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.

One-year results for myopia control of orthokeratology with different back optic zone diameters: a randomized trial using a novel multispectral-based topographer

AIM:To present the 1-year results of a prospective cohort study investigating the efficacy,potential mechanism,and safety of orthokeratology(ortho-k)with different back optic zone diameters(BOZD)for myopia control in children.METHODS:This randomized clinical study was performed between Dec.2020 and Dec.2021.Participants were randomly assigned to three groups wearing ortho-k:5 mm BOZD(5-MM group),5.5 mm BOZD(5.5-MM group),and 6 mm BOZD(6-MM group).The 1-year data were recorded,including axial length,relative peripheral refraction(RPR,measured by multispectral refractive topography,MRT),and visual quality.The contrast sensitivity(CS)was evaluated by CSV-1000 instrument with spatial frequencies of 3,6,12,and 18 cycles/degree(c/d);the corneal higher-order aberrations(HOAs)were measured by iTrace aberration analyzer.The one-way ANOVA was performed to assess the differences between the three groups.The correlation between the change in AL and RPR was calculated by Pearson’s correlation coefficient.RESULTS:The 1-year results of 20,21,and 21 subjects in the 5-MM,5.5-MM,and 6-MM groups,respectively,were presented.There were no statistical differences in baseline age,sex,or ocular parameters between the three groups(all P>0.05).At the 1-year visit,the 5-MM group had lower axial elongation than the 6-MM group(0.07±0.09 vs 0.18±0.11 mm,P=0.001).The 5-MM group had more myopic total RPR(TRPR,P=0.014),with RPR in the 15°–30°(RPR 15–30,P=0.015),30°–45°(RPR 30–45,P=0.011),temporal(RPR-T,P=0.008),and nasal area(RPR-N,P<0.001)than the 6-MM group.RPR 15–30 in the 5.5-MM group was more myopic than that in the 6-MM group(P=0.002),and RPR-N in the 5-MM group was more myopic than that in the 5.5-MM group(P<0.001).There were positive correlations between the axial elongation and the change in TRPR(r=0.756,P<0.001),RPR 15–30(r=0.364,P=0.004),RPR 30–45(r=0.306,P=0.016),and RPR-N(r=0.253,P=0.047).The CS decreased at 3 c/d(P<0.001),and the corneal HOAs increased in the 5-MM group(P=0.030).CONCLUSION:Ortho-k with 5 mm BOZD can control myopia progression more effectively.The mechanism may be associated with greater myopic shifts in RPR.

Hyperspectral Image Based Interpretable Feature Clustering Algorithm

Hyperspectral imagery encompasses spectral and spatial dimensions,reflecting the material properties of objects.Its application proves crucial in search and rescue,concealed target identification,and crop growth analysis.Clustering is an important method of hyperspectral analysis.The vast data volume of hyperspectral imagery,coupled with redundant information,poses significant challenges in swiftly and accurately extracting features for subsequent analysis.The current hyperspectral feature clustering methods,which are mostly studied from space or spectrum,do not have strong interpretability,resulting in poor comprehensibility of the algorithm.So,this research introduces a feature clustering algorithm for hyperspectral imagery from an interpretability perspective.It commences with a simulated perception process,proposing an interpretable band selection algorithm to reduce data dimensions.Following this,amulti-dimensional clustering algorithm,rooted in fuzzy and kernel clustering,is developed to highlight intra-class similarities and inter-class differences.An optimized P systemis then introduced to enhance computational efficiency.This system coordinates all cells within a mapping space to compute optimal cluster centers,facilitating parallel computation.This approach diminishes sensitivity to initial cluster centers and augments global search capabilities,thus preventing entrapment in local minima and enhancing clustering performance.Experiments conducted on 300 datasets,comprising both real and simulated data.The results show that the average accuracy(ACC)of the proposed algorithm is 0.86 and the combination measure(CM)is 0.81.

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.

Relative peripheral refraction in school children with different refractive errors using a novel multispectral refraction topographer

AIM:To compare relative peripheral refraction(RPR)in Chinese school children with different refractive errors using multispectral refraction topography(MRT).METHODS:A total of 713 eyes of primary school children[172 emmetropia(E),429 low myopia(LM),80 moderate myopia(MM),and 32 low hypermetropia(LH)]aged 10 to 13y were analyzed.RPRs were measured using MRT without mydriasis.MRT results showed RPR at 0-15°(RPR 0-15),15°-30°(RPR 15-30),and 30°-45°(RPR 30-45)annular in the inferior(RPR-I),superior(RPR-S),nasal(RPR-N),and temporal(RPR-T)quadrants.Spherical equivalent(SE)was detected and calculated using an autorefractor.RESULTS:There were significant differences of RPR 15-30 between groups MM[0.02(-0.12;0.18)]and LH[-0.13(-0.36;0.12)](P<0.05),MM and E[-0.06(-0.20;0.10)](P<0.05),and LM[-0.02(-0.15;0.15)]and E(P<0.05).There were also significant differences of RPR 30-45 between groups MM[0.45(0.18;0.74)]and E[0.29(-0.09;0.67)](P<0.05),and LM[0.44(0.14;0.76)]and E(P<0.001).RPR values increased from the hyperopic to medium myopic group in each annular.There were significant differences of RPR-S between groups MM[-0.02(-0.60;0.30)]and E[-0.44(-0.89;-0.04)](P<0.001),and LM[-0.28(-0.71;0.12)]and E(P<0.05).There were also significant differences of RPR-T between groups MM[0.37(0.21;0.78)]and LH[0.14(-0.52;0.50)](P<0.05),LM[0.41(0.06;0.84)]and LH(P<0.05),and LM and E[0.29(-0.10;0.68),P<0.05].A Spearman’s correlation analysis showed a negative correlation between RPR and SE in the 15°-30°(P=0.005),30°-45°(P<0.05)annular(P=0.002),superior(P<0.001),and temporal(P=0.001)quadrants.CONCLUSION:Without pupil dilation,values for RPR 15-30,30-45,RPR-S,and T shows significant differences between myopic eyes and emmetropia,and the differences are negatively correlated with SE.

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.

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.

Towards complex scenes: A deep learning-based camouflaged people detection method for snapshot multispectral images

Camouflaged people are extremely expert in actively concealing themselves by effectively utilizing cover and the surrounding environment. Despite advancements in optical detection capabilities through imaging systems, including spectral, polarization, and infrared technologies, there is still a lack of effective real-time method for accurately detecting small-size and high-efficient camouflaged people in complex real-world scenes. Here, this study proposes a snapshot multispectral image-based camouflaged detection model, multispectral YOLO(MS-YOLO), which utilizes the SPD-Conv and Sim AM modules to effectively represent targets and suppress background interference by exploiting the spatial-spectral target information. Besides, the study constructs the first real-shot multispectral camouflaged people dataset(MSCPD), which encompasses diverse scenes, target scales, and attitudes. To minimize information redundancy, MS-YOLO selects an optimal subset of 12 bands with strong feature representation and minimal inter-band correlation as input. Through experiments on the MSCPD, MS-YOLO achieves a mean Average Precision of 94.31% and real-time detection at 65 frames per second, which confirms the effectiveness and efficiency of our method in detecting camouflaged people in various typical desert and forest scenes. Our approach offers valuable support to improve the perception capabilities of unmanned aerial vehicles in detecting enemy forces and rescuing personnel in battlefield.

Hyperspectral image super resolution using deep internal and self-supervised learning

By automatically learning the priors embedded in images with powerful modelling ca-pabilities,deep learning-based algorithms have recently made considerable progress in reconstructing the high-resolution hyperspectral(HR-HS)image.With previously collected large-amount of external data,these methods are intuitively realised under the full supervision of the ground-truth data.Thus,the database construction in merging the low-resolution(LR)HS(LR-HS)and HR multispectral(MS)or RGB image research paradigm,commonly named as HSI SR,requires collecting corresponding training triplets:HR-MS(RGB),LR-HS and HR-HS image simultaneously,and often faces dif-ficulties in reality.The learned models with the training datasets collected simultaneously under controlled conditions may significantly degrade the HSI super-resolved perfor-mance to the real images captured under diverse environments.To handle the above-mentioned limitations,the authors propose to leverage the deep internal and self-supervised learning to solve the HSI SR problem.The authors advocate that it is possible to train a specific CNN model at test time,called as deep internal learning(DIL),by on-line preparing the training triplet samples from the observed LR-HS/HR-MS(or RGB)images and the down-sampled LR-HS version.However,the number of the training triplets extracted solely from the transformed data of the observation itself is extremely few particularly for the HSI SR tasks with large spatial upscale factors,which would result in limited reconstruction performance.To solve this problem,the authors further exploit deep self-supervised learning(DSL)by considering the observations as the unlabelled training samples.Specifically,the degradation modules inside the network were elaborated to realise the spatial and spectral down-sampling procedures for transforming the generated HR-HS estimation to the high-resolution RGB/LR-HS approximation,and then the reconstruction errors of the observations were formulated for measuring the network modelling performance.By consolidating the DIL and DSL into a unified deep framework,the authors construct a more robust HSI SR method without any prior training and have great potential of flexible adaptation to different settings per obser-vation.To verify the effectiveness of the proposed approach,extensive experiments have been conducted on two benchmark HS datasets,including the CAVE and Harvard datasets,and demonstrate the great performance gain of the proposed method over the state-of-the-art methods.

Lightweight Cross-Modal Multispectral Pedestrian Detection Based on Spatial Reweighted Attention Mechanism

Multispectral pedestrian detection technology leverages infrared images to provide reliable information for visible light images, demonstrating significant advantages in low-light conditions and background occlusion scenarios. However, while continuously improving cross-modal feature extraction and fusion, ensuring the model’s detection speed is also a challenging issue. We have devised a deep learning network model for cross-modal pedestrian detection based on Resnet50, aiming to focus on more reliable features and enhance the model’s detection efficiency. This model employs a spatial attention mechanism to reweight the input visible light and infrared image data, enhancing the model’s focus on different spatial positions and sharing the weighted feature data across different modalities, thereby reducing the interference of multi-modal features. Subsequently, lightweight modules with depthwise separable convolution are incorporated to reduce the model’s parameter count and computational load through channel-wise and point-wise convolutions. The network model algorithm proposed in this paper was experimentally validated on the publicly available KAIST dataset and compared with other existing methods. The experimental results demonstrate that our approach achieves favorable performance in various complex environments, affirming the effectiveness of the multispectral pedestrian detection technology proposed in this paper.

End-to-end computational design for an EUV solar corona multispectral imager with stray light suppression

An extreme ultraviolet solar corona multispectral imager can allow direct observation of high temperature coronal plasma,which is related to solar flares,coronal mass ejections and other significant coronal activities.This manuscript proposes a novel end-to-end computational design method for an extreme ultraviolet(EUV)solar corona multispectral imager operating at wavelengths near 100 nm,including a stray light suppression design and computational image recovery.To suppress the strong stray light from the solar disk,an outer opto-mechanical structure is designed to protect the imaging component of the system.Considering the low reflectivity(less than 70%)and strong-scattering(roughness)of existing extreme ultraviolet optical elements,the imaging component comprises only a primary mirror and a curved grating.A Lyot aperture is used to further suppress any residual stray light.Finally,a deep learning computational imaging method is used to correct the individual multi-wavelength images from the original recorded multi-slit data.In results and data,this can achieve a far-field angular resolution below 7",and spectral resolution below 0.05 nm.The field of view is±3 R_(☉)along the multi-slit moving direction,where R☉represents the radius of the solar disk.The ratio of the corona's stray light intensity to the solar center's irradiation intensity is less than 10-6 at the circle of 1.3 R_(☉).

Hyperspectral remote sensing identification of marine oil emulsions based on the fusion of spatial and spectral features

Marine oil spill emulsions are difficult to recover,and the damage to the environment is not easy to eliminate.The use of remote sensing to accurately identify oil spill emulsions is highly important for the protection of marine environments.However,the spectrum of oil emulsions changes due to different water content.Hyperspectral remote sensing and deep learning can use spectral and spatial information to identify different types of oil emulsions.Nonetheless,hyperspectral data can also cause information redundancy,reducing classification accuracy and efficiency,and even overfitting in machine learning models.To address these problems,an oil emulsion deep-learning identification model with spatial-spectral feature fusion is established,and feature bands that can distinguish between crude oil,seawater,water-in-oil emulsion(WO),and oil-in-water emulsion(OW)are filtered based on a standard deviation threshold–mutual information method.Using oil spill airborne hyperspectral data,we conducted identification experiments on oil emulsions in different background waters and under different spatial and temporal conditions,analyzed the transferability of the model,and explored the effects of feature band selection and spectral resolution on the identification of oil emulsions.The results show the following.(1)The standard deviation–mutual information feature selection method is able to effectively extract feature bands that can distinguish between WO,OW,oil slick,and seawater.The number of bands was reduced from 224 to 134 after feature selection on the Airborne Visible Infrared Imaging Spectrometer(AVIRIS)data and from 126 to 100 on the S185 data.(2)With feature selection,the overall accuracy and Kappa of the identification results for the training area are 91.80%and 0.86,respectively,improved by 2.62%and 0.04,and the overall accuracy and Kappa of the identification results for the migration area are 86.53%and 0.80,respectively,improved by 3.45%and 0.05.(3)The oil emulsion identification model has a certain degree of transferability and can effectively identify oil spill emulsions for AVIRIS data at different times and locations,with an overall accuracy of more than 80%,Kappa coefficient of more than 0.7,and F1 score of 0.75 or more for each category.(4)As the spectral resolution decreasing,the model yields different degrees of misclassification for areas with a mixed distribution of oil slick and seawater or mixed distribution of WO and OW.Based on the above experimental results,we demonstrate that the oil emulsion identification model with spatial–spectral feature fusion achieves a high accuracy rate in identifying oil emulsion using airborne hyperspectral data,and can be applied to images under different spatial and temporal conditions.Furthermore,we also elucidate the impact of factors such as spectral resolution and background water bodies on the identification process.These findings provide new reference for future endeavors in automated marine oil spill detection.

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.

Forest mapping:a comparison between hyperspectral and multispectral images and technologies

Mapping forests is an important process in managing natural resources.At present,due to spectral resolution limitations,multispectral images do not give a complete separation between different forest species.In contrast,advances in remote sensing technologies have provided hyperspectral tools and images as a solution for the determination of species.In this study,spectral signatures for stone pine（Pinus pinea L.） forests were collected using an advanced spectroradiometer ＂ASD FieldSpec 4 Hi-Res＂ with an accuracy of 1 nm.These spectral signatures are used to compare between different multispectral and hyperspectral satellite images.The comparison is based on processing satellite images： hyperspectral Hyperion,hyperspectral CHRIS-Proba,Advanced Land Imager（ALI）,and Landsat 8.Enhancement and classification methods for hyperspectral and multispectral images are investigated and analyzed.In addition,a well-known hyperspectral image classification algorithm,spectral angle mapper（SAM）,has been improved to perform the classification process efficiently based on collected spectral signatures.The results show that the modified SAM is 9% more accurate than the conventional SAM.In addition,experiments indicate that the CHRIS-Proba image is more accurate than Landsat 8（overall accuracy 82%,precision 93%,and Kappa coefficient 0.43 compared to 60,67%,and 0.035,respectively）.Similarly,Hyperion is better than ALI in mapping stone pine（overall accuracy 92%,precision 97%,and Kappa coefficient 0.74 compared to 52,56%,and -0.032,respectively）.

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.

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.

Multiple omics datasets reveal significant physical and physiological dormancy in alfalfa hard seeds identified by multispectral imaging analysis

Physical dormancy(PY) commonly present in the seeds of higher plants is believed to be responsible for the germination failure by impermeable seed coat in hard seeds of legume species, instead of physiological dormancy(PD). In this study, a non-destructive approach involving multispectral imaging was used to successfully identify hard seeds from non-hard seeds in Medicago sativa, with accuracy as high as96.8%–99.0%. We further adopted multiple-omics strategies to investigate the differences of physiology,metabolomics, methylomics, and transcriptomics in alfalfa hard seeds, with non-hard seeds as control.The hard seeds showed dramatically increased antioxidants and 125 metabolites of significant differences in non-targeted metabolomics analysis, which are enriched in the biosynthesis pathways of flavonoids, lipids and hormones, especially with significantly higher ABA, a hormone known to induce dormancy. In our transcriptomics results, the enrichment pathway of “response to abscisic acid” of differential expressed genes(DEG) supported the key role of ABA in metabolomics results. The methylome analysis identified 54,899, 46,216 and 54,452 differential methylation regions for contexts of CpG, CHG and CHH, and 344 DEGs might be regulated by hypermethylation and hypomethylation of promoter and exon regions, including four ABA-and JA-responsive genes. Among 8% hard seeds in seed lots,24.5% still did not germinate after scarifying seed coat, and were named as non-PY hard seeds.Compared to hard seeds, significantly higher contents of ABA/IAA and ABA/JA were identified in nonPY hard seeds, which indicated the potential presence of PD. In summary, the significantly changed metabolites, gene expressions, and methylations all suggested involvement of ABA responses in hard seeds, and germination failure of alfalfa hard seeds was caused by combinational dormancy(PY + PD),rather than PY alone.

Sanxingdui Cultural Relics Recognition Algorithm Based on Hyperspectral Multi-Network Fusion

Sanxingdui cultural relics are the precious cultural heritage of humanity with high values of history,science,culture,art and research.However,mainstream analytical methods are contacting and detrimental,which is unfavorable to the protection of cultural relics.This paper improves the accuracy of the extraction,location,and analysis of artifacts using hyperspectral methods.To improve the accuracy of cultural relic mining,positioning,and analysis,the segmentation algorithm of Sanxingdui cultural relics based on the spatial spectrum integrated network is proposed with the support of hyperspectral techniques.Firstly,region stitching algorithm based on the relative position of hyper spectrally collected data is proposed to improve stitching efficiency.Secondly,given the prominence of traditional HRNet(High-Resolution Net)models in high-resolution data processing,the spatial attention mechanism is put forward to obtain spatial dimension information.Thirdly,in view of the prominence of 3D networks in spectral information acquisition,the pyramid 3D residual network model is proposed to obtain internal spectral dimensional information.Fourthly,four kinds of fusion methods at the level of data and decision are presented to achieve cultural relic labeling.As shown by the experiment results,the proposed network adopts an integrated method of data-level and decision-level,which achieves the optimal average accuracy of identification 0.84,realizes shallow coverage of cultural relics labeling,and effectively supports the mining and protection of cultural relics.

Hyperspectral anomaly detection via memory‐augmented autoencoders

Recently,the autoencoder(AE)based method plays a critical role in the hyperspectral anomaly detection domain.However,due to the strong generalised capacity of AE,the abnormal samples are usually reconstructed well along with the normal background samples.Thus,in order to separate anomalies from the background by calculating reconstruction errors,it can be greatly beneficial to reduce the AE capability for abnormal sample reconstruction while maintaining the background reconstruction performance.A memory‐augmented autoencoder for hyperspectral anomaly detection(MAENet)is proposed to address this challenging problem.Specifically,the proposed MAENet mainly consists of an encoder,a memory module,and a decoder.First,the encoder transforms the original hyperspectral data into the low‐dimensional latent representation.Then,the latent representation is utilised to retrieve the most relevant matrix items in the memory matrix,and the retrieved matrix items will be used to replace the latent representation from the encoder.Finally,the decoder is used to reconstruct the input hyperspectral data using the retrieved memory items.With this strategy,the background can still be reconstructed well while the abnormal samples cannot.Experiments conducted on five real hyperspectral anomaly data sets demonstrate the superiority of the proposed method.