyze the mineral content and integrity of rock mass.Based on the carbonate mineral content and fissure area ratio,the strength reduction factor and integrity coefficient are calculated to improve the GSI evaluation method.According to the results of mineral classification and fissure identification,the strength reduction factor and integrity coefficient increase with the depth of rock mass.The rock mass GSI calculated by the improved method is mainly concentrated between 40 and 60,which is close to the calculation results of the traditional method.The GSI error rates obtained by the two methods are mostly less than 10%,indicating the rationality of the hyperspectral-digital borehole image coupled evaluation method.Moreover,the sensitivity of the fissure area ratio(Sr)to GSI is greater than that of the strength reduction factor(a),which means the proposed GSI is suitable for rocks with significant fissure development.The improved method reduces the influence of subjective factors and provides a reliable index for the deterioration evaluation of rock mass.

Quantification of the adulteration concentration of palm kernel oil in virgin coconut oil using near-infrared hyperspectral imaging

The adulteration concentration of palm kernel oil(PKO)in virgin coconut oil(VCO)was quantified using near-infrared(NIR)hyperspectral imaging.Nowadays,some VCO is adulterated with lower-priced PKO to reduce production costs,which diminishes the quality of the VCO.This study used NIR hyperspectral imaging in the wavelength region 900-1,650 nm to create a quantitative model for the detection of PKO contaminants(0-100%)in VCO and to develop predictive mapping.The prediction equation for the adulteration of VCO with PKO was constructed using the partial least squares regression method.The best predictive model was pre-processed using the standard normal variate method,and the coefficient of determination of prediction was 0.991,the root mean square error of prediction was 2.93%,and the residual prediction deviation was 10.37.The results showed that this model could be applied for quantifying the adulteration concentration of PKO in VCO.The prediction adulteration concentration mapping of VCO with PKO was created from a calibration model that showed the color level according to the adulteration concentration in the range of 0-100%.NIR hyperspectral imaging could be clearly used to quantify the adulteration of VCO with a color level map that provides a quick,accurate,and non-destructive detection method.

Hyperspectral remote sensing identification of marine oil spills and emulsions using feature bands and double-branch dual-attention mechanism network

The accurate identification of marine oil spills and their emulsions is of great significance for emergency response to oil spill pollution.The selection of characteristic bands with strong separability helps to realize the rapid calculation of data on aircraft or in orbit,which will improve the timeliness of oil spill emergency monitoring.At the same time,the combination of spectral and spatial features can improve the accuracy of oil spill monitoring.Two ground-based experiments were designed to collect measured airborne hyperspectral data of crude oil and its emulsions,for which the multiscale superpixel level group clustering framework(MSGCF)was used to select spectral feature bands with strong separability.In addition,the double-branch dual-attention(DBDA)model was applied to identify crude oil and its emulsions.Compared with the recognition results based on original hyperspectral images,using the feature bands determined by MSGCF improved the recognition accuracy,and greatly shortened the running time.Moreover,the characteristic bands for quantifying the volume concentration of water-in-oil emulsions were determined,and a quantitative inversion model was constructed and applied to the AVIRIS image of the deepwater horizon oil spill event in 2010.This study verified the effectiveness of feature bands in identifying oil spill pollution types and quantifying concentration,laying foundation for rapid identification and quantification of marine oil spills and their emulsions on aircraft or in orbit.

A Spectral Convolutional Neural Network Model Based on Adaptive Fick’s Law for Hyperspectral Image Classification

Hyperspectral image classification stands as a pivotal task within the field of remote sensing,yet achieving highprecision classification remains a significant challenge.In response to this challenge,a Spectral Convolutional Neural Network model based on Adaptive Fick’s Law Algorithm(AFLA-SCNN)is proposed.The Adaptive Fick’s Law Algorithm(AFLA)constitutes a novel metaheuristic algorithm introduced herein,encompassing three new strategies:Adaptive weight factor,Gaussian mutation,and probability update policy.With adaptive weight factor,the algorithmcan adjust theweights according to the change in the number of iterations to improve the performance of the algorithm.Gaussianmutation helps the algorithm avoid falling into local optimal solutions and improves the searchability of the algorithm.The probability update strategy helps to improve the exploitability and adaptability of the algorithm.Within the AFLA-SCNN model,AFLA is employed to optimize two hyperparameters in the SCNN model,namely,“numEpochs”and“miniBatchSize”,to attain their optimal values.AFLA’s performance is initially validated across 28 functions in 10D,30D,and 50D for CEC2013 and 29 functions in 10D,30D,and 50D for CEC2017.Experimental results indicate AFLA’s marked performance superiority over nine other prominent optimization algorithms.Subsequently,the AFLA-SCNN model was compared with the Spectral Convolutional Neural Network model based on Fick’s Law Algorithm(FLA-SCNN),Spectral Convolutional Neural Network model based on Harris Hawks Optimization(HHO-SCNN),Spectral Convolutional Neural Network model based onDifferential Evolution(DE-SCNN),SpectralConvolutionalNeuralNetwork(SCNN)model,and SupportVector Machines(SVM)model using the Indian Pines dataset and PaviaUniversity dataset.The experimental results show that the AFLA-SCNN model outperforms other models in terms of Accuracy,Precision,Recall,and F1-score on Indian Pines and Pavia University.Among them,the Accuracy of the AFLA-SCNN model on Indian Pines reached 99.875%,and the Accuracy on PaviaUniversity reached 98.022%.In conclusion,our proposed AFLA-SCNN model is deemed to significantly enhance the precision of hyperspectral image classification.

Improving Generalization for Hyperspectral Image Classification:The Impact of Disjoint Sampling on Deep Models

Disjoint sampling is critical for rigorous and unbiased evaluation of state-of-the-art(SOTA)models e.g.,Attention Graph and Vision Transformer.When training,validation,and test sets overlap or share data,it introduces a bias that inflates performance metrics and prevents accurate assessment of a model’s true ability to generalize to new examples.This paper presents an innovative disjoint sampling approach for training SOTA models for the Hyperspectral Image Classification(HSIC).By separating training,validation,and test data without overlap,the proposed method facilitates a fairer evaluation of how well a model can classify pixels it was not exposed to during training or validation.Experiments demonstrate the approach significantly improves a model’s generalization compared to alternatives that include training and validation data in test data(A trivial approach involves testing the model on the entire Hyperspectral dataset to generate the ground truth maps.This approach produces higher accuracy but ultimately results in low generalization performance).Disjoint sampling eliminates data leakage between sets and provides reliable metrics for benchmarking progress in HSIC.Disjoint sampling is critical for advancing SOTA models and their real-world application to large-scale land mapping with Hyperspectral sensors.Overall,with the disjoint test set,the performance of the deep models achieves 96.36%accuracy on Indian Pines data,99.73%on Pavia University data,98.29%on University of Houston data,99.43%on Botswana data,and 99.88%on Salinas data.

Batch Active Learning for Multispectral and Hyperspectral Image Segmentation Using Similarity Graphs

Graph learning,when used as a semi-supervised learning(SSL)method,performs well for classification tasks with a low label rate.We provide a graph-based batch active learning pipeline for pixel/patch neighborhood multi-or hyperspectral image segmentation.Our batch active learning approach selects a collection of unlabeled pixels that satisfy a graph local maximum constraint for the active learning acquisition function that determines the relative importance of each pixel to the classification.This work builds on recent advances in the design of novel active learning acquisition functions(e.g.,the Model Change approach in arXiv:2110.07739)while adding important further developments including patch-neighborhood image analysis and batch active learning methods to further increase the accuracy and greatly increase the computational efficiency of these methods.In addition to improvements in the accuracy,our approach can greatly reduce the number of labeled pixels needed to achieve the same level of the accuracy based on randomly selected labeled pixels.

Multiscale Fusion Transformer Network for Hyperspectral Image Classification

Convolutional neural network(CNN)has excellent ability to model locally contextual information.However,CNNs face challenges for descripting long-range semantic features,which will lead to relatively low classification accuracy of hyperspectral images.To address this problem,this article proposes an algorithm based on multiscale fusion and transformer network for hyperspectral image classification.Firstly,the low-level spatial-spectral features are extracted by multi-scale residual structure.Secondly,an attention module is introduced to focus on the more important spatialspectral information.Finally,high-level semantic features are represented and learned by a token learner and an improved transformer encoder.The proposed algorithm is compared with six classical hyperspectral classification algorithms on real hyperspectral images.The experimental results show that the proposed algorithm effectively improves the land cover classification accuracy of hyperspectral images.

Hyperspectral Image Super-Resolution Network Based on Reinforcing Inter-Spectral Incremental Information

Hyperspectral images typically have high spectral resolution but low spatial resolution,which impacts the reliability and accuracy of subsequent applications,for example,remote sensingclassification and mineral identification.But in traditional methods via deep convolution neural net-works,indiscriminately extracting and fusing spectral and spatial features makes it challenging toutilize the differentiated information across adjacent spectral channels.Thus,we proposed a multi-branch interleaved iterative upsampling hyperspectral image super-resolution reconstruction net-work(MIIUSR)to address the above problems.We reinforce spatial feature extraction by integrat-ing detailed features from different receptive fields across adjacent channels.Furthermore,we pro-pose an interleaved iterative upsampling process during the reconstruction stage,which progres-sively fuses incremental information among adjacent frequency bands.Additionally,we add twoparallel three dimensional(3D)feature extraction branches to the backbone network to extractspectral and spatial features of varying granularity.We further enhance the backbone network’sconstruction results by leveraging the difference between two dimensional(2D)channel-groupingspatial features and 3D multi-granularity features.The results obtained by applying the proposednetwork model to the CAVE test set show that,at a scaling factor of×4,the peak signal to noiseratio,spectral angle mapping,and structural similarity are 37.310 dB,3.525 and 0.9438,respec-tively.Besides,extensive experiments conducted on the Harvard and Foster datasets demonstratethe superior potential of the proposed model in hyperspectral super-resolution reconstruction.

Rapid determination of oil content of single peanut seed by near-infrared hyperspectral imaging

Oil content is a crucial indicator for evaluating the quality of peanuts.A rapid and non-destructive method to determine oil content of individual peanut seed can provide robust technical support for breeding high-oil-content peanut varieties.In this study,we established a rapid determination method using near-infrared hyperspectral imaging and chemometrics to assess the oil content of single peanut seed.After selecting key wavelengths through competitive adaptive reweighted sampling(CARS),uninformative variable elimination(UVE),and random frog(RF),we constructed an oil content calibration model based on partial least squares regression for single peanut seed.Validation results demonstrated that the correlation coefficient was 0.8393 with a root mean square error of 1.7771 in the calibration set,while it was 0.7915 with a root mean square error of 2.2943 in the independent prediction set.Most samples exhibited relative errors below 5%,confirming the reliability of this model in predicting oil content of single peanut seed.

Detection of Thrips Defect on Green-Peel Citrus Using Hyperspectral Imaging Technology Combining PCA and B-Spline Lighting Correction Method

In order to find an effective method of detecting thrips defect on green-peel citrus, a defect segmentation method was developed using a single threshold value based on combination of characteristic wavelengths principal component analysis （PCA） and B-spline lighting correction method in this study. At first, four characteristic wavelengths （523, 587, 700 and 768 nm） were obtained using PCA of Vis-NIR （visible and near-infrared） bands and analysis of weighting coefficients; secondarily, PCA was performed using characteristic wavelengths and the second principal component （PC2） was selected to classify images; then, B-spline lighting correction method was proposed to overcome the influence of lighting non-uniform on citrus when thrips defect was segmented; finally, thrips defect on citrus was extracted by global threshold segmentation and morphological image processing. The experimental results show that thrips defect in citrus can be detected with an accuracy of 96.5% by characteristic wavelengths PCA and B-spline lighting correction method. This study shows that thrips defect on green-peel citrus can be effectively identified using hyperspectral imaging technology.

Hyperspectral Image Super-Resolution Meets Deep Learning:A Survey and Perspective

Hyperspectral image super-resolution,which refers to reconstructing the high-resolution hyperspectral image from the input low-resolution observation,aims to improve the spatial resolution of the hyperspectral image,which is beneficial for subsequent applications.The development of deep learning has promoted significant progress in hyperspectral image super-resolution,and the powerful expression capabilities of deep neural networks make the predicted results more reliable.Recently,several latest deep learning technologies have made the hyperspectral image super-resolution method explode.However,a comprehensive review and analysis of the latest deep learning methods from the hyperspectral image super-resolution perspective is absent.To this end,in this survey,we first introduce the concept of hyperspectral image super-resolution and classify the methods from the perspectives with or without auxiliary information.Then,we review the learning-based methods in three categories,including single hyperspectral image super-resolution,panchromatic-based hyperspectral image super-resolution,and multispectral-based hyperspectral image super-resolution.Subsequently,we summarize the commonly used hyperspectral dataset,and the evaluations for some representative methods in three categories are performed qualitatively and quantitatively.Moreover,we briefly introduce several typical applications of hyperspectral image super-resolution,including ground object classification,urban change detection,and ecosystem monitoring.Finally,we provide the conclusion and challenges in existing learning-based methods,looking forward to potential future research directions.

Spatial-spectral identication of abnormal leukocytes based on microscopic hyperspectral imaging technology

Screening and diagnosing of abnormal Leukocytes are crucial for the diagnosis of immune diseases and Acute Lymphoblastic Leukemia(ALL).As the deterioration of abnormal leukocytes is mainly due to the changes in the chromatin distribution,which signicantly affects the absorption and reflection of light,the spectral feature is proved to be important for leukocytes classication and identication.This paper proposes an accurate identication method for healthy and abnormal leukocytes based on microscopic hyperspectral imaging(HSI)technology which combines the spectral information.The segmentation of nucleus and cytoplasm is obtained by the morphological watershed algorithm.Then,the spectral features are extracted and combined with the spatial features.Based on this,the support vector machine(SVM)is applied for classication ofve types of leukocytes and abnormal leukocytes.Compared with different classication methods,the proposed method utilizes spectral features which highlight the differences between healthy leukocytes and abnormal leukocytes,improving the accuracy in the classication and identication of leukocytes.This paper only selects one subtype of ALL for test,and the proposed method can be applied for detection of other leukemia in the future.

Detection and Discrimination of Tea Plant Stresses Based on Hyperspectral Imaging Technique at a Canopy Level

Tea plant stresses threaten the quality of tea seriously.The technology corresponding to the fast detection and differentiation of stresses is of great significance for plant protection in tea plantation.In recent years,hyperspectral imaging technology has shown great potential in detecting and differentiating plant diseases,pests and some other stresses at the leaf level.However,the lack of studies at canopy level hampers the detection of tea plant stresses at a larger scale.In this study,based on the canopy-level hyperspectral imaging data,the methods for identifying and differentiating the three commonly occurred tea stresses(i.e.,the tea leafhopper,anthrax and sun burn)were studied.To account for the complexity of the canopy scenario,a stepwise detecting strategy was proposed that includes the process of background removal,identification of damaged areas and discrimination of stresses.Firstly,combining the successive projection algorithm(SPA)spectral analysis and K-means cluster analysis,the background and overexposed non-plant regions were removed from the image.Then,a rigorous sensitivity analysis and optimization were performed on various forms of spectral features,which yielded optimal features for detecting damaged areas(i.e.,YSV,Area,GI,CARI and NBNDVI)and optimal features for stresses discrimination(i.e.,MCARI,CI,LCI,RARS,TCI and VOG).Based on this information,the models for identifying damaged areas and those models for discriminating different stresses were established using K-nearest neighbor(KNN),Random Forest(RF)and Fisher discriminant analysis.The identification model achieved an accuracy over 95%,and the discrimination model achieved an accuracy over 93%for all stresses.The results suggested the feasibility of stress detection and differentiation using canopy-level hyperspectral imaging techniques,and indicated the potential for its extension over large areas.

Deep hybrid: Multi-graph neural network collaboration for hyperspectral image classification

With limited number of labeled samples,hyperspectral image(HSI)classification is a difficult Problem in current research.The graph neural network(GNN)has emerged as an approach to semi-supervised classification,and the application of GNN to hyperspectral images has attracted much attention.However,in the existing GNN-based methods a single graph neural network or graph filter is mainly used to extract HSI features,which does not take full advantage of various graph neural networks(graph filters).Moreover,the traditional GNNs have the problem of oversmoothing.To alleviate these shortcomings,we introduce a deep hybrid multi-graph neural network(DHMG),where two different graph filters,i.e.,the spectral filter and the autoregressive moving average(ARMA)filter,are utilized in two branches.The former can well extract the spectral features of the nodes,and the latter has a good suppression effect on graph noise.The network realizes information interaction between the two branches and takes good advantage of different graph filters.In addition,to address the problem of oversmoothing,a dense network is proposed,where the local graph features are preserved.The dense structure satisfies the needs of different classification targets presenting different features.Finally,we introduce a GraphSAGEbased network to refine the graph features produced by the deep hybrid network.Extensive experiments on three public HSI datasets strongly demonstrate that the DHMG dramatically outperforms the state-ofthe-art models.