Search

Recent classification-oriented proposals to thematic maps building from hyperspectral images have used both semisupervised approaches and spatial information for correction of spectral classification. Semisupervised approaches enrich the training data set adding similar samples to each class, whereas spatial correction is based on the natural assumption of thematic class spatial compactness. In this paper, we propose and validate the following innovations: 1) a new spectral classifier, which is called anticipative hybrid extreme rotation forest (AHERF); 2) a spatial–spectral semisupervised approach; and 3) a final spatial classification correction step. The novel heterogeneous ensemble learning approach AHERF starts with a model selection phase, using a small subsample of the training data, in order to define a ranking-based selection probability distribution of the classifier architectures that will be used in the ensemble, so that the architecture best adapted to the data domain will be used more frequently to train individual classifiers in the ensemble. After this initial phase, AHERF trains a heterogeneous ensemble applying random rotations to bootstrapped samples of the remaining training data, aiming to obtain diversified and data-domain adapted individual classifiers. The natural assumption that spatially close pixels will most likely have highly correlated values is exploited in two phases of the process pipeline. First, semisupervised label assignment is supported by spectral similarity and spatial proximity. Unsupervised spectral similarity is detected by latent class discovery. In this paper, we use a clustering algorithm (i.e., k-means). Second, maximizing class spatial compactness removes classification errors that appear as speckle noise in the classification image. The whole approach aims to use minimal sets of labeled pixels for training, which we call the seed training data set. Testing results are computed over the entire image ground truth. For comparison, we provide results in several steps: 1) of classification by AHERF and competing classifiers built by semisupervised training and 2) after spatial correction. We validate the approach on several conventional benchmarking images, achieving results which are comparable with state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

This paper describes a new algorithm for hyperspectral image unmixing. Most unmixing algorithms proposed in the literature do not take into account the possible spatial correlations between the pixels. In this paper, a Bayesian model is introduced to exploit these correlations. The image to be unmixed is assumed to be partitioned into regions (or classes) where the statistical properties of the abundance coefficients are homogeneous. A Markov random field, is then proposed to model the spatial dependencies between the pixels within any class. Conditionally upon a given class, each pixel is modeled by using the classical linear mixing model with additive white Gaussian noise. For this model, the posterior distributions of the unknown parameters and hyperparameters allow the parameters of interest to be inferred. These parameters include the abundances for each pixel, the means and variances of the abundances for each class, as well as a classification map indicating the classes of all pixels in the image. To overcome the complexity of the posterior distribution, we consider a Markov chain Monte Carlo method that generates samples asymptotically distributed according to the posterior. The generated samples are then used for parameter and hyperparameter estimation. The accuracy of the proposed algorithms is illustrated on synthetic and real data. [ABSTRACT FROM AUTHOR]

This paper presents an unsupervised approach to band selection in hyperspectral images that considers both spectral and spatial information in data dimensionality reduction. The approach exploits the concepts of superpixel and chunklets for identifying the spectral channels most suitable to be used in classification for discriminating land-cover classes. The segmented superpixels can be regarded as many small spectral homogeneous and spatial neighboring pixel chunklets. Based on the observation that the superpixel chunklets achieve high homogeneity and consistency within land-cover classes, a series of band criteria (BC) is identified by learning the optimal band transformation that results in low within-class variability and high total variability. Then, the learned BC, which are called band measures, are given in input to an efficient clustering algorithm, i.e., the affinity propagation, for selecting highly separable bands with low redundancy. The effectiveness of proposed approach was assessed on three hyperspectral data sets. The results point out the advantages of the proposed methods over five state-of-the-art unsupervised methods. [ABSTRACT FROM AUTHOR]

Predictive coding is attractive for compression on board of spacecraft due to its low computational complexity, modest memory requirements, and the ability to accurately control quality on a pixel-by-pixel basis. Traditionally, predictive compression focused on the lossless and near-lossless modes of operation, where the maximum error can be bounded but the rate of the compressed image is variable. Rate control is considered a challenging problem for predictive encoders due to the dependencies between quantization and prediction in the feedback loop and the lack of a signal representation that packs the signal's energy into few coefficients. In this paper, we show that it is possible to design a rate control scheme intended for onboard implementation. In particular, we propose a general framework to select quantizers in each spatial and spectral region of an image to achieve the desired target rate while minimizing distortion. The rate control algorithm allows achieving lossy near-lossless compression and any in-between type of compression, e.g., lossy compression with a near-lossless constraint. While this framework is independent of the specific predictor used, in order to show its performance, in this paper, we tailor it to the predictor adopted by the CCSDS-123 lossless compression standard, obtaining an extension that allows performing lossless, near-lossless, and lossy compression in a single package. We show that the rate controller has excellent performance in terms of accuracy in the output rate, rate-distortion characteristics, and is extremely competitive with respect to state-of-the-art transform coding. [ABSTRACT FROM PUBLISHER]

In recent years, many studies on hyperspectral image classification have shown that using multiple features can effectively improve the classification accuracy. As a very powerful means of learning, multiple kernel learning (MKL) can conveniently be embedded in a variety of characteristics. This paper proposes a class-specific sparse MKL (CS-SMKL) framework to improve the capability of hyperspectral image classification. In terms of the features, extended multiattribute profiles are adopted because it can effectively represent the spatial and spectral information of hyperspectral images. CS-SMKL classifies the hyperspectral images, simultaneously learns class-specific significant features, and selects class-specific weights. Using an L1-norm constraint (i.e., group lasso) as the regularizer, we can enforce the sparsity at the group/feature level and automatically learn a compact feature set for the classification of any two classes. More precisely, our CS-SMKL determines the associated weights of optimal base kernels for any two classes and results in improved classification performances. The advantage of the proposed method is that only the features useful for the classification of any two classes can be retained, which leads to greatly enhanced discriminability. Experiments are conducted on three hyperspectral data sets. The experimental results show that the proposed method achieves better performances for hyperspectral image classification compared with several state-of-the-art algorithms, and the results confirm the capability of the method in selecting the useful features. [ABSTRACT FROM PUBLISHER]

This paper presents the utilization of empirical mode decomposition (EMD) of hyperspectral images to increase the classification accuracy using support vector machine (SVM)-based classification. EMD has been shown in the literature to be particularly suitable for nonlinear and nonstationary signals and is used in this paper to decompose hyperspectral image bands into several intrinsic mode functions (IMFs) and a final residue. EMD is utilized in this paper to improve hyperspectral-image-classification accuracy by effectively exploiting the feature that EMD performs a decomposition that is spatially adaptive with respect to intrinsic features. This paper presents two different approaches for improved hyperspectral image classification making use of EMD. In the first approach, IMFs corresponding to each hyperspectral image band are obtained and the sums of lower order IMFs are used as new features for classification with SVM. In the second approach, the pieces of information contained in the first and second IMFs of each hyperspectral image band are combined using composite kernels for SVM classification with higher accuracy. [ABSTRACT FROM AUTHOR]

Sparse unmixing has become a popular tool for hyperspectral imagery interpretation. It refers to finding the optimal subset of a spectral library to reconstruct the image data and further estimate the proportions of different materials. Recently, multi-objective based sparse unmixing methods have presented promising performance because of their advantages in addressing combinatorial problems. A spectral and multi-objective based sparse unmixing (SMoSU) algorithm was proposed in our previous work, which solves the decision-making problem well. However, it does not show outstanding advantages in strong noise cases. To solve the problem, in this paper, SMoSU is improved based on the estimation of distribution algorithms (EDAs). The machine learning based EDAs have been a reliable approach in solving multi-objective problems. However, most of them are for special problems and relatively weak in theoretical foundations. Thus, it is unreliable to extend it directly to sparse unmixing. Here, we improve EDA on the basis of classification and propose a classification-based model for individual generating under the framework of SMoSU (CM-MoSU). In CM-MoSU, the whole population is divided to be positive and negative. Then, the macroinformation of positive individuals is used to guide the generation of new individuals. Therefore, the optimization task could pay more attention to the feasible space with high quality. Moreover, some theoretical analyses are presented to prove the reliability of CM-MoSU. In experiments, several state-of-the-art sparse unmixing algorithms are compared. Both synthetic and real-world experiments demonstrate the effectiveness of CM-MoSU. [ABSTRACT FROM AUTHOR]

In this paper, we present a nonlinear version of the well-known anomaly detection method referred to as the RX-algorithm. Extending this algorithm to a feature space associated with the original input space via a certain nonlinear mapping function can provide a nonlinear version of the RX-algorithm. This non- linear RX-algorithm, referred to as the kernel RX-algorithm, is basically intractable mainly due to the high dimensionality of the feature space produced by the nonlinear mapping function. However, in this paper it is shown that the kernel RX-algorithm can easily be implemented by kernelizing the RX-algorithm in the feature space in terms of kernels that implicitly compute dot products in the feature space. Improved performance of the kernel RX-algorithm over the conventional RX-algorithm is shown by testing several hyperspectral imagery for military target and mine detection. [ABSTRACT FROM AUTHOR]

Classification of hyperspectral images usually suffers from high dimensionality and few reference data, which limits the performance of the pixelwise classifiers. The spectral–spatial classifiers, which integrate the spectral data and the spatial information during the classification, perform impressively in terms of the high classification accuracy and the homogeneous appearance of the classification map. In this paper, we propose a new probabilistic framework for spectral–spatial classification (PFSSC), which integrates the spectral data and the spatial information from the probabilistic point of view. Both the spectral data and the spatial information are used to estimate the per-pixel probability, which gives the likelihood that one pixel belongs to one class, respectively. The classification map can then be directly derived from the joint probability. In the proposed framework, a pixelwise probabilistic classifier can be extended as a spectral–spatial one since it can integrate spatial information easily. Furthermore, these spectral–spatial classifiers in the proposed framework are realized in an iterative way to avoid the problem caused by the limited reference data to some extent. In each iterative step, some unassigned pixels are classified by considering the pixels assigned in previous iterative steps. In this iterative process, pixels are assigned to specific labels step by step gradually. In the proposed framework, the probabilistic support vector machine (SVM) and random forest (RF) are extended to be two spectral–spatial classifiers. In short, we denote them as SVM-PFSSC and RF-PFSSC, respectively. The experimental results show that SVM-PFSSC and RF-PFSSC outperform some pixelwise and spectral–spatial classifiers. [ABSTRACT FROM AUTHOR]

Morphological attribute profiles are among the most prominent spectral–spatial pixel description methods. They are efficient, effective, and highly customizable multiscale tools based on hierarchical representations of a scalar input image. Their application to multivariate images in general and hyperspectral images in particular has been so far conducted using the marginal strategy, i.e., by processing each image band (eventually obtained through a dimension reduction technique) independently. In this paper, we investigate the alternative vector strategy, which consists in processing the available image bands simultaneously. The vector strategy is based on a vector-ordering relation that leads to the computation of a single max and min tree per hyperspectral data set, from which attribute profiles can then be computed as usual. We explore known vector-ordering relations for constructing such max trees and, subsequently, vector attribute profiles and introduce a combination of marginal and vector strategies. We provide an experimental comparison of these approaches in the context of hyperspectral classification with common data sets, where the proposed approach outperforms the widely used marginal strategy. [ABSTRACT FROM AUTHOR]

In this paper, we propose a novel multiple kernel learning (MKL) framework to incorporate both spectral and spatial features for hyperspectral image classification, which is called multiple-structure-element nonlinear MKL (MultiSE-NMKL). In the proposed framework, multiple structure elements (MultiSEs) are employed to generate extended morphological profiles (EMPs) to present spatial–spectral information. In order to better mine interscale and interstructure similarity among EMPs, a nonlinear MKL (NMKL) is introduced to learn an optimal combined kernel from the predefined linear base kernels. We integrate this NMKL with support vector machines (SVMs) and reduce the min–max problem to a simple minimization problem. The optimal weight for each kernel matrix is then solved by a projection-based gradient descent algorithm. The advantages of using nonlinear combination of base kernels and multiSE-based EMP are that similarity information generated from the nonlinear interaction of different kernels is fully exploited, and the discriminability of the classes of interest is deeply enhanced. Experiments are conducted on three real hyperspectral data sets. The experimental results show that the proposed method achieves better performance for hyperspectral image classification, compared with several state-of-the-art algorithms. The MultiSE EMPs can provide much higher classification accuracy than using a single-SE EMP. [ABSTRACT FROM AUTHOR]

This paper presents a kernel-based feature selection method for the classification of hyperspectral images. The proposed method aims at selecting a subset of the original features that are both 1) relevant (discriminant) for the considered classification problem, i.e., preserve the functional relationship between input and output variables, and 2) invariant (stable) across different domains, i.e., minimize the data-set shift between the source and the target domains. Domains can be associated with hyperspectral images collected either on different geographical areas or on the same area at different times. We propose a novel measure of data-set shift for evaluating the domain stability, which computes the distance of the conditional distributions between the source and target domains in a reproducing kernel Hilbert space. Such a measure is defined on the basis of the kernel embeddings of the conditional distributions resulting in a nonparametric approach that does not require estimating the distribution of the classes. The adopted search strategy is based on a multiobjective optimization algorithm, which optimizes the two terms of the criterion function for the estimation of the Pareto-optimal solutions. This results in an effective approach of performing feature selection in a transfer learning setting. The experimental results obtained on two hyperspectral images show the effectiveness of the proposed method in selecting features with high generalization capabilities. [ABSTRACT FROM AUTHOR]

Classification of remotely sensed hyperspectral images via supervised approaches is typically affected by high dimensionality of the spectral data and a limited number of labeled samples. Dimensionality reduction via feature extraction and active learning (AL) are two approaches that researchers have investigated independently to deal with these two problems. In this paper, we propose a new method in which the feature extraction and AL steps are combined into a unique framework. The idea is to learn and update a reduced feature space in a supervised way at each iteration of the AL process, thus taking advantage of the increasing labeled information provided by the user. In particular, the computation of the reduced feature space is based on the large-margin nearest neighbor (LMNN) metric learning principle. This strategy is applied in conjunction with $k$-nearest neighbor ( $k$-NN) classification, for which a new sample selection strategy is proposed. The methodology is validated experimentally on four benchmark hyperspectral data sets. Good improvements in terms of classification accuracy and computational time are achieved with respect to the state-of-the-art strategies that do not combine feature extraction and AL. [ABSTRACT FROM PUBLISHER]

The availability of hyperspectral images with improved spectral and spatial resolutions provides the opportunity to obtain accurate land-cover classification. In this paper, a novel methodology that combines spectral and spatial information for supervised hyperspectral image classification is proposed. A feature reduction strategy based on independent component analysis is the main core of the spectral analysis, where the exploitation of prior information coupled to the evaluation of the reconstruction error assures the identification of the best class-informative subset of independent components. Reduced attribute profiles (APs), which are designed to address well-known issues related to information redundancy that affect the common morphological APs, are then employed for the modeling and fusion of the contextual information. Four real hyperspectral data sets, which are characterized by different spectral and spatial resolutions with a variety of scene typologies (urban, agriculture areas), have been used for assessing the accuracy and generalization capabilities of the proposed methodology. The obtained results demonstrate the classification effectiveness of the proposed approach in all different scene typologies, with respect to other state-of-the-art techniques. [ABSTRACT FROM PUBLISHER]

In this paper, a new sparse representation-based binary hypothesis (SRBBH) model for hyperspectral target detection is proposed. The proposed approach relies on the binary hypothesis model of an unknown sample induced by sparse representation. The sample can be sparsely represented by the training samples from the background-only dictionary under the null hypothesis and the training samples from the target and background dictionary under the alternative hypothesis. The sparse vectors in the model can be recovered by a greedy algorithm, and the same sparsity levels are employed for both hypotheses. Thus, the recovery process leads to a competition between the background-only subspace and the target and background subspace, which are directly represented by the different hypotheses. The detection decision can be made by comparing the reconstruction residuals under the different hypotheses. Extensive experiments were carried out on hyperspectral images, which reveal that the SRBBH model shows an outstanding detection performance. [ABSTRACT FROM PUBLISHER]

Due to the high spectral resolution, anomaly detection from hyperspectral images provides a new way to locate potential targets in a scene, especially those targets that are spectrally different from the majority of the data set. Conventional Mahalanobis-distance-based anomaly detection methods depend on the background statistics to construct the anomaly detection metric. One of the main problems with these methods is that the Gaussian distribution assumption of the background may not be reasonable. Furthermore, these methods are also susceptible to contamination of the conventional background covariance matrix by anomaly pixels. This paper proposes a new anomaly detection method by effectively exploiting a robust anomaly degree metric for increasing the separability between anomaly pixels and other background pixels, using discriminative information. First, the manifold feature is used so as to divide the pixels into the potential anomaly part and the potential background part. This procedure is called discriminative information learning. A metric learning method is then performed to obtain the robust anomaly degree measurements. Experiments with three hyperspectral data sets reveal that the proposed method outperforms other current anomaly detection methods. The sensitivity of the method to several important parameters is also investigated. [ABSTRACT FROM PUBLISHER]

This paper proposes a lossless to lossy compression scheme for hyperspectral images based on dual-tree Binary Embedded Zerotree Wavelet (BEZW) algorithm. The algorithm adapts Karhunen-Loève Transform and Discrete Wavelet Transform to achieve 3-D integer reversible hybrid transform and decorrelate spectral and spatial data. Since statistics of the hyperspectral image are not symmetrical, the asymmetrical dual-tree structure is introduced. The 3-D BEZW algorithm compresses hyperspectral images by implementing progressive bitplane coding. The lossless and lossy compression performance is compared with other state-of-the-art predictive coding and transform-based coding algorithms on Airborne Visible/Infrared Imaging Spectrometer images. Results show that the 3-D-BEZW lossless compression performance is comparable with the best predictive algorithms, while its computational cost is comparable with those of transform-based algorithms. [ABSTRACT FROM PUBLISHER]

Band selection is an important preprocessing step for hyperspectral data processing. It involves two crucial problems, i.e., suitable measure criterion and effective search strategy. Mutual information (MI) has been widely used as the measure criterion for its nonlinear and nonparametric characteristics. For efficient calculation, traditional MI-based criteria commonly use bivariate MI (BMI) to approximate the ideal MI-based criterion. However, these BMI-based criteria may miss the bands having discriminative information and do not give the condition of the approximation. In this paper, a novel criterion based on trivariate MI (TMI) is proposed to measure the redundancy for classification. From the multivariate MI perspective, the proposed TMI-based and traditional BMI-based criteria are proved as the low-order approximations of the ideal criterion under some assumptions. Compared with the BMI-based criteria, a more relaxed assumption condition is required for the TMI-based criterion. To alleviate the problem of few labeled samples existing in hyperspectral images, the TMI-based criterion is extended to the semisupervised TMI-based (STMI) method by adding a graph regulation term. Additionally, to search an appropriate band subset by the TMI- and STMI-based criteria, a new clonal selection algorithm (CSA) is proposed. In CSA, integer encoding and adaptive operators are devised to reduce space and time cost. Experimental results demonstrate the effectiveness of the proposed algorithms for hyperspectral band selection. [ABSTRACT FROM PUBLISHER]

Feature extraction is known to be an effective way in both reducing computational complexity and increasing accuracy of hyperspectral image classification. In this paper, a simple yet quite powerful feature extraction method based on image fusion and recursive filtering (IFRF) is proposed. First, the hyperspectral image is partitioned into multiple subsets of adjacent hyperspectral bands. Then, the bands in each subset are fused together by averaging, which is one of the simplest image fusion methods. Finally, the fused bands are processed with transform domain recursive filtering to get the resulting features for classification. Experiments are performed on different hyperspectral images, with the support vector machines (SVMs) serving as the classifier. By using the proposed method, the accuracy of the SVM classifier can be improved significantly. Furthermore, compared with other hyperspectral classification methods, the proposed IFRF method shows outstanding performance in terms of classification accuracy and computational efficiency. [ABSTRACT FROM PUBLISHER]

Hyperspectral remote sensing technology allows one to acquire a sequence of possibly hundreds of contiguous spectral images from ultraviolet to infrared. Conventional spectral classifiers treat hyperspectral images as a list of spectral measurements and do not consider spatial dependences, which leads to a dramatic decrease in classification accuracies. In this paper, a new automatic framework for the classification of hyperspectral images is proposed. The new method is based on combining hidden Markov random field segmentation with support vector machine (SVM) classifier. In order to preserve edges in the final classification map, a gradient step is taken into account. Experiments confirm that the new spectral and spatial classification approach is able to improve results significantly in terms of classification accuracies compared to the standard SVM method and also outperforms other studied methods. [ABSTRACT FROM AUTHOR]

Integrating spatial information into hyperspectral unmixing procedures has been shown to have a positive effect on the estimation of fractional abundances due to the inherent spatial-spectral duality in hyperspectral scenes. However, current research works that take spatial information into account are mainly focused on the linear mixing model. In this paper, we investigate how to incorporate spatial correlation into a nonlinear abundance estimation process. A nonlinear unmixing algorithm operating in reproducing kernel Hilbert spaces, coupled with a l1-type spatial regularization, is derived. Experiment results, with both synthetic and real hyperspectral images, illustrate the effectiveness of the proposed scheme. [ABSTRACT FROM AUTHOR]

Although hyperspectral images acquired by on-board satellites provide information from a wide range of wavelengths in the spectrum, the obtained information is usually highly correlated. This paper proposes a novel framework to reduce the computation cost for large amounts of data based on the efficiency of the optimum-path forest (OPF) classifier and the power of metaheuristic algorithms to solve combinatorial optimizations. Simulations on two public data sets have shown that the proposed framework can indeed improve the effectiveness of the OPF and considerably reduce data storage costs. [ABSTRACT FROM PUBLISHER]

Anomaly detection (AD) in remotely sensed hyperspectral images has been proven to be valuable in many applications. In this paper, we propose a scheme for detecting global anomalies in which a likelihood ratio test-based decision rule is applied in conjunction with automated data-driven estimation of the background probability density function (PDF). Specifically, the use of both semiparametric (finite mixtures) and nonparametric (Parzen windows) models is investigated for background PDF estimation. Although such approaches are well known in multivariate data analysis, they have been very seldom applied to estimate the hyperspectral image background PDF, mostly due to the difficulty of reliably learning the model parameters without operator intervention. In this paper, semi and nonparametric estimators have been successfully employed to estimate the image background PDF with the aim of detecting global anomalies in a scene benefiting from the application of ad hoc Bayesian learning strategies. Two real hyperspectral images have been used to experimentally evaluate the ability of the proposed AD scheme resulting from the application of different global background PDF models and learning methods. [ABSTRACT FROM PUBLISHER]

This paper presents a novel technique for addressing domain adaptation (DA) problems with active learning (AL) in the classification of remote sensing images. DA models the important problem of adapting a supervised classifier trained on a given image (source domain) to the classification of another similar but not identical image (target domain) acquired on a different area. The main idea of the proposed approach is iteratively labeling and adding to the training set the minimum number of the most informative samples from the target domain, while removing the source-domain samples that do not fit with the distributions of the classes in the target domain. In this way, the classification system exploits already available information, i.e., the labeled samples of source domain, in order to minimize the number of target domain samples to be labeled, thus reducing the cost associated to the definition of the training set for the classification of the target domain. In addition, we define a convergence criterion that allows the technique to stop the iterative AL process on the target domain without relying on the availability of a test set for it. This is an important contribution, as in operational applications, it is not realistic to assume that a test set for the target domain is available. Experimental results obtained in the classification of very high resolution and hyperspectral images confirm the effectiveness of the proposed technique. [ABSTRACT FROM AUTHOR]

The purpose of this paper is to introduce a general type of detection fusion that allows combining a set of basic detectors into one more versatile detector. The fusion can be performed based on the spectral information contained in a pixel, the global characteristics of the background and target spaces, as well as spatial local information. As an example of generalized fusion, we introduce a new class of detectors called the directional segmented matched filters (DSMFs). We then concentrate on the more basic type of fusion that does not use the spatial local information. Our goal is to build a theoretical foundation for the future more sophisticated detectors. Within this setup, we define max-min and min-max types of fusion, which turn out to be equivalent to the geometric approach to continuum fusion already introduced in the literature. Nevertheless, this new framework allows natural formulation of other types of approaches, such as discrete fusion, without the continuity assumption. This new formalism also allows formulation of a general theorem about the relationship between the max-min and min-max detectors. We also provide experimental results that demonstrate the benefits of the new approach. We compare two new detectors with the global matched filter using two different targets in an AVIRIS (Airborne Visible/Infrared Imaging Spectrometer) image. The results show that various forms of the DSMFs dominate depending on the target type. [ABSTRACT FROM AUTHOR]

This paper presents an unsupervised hyperspectral image segmentation with a new subtractive-clustering-based similarity segmentation and a novel cluster validation method using one-class support vector (SV) machine (OC-SVM). An estimation of the correct number of clusters is an important task in hyperspectral image segmentation. The proposed cluster validity measure is based on the power of spectral discrimination (PWSD) measure and utilizes the advantage of the inherited cluster contour definition feature of OC-SVM. Hence, this novel cluster validity method is referred to as SV-PWSD. SVs found by OC-SVM are located at the minimum distance to the hyperplane in the feature space and at the arbitrarily shaped cluster contours in the input space. SV-PWSD guides the segmentation/clustering process to find the optimal number of clusters in hyperspectral data. Because of the high computational load of subtractive clustering and OC-SVM, a subset of the image (only ground-truth data) is initially used in the clustering and validation phases. Then, it is proposed to use K-nearest neighbor classification, with the already clustered subset being used as training data, to project the initial clustering results onto the entire data set. [ABSTRACT FROM AUTHOR]

In this paper, we propose a lossless compression algorithm for hyperspectral images inspired by the distributed-source-coding (DSC) principle. DSC refers to separate compression and joint decoding of correlated sources, which are taken as adjacent bands of a hyperspectral image. This concept is used to design a compression scheme that provides error resilience, very low complexity, and good compression performance. These features are obtained employing scalar coset codes to encode the current band at a rate that depends on its correlation with the previous band, without encoding the prediction error. Iterative decoding employs the decoded version of the previous band as side information and uses a cyclic redundancy code to verify correct reconstruction. We develop three algorithms based on this paradigm, which provide different tradeoffs between compression performance, error resilience, and complexity. Their performance is evaluated on raw and calibrated AVIRIS images and compared with several existing algorithms. Preliminary results of a field-programmable gate array implementation are also provided, which show that the proposed algorithms can sustain an extremely high throughput. [ABSTRACT FROM AUTHOR]

In this paper, we present a new methodology for clustering hyperspectral images. It aims at simultaneously solving the following three different issues: 1) estimation of the class statistical parameters; 2) detection of the best discriminative bands without requiring the a priori setting of their number by the user; and 3) estimation of the number of data classes characterizing the considered image. It is formulated within a multiobjective particle swarm optimization (MOPSO) framework and is guided by three different optimization criteria, which are the log-likelihood function, the Bhattacharyya statistical distance between classes, and the minimum description length (MDL). A detailed experimental analysis was conducted on both simulated and real hyperspectral images. In general, the obtained results show that interesting classification performances can be achieved by the proposed methodology despite its completely unsupervised nature. [ABSTRACT FROM AUTHOR]

This paper presents a novel approach to feature selection for the classification of hyperspectral images. The proposed approach aims at selecting a subset of the original set of features that exhibits at the same time high capability to discriminate among the considered classes and high invariance in the spatial domain of the investigated scene. This approach results in a more robust classification system with improved generalization properties with respect to standard feature-selection methods. The feature selection is accomplished by defining a multiobjective criterion function made up of two terms: 1) a term that measures the class separability and 2) a term that evaluates the spatial invariance of the selected features. In order to assess the spatial invariance of the feature subset, we propose both a supervised method (which assumes that training samples acquired in two or more spatially disjoint areas are available) and a semisupervised method (which requires only a standard training set acquired in a single area of the scene and takes advantage of unlabeled samples selected in portions of the scene spatially disjoint from the training set). The choice for the supervised or semisupervised method depends on the available reference data. The multiobjective problem is solved by an evolutionary algorithm that estimates the set of Pareto-optimal solutions. Experiments carried out on a hyperspectral image acquired by the Hyperion sensor on a complex area confirmed the effectiveness of the proposed approach. [ABSTRACT FROM AUTHOR]

This paper proposes an innovative spectral feature extraction (SFE) method called prototype space (PS) feature extraction (PSFE) based only on class spectra. The main novelties of the proposed SFE lie in the following: representing channels in a new space called PS, where they are characterized in terms of reflection properties of classes; and proposing uncertainty, angle, and distance measures to distinguish highly correlated and informative channels. Having clustered the channels by Fuzzy C-Means (FCM) in PS, highly correlated and isolated channels are separated by an uncertainty measure. Consequently, PSFE is built by a linear combination of spectra weighted by class membership values of channels that fall in each cluster. Furthermore, we will enrich PSFE with informative channels which are outlier channels identified through their angle and distance with respect to diagonal and cluster centers in PS. In contrast to the previous SFE methods, PSFE substitutes the search strategies with FCM clustering to find relevant channels. Moreover, instead of optimizing separability criteria, the accuracy of classification over a subset of training data is used to decide which disjoint optical region yields maximum accuracy. According to how class spectra are obtained, PSFE incorporates four approaches: knowledge based, supervised, semisupervised, and unsupervised. The latter three PSFE approaches are assessed in two main cases including with and without informative channels and compared with the conventional feature extraction methods. Experimental results demonstrated higher overall accuracy of PSFE compared to its conventional counterparts with limited sample sizes. [ABSTRACT FROM AUTHOR]

This paper analyzes the classification of hyperspectral remote sensing images with linear discriminant analysis (LDA) in the presence of a small ratio between the number of training samples and the number of spectral features. In these particular ill-posed problems, a reliable LDA requires one to introduce regularization for problem solving. Nonetheless, in such a challenging scenario, the resulting regularized LDA (RLDA) is highly sensitive to the tuning of the regularization parameter. In this context, we introduce in the remote sensing community an efficient version of the RLDA recently presented by Ye et al. to cope with critical ill-posed problems. In addition, several LDA-based classifiers (i.e., penalized LDA, orthogonal LDA, and uncorrelated LDA) are compared theoretically and experimentally with the standard LDA and the RLDA. Method differences are highlighted through toy examples and are exhaustively tested on several ill-posed problems related to the classification of hyperspectral remote sensing images. Experimental results confirm the effectiveness of the presented RLDA technique and point out the main properties of other analyzed LDA techniques in critical ill-posed hyperspectral image classification problems. [ABSTRACT FROM AUTHOR]

A fast algorithm for multiscale representation and segmentation of hyperspectral imagery is introduced in this paper. The multiscale/scale-space representation is obtained by solving a nonlinear diffusion partial differential equation (PDE) for vector-valued images. We use algebraic multigrid techniques to obtain a fast and scalable solution of the PDE and to segment the hyperspectral image following the intrinsic multigrid structure. We test our algorithm on four standard hyperspectral images that represent different environments commonly found in remote sensing applications: agricultural, urban, mining, and marine. The experimental results show that the segmented images lead to better classification than using the original data directly, in spite of the use of simple similarity metrics and piecewise constant approximations obtained from the segmentation maps. [ABSTRACT FROM AUTHOR]

In this paper, we propose an analysis on the joint effect of hyperspectral and light detection and ranging (LIDAR) data for the classification of complex forest areas. In greater detail, we present: 1) an advanced system for the joint use of hyperspectral and LIDAR data in complex classification problems; 2) an investigation on the effectiveness of the very promising support vector machines (SVMs) and Gaussian maximum likelihood with leave-one-out-covariance algorithm classifiers for the analysis of complex forest scenarios characterized from a high number of species in a multisource framework; and 3) an analysis on the effectiveness of different LIDAR returns and channels (elevation and intensity) for increasing the classification accuracy obtained with hyperspectral images, particularly in relation to the discrimination of very similar classes. Several experiments carried out on a complex forest area in Italy provide interesting conclusions on the effectiveness and potentialities of the joint use of hyperspectral and LIDAR data and on the accuracy of the different classification techniques analyzed in the proposed system. In particular, the elevation channel of the first LIDAR return was very effective for the separation of species with similar spectral signatures but different mean heights, and the SVM classifier proved to be very robust and accurate in the exploitation of the considered multisource data. [ABSTRACT FROM AUTHOR]

This paper addresses classification of hyperspectral remote sensing images with kernel-based methods defined in the framework of semisupervised support vector machines (S³ VMs). In particular, we analyzed the critical problem of the nonconvexity of the cost function associated with the learning phase of S³ VMs by considering different (S³ VMs) techniques that solve optimization directly in the primal formulation of the objective function. As the nonconvex cost function can be characterized by many local minima, different optimization techniques may lead to different classification results. Here, we present two implementations, which are based on different rationales and optimization methods. The presented techniques are compared with S³VMs implemented in the dual formulation in the context of classification of real hyperspectral remote sensing images. Experimental results point out the effectiveness of the techniques based on the optimization of the primal formulation, which provided higher accuracy and better generalization ability than the S³ VMs optimized in the dual formulation. [ABSTRACT FROM AUTHOR]

This paper addresses the problem of efficient predictive lossless compression on the regions of interest (ROIs) in the hyperspectral images with no-data regions. We propose a two-stage prediction scheme, where a context-similarity-based weighted average prediction is followed by recursive least square filtering to decorrelate the hyperspectral images for compression. We then propose to apply separate Golomb–Rice codes for coding the prediction residuals of the full-context pixels and boundary pixels, respectively. To study the coding gains of this separate coding scheme, we introduce a mixture geometric model to represent the residuals associated with various combinations of the full-context pixels and boundary pixels. Both information-theoretic analysis and simulations on synthetic data confirm the advantage of the separate coding scheme over the conventional coding method based on a single underlying geometric distribution. We apply the aforementioned prediction and coding methods to four publicly available hyperspectral image data sets, attaining significant improvements over several other state-of-the-art methods, including the shape-adaptive JPEG 2000 method. [ABSTRACT FROM PUBLISHER]

In this paper, we present a new lossy compression method for hyperspectral images that aims to optimally compress in both spatial and spectral domains and simultaneously minimizes the effect of the compression on linear spectral unmixing performance. To achieve this, a nonnegative Tucker decomposition is applied. This decomposition is a function of three dimension parameters. By employing a link between this decomposition and the linear spectral mixing model, an optimization problem is defined to find the optimal parameters by minimizing the root-mean-square error between the abundance matrices of the original and reconstructed data sets. The resulting optimization problem is solved by a particle swarm optimization algorithm. An approximate method for fast estimation of the free parameters is introduced as well. Our simulation results show that, in comparison with well-known state-of-the-art lossy compression methods, an improved compression and spectral unmixing performance of the reconstructed hyperspectral image is obtained. It is noteworthy to mention that the superiority of our method becomes more apparent as the compression ratio grows. [ABSTRACT FROM AUTHOR]

Due to the complementary properties of different features, multiple feature fusion has a large potential for hyperspectral imagery classification. At the meantime, hashing is promising in representing a high-dimensional float-type feature with extremely low bit binary codes while maintaining the performance. In this paper, we study the possibility of using hashing to fuse multiple features for hyperspectral imagery classification. For this purpose, we propose a multiple feature fusion framework to evaluate the performance of using different hashing methods. For comparison and completeness, we also have an extensive comparison to five subspace-based dimension reduction methods and six fusion-based methods which are popular solutions to deal with multiple features in hyperspectral image classification. Experimental results on four benchmark hyperspectral data sets demonstrate that using hashing to fuse multiple features can achieve comparable or better performance with the traditional subspace-based dimension reduction methods and fusion-based methods. Moreover, the binary features obtained by using hashing need much less storage and are faster to compute distances with the help of machine instructions. [ABSTRACT FROM PUBLISHER]

Hyperspectral endmember extraction is to estimate endmember signatures (or material spectra) from the hyperspectral data of an area for analyzing the materials and their composition therein. The presence of noise and outliers in the data poses a serious problem in endmember extraction. In this paper, we handle the noise- and outlier-contaminated data by a two-step approach. We first propose a robust-affine-set-fitting algorithm for joint dimension reduction and outlier removal. The idea is to find a contamination-free data-representative affine set from the corrupted data, while keeping the effects of outliers minimum, in the least squares error sense. Then, we devise two computationally efficient algorithms for extracting endmembers from the outlier-removed data. The two algorithms are established from a simplex volume max-min formulation which is recently proposed to cope with noisy scenarios. A robust algorithm, called worst case alternating volume maximization (WAVMAX), has been previously developed for the simplex volume max-min formulation but is computationally expensive to use. The two new algorithms employ a different kind of decoupled max-min partial optimizations, wherein the design emphasis is on low-complexity implementations. Some computer simulations and real data experiments demonstrate the efficacy, the computational efficiency, and the applicability of the proposed algorithms, in comparison with the WAVMAX algorithm and some benchmark endmember extraction algorithms. [ABSTRACT FROM AUTHOR]

Orthogonal subspace projection (OSP) is a powerful tool for dimensionality reduction (DR) in hyperspectral images (HSIs). In the OSP approach, the basis of the signal subspace must be estimated from the data themselves. Such estimation task is referred to as signal subspace identification (SSI). Most of the SSI methods in the literature are based on the analysis of the data second-order statistics (SOS) and have two main drawbacks: 1) They do not take into account the rare signal components (or rare vectors), 2) they assume that noise is spatially stationary. Rare vectors are those signal components that are present in pixels scarcely represented in the image and linearly independent on the signal components characterizing the rest of the image pixels. SOS-based SSI algorithms estimate the signal subspace addressing mostly the background and ignoring the presence of the rare pixels. This may be detrimental for the performance of detection algorithms when DR is adopted as a pre-processing step in small target detection applications. In this paper, a new technique for SSI in HSIs is presented. The algorithm is developed to account for both the abundant and the rare signal components. The method is derived by assuming a signal-dependent model for the noise affecting the data. This makes the SSI algorithm particularly suitable for the processing of images acquired by new generation sensors where, due to the improved sensitivity of the electronic components, noise includes a signal-dependent term. Results on simulated data are discussed, and the comparison with a recently proposed technique based on the analysis of SOS is performed. Furthermore, the results obtained by applying the SSI algorithm to a real HSI affected by signal-dependent noise are presented and discussed. [ABSTRACT FROM AUTHOR]

Both supervised and semisupervised algorithms for hyperspectral data analysis typically assume that all unlabeled data belong to the same set of land-cover classes that is represented by labeled data. This is not true in general, however, since there may be new classes in the unexplored regions within an image or in areas that are geographically near but topographically distinct. This problem is more likely to occur when one attempts to build classifiers that cover wider areas; such classifiers also need to address spatial variations in acquired spectral signatures if they are to be accurate and robust. This paper presents a semisupervised spatially adaptive mixture model (SESSAMM) to identify land covers from hyperspectral images in the presence of previously unknown land-cover classes and spatial variation of spectral responses. SESSAMM uses a nonparametric Bayesian framework to apply spatially adaptive mechanisms to the mixture model with (potentially) infinitely many components. In this method, each component in the mixture has spatially adapted parameters estimated by Gaussian process regression, and spatial correlations between indicator variables are also considered. The proposed SESSAMM algorithm is applied to hyperspectral data from Botswana and from the DC Mall, where some classes are present only in the unlabeled data. SESSAMM successfully differentiates unlabeled instances of previously known classes from unknown classes and provides better results than the standard Dirichlet process mixture model and other alternatives. [ABSTRACT FROM AUTHOR]

Recently, multiple kernel learning (MKL) methods have been developed to improve the flexibility of kernel-based learning machine. The MKL methods generally focus on determining key kernels to be preserved and their significance in optimal kernel combination. Unfortunately, computational demand of finding the optimal combination is prohibitive when the number of training samples and kernels increase rapidly, particularly for hyperspectral remote sensing data. In this paper, we address the MKL for classification in hyperspectral images by extracting the most variation from the space spanned by multiple kernels and propose a representative MKL (RMKL) algorithm. The core idea embedded in the algorithm is to determine the kernels to be preserved and their weights according to statistical significance instead of time-consuming search for optimal kernel combination. The noticeable merits of RMKL consist that it greatly reduces the computational load for searching optimal combination of basis kernels and has no limitation from strict selection of basis kernels like most MKL algorithms do; meanwhile, RMKL keeps excellent properties of MKL in terms of both good classification accuracy and interpretability. Experiments are conducted on different real hyperspectral data, and the corresponding experimental results show that RMKL algorithm provides the best performances to date among several the state-of-the-art algorithms while demonstrating satisfactory computational efficiency. [ABSTRACT FROM AUTHOR]

This paper investigates different batch-mode active-learning (AL) techniques for the classification of remote sensing (RS) images with support vector machines. This is done by generalizing to multiclass problem techniques defined for binary classifiers. The investigated techniques exploit different query functions, which are based on the evaluation of two criteria: uncertainty and diversity. The uncertainty criterion is associated to the confidence of the supervised algorithm in correctly classifying the considered sample, while the diversity criterion aims at selecting a set of unlabeled samples that are as more diverse (distant one another) as possible, thus reducing the redundancy among the selected samples. The combination of the two criteria results in the selection of the potentially most informative set of samples at each iteration of the AL process. Moreover, we propose a novel query function that is based on a kernel-clustering technique for assessing the diversity of samples and a new strategy for selecting the most informative representative sample from each cluster. The investigated and proposed techniques are theoretically and experimentally compared with state-of-the-art methods adopted for RS applications. This is accomplished by considering very high resolution multispectral and hyperspectral images. By this comparison, we observed that the proposed method resulted in better accuracy with respect to other investigated and state-of-the art methods on both the considered data sets. Furthermore, we derived some guidelines on the design of AL systems for the classification of different types of RS images. [ABSTRACT FROM AUTHOR]

Superpixels are homogeneous image regions comprised of multiple contiguous pixels. Superpixel representations can reduce noise in hyperspectral images by exploiting the spatial contiguity of scene features. This paper combines superpixels with endmember extraction to produce concise mineralogical summaries that assist in browsing large image catalogs. First, a graph-based agglomerative algorithm oversegments the image. We then use segments' mean spectra as input to existing statistical endmember detection algorithms such as sequential maximum angle convex cone (SMACC) and N-FINDR. Experiments compare automatically detected endmembers to target minerals in an Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) scene of Cuprite, Nevada. We also consider a planetary science data set from the Compact Reconnaissance Imaging Spectrometer (CRISM) instrument that benefits from spatial averaging due to higher noise. In both cases, superpixel representations significantly reduce the computational complexity of later processing while improving endmembers' match to the target spectra. [ABSTRACT FROM AUTHOR]

Given the hyperspectral-oriented waveband configuration of multiangular CHRIS/Proba imagery, the scope of its application could widen if the present 18-m resolution would be improved. The multiangular images of CHRIS could be used as input for superresolution (SR) image reconstruction. A critical procedure in SR is an accurate registration of the low-resolution images. Conventional methods based on affine transformation may not be effective given the local geometric distortion in high off-nadir angular images. This paper examines the use of a nonrigid transform to improve the result of a nonuniform interpolation and deconvolution SR method. A scale-invariant feature transform is used to collect control points (CPs). To ensure the quality of CPs, a rigorous screening procedure is designed: 1) an ambiguity test; 2) the m-estimator sample consensus method; and 3) an iterative method using statistical characteristics of the distribution of random errors. A thin-plate spline (TPS) nonrigid transform is then used for the registration. The proposed registration method is examined with a Delaunay triangulation-based nonuniform interpolation and reconstruction SR method. Our results show that the TPS nonrigid transform allows accurate registration of angular images. SR results obtained from simulated LR images are evaluated using three quantitative measures, namely, relative mean-square error, structural similarity, and edge stability. Compared to the SR methods that use an affine transform, our proposed method performs better with all three evaluation measures. With a higher level of spatial detail, SR-enhanced CHRIS images might be more effective than the original data in various applications. [ABSTRACT FROM AUTHOR]

Denoising of hyperspectral images in the domain of imaging spectroscopy by vectorial anisotropic diffusion is addressed. Anisotropic diffusion has shown to be a powerful denoising technique with many applications in several fields of image processing, and in the recent years, some significant advances have been published. However, these had not yet been specifically adapted to hyperspectral imagery. This paper reviews recent advances in anisotropic diffusion for multivalued images, analyzes their application to hyperspectral images, and proposes a new diffusion method which takes advantage of the recent improvements and conforms to the specificities of hyperspectral remote sensing. Some examples are provided using both a noisy image and a clean image with added noise. [ABSTRACT FROM AUTHOR]

This paper proposes a procedure to extract spectral channels of variable bandwidths and spectral positions from the hyperspectral image in such a way as to optimize the accuracy for a specific classification problem. In particular, each spectral channel (‘s-band’) is obtained by averaging a group of contiguous channels of the hyperspectral image (‘h-bands’). Therefore, if one wants to define m s-bands, the problem can be formulated as the optimization of the related m starting and m ending h-bands. Toward this end, we propose to adopt, as an optimization criterion, an interclass distance computed on a training set and to generate a sequence of possible solutions by one of three possible search strategies. As the proposed formalization of the problem makes it analogous to a feature-selection problem, the proposed three strategies have been derived by modifying three feature-selection strategies, namely 1) the ‘sequential forward selection,’ 2) the ‘steepest ascent,’ and 3) the ‘fast constrained search.’ Experimental results on a well-known hyperspectral data set confirm the effectiveness of the approach, which yields better results than other widely used methods. The importance of this kind of procedure lies in feature reduction for hyperspectral image classification or in the case-based design of the spectral bands of a programmable sensor. It represents a special case of feature extraction that is expected to be more powerful than feature selection. The kind of transformation used allows the interpretability of the new features (i.e., the spectral bands) to be saved. [ABSTRACT FROM AUTHOR]

This paper addresses the problem of the classification of hyperspectral remote sensing images by support vector machines (SVMs). First, we propose a theoretical discussion and experimental analysis aimed at understanding and assessing the potentialities of SVM classifiers in hyperdimensional feature spaces. Then, we assess the effectiveness of SVMs with respect to, conventional feature-reduction-based approaches and their performances in hypersubspaces of various dimenslonalities. To sustain such an analysis, the performances of SVMs are compared with those of two other nonparametric classifiers (i.e., radial basis function neural networks and the K-nearest neighbor classifier). Finally, we study the potentially critical issue of applying binary SVMs to multiclass problems in hyperspectral data. In particular, four different multiclass strategies are analyzed and compared: the one-against-all, the one-against-one, and two hierarchical tree-based strategies. Different performance indicators have been used to support our experimental studies in a detailed and accurate way, i.e., the classification accuracy, the computational time, the stability to parameter setting, and the complexity of the multiclass architecture. The results obtained on a real Airborne Visible/Infrared Imaging Spectroradiometer hyperspectral dataset allow to conclude that, whatever the multiclass strategy adopted, SVMs area valid and effective alternative to conventional pattern recognition approaches (feature-reduction procedures combined with a classification method) for the classification of hyperspectral remote sensing data. [ABSTRACT FROM AUTHOR]

Sparse subspace clustering (SSC) has emerged as an effective approach for the automatic analysis of hyperspectral images (HSI). Traditional SSC-based approaches employ the input HSI data as a dictionary of atoms, in terms of which all the data samples are linearly represented. This leads to highly redundant dictionaries of huge size, and the computational complexity of the resulting optimization problems becomes prohibitive for large-scale data. In this article, we propose a scalable subspace clustering method, which integrates the learning of a concise dictionary and robust subspace representation in a unified model. This reduces significantly the size of the involved optimization problems. We introduce a new adaptive spatial regularization for the representation coefficients, which incorporates spatial information of HSI and improves the robustness of the model to noise. We derive an effective solver based on alternating minimization and alternating direction method of multipliers (ADMMs) to solve the resulting optimization problem. Experimental results on four representative hyperspectral images show the effectiveness of the proposed method and excellent clustering performance relative to the state of the art. [ABSTRACT FROM AUTHOR]

Anomaly detection in hyperspectral images is of great interest in the target detection domain since it requires no prior information and makes full use of the spectral differences revealed in hyperspectral images. The current anomaly detection methods are susceptible to anomalies in the processing window range or the image scope. In addition, for the local anomaly detection methods themselves, it is difficult to determine the window size suitable for processing background statistics. This paper proposes an anomaly detection method based on the random selection of background pixels, the random-selection-based anomaly detector (RSAD). Pixels are randomly selected from the image scene to represent the background statistics; the random selections are performed a sufficient number of times; blocked adaptive computationally efficient outlier nominators are used to detect anomalies each time after a proper subset of background pixels is selected; finally, a fusion procedure is employed to avoid contamination of the background statistics by anomaly pixels. In addition, the real-time implementation of the RSAD is also developed by random selection from updating data and QR decomposition. Several hyperspectral data sets are used in the experiments, and the RSAD shows a better performance than the current hyperspectral anomaly detection algorithms. The real-time version also outperforms its real-time counterparts. [ABSTRACT FROM PUBLISHER]

Generative adversarial networks (GANs) are famous for generating samples by training a generator and a discriminator via an adversarial procedure. For hyperspectral image classification, the collection of samples is always difficult. However, directly applying GAN to hyperspectral image classification exists two problems. One is that the generated samples lack discriminative information. Meanwhile, the discriminator has no discriminative ability for multiclassification. Another is that spatial and spectral information requires to be considered in hyperspectral image classification simultaneously. To address these problems, a novel multiclass spatial–spectral GAN (MSGAN) method is proposed. In MSGAN, two generators are devised to generate the samples containing spatial and spectral information, respectively, and the discriminator is devised to extract joint spatial–spectral features and output multiclass probabilities. Moreover, novel adversarial objectives for multiclass are defined. The discriminator is devised to predict training samples belonging to true classes and generated samples belonging to all the classes with the same probability. The generators are devised to make the discriminator mistake. By adversarial learning between the discriminator and generators, the classification performance of the discriminator is promoted with the assistance of discriminative generated samples. Experimental results on hyperspectral images demonstrate that the proposed method achieves encouraging classification performance compared with several state-of-the-art methods, especially with the limited training samples. [ABSTRACT FROM AUTHOR]