Hyperspectral Data Sets Research Articles

SI2FM: SID Isolation Double Forest Model for Hyperspectral Anomaly Detection

Hyperspectral image (HSI) anomaly detection (HSI-AD) has become a hot issue in hyperspectral information processing as a method for detecting undesired targets without a priori information against unknown background and target information, which can be better adapted to the needs of practical applications. However, the demanding detection environment with no prior and small targets, as well as the large data and high redundancy of HSI itself, make the study of HSI-AD very challenging. First, we propose an HSI-AD method based on the nonsubsampled shearlet transform (NSST) domain spectral information divergence isolation double forest (SI2FM) in this paper. Further, the method excavates the intrinsic deep correlation properties between NSST subband coefficients of HSI in two ways to provide synergistic constraints and guidance on the prediction of abnormal target coefficients. On the one hand, with the “difference band” as a guide, the global isolation forest and local isolation forest models are constructed based on the spectral information divergence (SID) attribute values of the difference band and the low-frequency and high-frequency subbands, and the anomaly scores are determined by evaluating the path lengths of the isolation binary tree nodes in the forest model to obtain a progressively optimized anomaly detection map. On the other hand, based on the relationship of NSST high-frequency subband coefficients of spatial-spectral dimensions, the three-dimensional forest structure is constructed to realize the co-optimization of multiple anomaly detection maps obtained from the isolation forest. Finally, the guidance of the difference band suppresses the background noise and anomaly interference to a certain extent, enhancing the separability of target and background. The two-branch collaborative optimization based on the NSST subband coefficient correlation mining of HSI enables the prediction of anomaly sample coefficients to be gradually improved from multiple perspectives, which effectively improves the accuracy of anomaly detection. The effectiveness of the algorithm is verified by comparing real hyperspectral datasets captured in four different scenes with eleven typical anomaly detection algorithms currently available.

Recursive RX with Extended Multi-Attribute Profiles for Hyperspectral Anomaly Detection

Hyperspectral anomaly detection (HAD) plays an important role in military and civilian applications and has attracted a lot of research. The well-known Reed–Xiaoli (RX) algorithm is the benchmark of HAD methods. Based on the RX model, many variants have been developed. However, most of them ignore the spatial characteristics of hyperspectral images (HSIs). In this paper, we combine the extended multi-attribute profiles (EMAP) and RX algorithm to propose the Recursive RX with Extended Multi-Attribute Profiles (RRXEMAP) algorithm. Firstly, EMAP is utilized to extract the spatial structure information of HSI. Then, a simple method of background purification is proposed. That is, the background is purified by utilizing the RX detector to remove the pixels that are more likely to be anomalies, which helps improve the ability of background estimation. In addition, a parameter is utilized to control the purification level and can be selected by experiments. Finally, the RX detector is used again between the EMAP feature and the new background distribution to judge the anomaly. Experimental results on six real hyperspectral datasets and a synthetic dataset demonstrate the effectiveness of the proposed RRXEMAP method and the importance of using the EMAP feature and background purity means. Especially, on the abu-airport-2 dataset, the AUC value obtained by the present method is 0.9858, which is higher than the second one, CRD, by 0.0198.

An Attention-Based 3D Convolutional Autoencoder for Few-Shot Hyperspectral Unmixing and Classification

Few-shot hyperspectral classification is a challenging problem that involves obtaining effective spatial–spectral features in an unsupervised or semi-supervised manner. In recent years, as a result of the development of computer vision, deep learning techniques have demonstrated their superiority in tackling the problems of hyperspectral unmixing (HU) and classification. In this paper, we present a new semi-supervised pipeline for few-shot hyperspectral classification, where endmember abundance maps obtained by HU are treated as latent features for classification. A cube-based attention 3D convolutional autoencoder network (CACAE), is applied to extract spectral–spatial features. In addition, an attention approach is used to improve the accuracy of abundance estimation by extracting the diagnostic spectral features associated with the given endmember more effectively. The endmember abundance estimated by the proposed model outperforms other convolutional neural networks (CNNs) with respect to the root mean square error (RMSE) and abundance spectral angle distance (ASAD). Classification experiments are performed on real hyperspectral datasets and compared to several supervised and semi-supervised models. The experimental findings demonstrate that the proposed approach has promising potential for hyperspectral feature extraction and has better performance relative to CNN-based supervised classification under small-sample conditions.

Airborne Spectral Reflectance Dataset of Submerged Plastic Targets in a Coastal Environment

Among the emerging applications of remote sensing technologies, the remote detection of plastic litter has observed successful applications in recent years. However, while the number of studies and datasets for spectral characterization of plastic is growing, few studies address plastic litter while being submerged in natural seawater in an outdoor context. This study aims to investigate the feasibility of hyperspectral characterization of submerged plastic litter in less-than-ideal conditions. We present a hyperspectral dataset of eight different polymers in field conditions, taken by an unmanned aerial vehicle (UAV) on different days in a three-week period. The measurements were carried out off the coast of Mytilene, Greece. The team collected the dataset using a Bayspec OCI-F push broom sensor from 25 m and 40 m height above the water. For a contextual background, the dataset also contains optical (RGB) high-resolution orthomosaics.

Estimating vertically growing crop above-ground biomass based on UAV remote sensing

The accurate estimation of crop above-ground biomass (AGB) can assist in crop growth monitoring and grain yield prediction. Remote sensing has been widely used for AGB estimation at regional and local scales in recent years. However, optical remote sensing spectral indices (SIs) become saturated at medium-to-high crop covers. The combined use of remote sensing techniques and statistical regression models is not based on an understanding of how crop leaves and vertical organs contribute to the crop AGB. This causes difficulties in measuring the biomass stored in vertical organs (e.g., plant stem, wheat-spike, maize-tassel; abbreviated as AGBv) using optical remote sensing. This study aims to develop an unmanned aerial vehicle (UAV)-based vertically growing crop AGB (VGC-AGB) model. We defined Csm (g/m) to describe the crop stem and reproductive organs’ average dry mass content. This was done to improve the estimation of AGBv. The crop leaf area index (LAI, m2/m2), leaf dry matter content (Cm, g/m2), height (Ch, m), and density (Cd, m−2) were used in the VGC-AGB. The VGC-AGB calculated crop leaf AGB (AGBl) using LAI × Cm (g/m2) and AGBv using Cd × Ch × Csm (g/m2). The proposed VGC-AGB (AGB = LAI × Cm + Cd × Ch × Csm) was verified using field and UAV-based hyperspectral datasets of winter-wheat and summer-maize at three growth stages. Our results indicate that UAV-based VGC-AGB (R2 = 0.92–0.93, RMSE = 68.82–75.15 g/m2) is superior to the statistical regression model that is based on remote sensing SIs and CSMs (R2 = 0.77, RMSE = 134.94 g/m2). The results indicate that the UAV-based VGC-AGB supports the analysis of crop photosynthetic product transfers and high-performance UAV-based high-performance non-destructive AGB monitoring.

Low-Rank Constrained Attention-Enhanced Multiple Spatial–Spectral Feature Fusion for Small Sample Hyperspectral Image Classification

Hyperspectral images contain rich features in both spectral and spatial domains, which bring opportunities for accurate recognition of similar materials and promote various fine-grained remote sensing applications. Although deep learning models have been extensively investigated in the field of hyperspectral image classification (HSIC) tasks, classification performance is still limited under small sample conditions, and this has been a longstanding problem. The features extracted by complex network structures with large model size are redundant to some extent and prone to overfitting. This paper proposes a low-rank constrained attention-enhanced multiple feature fusion network (LAMFN). Firstly, factor analysis is used to extract very few components that can describe the original data using covariance information to perform spectral feature preprocessing. Then, a lightweight attention-enhanced 3D convolution module is used for deep feature extraction, and the position-sensitive information is supplemented using a 2D coordinate attention. The above widely varying spatial–spectral feature groups are fused through a simple composite residual structure. Finally, low-rank second-order pooling is adopted to enhance the convolutional feature selectivity and achieve classification. Extensive experiments were conducted on four representative hyperspectral datasets with different spatial–spectral characteristics, namely Indian Pines (IP), Pavia Center (PC), Houston (HU), and WHU-HongHu (WHU). The contrast methods include several advanced models proposed recently, including residual CNNs, attention-based CNNs, and transformer-based models. Using only five samples per class for training, LAMFN achieved overall accuracies of 78.15%, 97.18%, 81.35%, and 87.93% on the above datasets, which has an improvement of 0.82%, 1.12%, 1.67%, and 0.89% compared to the second-best model. The running time of LAMFN is moderate. For example, the training time of LAMFN on the WHU dataset was 29.1 s, and the contrast models ranged from 3.0 s to 341.4 s. In addition, ablation experiments and comparisons with some advanced semi-supervised learning methods further validated the effectiveness of the proposed model designs.

A joint method of spatial–spectral features and BP neural network for hyperspectral image classification

A hyperspectral image (HSI) has also highly correlated and redundant data, in addition to abundant spatial and spectral information. Only the spectral characteristics were usually utilized to perform the HSI classification in most previous studies, which leads to unsatisfactory accuracy and precision. The combination of Principal Component Analysis (PCA), Local Binary Pattern (LBP) and Back Propagation Neural Network (BPNN) (PCA-LBP-BPNN) was used to propose a novel classification method. More specifically, PCA was first used to reduce the dimensionality of HSIs for obtaining independent spectral bands sensitive to the classified objects. LBP was then adopted to extract the spatial texture features. Finally, the feature vectors were formed by fusing spatial–spectral features and input into BPNN for HSI classification. Three key parameters including the number of principal components (p) and the neurons in the hidden layer (l) as well as the learning rate (r) were optimally selected to improve the classification accuracy. Three publicly available hyperspectral datasets including Pavia University (PU), Salinas (Sa) and Botswana (Bo) were selected to validate the performance by comparing the kNN (k-Nearest Neighbor), SVM (Support Vector Machine) and Contextual Deep Convolutional Neural Network (CDCNN). The overall accuracy of PCA-LBP-BPNN reached 93.67%, 98.09% and 92.97%, respectively, for the three datasets. The method had a satisfying performance than kNN, SVM and CDCNN for the PU and Sa, but it had lower accuracies than kNN and CDCNN for the Bo due to extremely similar spectral responses. PCA-LBP-BPNN generally has satisfactory practicability and robustness in adapting to different hyperspectral datasets.

Toward Universal Representation Learning for Multidomain Hyperspectral Image Classification

Deep learning-based methods have greatly improved the performance of hyperspectral image classification over the past several years. Nevertheless, current deep learning methods require training and deploying an independent model for each hyperspectral data domain. Representations learned for one data domain can hardly be generalized to other data domains, so multiple models are needed in real-world applications when data from multiple domains are involved. In this paper, we design a single neural network that learns universal representations simultaneously from multiple hyperspectral remote sensing data domains. The universal convolutional neural network adapts its behaviour to different hyperspectral datasets. The majority of parameters of the network are shared to learn common knowledge from multiple datasets. A small number of domain-specific parameters are assigned to handle the domain shift. In addition, we propose a two-step training strategy to fully utilize the capacity of the universal network. Experiments conducted on seven hyperspectral image datasets demonstrate that the proposed universal network outperforms multiple individual specialized single domain networks.

Application of hyperspectral and multispectral datasets for mineral mapping

In this study, hyperspectral datasets are simulated from multispectral data using a spectral reconstruction approach which is a sensor-independent technique. This technique makes use of information from atmospherically corrected multispectral Remote Sensing (MRS) data and normalized ground spectra for the simulation of HRS data. In this study EO-1, the ALI dataset was used for the simulation of hyperspectral Remote Sensing (HRS) data to discover the Udaipur region’s unique minerals. A total of 61 spectral bands with 10 nm bandwidth were simulated. The simulated HRS data were validated using visual interpretation, statistical and classification approaches. Simulated HRS data from EO-1 Advanced Land Imager (ALI) has shown a high correlation with EO-1 Hyperion data. Spectral Angle Mapper (SAM) classification was also performed on simulated hyperspectral data for mineral mapping. It was observed that simulated hyperspectral data have shown comparable results with Hyperion and are better than their corresponding multispectral datasets.

Center Weighted Convolution and GraphSAGE Cooperative Network for Hyperspectral Image Classification

Hyperspectral image (HSI) classification is one of the basic tasks of remote sensing image processing, which is to predict the label of each HSI pixel. Convolution neural network (CNN) and graph convolution neural network (GCN) have become the current research focus due to their outstanding performance in the field of HSI classification in recent years. However, GCN is a transductive learning method, which needs all nodes to participate in the training process to get the node embedding. Graph sample and aggregation (GraphSAGE) is an important branch of graph neural network, which can flexibly aggregate new neighbor nodes in non-Euclidean data of any structure, and capture long-range contextual relationships. Superpixel-based GraphSAGE can not only integrate the global spatial relationship of data, but also further reduce its computing cost. CNN can extract pixel-level features in a small area, and our center attention module (CAM) and center weighted convolution (CW-Conv) can also improve the feature extraction ability of CNN by enhancing the dominant position of target pixels. In order to make full use of the advantages of CNN and GraphSAGE, we propose a center weighted convolution and GraphSAGE (CW-SAGE) cooperative network for HSI classification. Specifically, graph simple and aggregate branch is constructed by superpixel-based encoder and decoder modules, then pixel-level features are extracted by a central attention convolutional neural network. Finally, the features of the two branches are spliced together for feature fusion. We conduct experiments on three hyperspectral datasets and compare the results with other current state-of-the-art methods. A series of experiments demonstrate the advantages of our method.

MR-Selection: A Meta-Reinforcement Learning Approach for Zero-Shot Hyperspectral Band Selection

Band selection is an effective method to deal with the difficulties in image transmission, storage, and processing caused by redundant and noisy bands in hyperspectral images (HSIs). Existing band selection methods usually need to learn a specific model for each HSI dataset, which ignores the inherent correlation and common knowledge among different band selection tasks. Meanwhile, these methods lead to a huge waste of computation. In this article, a novel zero-shot band selection method, called MR-Selection, is proposed for HSI classification. It formalizes zero-shot band selection as a metalearning problem, where advantage actor–critic algorithm-based reinforcement learning (A2C-RL) is designed to extract the metaknowledge in the band selection tasks of various seen hyperspectral datasets through a shared agent. To learn a consistent representation among different tasks, a dynamic structure-aware graph convolutional network is constructed to build a shared agent in A2C-RL. In A2C-RL, the state is tailored in a feasible way and easy to adapt to various tasks. Meanwhile, the reward is defined according to an efficient evaluation network, which can evaluate each state effectively without any fine-tuning. Furthermore, a two-stage optimization strategy is designed to coordinate optimization directions of a shared agent from different tasks effectively. Once the shared agent is optimized, it can be directly applied to unseen HSI band selection tasks without any available samples. Experimental results demonstrate the effectiveness and efficiency of the MR-Selection on the band selection of unseen HSI datasets.

From Trained to Untrained: A Novel Change Detection Framework Using Randomly Initialized Models With Spatial–Channel Augmentation for Hyperspectral Images

Deep learning approaches have been extensively applied to change detection in hyperspectral images (HSIs). However, the majority of them encounter scarcity of training samples or rely on complex structures and learning strategies. Although untrained change detection models have been proved to be effective in relief above problems, they were constructed using regular convolutions and treated spatial locations and channels equally, which are insufficient to extract discriminative features and lead to limited accuracy. Given this, a novel untrained framework using randomly initialized models with spatial-channel augmentation (RICD) is proposed for HSI change detection in this paper. It consists of two major modules: 1) an enhanced feature extraction network using successive dilation-deformable feature extraction blocks, which can extract multiscale spatial-spectral features over unfixed sampling locations. It enlarges the field of view of convolutions and takes arbitrary neighborhood into consideration, which helps to increase the discriminativeness of the extracted features; 2) a change sensitive feature augmentation and comparison module integrating feature selection and spatial-channel augmentation strategies, which can exploit spatial context and channel importance. It magnifies difference between changed pixels and unchanged ones and emphasizes contribution of significant channels of the selected change sensitive features. Despite that convolution operations are included in RICD, all the weights are untrained and fixed once they are randomly initialized, indicating that the RICD can work in an unsupervised manner. Its performance is tested over three widely used hyperspectral datasets. Quantitative and qualitative comparisons with several state-of-the-art unsupervised methods reveal the effectiveness of the RICD method.

SIGMA: Spectral Interpretation Using Gaussian Mixtures and Autoencoder

AbstractIdentification of unknown micro‐ and nano‐sized mineral phases is commonly achieved by analyzing chemical maps generated from hyperspectral imaging data sets, particularly scanning electron microscope—energy dispersive X‐ray spectroscopy (SEM‐EDS). However, the accuracy and reliability of mineral identification are often limited by subjective human interpretation, non‐ideal sample preparation, and the presence of mixed chemical signals generated within the electron‐beam interaction volume. Machine learning has emerged as a powerful tool to overcome these problems. Here, we propose a machine‐learning approach to identify unknown phases and unmix their overlapped chemical signals. This approach leverages the guidance of Gaussian mixture modeling clustering fitted on an informative latent space of pixel‐wise elemental data points modeled using a neural network autoencoder, and unmixes the overlapped chemical signals of phases using non‐negative matrix factorization. We evaluate the reliability and the accuracy of the new approach using two SEM‐EDS data sets: a synthetic mixture sample and a real‐world particulate matter sample. In the former, the proposed approach successfully identifies all major phases and extracts background‐subtracted single‐phase chemical signals. The unmixed chemical spectra show an average similarity of 83.0% with the ground truth spectra. In the second case, the approach demonstrates the ability to identify potentially magnetic Fe‐bearing particles and their background‐subtracted chemical signals. We demonstrate a flexible and adaptable approach that brings a significant improvement to mineralogical and chemical analysis in a fully automated manner. The proposed analysis process has been built into a user‐friendly Python code with a graphical user interface for ease of use by general users.

A micro-hyperspectral image classification method of gallbladder cancer based on multi-scale fusion attention mechanism

A micro-hyperspectral image classification method of gallbladder cancer based on multi-scale fusion attention mechanism

You Only Train Once: Learning a General Anomaly Enhancement Network With Random Masks for Hyperspectral Anomaly Detection

In this paper, we introduce a new approach to address the challenge of generalization in hyperspectral anomaly detection (AD). Our method eliminates the need for adjusting parameters or retraining on new test scenes as required by most existing methods. Employing an image-level training paradigm, we achieve a general anomaly enhancement network for hyperspectral AD that only needs to be trained once. Trained on a set of anomaly-free hyperspectral images with random masks, our network can learn the spatial context characteristics between anomalies and background in an unsupervised way. Additionally, a plug-and-play model selection module is proposed to search for a spatial-spectral transform domain that is more suitable for AD task than the original data. To establish a unified benchmark to comprehensive evaluate our method and existing methods, we develop a large-scale hyperspectral AD dataset (HAD100) that includes 100 real test scenes with diverse anomaly targets. In comparison experiments, we combine our network with a parameter-free detector, and achieve the optimal balance between detection accuracy and inference speed among state-of-the-art AD methods. Experimental results also show that our method still achieves competitive performance when the training and test set are captured by different sensor devices. Our code is available at https://github.com/ZhaoxuLi123/AETNet.

Convolutional Transformer-Based Few-Shot Learning for Cross-Domain Hyperspectral Image Classification

In cross-domain hyperspectral image (HSI) classification, the labeled samples of the target domain are very limited, and it is a worthy attention to obtain sufficient class information from the source domain to categorize the target domain classes (both the same and new unseen classes). This article investigates this problem by employing few-shot learning (FSL) in a meta-learning paradigm. However, most existing cross-domain FSL methods extract statistical features based on convolutional neural networks (CNNs), which typically only consider the local spatial information among features, while ignoring the global information. To make up for these shortcomings, this article proposes novel convolutional transformer-based few-shot learning (CTFSL). Specifically, FSL is first performed in the classes of source and target domains simultaneously to build the consistent scenario. Then, a domain aligner is set up to map the source and target domains to the same dimensions. In addition, a convolutional transformer (CT) network is utilized to extract local-global features. Finally, a domain discriminator is executed subsequently that can not only reduce domain shift but also distinguish from which domain a feature originates. Experiments on three widely used hyperspectral image datasets indicate that the proposed CTFSL method is superior to the state-of-the-art cross-domain FSL methods and several typical HSI classification methods in terms of classification accuracy.

SSViT-HCD: A Spatial–Spectral Convolutional Vision Transformer for Hyperspectral Change Detection

In recent decades, the wide use of deep learning-based methods has consistently improved the performance of remote sensing images and is widely used for hyperspectral change detection (HCD) tasks. However, most of the existing HCD method is based on the convolutional neural network (CNN), which shows limitations in long-range dependencies and also cannot mine sequence features well. The CD performance still has margins for improvement. In this study, inspired by the excellent performance of transformers in computer vision and which has shown a significant ability to model global dependencies to attenuate the loss of long-range information, we built a hybrid spatial-spectral convolutional vision transformer (SSViT) for HCD. Our proposed method combines the merits of CNN and transformer to fulfill effective and efficient HCD. This study focused on highly reliable pseudo-sample data generation by selection scenario. To generate a pseudo sample, we have used different methods: (1) we predict change and no-change areas by using Euclidean distance, (2) thresholding by Chan-Vese segmentation method for determining change and no-change pixels for intensity maps, (3) sorting of change and no-change pixels, and (4) selection of the minimum value of initial no-change pixels as pseudo change sample data, in addition to, choosing the maximum intensity value for change candidate pixels as change sample data. The highly reliable change pixels were selected, and then pseudo-training data was used to train the SSViT model. At last, the change map is generated by training the SSViT network based on pseudo-training data. The performance of the SSViT model is evaluated for real-world hyperspectral (HS) datasets with different change landcover types. Furthermore, a new series of HS images is introduced for CD purposes. The results of CD show that the HS images have a high potential for detecting subtle changes. The experimental results demonstrate that the proposed SSViT could outperform the advanced HCD methods.

Feature-Band-Based Unsupervised Hyperspectral Underwater Target Detection Near the Coastline

With the improvement of imaging equipment, hyperspectral underwater target detection (HUTD) has raised much interest in recent years. The existing HUTD methods do not fully utilize spectral characteristics and need prior information about targets. Besides, the detection performance lacks verification in natural scenarios. In this paper, the authors propose a Feature Bands based Unsupervised underwater target Detection method (FBUD), which aims at finding the optimal feature bands to identify the underwater target near the coastline. Specifically, the normalized difference water index (NDWI) and unmixing technique are adopted to find the target and background pixels. Then, the spectral difference between the target and background is used to find the feature bands. With a simple and fast math operation of the feature bands, the probability map of the underwater target can be easily obtained. Besides, a new unmanned aerial vehicle (UAV)-borne hyperspectral image dataset named HNU-UTD is built for underwater target detection in real-world scenes. Experimental results obtained with the HNU-UTD dataset confirm the accuracy and effectiveness of the proposed detection method, which even outperforms supervised detection methods.

CDFSL: Image Registration for Spaceborne Hyperspectral and Multispectral Data Having Large Spatial-Resolution Difference

Image registration aims to eliminate the geometric deviation between multi-source data with the same range, and to promote the collaborative application of data. In recent years, spaceborne hyperspectral (HS) and multispectral (MS) data have been widely used in Earth observation. However, the difference in the number of bands, spatial resolution, and spectral resolution puts forward higher requirements on the registration algorithm. The key to HS and MS image registration is to extract more common key points, weaken and eliminate the difference of radiation and spatial texture information to build superior descriptors, and achieve high-precision matching of key points. This paper introduces a new robust HS and MS registration method based on common deep feature subspaces. We first construct the common deep feature subspaces extraction network to extract consistent edge features and common subspace images of the image pair. Then, Harris algorithm is used to extract key points from consistent edge features between images, which reduces the impact of spatial resolution differences between images. Besides, the SIFT descriptor and subspace images are used to describe key points, which reduces the impact of radiation differences between images. Finally, Euclidean distance is used for the initial matching of key points, and the affine matrix is calculated after the outliers are eliminated, and image registration is performed. We perform experiments on spaceborne HS and MS datasets of different spatial resolutions and comparisons with state-of-the-art methods. Experimental results show that our method can obtain satisfactory registration results and is robust.

Kmeans-CM Algorithm With Spectral Angle Mapper for Hyperspectral Image Classification

Hyperspectral images possess the characteristics of high dimensionality, which causes “dimensional disaster” and low classification accuracy, in response to the problems, based on traditional k-means algorithm and considering the importance of different bands for classification, and also combining both intra-class and inter-class information, a Kmeans-CM (K-means with correlation coefficient and maximize inter-class distance) algorithm with spectral angle mapper for hyperspectral image classification is proposed. First, weights of bands are defined by introducing coefficient of variation and spectral angle mapping, which measures the importance of bands for classification. Second, in order to intensify correlation between pixels in the same category, correlation coefficient is introduced to reset intra-class distance. Then, inter-class information is introduced for clustering by maximizing the distance between class centers and global center to reduce effect of local optimum of clustering effect. Finally, the K-means clustering objective function is redefined according to the band weights and intra-class, inter-class information, and also solving optimally. The overall classification accuracy of the method reached 84.47%, 90.08% and 80.45% on classical hyperspectral data sets Pavia University, Salinas and Botswana respectively, and the results show that the proposed algorithm owns good classification performance.