Hyperspectral image(HSI)classification is crucial for numerous remote sensing applications.Traditional deep learning methods may miss pixel relationships and context,leading to inefficiencies.This paper introduces the...Hyperspectral image(HSI)classification is crucial for numerous remote sensing applications.Traditional deep learning methods may miss pixel relationships and context,leading to inefficiencies.This paper introduces the spectral band graph convolutional and attention-enhanced CNN joint network(SGCCN),a novel approach that harnesses the power of spectral band graph convolutions for capturing long-range relationships,utilizes local perception of attention-enhanced multi-level convolutions for local spatial feature and employs a dynamic attention mechanism to enhance feature extraction.The SGCCN integrates spectral and spatial features through a self-attention fusion network,significantly improving classification accuracy and efficiency.The proposed method outperforms existing techniques,demonstrating its effectiveness in handling the challenges associated with HSI data.展开更多
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...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.展开更多
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 Convol...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.展开更多
Hyperspectral image(HSI)classification has been one of themost important tasks in the remote sensing community over the last few decades.Due to the presence of highly correlated bands and limited training samples in H...Hyperspectral image(HSI)classification has been one of themost important tasks in the remote sensing community over the last few decades.Due to the presence of highly correlated bands and limited training samples in HSI,discriminative feature extraction was challenging for traditional machine learning methods.Recently,deep learning based methods have been recognized as powerful feature extraction tool and have drawn a significant amount of attention in HSI classification.Among various deep learning models,convolutional neural networks(CNNs)have shown huge success and offered great potential to yield high performance in HSI classification.Motivated by this successful performance,this paper presents a systematic review of different CNN architectures for HSI classification and provides some future guidelines.To accomplish this,our study has taken a few important steps.First,we have focused on different CNN architectures,which are able to extract spectral,spatial,and joint spectral-spatial features.Then,many publications related to CNN based HSI classifications have been reviewed systematically.Further,a detailed comparative performance analysis has been presented between four CNN models namely 1D CNN,2D CNN,3D CNN,and feature fusion based CNN(FFCNN).Four benchmark HSI datasets have been used in our experiment for evaluating the performance.Finally,we concluded the paper with challenges on CNN based HSI classification and future guidelines that may help the researchers to work on HSI classification using CNN.展开更多
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 th...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.展开更多
Aiming at the problem of image information loss,dilated convolution is introduced and a novel multi⁃scale dilated convolutional neural network(MDCNN)is proposed.Dilated convolution can polymerize image multi⁃scale inf...Aiming at the problem of image information loss,dilated convolution is introduced and a novel multi⁃scale dilated convolutional neural network(MDCNN)is proposed.Dilated convolution can polymerize image multi⁃scale information without reducing the resolution.The first layer of the network used spectral convolutional step to reduce dimensionality.Then the multi⁃scale aggregation extracted multi⁃scale features through applying dilated convolution and shortcut connection.The extracted features which represent properties of data were fed through Softmax to predict the samples.MDCNN achieved the overall accuracy of 99.58% and 99.92% on two public datasets,Indian Pines and Pavia University.Compared with four other existing models,the results illustrate that MDCNN can extract better discriminative features and achieve higher classification performance.展开更多
Hyperspectral(HS)image classification plays a crucial role in numerous areas including remote sensing(RS),agriculture,and the monitoring of the environment.Optimal band selection in HS images is crucial for improving ...Hyperspectral(HS)image classification plays a crucial role in numerous areas including remote sensing(RS),agriculture,and the monitoring of the environment.Optimal band selection in HS images is crucial for improving the efficiency and accuracy of image classification.This process involves selecting the most informative spectral bands,which leads to a reduction in data volume.Focusing on these key bands also enhances the accuracy of classification algorithms,as redundant or irrelevant bands,which can introduce noise and lower model performance,are excluded.In this paper,we propose an approach for HS image classification using deep Q learning(DQL)and a novel multi-objective binary grey wolf optimizer(MOBGWO).We investigate the MOBGWO for optimal band selection to further enhance the accuracy of HS image classification.In the suggested MOBGWO,a new sigmoid function is introduced as a transfer function to modify the wolves’position.The primary objective of this classification is to reduce the number of bands while maximizing classification accuracy.To evaluate the effectiveness of our approach,we conducted experiments on publicly available HS image datasets,including Pavia University,Washington Mall,and Indian Pines datasets.We compared the performance of our proposed method with several state-of-the-art deep learning(DL)and machine learning(ML)algorithms,including long short-term memory(LSTM),deep neural network(DNN),recurrent neural network(RNN),support vector machine(SVM),and random forest(RF).Our experimental results demonstrate that the Hybrid MOBGWO-DQL significantly improves classification accuracy compared to traditional optimization and DL techniques.MOBGWO-DQL shows greater accuracy in classifying most categories in both datasets used.For the Indian Pine dataset,the MOBGWO-DQL architecture achieved a kappa coefficient(KC)of 97.68%and an overall accuracy(OA)of 94.32%.This was accompanied by the lowest root mean square error(RMSE)of 0.94,indicating very precise predictions with minimal error.In the case of the Pavia University dataset,the MOBGWO-DQL model demonstrated outstanding performance with the highest KC of 98.72%and an impressive OA of 96.01%.It also recorded the lowest RMSE at 0.63,reinforcing its accuracy in predictions.The results clearly demonstrate that the proposed MOBGWO-DQL architecture not only reaches a highly accurate model more quickly but also maintains superior performance throughout the training process.展开更多
Hyperspectral Image(HSI)classification based on deep learning has been an attractive area in recent years.However,as a kind of data-driven algorithm,the deep learning method usually requires numerous computational res...Hyperspectral Image(HSI)classification based on deep learning has been an attractive area in recent years.However,as a kind of data-driven algorithm,the deep learning method usually requires numerous computational resources and high-quality labelled datasets,while the expenditures of high-performance computing and data annotation are expensive.In this paper,to reduce the dependence on massive calculation and labelled samples,we propose a deep Double-Channel dense network(DDCD)for Hyperspectral Image Classification.Specifically,we design a 3D Double-Channel dense layer to capture the local and global features of the input.And we propose a Linear Attention Mechanism that is approximate to dot-product attention with much less memory and computational costs.The number of parameters and the consumptions of calculation are observably less than contrapositive deep learning methods,which means DDCD owns simpler architecture and higher efficiency.A series of quantitative experiences on 6 widely used hyperspectral datasets show that the proposed DDCD obtains state-of-the-art performance,even though when the absence of labelled samples is severe.展开更多
In hyperspectral image classification(HSIC),accurately extracting spatial and spectral information from hyperspectral images(HSI)is crucial for achieving precise classification.However,due to low spatial resolution an...In hyperspectral image classification(HSIC),accurately extracting spatial and spectral information from hyperspectral images(HSI)is crucial for achieving precise classification.However,due to low spatial resolution and complex category boundary,mixed pixels containing features from multiple classes are inevitable in HSIs.Additionally,the spectral similarity among different classes challenge for extracting distinctive spectral features essential for HSIC.To address the impact of mixed pixels and spectral similarity for HSIC,we propose a central-pixel guiding sub-pixel and sub-channel convolution network(CP-SPSC)to extract more precise spatial and spectral features.Firstly,we designed spatial attention(CP-SPA)and spectral attention(CP-SPE)informed by the central pixel to effectively reduce spectral interference of irrelevant categories in the same patch.Furthermore,we use CP-SPA to guide 2D sub-pixel convolution(SPConv2d)to capture spatial features finer than the pixel level.Meanwhile,CP-SPE is also utilized to guide 1D sub-channel con-volution(SCConv1d)in selecting more precise spectral channels.For fusing spatial and spectral information at the feature-level,the spectral feature extension transformation module(SFET)adopts mirror-padding and snake permutation to transform 1D spectral information of the center pixel into 2D spectral features.Experiments on three popular datasets demonstrate that ours out-performs several state-of-the-art methods in accuracy.展开更多
In the field of hyperspectral image(HSI)classification in remote sensing,the combination of spectral and spatial features has gained considerable attention.In addition,the multiscale feature extraction approach is ver...In the field of hyperspectral image(HSI)classification in remote sensing,the combination of spectral and spatial features has gained considerable attention.In addition,the multiscale feature extraction approach is very effective at improving the classification accuracy for HSIs,capable of capturing a large amount of intrinsic information.However,some existing methods for extracting spectral and spatial features can only generate low-level features and consider limited scales,leading to low classification results,and dense-connection based methods enhance the feature propagation at the cost of high model complexity.This paper presents a two-branch multiscale spectral-spatial feature extraction network(TBMSSN)for HSI classification.We design the mul-tiscale spectral feature extraction(MSEFE)and multiscale spatial feature extraction(MSAFE)modules to improve the feature representation,and a spatial attention mechanism is applied in the MSAFE module to reduce redundant information and enhance the representation of spatial fea-tures at multiscale.Then we densely connect series of MSEFE or MSAFE modules respectively in a two-branch framework to balance efficiency and effectiveness,alleviate the vanishing-gradient problem and strengthen the feature propagation.To evaluate the effectiveness of the proposed method,the experimental results were carried out on bench mark HsI datasets,demonstrating that TBMSSN obtained higher classification accuracy compared with several state-of-the-art methods.展开更多
The emergence of adversarial examples poses a significant challenge to hyperspectral image(HSI)classification,as they can attack deep neural network-based models.Recent adversarial defense research tends to establish ...The emergence of adversarial examples poses a significant challenge to hyperspectral image(HSI)classification,as they can attack deep neural network-based models.Recent adversarial defense research tends to establish global connections of spatial pixels to resist adversarial attacks.However,it cannot yield satisfactory results when only spatial pixel information is used.Starting from the premise that the spectral band is equally important for HSI classification,this paper explores the impact of spectral information on model robustness.We aim to discover potential relationships between different spectral bands and establish global connections to resist adversarial attacks.We design a spectral transformer based on the transformer structure to model long-distance dependency relationships among spectral bands.Additionally,we use a self-attention mechanism in the spatial domain to develop global relationships among spatial pixels.Based on the above framework,we further explore the influence of both spectral and spatial domains on the robustness of the model against adversarial attacks.Specifically,a weighted fusion of spectral transformer and spatial self-attention(WFSS)is designed to achieve the multi-scale fusion of spectral and spatial connections,which further improves the model’s robustness.Comprehensive experiments on three benchmarks show that the WFSS framework has superior defensive capabilities compared to state-of-the-art HSI classification methods.展开更多
In recent years,the use of convolutional neural networks(CNNs)and graph neural networks(GNNs)to identify hyperspectral images(HSIs)has achieved excellent results,and such methods are widely used in agricultural remote...In recent years,the use of convolutional neural networks(CNNs)and graph neural networks(GNNs)to identify hyperspectral images(HSIs)has achieved excellent results,and such methods are widely used in agricultural remote sensing,geological exploration,and marine remote sensing.Although many generalization classification algorithms are designed for the purpose of learning a small number of samples,there is often a problem of a low utilization rate of position information in the empty spectral domain.Based on this,a GNN with an autoregressive moving average(ARMA)-based smoothingfilter samples the node information in the null spectral domain and then captures the spatial information at the pixel level via spatial feature convolution;then,the null spectral domain position information lost by the CNN is located by a coordinate attention(CA)mechanism.Finally,autoregressive,spatial convolution,and CA mechanisms are combined into multiscale features to enhance the learning capacity of the network for tiny samples.Experiments conducted on the widely used Indian Pines(IP)dataset,the Botswana(BS)dataset,Houton 2013(H2013),and the WHU-Hi-HongHu(WHU)benchmark HSI dataset demonstrate that the proposed GACP technique can perform classification work with good accuracy even with a small number of training examples.展开更多
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...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.展开更多
Spectral-spatial Gabor filtering(GF),a robust feature extraction tool,has been widely investigated for hyperspectral image(HSI)classification.Recently,a new type of GF method,named phase-induced GF,which showed great ...Spectral-spatial Gabor filtering(GF),a robust feature extraction tool,has been widely investigated for hyperspectral image(HSI)classification.Recently,a new type of GF method,named phase-induced GF,which showed great potential for HSI feature extraction,was proposed.Although this new type of GF possibly better explores the frequency characteristics of HSIs,with a new parameter added,it generates a much larger amount of features,yielding redundancies and noises,and is therefore risky to severely deteriorate the efficiency and accuracy of classification.To tackle this problem,we fully exploit phase-induced Gabor features efficiently,proposing an efficient phase-induced Gabor cube selection and weighted fusion(EPCS-WF)method for HSI classification.Specifically,to eliminate the redundancies and noises,we first select the most representative Gabor cubes using a newly designed energy-based phase-induced Gabor cube selection(EPCS)algorithm before feeding them into classifiers.Then,a weighted fusion(WF)strategy is adopted to integrate the mutual information residing in different feature cubes to generate the final predictions.Our experimental results obtained on four well-known HSI datasets demonstrate that the EPCS-WF method,while only adopting four selected Gabor cubes for classification,delivers better performance as compared with other Gabor-based methods.The code of this work is available at https://github.com/cairlin5/EPCS-WF-hyperspectral-image-classification for the sake of reproducibility.展开更多
Most deep learning methods in hyperspectral image(HSI)classification use local learning methods,where overlapping areas between pixels can lead to spatial redundancy and higher computational cost.This paper proposes a...Most deep learning methods in hyperspectral image(HSI)classification use local learning methods,where overlapping areas between pixels can lead to spatial redundancy and higher computational cost.This paper proposes an efficient global learning(EGL)framework for HSI classification.The EGL framework was composed of universal global random stratification(UGSS)sampling strategy and a classification model BrsNet.The UGSS sampling strategy was used to solve the problem of insufficient gradient variance resulted from limited training samples.To fully extract and explore the most distinguishing feature representation,we used the modified linear bottleneck structure with spectral attention as a part of the BrsNet network to extract spectral spatial information.As a type of spectral attention,the shuffle spectral attention module screened important spectral features from the rich spectral information of HSI to improve the classification accuracy of the model.Meanwhile,we also designed a double branch structure in BrsNet that extracted more abundant spatial information from local and global perspectives to increase the performance of our classification framework.Experiments were conducted on three famous datasets,IP,PU,and SA.Compared with other classification methods,our proposed method produced competitive results in training time,while having a greater advantage in test time.展开更多
基金supported in part by the National Natural Science Foundations of China(No.61801214)the Postgraduate Research Practice Innovation Program of NUAA(No.xcxjh20231504)。
文摘Hyperspectral image(HSI)classification is crucial for numerous remote sensing applications.Traditional deep learning methods may miss pixel relationships and context,leading to inefficiencies.This paper introduces the spectral band graph convolutional and attention-enhanced CNN joint network(SGCCN),a novel approach that harnesses the power of spectral band graph convolutions for capturing long-range relationships,utilizes local perception of attention-enhanced multi-level convolutions for local spatial feature and employs a dynamic attention mechanism to enhance feature extraction.The SGCCN integrates spectral and spatial features through a self-attention fusion network,significantly improving classification accuracy and efficiency.The proposed method outperforms existing techniques,demonstrating its effectiveness in handling the challenges associated with HSI data.
基金the Researchers Supporting Project number(RSPD2024R848),King Saud University,Riyadh,Saudi Arabia.
文摘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.
基金Natural Science Foundation of Shandong Province,China(Grant No.ZR202111230202).
文摘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.
文摘Hyperspectral image(HSI)classification has been one of themost important tasks in the remote sensing community over the last few decades.Due to the presence of highly correlated bands and limited training samples in HSI,discriminative feature extraction was challenging for traditional machine learning methods.Recently,deep learning based methods have been recognized as powerful feature extraction tool and have drawn a significant amount of attention in HSI classification.Among various deep learning models,convolutional neural networks(CNNs)have shown huge success and offered great potential to yield high performance in HSI classification.Motivated by this successful performance,this paper presents a systematic review of different CNN architectures for HSI classification and provides some future guidelines.To accomplish this,our study has taken a few important steps.First,we have focused on different CNN architectures,which are able to extract spectral,spatial,and joint spectral-spatial features.Then,many publications related to CNN based HSI classifications have been reviewed systematically.Further,a detailed comparative performance analysis has been presented between four CNN models namely 1D CNN,2D CNN,3D CNN,and feature fusion based CNN(FFCNN).Four benchmark HSI datasets have been used in our experiment for evaluating the performance.Finally,we concluded the paper with challenges on CNN based HSI classification and future guidelines that may help the researchers to work on HSI classification using CNN.
文摘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.
基金Sponsored by the Project of Multi Modal Monitoring Information Learning Fusion and Health Warning Diagnosis of Wind Power Transmission System(Grant No.61803329)the Research on Product Quality Inspection Method Based on Time Series Analysis(Grant No.201703A020)the Research on the Theory and Reliability of Group Coordinated Control of Hydraulic System for Large Engineering Transportation Vehicles(Grant No.51675461).
文摘Aiming at the problem of image information loss,dilated convolution is introduced and a novel multi⁃scale dilated convolutional neural network(MDCNN)is proposed.Dilated convolution can polymerize image multi⁃scale information without reducing the resolution.The first layer of the network used spectral convolutional step to reduce dimensionality.Then the multi⁃scale aggregation extracted multi⁃scale features through applying dilated convolution and shortcut connection.The extracted features which represent properties of data were fed through Softmax to predict the samples.MDCNN achieved the overall accuracy of 99.58% and 99.92% on two public datasets,Indian Pines and Pavia University.Compared with four other existing models,the results illustrate that MDCNN can extract better discriminative features and achieve higher classification performance.
文摘Hyperspectral(HS)image classification plays a crucial role in numerous areas including remote sensing(RS),agriculture,and the monitoring of the environment.Optimal band selection in HS images is crucial for improving the efficiency and accuracy of image classification.This process involves selecting the most informative spectral bands,which leads to a reduction in data volume.Focusing on these key bands also enhances the accuracy of classification algorithms,as redundant or irrelevant bands,which can introduce noise and lower model performance,are excluded.In this paper,we propose an approach for HS image classification using deep Q learning(DQL)and a novel multi-objective binary grey wolf optimizer(MOBGWO).We investigate the MOBGWO for optimal band selection to further enhance the accuracy of HS image classification.In the suggested MOBGWO,a new sigmoid function is introduced as a transfer function to modify the wolves’position.The primary objective of this classification is to reduce the number of bands while maximizing classification accuracy.To evaluate the effectiveness of our approach,we conducted experiments on publicly available HS image datasets,including Pavia University,Washington Mall,and Indian Pines datasets.We compared the performance of our proposed method with several state-of-the-art deep learning(DL)and machine learning(ML)algorithms,including long short-term memory(LSTM),deep neural network(DNN),recurrent neural network(RNN),support vector machine(SVM),and random forest(RF).Our experimental results demonstrate that the Hybrid MOBGWO-DQL significantly improves classification accuracy compared to traditional optimization and DL techniques.MOBGWO-DQL shows greater accuracy in classifying most categories in both datasets used.For the Indian Pine dataset,the MOBGWO-DQL architecture achieved a kappa coefficient(KC)of 97.68%and an overall accuracy(OA)of 94.32%.This was accompanied by the lowest root mean square error(RMSE)of 0.94,indicating very precise predictions with minimal error.In the case of the Pavia University dataset,the MOBGWO-DQL model demonstrated outstanding performance with the highest KC of 98.72%and an impressive OA of 96.01%.It also recorded the lowest RMSE at 0.63,reinforcing its accuracy in predictions.The results clearly demonstrate that the proposed MOBGWO-DQL architecture not only reaches a highly accurate model more quickly but also maintains superior performance throughout the training process.
基金National Natural Science Foundations of China(41671452)China Postdoctoral Science Foundation Funded Project(2017M612510)。
文摘Hyperspectral Image(HSI)classification based on deep learning has been an attractive area in recent years.However,as a kind of data-driven algorithm,the deep learning method usually requires numerous computational resources and high-quality labelled datasets,while the expenditures of high-performance computing and data annotation are expensive.In this paper,to reduce the dependence on massive calculation and labelled samples,we propose a deep Double-Channel dense network(DDCD)for Hyperspectral Image Classification.Specifically,we design a 3D Double-Channel dense layer to capture the local and global features of the input.And we propose a Linear Attention Mechanism that is approximate to dot-product attention with much less memory and computational costs.The number of parameters and the consumptions of calculation are observably less than contrapositive deep learning methods,which means DDCD owns simpler architecture and higher efficiency.A series of quantitative experiences on 6 widely used hyperspectral datasets show that the proposed DDCD obtains state-of-the-art performance,even though when the absence of labelled samples is severe.
基金supported by the National Natural Science Foundation of China(No.62071323).
文摘In hyperspectral image classification(HSIC),accurately extracting spatial and spectral information from hyperspectral images(HSI)is crucial for achieving precise classification.However,due to low spatial resolution and complex category boundary,mixed pixels containing features from multiple classes are inevitable in HSIs.Additionally,the spectral similarity among different classes challenge for extracting distinctive spectral features essential for HSIC.To address the impact of mixed pixels and spectral similarity for HSIC,we propose a central-pixel guiding sub-pixel and sub-channel convolution network(CP-SPSC)to extract more precise spatial and spectral features.Firstly,we designed spatial attention(CP-SPA)and spectral attention(CP-SPE)informed by the central pixel to effectively reduce spectral interference of irrelevant categories in the same patch.Furthermore,we use CP-SPA to guide 2D sub-pixel convolution(SPConv2d)to capture spatial features finer than the pixel level.Meanwhile,CP-SPE is also utilized to guide 1D sub-channel con-volution(SCConv1d)in selecting more precise spectral channels.For fusing spatial and spectral information at the feature-level,the spectral feature extension transformation module(SFET)adopts mirror-padding and snake permutation to transform 1D spectral information of the center pixel into 2D spectral features.Experiments on three popular datasets demonstrate that ours out-performs several state-of-the-art methods in accuracy.
基金supported by the National Natural Science Foundation of China(62077038,61672405,62176196 and 62271374)。
文摘In the field of hyperspectral image(HSI)classification in remote sensing,the combination of spectral and spatial features has gained considerable attention.In addition,the multiscale feature extraction approach is very effective at improving the classification accuracy for HSIs,capable of capturing a large amount of intrinsic information.However,some existing methods for extracting spectral and spatial features can only generate low-level features and consider limited scales,leading to low classification results,and dense-connection based methods enhance the feature propagation at the cost of high model complexity.This paper presents a two-branch multiscale spectral-spatial feature extraction network(TBMSSN)for HSI classification.We design the mul-tiscale spectral feature extraction(MSEFE)and multiscale spatial feature extraction(MSAFE)modules to improve the feature representation,and a spatial attention mechanism is applied in the MSAFE module to reduce redundant information and enhance the representation of spatial fea-tures at multiscale.Then we densely connect series of MSEFE or MSAFE modules respectively in a two-branch framework to balance efficiency and effectiveness,alleviate the vanishing-gradient problem and strengthen the feature propagation.To evaluate the effectiveness of the proposed method,the experimental results were carried out on bench mark HsI datasets,demonstrating that TBMSSN obtained higher classification accuracy compared with several state-of-the-art methods.
基金partly supported by the National Natural Science Foundation of China(No.62172001,No.62076147,and No.61860206004).
文摘The emergence of adversarial examples poses a significant challenge to hyperspectral image(HSI)classification,as they can attack deep neural network-based models.Recent adversarial defense research tends to establish global connections of spatial pixels to resist adversarial attacks.However,it cannot yield satisfactory results when only spatial pixel information is used.Starting from the premise that the spectral band is equally important for HSI classification,this paper explores the impact of spectral information on model robustness.We aim to discover potential relationships between different spectral bands and establish global connections to resist adversarial attacks.We design a spectral transformer based on the transformer structure to model long-distance dependency relationships among spectral bands.Additionally,we use a self-attention mechanism in the spatial domain to develop global relationships among spatial pixels.Based on the above framework,we further explore the influence of both spectral and spatial domains on the robustness of the model against adversarial attacks.Specifically,a weighted fusion of spectral transformer and spatial self-attention(WFSS)is designed to achieve the multi-scale fusion of spectral and spatial connections,which further improves the model’s robustness.Comprehensive experiments on three benchmarks show that the WFSS framework has superior defensive capabilities compared to state-of-the-art HSI classification methods.
基金supported by National Natural Science Foundation of China(No.62166005)National Key R&D Program of China(No.2018AAA0101800)+3 种基金Guizhou Provincial Key Technology R&D Program(No.QKH[2022]130,QKH[2022]003,QKH[2021]335)Developing Objects and Projects of Scientific and Technological Talents in Guiyang City(No.ZKHT[2023]48-8)Joint Open Fund Project of Key Laboratories of the Ministry of Education([2020]245,[2020]248)Foundation of State Key Laboratory of Public Big Data(No.QJJ[2022]418).
文摘In recent years,the use of convolutional neural networks(CNNs)and graph neural networks(GNNs)to identify hyperspectral images(HSIs)has achieved excellent results,and such methods are widely used in agricultural remote sensing,geological exploration,and marine remote sensing.Although many generalization classification algorithms are designed for the purpose of learning a small number of samples,there is often a problem of a low utilization rate of position information in the empty spectral domain.Based on this,a GNN with an autoregressive moving average(ARMA)-based smoothingfilter samples the node information in the null spectral domain and then captures the spatial information at the pixel level via spatial feature convolution;then,the null spectral domain position information lost by the CNN is located by a coordinate attention(CA)mechanism.Finally,autoregressive,spatial convolution,and CA mechanisms are combined into multiscale features to enhance the learning capacity of the network for tiny samples.Experiments conducted on the widely used Indian Pines(IP)dataset,the Botswana(BS)dataset,Houton 2013(H2013),and the WHU-Hi-HongHu(WHU)benchmark HSI dataset demonstrate that the proposed GACP technique can perform classification work with good accuracy even with a small number of training examples.
文摘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.
基金supported by the National Natural Science Foundation of China (Grant Nos. 61771496, 42030111, and 61976234)partially supported by the National Program on Key Research Projects of China (Grant No. 2017YFC1502706)
文摘Spectral-spatial Gabor filtering(GF),a robust feature extraction tool,has been widely investigated for hyperspectral image(HSI)classification.Recently,a new type of GF method,named phase-induced GF,which showed great potential for HSI feature extraction,was proposed.Although this new type of GF possibly better explores the frequency characteristics of HSIs,with a new parameter added,it generates a much larger amount of features,yielding redundancies and noises,and is therefore risky to severely deteriorate the efficiency and accuracy of classification.To tackle this problem,we fully exploit phase-induced Gabor features efficiently,proposing an efficient phase-induced Gabor cube selection and weighted fusion(EPCS-WF)method for HSI classification.Specifically,to eliminate the redundancies and noises,we first select the most representative Gabor cubes using a newly designed energy-based phase-induced Gabor cube selection(EPCS)algorithm before feeding them into classifiers.Then,a weighted fusion(WF)strategy is adopted to integrate the mutual information residing in different feature cubes to generate the final predictions.Our experimental results obtained on four well-known HSI datasets demonstrate that the EPCS-WF method,while only adopting four selected Gabor cubes for classification,delivers better performance as compared with other Gabor-based methods.The code of this work is available at https://github.com/cairlin5/EPCS-WF-hyperspectral-image-classification for the sake of reproducibility.
基金funded by National Natural Special Foundation of Central Government to Guide Local Science&Technology Development(2021Szvup032).
文摘Most deep learning methods in hyperspectral image(HSI)classification use local learning methods,where overlapping areas between pixels can lead to spatial redundancy and higher computational cost.This paper proposes an efficient global learning(EGL)framework for HSI classification.The EGL framework was composed of universal global random stratification(UGSS)sampling strategy and a classification model BrsNet.The UGSS sampling strategy was used to solve the problem of insufficient gradient variance resulted from limited training samples.To fully extract and explore the most distinguishing feature representation,we used the modified linear bottleneck structure with spectral attention as a part of the BrsNet network to extract spectral spatial information.As a type of spectral attention,the shuffle spectral attention module screened important spectral features from the rich spectral information of HSI to improve the classification accuracy of the model.Meanwhile,we also designed a double branch structure in BrsNet that extracted more abundant spatial information from local and global perspectives to increase the performance of our classification framework.Experiments were conducted on three famous datasets,IP,PU,and SA.Compared with other classification methods,our proposed method produced competitive results in training time,while having a greater advantage in test time.
